@comment{{This file has been generated by bib2bib 1.97}}
@comment{{Command line: bib2bib ../bibli.bib -c 'subject:"biosvm" or keywords:"biosvm"' -ob tmp.bib}}
@article{Aires-de-Sousa2005Prediction,
author = {Aires-de-Sousa, J. and Gasteiger, J.},
title = {Prediction of enantiomeric excess in a combinatorial library of catalytic
enantioselective reactions.},
journal = {J {C}omb {C}hem},
year = {2005},
volume = {7},
pages = {298-301},
number = {2},
abstract = {A quantitative structure-enantioselectivity relationship was established
for a combinatorial library of enantioselective reactions performed
by addition of diethyl zinc to benzaldehyde. {C}hiral catalysts and
additives were encoded by their chirality codes and presented as
input to neural networks. {T}he networks were trained to predict
the enantiomeric excess. {W}ith independent test sets, predictions
of enantiomeric excess could be made with an average error as low
as 6\% ee. {M}ultilinear regression, perceptrons, and support vector
machines were also evaluated as modeling tools. {T}he method is of
interest for the computer-aided design of combinatorial libraries
involving chiral compounds or enantioselective reactions. {T}his
is the first example of a quantitative structure-property relationship
based on chirality codes.},
doi = {10.1021/cc049961q},
pdf = {../local/Aires-de-Sousa2005Prediction.pdf},
file = {Aires-de-Sousa2005Prediction.pdf:local/Aires-de-Sousa2005Prediction.pdf:PDF},
keywords = {biosvm chemoinformatics},
url = {http://dx.doi.org/10.1021/cc049961q}
}
@inproceedings{Aliferis2002Machine,
author = {Aliferis, C.F. and Hardin, D.P. and Massion, P.},
title = {Machine {L}earning {M}odels {F}or {L}ung {C}ancer {C}lassification
{U}sing {A}rray {C}omparative {G}enomic {H}ybridization},
booktitle = {Proceedings of the 2002 {A}merican {M}edical {I}nformatics {A}ssociation
({AMIA}) {A}nnual {S}ymposium},
year = {2002},
pages = {7-11},
abstract = {Array {CGH} is a recently introduced technology that measures changes
in the gene copy number of hundreds of genes in a single experiment.
{T}he primary goal of this study was to develop machine learning
models that classify non-small {L}ung {C}ancers according to histopathology
types and to compare several machine learning methods in this learning
task. {DNA} from tumors of 37 patients (21 squamous carcinomas, and
16 adenocarcinomas) were extracted and hybridized onto a 452 {BAC}
clone array. {T}he following algorithms were used: {KNN}, {D}ecision
{T}ree {I}nduction, {S}upport {V}ector {M}achines and {F}eed-{F}orward
{N}eural {N}etworks. {P}erformance was measured via leave-one-out
classification accuracy. {T}he best multi-gene model found had a
leave-one-out accuracy of 89.2\%. {D}ecision {T}rees performed poorer
than the other methods in this learning task and dataset. {W}e conclude
that gene copy numbers as measured by array {CGH} are, collectively,
an excellent indicator of histological subtype. {S}everal interesting
research directions are discussed.},
pdf = {../local/Aliferis2002Machine.pdf},
file = {Aliferis2002Machine.pdf:local/Aliferis2002Machine.pdf:PDF},
keywords = {biosvm microarray, cgh},
owner = {jeanphilippevert}
}
@article{Ambroise2002Selection,
author = {Ambroise, C. and McLachlan, G.J.},
title = {Selection bias in gene extraction on the basis of microarray gene-expression
data},
journal = {Proc. {N}atl. {A}cad. {S}ci. {USA}},
year = {2002},
volume = {99},
pages = {6562-6566},
number = {10},
abstract = {In the context of cancer diagnosis and treatment, we consider the
problem of constructing an accurate prediction rule on the basis
of a relatively small number of tumor tissue samples of known type
containing the expression data on very many (possibly thousands)
genes. {R}ecently, results have been presented in the literature
suggesting that it is possible to construct a prediction rule from
only a few genes such that it has a negligible prediction error rate.
{H}owever, in these results the test error or the leave-one-out cross-validated
error is calculated without allowance for the selection bias. {T}here
is no allowance because the rule is either tested on tissue samples
that were used in the first instance to select the genes being used
in the rule or because the cross-validation of the rule is not external
to the selection process; that is, gene selection is not performed
in training the rule at each stage of the cross-validation process.
{W}e describe how in practice the selection bias can be assessed
and corrected for by either performing a cross-validation or applying
the bootstrap external to the selection process. {W}e recommend using
10-fold rather than leave-one-out cross-validation, and concerning
the bootstrap, we suggest using the so-called .632+ bootstrap error
estimate designed to handle overfitted prediction rules. {U}sing
two published data sets, we demonstrate that when correction is made
for the selection bias, the cross-validated error is no longer zero
for a subset of only a few genes.},
pdf = {../local/Ambroise2002Selection.pdf},
file = {Ambroise2002Selection.pdf:local/Ambroise2002Selection.pdf:PDF},
keywords = {featureselection biosvm},
owner = {jeanphilippevert},
url = {http://www.pnas.org/cgi/content/abstract/99/10/6562}
}
@article{Anderson2003new,
author = {Anderson, D.C. and Li, W. and Payan, D.G. and Noble, W.S.},
title = {A new algorithm for the evaluation of shotgun peptide sequencing
in proteomics: support vector machine classification of peptide {{MS}/{MS}}
spectra and {SEQUEST} scores.},
journal = {J {P}roteome {R}es},
year = {2003},
volume = {2},
pages = {137-146},
number = {2},
abstract = {Shotgun tandem mass spectrometry-based peptide sequencing using programs
such as {SEQUEST} allows high-throughput identification of peptides,
which in turn allows the identification of corresponding proteins.
{W}e have applied a machine learning algorithm, called the support
vector machine, to discriminate between correctly and incorrectly
identified peptides using {SEQUEST} output. {E}ach peptide was characterized
by {SEQUEST}-calculated features such as delta {C}n and {X}corr,
measurements such as precursor ion current and mass, and additional
calculated parameters such as the fraction of matched {MS}/{MS} peaks.
{T}he trained {SVM} classifier performed significantly better than
previous cutoff-based methods at separating positive from negative
peptides. {P}ositive and negative peptides were more readily distinguished
in training set data acquired on a {QTOF}, compared to an ion trap
mass spectrometer. {T}he use of 13 features, including four new parameters,
significantly improved the separation between positive and negative
peptides. {U}se of the support vector machine and these additional
parameters resulted in a more accurate interpretation of peptide
{MS}/{MS} spectra and is an important step toward automated interpretation
of peptide tandem mass spectrometry data in proteomics.},
pdf = {../local/Anderson2003new.pdf},
file = {Anderson2003new.pdf:local/Anderson2003new.pdf:PDF},
keywords = {biosvm proteomics},
owner = {jeanphilippevert}
}
@article{Aphinyanaphongs2005Text,
author = {Yindalon Aphinyanaphongs and Ioannis Tsamardinos and Alexander Statnikov
and Douglas Hardin and Constantin F Aliferis},
title = {Text categorization models for high-quality article retrieval in
internal medicine.},
journal = {J. {A}m. {M}ed. {I}nform. {A}ssoc.},
year = {2005},
volume = {12},
pages = {207-16},
number = {2},
abstract = {O{BJECTIVE} {F}inding the best scientific evidence that applies to
a patient problem is becoming exceedingly difficult due to the exponential
growth of medical publications. {T}he objective of this study was
to apply machine learning techniques to automatically identify high-quality,
content-specific articles for one time period in internal medicine
and compare their performance with previous {B}oolean-based {P}ub{M}ed
clinical query filters of {H}aynes et al. {DESIGN} {T}he selection
criteria of the {ACP} {J}ournal {C}lub for articles in internal medicine
were the basis for identifying high-quality articles in the areas
of etiology, prognosis, diagnosis, and treatment. {N}aive {B}ayes,
a specialized {A}da{B}oost algorithm, and linear and polynomial support
vector machines were applied to identify these articles. {MEASUREMENTS}
{T}he machine learning models were compared in each category with
each other and with the clinical query filters using area under the
receiver operating characteristic curves, 11-point average recall
precision, and a sensitivity/specificity match method. {RESULTS}
{I}n most categories, the data-induced models have better or comparable
sensitivity, specificity, and precision than the clinical query filters.
{T}he polynomial support vector machine models perform the best among
all learning methods in ranking the articles as evaluated by area
under the receiver operating curve and 11-point average recall precision.
{CONCLUSION} {T}his research shows that, using machine learning methods,
it is possible to automatically build models for retrieving high-quality,
content-specific articles using inclusion or citation by the {ACP}
{J}ournal {C}lub as a gold standard in a given time period in internal
medicine that perform better than the 1994 {P}ub{M}ed clinical query
filters.},
doi = {10.1197/jamia.M1641},
pdf = {../local/Aphinyanaphongs2005Text.pdf},
file = {Aphinyanaphongs2005Text.pdf:local/Aphinyanaphongs2005Text.pdf:PDF},
keywords = {biosvm nlp},
pii = {M1641},
url = {http://dx.doi.org/10.1197/jamia.M1641}
}
@article{Arimoto2005Development,
author = {Rieko Arimoto and Madhu-Ashni Prasad and Eric M Gifford},
title = {Development of {CYP}3{A}4 inhibition models: comparisons of machine-learning
techniques and molecular descriptors.},
journal = {J {B}iomol {S}creen},
year = {2005},
volume = {10},
pages = {197-205},
number = {3},
month = {Apr},
abstract = {Computational models of cytochrome {P}450 3{A}4 inhibition were developed
based on high-throughput screening data for 4470 proprietary compounds.
{M}ultiple models differentiating inhibitors ({IC}(50) <3 micro{M})
and noninhibitors were generated using various machine-learning algorithms
(recursive partitioning [{RP}], {B}ayesian classifier, logistic regression,
k-nearest-neighbor, and support vector machine [{SVM}]) with structural
fingerprints and topological indices. {N}ineteen models were evaluated
by internal 10-fold cross-validation and also by an independent test
set. {T}hree most predictive models, {B}arnard {C}hemical {I}nformation
({BCI})-fingerprint/{SVM}, {MDL}-keyset/{SVM}, and topological indices/{RP},
correctly classified 249, 248, and 236 compounds of 291 noninhibitors
and 135, 137, and 147 compounds of 179 inhibitors in the validation
set. {T}heir overall accuracies were 82\%, 82\%, and 81\%, respectively.
{I}nvestigating applicability of the {BCI}/{SVM} model found a strong
correlation between the predictive performance and the structural
similarity to the training set. {U}sing {T}animoto similarity index
as a confidence measurement for the predictions, the limitation of
the extrapolation was 0.7 in the case of the {BCI}/{SVM} model. {T}aking
consensus of the 3 best models yielded a further improvement in predictive
capability, kappa = 0.65 and accuracy = 83\%. {T}he consensus model
could also be tuned to minimize either false positives or false negatives
depending on the emphasis of the screening.},
doi = {10.1177/1087057104274091},
keywords = {biosvm chemoinformatics},
pii = {10/3/197},
url = {http://dx.doi.org/10.1177/1087057104274091}
}
@article{Arodz2005Pattern,
author = {Tomasz Arod{\'z} and Marcin Kurdziel and Erik O D Sevre and David
A Yuen},
title = {Pattern recognition techniques for automatic detection of suspicious-looking
anomalies in mammograms.},
journal = {Comput. {M}ethods {P}rograms {B}iomed.},
year = {2005},
volume = {79},
pages = {135-49},
number = {2},
month = {Aug},
abstract = {We have employed two pattern recognition methods used commonly for
face recognition in order to analyse digital mammograms. {T}he methods
are based on novel classification schemes, the {A}da{B}oost and the
support vector machines ({SVM}). {A} number of tests have been carried
out to evaluate the accuracy of these two algorithms under different
circumstances. {R}esults for the {A}da{B}oost classifier method are
promising, especially for classifying mass-type lesions. {I}n the
best case the algorithm achieved accuracy of 76\% for all lesion
types and 90\% for masses only. {T}he {SVM} based algorithm did not
perform as well. {I}n order to achieve a higher accuracy for this
method, we should choose image features that are better suited for
analysing digital mammograms than the currently used ones.},
doi = {10.1016/j.cmpb.2005.03.009},
pdf = {../local/Arodz2005Pattern.pdf},
file = {Arodz2005Pattern.pdf:local/Arodz2005Pattern.pdf:PDF},
keywords = {biosvm image},
pii = {S0169-2607(05)00083-0},
url = {http://dx.doi.org/10.1016/j.cmpb.2005.03.009}
}
@article{Atalay2005Implicit,
author = {Atalay, V. and Cetin-Atalay, R.},
title = {Implicit motif distribution based hybrid computational kernel for
sequence classification},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {1429-1436},
number = {8},
month = {Apr},
abstract = {M{OTIVATION}: {W}e designed a general computational kernel for classification
problems that require specific motif extraction and search from sequences.
{I}nstead of searching for explicit motifs, our approach finds the
distribution of implicit motifs and uses as a feature for classification.
{I}mplicit motif distribution approach may be used as modus operandi
for bioinformatics problems that require specific motif extraction
and search, which is otherwise computationally prohibitive. {RESULTS}:
{A} system named {P}2{SL} that infer protein subcellular targeting
was developed through this computational kernel. {T}argeting-signal
was modeled by the distribution of subsequence occurrences (implicit
motifs) using self-organizing maps. {T}he boundaries among the classes
were then determined with a set of support vector machines. {P}2{SL}
hybrid computational system achieved approximately 81\% of prediction
accuracy rate over {ER} targeted, cytosolic, mitochondrial and nuclear
protein localization classes. {P}2{SL} additionally offers the distribution
potential of proteins among localization classes, which is particularly
important for proteins, shuttle between nucleus and cytosol. {AVAILABILITY}:
http://staff.vbi.vt.edu/volkan/p2sl and http://www.i-cancer.fen.bilkent.edu.tr/p2sl
{CONTACT}: rengul@bilkent.edu.tr.},
doi = {10.1093/bioinformatics/bti212},
pdf = {../local/Atalay2005Implicit.pdf},
file = {Atalay2005Implicit.pdf:local/Atalay2005Implicit.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1093/bioinformatics/bti212}
}
@article{Bao2005Identifying,
author = {Lei Bao},
title = {Identifying genes related to chemosensitivity using support vector
machine.},
journal = {Methods {M}ol {M}ed},
year = {2005},
volume = {111},
pages = {233-40},
abstract = {In an effort to identify genes involved in chemosensitivity and to
evaluate the functional relationships between genes and anticancer
drugs acting by the same mechanism, a supervised machine learning
approach called support vector machine ({SVM}) is used to associate
genes with any of five predefined anticancer drug mechanistic categories.
{T}he drug activity profiles are used as training examples to train
the {SVM} and then the gene expression profiles are used as test
examples to predict their associated mechanistic categories. {T}his
method of correlating drugs and genes provides a strategy for finding
novel biologically significant relationships for molecular pharmacology.},
keywords = {biosvm},
pii = {1-59259-889-7:233}
}
@article{Bao2005Prediction,
author = {Lei Bao and Yan Cui},
title = {Prediction of the phenotypic effects of non-synonymous single nucleotide
polymorphisms using structural and evolutionary information.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {2185-90},
number = {10},
month = {May},
abstract = {M{OTIVATION}: {T}here has been great expectation that the knowledge
of an individual's genotype will provide a basis for assessing susceptibility
to diseases and designing individualized therapy. {N}on-synonymous
single nucleotide polymorphisms (ns{SNP}s) that lead to an amino
acid change in the protein product are of particular interest because
they account for nearly half of the known genetic variations related
to human inherited diseases. {T}o facilitate the identification of
disease-associated ns{SNP}s from a large number of neutral ns{SNP}s,
it is important to develop computational tools to predict the phenotypic
effects of ns{SNP}s. {RESULTS}: {W}e prepared a training set based
on the variant phenotypic annotation of the {S}wiss-{P}rot database
and focused our analysis on ns{SNP}s having homologous 3{D} structures.
{S}tructural environment parameters derived from the 3{D} homologous
structure as well as evolutionary information derived from the multiple
sequence alignment were used as predictors. {T}wo machine learning
methods, support vector machine and random forest, were trained and
evaluated. {W}e compared the performance of our method with that
of the {SIFT} algorithm, which is one of the best predictive methods
to date. {A}n unbiased evaluation study shows that for ns{SNP}s with
sufficient evolutionary information (with not <10 homologous sequences),
the performance of our method is comparable with the {SIFT} algorithm,
while for ns{SNP}s with insufficient evolutionary information (<10
homologous sequences), our method outperforms the {SIFT} algorithm
significantly. {T}hese findings indicate that incorporating structural
information is critical to achieving good prediction accuracy when
sufficient evolutionary information is not available. {AVAILABILITY}:
{T}he codes and curated dataset are available at http://compbio.utmem.edu/snp/dataset/},
doi = {10.1093/bioinformatics/bti365},
pdf = {../local/Bao2005Prediction.pdf},
file = {Bao2005Prediction.pdf:local/Bao2005Prediction.pdf:PDF},
keywords = {biosvm},
pii = {bti365},
url = {http://dx.doi.org/10.1093/bioinformatics/bti365}
}
@article{Bao2002Identifying,
author = {Bao, L. and Sun, Z.},
title = {Identifying genes related to drug anticancer mechanisms using support
vector machine},
journal = {F{EBS} {L}ett.},
year = {2002},
volume = {521},
pages = {109--114},
abstract = {In an effort to identify genes related to the cell line chemosensitivity
and to evaluate the functional relationships between genes and anticancer
drugs acting by the same mechanism, a supervised machine learning
approach called support vector machine was used to label genes into
any of the five predefined anticancer drug mechanistic categories.
{A}mong dozens of unequivocally categorized genes, many were known
to be causally related to the drug mechanisms. {F}or example, a few
genes were found to be involved in the biological process triggered
by the drugs (e.g. {DNA} polymerase epsilon was the direct target
for the drugs from {DNA} antimetabolites category). {DNA} repair-related
genes were found to be enriched for about eight-fold in the resulting
gene set relative to the entire gene set. {S}ome uncharacterized
transcripts might be of interest in future studies. {T}his method
of correlating the drugs and genes provides a strategy for finding
novel biologically significant relationships for molecular pharmacology.},
pdf = {../local/bao02.pdf},
file = {bao02.pdf:local/bao02.pdf:PDF},
keywords = {biosvm microarray},
subject = {biokernel},
url = {http://www.elsevier.com/febs/402/19/42/article.html}
}
@article{Baumgartner2004Supervised,
author = {Baumgartner, C. and Bohm, C. and Baumgartner, D. and Marini, G. and
Weinberger, K. and Olgemoller, B. and Liebl, B. and Roscher, A. A.},
title = {Supervised machine learning techniques for the classification of
metabolic disorders in newborns},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {2985-2996},
number = {17},
abstract = {Motivation: {D}uring the {B}avarian newborn screening programme all
newborns have been tested for about 20 inherited metabolic disorders.
{O}wing to the amount and complexity of the generated experimental
data, machine learning techniques provide a promising approach to
investigate novel patterns in high-dimensional metabolic data which
form the source for constructing classification rules with high discriminatory
power. {R}esults: {S}ix machine learning techniques have been investigated
for their classification accuracy focusing on two metabolic disorders,
phenylketo nuria ({PKU}) and medium-chain acyl-{C}o{A} dehydrogenase
deficiency ({MCADD}). {L}ogistic regression analysis led to superior
classification rules (sensitivity >96.8%, specificity >99.98%) compared
to all investigated algorithms. {I}ncluding novel constellations
of metabolites into the models, the positive predictive value could
be strongly increased ({PKU} 71.9% versus 16.2%, {MCADD} 88.4% versus
54.6% compared to the established diagnostic markers). {O}ur results
clearly prove that the mined data confirm the known and indicate
some novel metabolic patterns which may contribute to a better understanding
of newborn metabolism. {A}vailability: {WEKA} machine learning package:
www.cs.waikato.ac.nz/~ml/weka and statistical software package {ADE}-4:
http://pbil.univ-lyon1.fr/{ADE}-4},
doi = {10.1093/bioinformatics/bth343},
pdf = {../local/Baumgartner2004Supervised.pdf},
file = {Baumgartner2004Supervised.pdf:local/Baumgartner2004Supervised.pdf:PDF},
keywords = {biosvm proteomics},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/17/2985}
}
@article{Bazzani2001SVM,
author = {A. Bazzani and A. Bevilacqua and D. Bollini and R. Brancaccio and
R. Campanini and N. Lanconelli and A. Riccardi and D. Romani},
title = {An {SVM} classifier to separate false signals from microcalcifications
in digital mammograms.},
journal = {Phys {M}ed {B}iol},
year = {2001},
volume = {46},
pages = {1651-63},
number = {6},
month = {Jun},
abstract = {In this paper we investigate the feasibility of using an {SVM} (support
vector machine) classifier in our automatic system for the detection
of clustered microcalcifications in digital mammograms. {SVM} is
a technique for pattern recognition which relies on the statistical
learning theory. {I}t minimizes a function of two terms: the number
of misclassified vectors of the training set and a term regarding
the generalization classifier capability. {W}e compare the {SVM}
classifier with an {MLP} (multi-layer perceptron) in the false-positive
reduction phase of our detection scheme: a detected signal is considered
either microcalcification or false signal, according to the value
of a set of its features. {T}he {SVM} classifier gets slightly better
results than the {MLP} one ({A}z value of 0.963 against 0.958) in
the presence of a high number of training data; the improvement becomes
much more evident ({A}z value of 0.952 against 0.918) in training
sets of reduced size. {F}inally, the setting of the {SVM} classifier
is much easier than the {MLP} one.},
doi = {10.1088/0031-9155/46/6/305},
pdf = {../local/Bazzani2001SVM.pdf},
file = {Bazzani2001SVM.pdf:local/Bazzani2001SVM.pdf:PDF},
keywords = {biosvm image},
url = {http://dx.doi.org/10.1088/0031-9155/46/6/305}
}
@article{Beerenwinkel2003Methods,
author = {Beerenwinkel, N. and Lengauer, T. and Daumer, M. and Kaiser, R. and
Walter, H. and Korn, K. and Hoffmann, D. and Selbig, J.},
title = {Methods for optimizing antiviral combination therapies},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {i16-i25},
number = {Suppl. 1},
abstract = {Motivation: {D}espite some progress with antiretroviral combination
therapies, therapeutic success in the management of {HIV}-infected
patients is limited. {T}he evolution of drug-resistant genetic variants
in response to therapy plays a key role in treatment failure and
finding a new potent drug combination after therapy failure is considered
challenging. {R}esults: {T}o estimate the activity of a drug combination
against a particular viral strain, we develop a scoring function
whose independent variables describe a set of antiviral agents and
viral {DNA} sequences coding for the molecular targets of the respective
drugs. {T}he construction of this activity score involves (1) predicting
phenotypic drug resistance from genotypes for each drug individually,
(2) probabilistic modeling of predicted resistance values and integration
into a score for drug combinations, and (3) searching through the
mutational neighborhood of the considered strain in order to estimate
activity on nearby mutants. {F}or a clinical data set, we determine
the optimal search depth and show that the scoring scheme is predictive
of therapeutic outcome. {P}roperties of the activity score and applications
are discussed. {C}ontact: beerenwinkel@mpi-sb.mpg.de {K}eywords:
{HIV}, antiretroviral therapy, drug resistance, {SVM} regression,
therapy optimization, sequence space search.},
pdf = {../local/Beerenwinkel2003Methods.pdf},
file = {Beerenwinkel2003Methods.pdf:local/Beerenwinkel2003Methods.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/suppl_1/i16}
}
@article{Beerenwinkel2001Geno2pheno,
author = {Beerenwinkel, N. and Schmidt, B. and Walter, H. and Kaiser, R. and
Lengauer, T. and Hoffman, D. and Korn, K. and Selbig, J.},
title = {{{G}eno2pheno: {I}nterpreting {G}enotypic {HIV} {D}rug {R}esistance
{T}ests}},
journal = {I{EEE} {I}ntelligent {S}ystems},
year = {2001},
volume = {6},
pages = {35-41},
number = {6},
abstract = {Rapid accumulation of resistance mutations in the genome of the human
immunodeficiency virus ({HIV}) plays a central role in drug treatment
failure in infected patients. {T}he authors have developed geno2pheno,
an intelligent system that uses the information encoded in the viral
genomic sequence to predict resistance or susceptibility of the virus
to 13 antiretroviral agents. {T}o predict phenotypic drug resistance
from genotype, they applied two machine learning techniques: decision
trees and linear support vector machines. {T}hese techniques performed
learning on more than 400 genotype-phenotype pairs for each drug.
{T}he authors compared the generalization performance of the two
families of models in leave-one-out experiments. {E}xcept for three
drugs, all error estimates ranged between 7.25 and 15.5 percent.
{S}upport vector machines performed slightly better for most drugs,
but knowledge extraction was easier for decision trees. {G}eno2pheno
is freely available at http://cartan.gmd.de/geno2pheno.html.},
doi = {10.1109/5254.972080},
pdf = {../local/Beerenwinkel2001Geno2pheno.pdf},
file = {Beerenwinkel2001Geno2pheno.pdf:local/Beerenwinkel2001Geno2pheno.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1109/5254.972080}
}
@article{Ben-Dor2000Tissue,
author = {Ben-Dor, A. and Bruhn, L. and Friedman, N. and Nachman, I. and Schummer,
M. and Yakhini, Z.},
title = {Tissue Classification with Gene Expression Profiles},
journal = {J. Comput. Biol.},
year = {2000},
volume = {7},
pages = {559-583},
number = {3-4},
abstract = {Constantly improving gene expression profiling technologies are expected
to provide understanding and insight into cancer-related cellular
processes. {G}ene expression data is also expected to significantly
aid in the development of efficient cancer diagnosis and classification
platforms. {I}n this work we examine three sets of gene expression
data measured across sets of tumor(s) and normal clinical samples:
{T}he first set consists of 2,000 genes, measured in 62 epithelial
colon samples ({A}lon et al., 1999). {T}he second consists of approximately
equal to 100,000 clones, measured in 32 ovarian samples (unpublished
extension of data set described in {S}chummer et al. (1999)). {T}he
third set consists of approximately equal to 7,100 genes, measured
in 72 bone marrow and peripheral blood samples ({G}olub et al, 1999).
{W}e examine the use of scoring methods, measuring separation of
tissue type (e.g., tumors from normals) using individual gene expression
levels. {T}hese are then coupled with high-dimensional classification
methods to assess the classification power of complete expression
profiles. {W}e present results of performing leave-one-out cross
validation ({LOOCV}) experiments on the three data sets, employing
nearest neighbor classifier, {SVM} ({C}ortes and {V}apnik, 1995),
{A}da{B}oost ({F}reund and {S}chapire, 1997) and a novel clustering-based
classification technique. {A}s tumor samples can differ from normal
samples in their cell-type composition, we also perform {LOOCV} experiments
using appropriately modified sets of genes, attempting to eliminate
the resulting bias. {W}e demonstrate success rate of at least 90%
in tumor versus normal classification, using sets of selected genes,
with, as well as without, cellular-contamination-related members.
{T}hese results are insensitive to the exact selection mechanism,
over a certain range.},
pdf = {../local/Ben-Dor2000Tissue.pdf},
file = {Ben-Dor2000Tissue.pdf:local/Ben-Dor2000Tissue.pdf:PDF},
keywords = {biosvm microarray},
owner = {jeanphilippevert},
url = {http://www.liebertonline.com/doi/abs/10.1089/106652700750050943}
}
@article{Ben-Hur2003Remote,
author = {Ben-Hur, A. and Brutlag, D.},
title = {Remote homology detection: a motif based approach},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {i26-i33},
number = {Suppl. 1},
abstract = {Motivation: {R}emote homology detection is the problem of detecting
homology in cases of low sequence similarity. {I}t is a hard computational
problem with no approach that works well in all cases. {R}esults:
{W}e present a method for detecting remote homology that is based
on the presence of discrete sequence motifs. {T}he motif content
of a pair of sequences is used to define a similarity that is used
as a kernel for a {S}upport {V}ector {M}achine ({SVM}) classifier.
{W}e test the method on two remote homology detection tasks: prediction
of a previously unseen {SCOP} family and prediction of an enzyme
class given other enzymes that have a similar function on other substrates.
{W}e find that it performs significantly better than an {SVM} method
that uses {BLAST} or {S}mith-{W}aterman similarity scores as features.
{A}vailability: {T}he software is available from the authors upon
request.},
pdf = {../local/Ben-Hur2003Remote.pdf},
file = {Ben-Hur2003Remote.pdf:local/Ben-Hur2003Remote.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/suppl_1/i26}
}
@article{Ben-Hur2005Kernel,
author = {Ben-Hur, A. and Noble, W. S.},
title = {Kernel methods for predicting protein-protein interactions.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {i38-i46},
number = {Suppl. 1},
month = {Jun},
abstract = {M{OTIVATION}: {D}espite advances in high-throughput methods for discovering
protein-protein interactions, the interaction networks of even well-studied
model organisms are sketchy at best, highlighting the continued need
for computational methods to help direct experimentalists in the
search for novel interactions. {RESULTS}: {W}e present a kernel method
for predicting protein-protein interactions using a combination of
data sources, including protein sequences, {G}ene {O}ntology annotations,
local properties of the network, and homologous interactions in other
species. {W}hereas protein kernels proposed in the literature provide
a similarity between single proteins, prediction of interactions
requires a kernel between pairs of proteins. {W}e propose a pairwise
kernel that converts a kernel between single proteins into a kernel
between pairs of proteins, and we illustrate the kernel's effectiveness
in conjunction with a support vector machine classifier. {F}urthermore,
we obtain improved performance by combining several sequence-based
kernels based on k-mer frequency, motif and domain content and by
further augmenting the pairwise sequence kernel with features that
are based on other sources of data.{W}e apply our method to predict
physical interactions in yeast using data from the {BIND} database.
{A}t a false positive rate of 1\% the classifier retrieves close
to 80\% of a set of trusted interactions. {W}e thus demonstrate the
ability of our method to make accurate predictions despite the sizeable
fraction of false positives that are known to exist in interaction
databases. {AVAILABILITY}: {T}he classification experiments were
performed using {P}y{ML} available at http://pyml.sourceforge.net.
{D}ata are available at: http://noble.gs.washington.edu/proj/sppi
{CONTACT}: asa@gs.washington.edu.},
doi = {10.1093/bioinformatics/bti1016},
pdf = {../local/Ben-Hur2005Kernel.pdf},
file = {Ben-Hur2005Kernel.pdf:local/Ben-Hur2005Kernel.pdf:PDF},
keywords = {biosvm},
pii = {21/suppl_1/i38},
url = {http://dx.doi.org/10.1093/bioinformatics/bti1016}
}
@article{Bern2004Automatic,
author = {Bern, M. and Goldberg, D. and McDonald, W. H. and Yates, J. R., III},
title = {Automatic {Q}uality {A}ssessment of {P}eptide {T}andem {M}ass {S}pectra},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {i49-i54},
number = {Suppl. 1},
abstract = {Motivation: {A} powerful proteomics methodology couples high-performance
liquid chromatography ({HPLC}) with tandem mass spectrometry and
database-search software, such as {SEQUEST}. {S}uch a set-up, however,
produces a large number of spectra, many of which are of too poor
quality to be useful. {H}ence a filter that eliminates poor spectra
before the database search can significantly improve throughput and
robustness. {M}oreover, spectra judged to be of high quality, but
that cannot be identified by database search, are prime candidates
for still more computationally intensive methods, such as de novo
sequencing or wider database searches including post-translational
modifications. {R}esults: {W}e report on two different approaches
to assessing spectral quality prior to identification: binary classification,
which predicts whether or not {SEQUEST} will be able to make an identification,
and statistical regression, which predicts a more universal quality
metric involving the number of b- and y-ion peaks. {T}he best of
our binary classifiers can eliminate over 75% of the unidentifiable
spectra while losing only 10% of the identifiable spectra. {S}tatistical
regression can pick out spectra of modified peptides that can be
identified by a de novo program but not by {SEQUEST}. {I}n a section
of independent interest, we discuss intensity normalization of mass
spectra.},
pdf = {../local/Bern2004Automatic.pdf},
file = {Bern2004Automatic.pdf:local/Bern2004Automatic.pdf:PDF},
keywords = {biosvm proteomics},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/suppl_1/i49}
}
@article{Bhasin2005GPCRsclass,
author = {Bhasin, M. and Raghava, G. P. S.},
title = {G{PCR}sclass: a web tool for the classification of amine type of
{G}-protein-coupled receptors.},
journal = {Nucleic {A}cids {R}es.},
year = {2005},
volume = {33},
pages = {W143-7},
number = {Web Server issue},
month = {Jul},
abstract = {The receptors of amine subfamily are specifically major drug targets
for therapy of nervous disorders and psychiatric diseases. {T}he
recognition of novel amine type of receptors and their cognate ligands
is of paramount interest for pharmaceutical companies. {I}n the past,
{C}hou and co-workers have shown that different types of amine receptors
are correlated with their amino acid composition and are predictable
on its basis with considerable accuracy [{E}lrod and {C}hou (2002)
{P}rotein {E}ng., 15, 713-715]. {T}his motivated us to develop a
better method for the recognition of novel amine receptors and for
their further classification. {T}he method was developed on the basis
of amino acid composition and dipeptide composition of proteins using
support vector machine. {T}he method was trained and tested on 167
proteins of amine subfamily of {G}-protein-coupled receptors ({GPCR}s).
{T}he method discriminated amine subfamily of {GPCR}s from globular
proteins with {M}atthew's correlation coefficient of 0.98 and 0.99
using amino acid composition and dipeptide composition, respectively.
{I}n classifying different types of amine receptors using amino acid
composition and dipeptide composition, the method achieved an accuracy
of 89.8 and 96.4\%, respectively. {T}he performance of the method
was evaluated using 5-fold cross-validation. {T}he dipeptide composition
based method predicted 67.6\% of protein sequences with an accuracy
of 100\% with a reliability index > or =5. {A} web server {GPCR}sclass
has been developed for predicting amine-binding receptors from its
amino acid sequence [http://www.imtech.res.in/raghava/gpcrsclass/
and http://bioinformatics.uams.edu/raghava/gpersclass/ (mirror site)].},
doi = {10.1093/nar/gki351},
pdf = {../local/Bhasin2005GPCRsclass.pdf},
file = {Bhasin2005GPCRsclass.pdf:local/Bhasin2005GPCRsclass.pdf:PDF},
keywords = {biosvm},
pii = {33/suppl_2/W143},
url = {http://dx.doi.org/10.1093/nar/gki351}
}
@article{Bhasin2005Pcleavage,
author = {Bhasin, M. and Raghava, G. P. S.},
title = {Pcleavage: an {SVM} based method for prediction of constitutive proteasome
and immunoproteasome cleavage sites in antigenic sequences.},
journal = {Nucleic {A}cids {R}es},
year = {2005},
volume = {33},
pages = {W202-7},
number = {Web Server issue},
month = {Jul},
abstract = {This manuscript describes a support vector machine based method for
the prediction of constitutive as well as immunoproteasome cleavage
sites in antigenic sequences. {T}his method achieved {M}atthew's
correlation coefficents of 0.54 and 0.43 on in vitro and major histocompatibility
complex ligand data, respectively. {T}his shows that the performance
of our method is comparable to that of the {N}et{C}hop method, which
is currently considered to be the best method for proteasome cleavage
site prediction. {B}ased on the method, a web server, {P}cleavage,
has also been developed. {T}his server accepts protein sequences
in any standard format and present results in a user-friendly format.
{T}he server is available for free use by all academic users at the
{URL} http://www.imtech.res.in/raghava/pcleavage/ or http://bioinformatics.uams.edu/mirror/pcleavage/.},
doi = {10.1093/nar/gki587},
pdf = {../local/Bhasin2005Pcleavage.pdf},
file = {Bhasin2005Pcleavage.pdf:local/Bhasin2005Pcleavage.pdf:PDF},
keywords = {biosvm immunoinformatics},
url = {http://dx.doi.org/10.1093/nar/gki587}
}
@article{Bhasin2004Analysis,
author = {Bhasin, M. and Raghava, G. P. S.},
title = {Analysis and prediction of affinity of {TAP} binding peptides using
cascade {SVM}},
journal = {Protein {S}ci.},
year = {2004},
volume = {13},
pages = {596-607},
number = {3},
month = {Mar},
abstract = {The generation of cytotoxic {T} lymphocyte ({CTL}) epitopes from an
antigenic sequence involves number of intracellular processes, including
production of peptide fragments by proteasome and transport of peptides
to endoplasmic reticulum through transporter associated with antigen
processing ({TAP}). {I}n this study, 409 peptides that bind to human
{TAP} transporter with varying affinity were analyzed to explore
the selectivity and specificity of {TAP} transporter. {T}he abundance
of each amino acid from {P}1 to {P}9 positions in high-, intermediate-,
and low-affinity {TAP} binders were examined. {T}he rules for predicting
{TAP} binding regions in an antigenic sequence were derived from
the above analysis. {T}he quantitative matrix was generated on the
basis of contribution of each position and residue in binding affinity.
{T}he correlation of r = 0.65 was obtained between experimentally
determined and predicted binding affinity by using a quantitative
matrix. {F}urther a support vector machine ({SVM})-based method has
been developed to model the {TAP} binding affinity of peptides. {T}he
correlation (r = 0.80) was obtained between the predicted and experimental
measured values by using sequence-based {SVM}. {T}he reliability
of prediction was further improved by cascade {SVM} that uses features
of amino acids along with sequence. {A}n extremely good correlation
(r = 0.88) was obtained between measured and predicted values, when
the cascade {SVM}-based method was evaluated through jackknife testing.
{A} {W}eb service, {TAPP}red (http://www.imtech.res.in/raghava/tappred/
or http://bioinformatics.uams.edu/mirror/tappred/), has been developed
based on this approach.},
doi = {10.1110/ps.03373104},
pdf = {../local/Bhasin2004Analysis.pdf},
file = {Bhasin2004Analysis.pdf:local/Bhasin2004Analysis.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1110/ps.03373104}
}
@article{Bhasin2004Classification,
author = {Bhasin, M. and Raghava, G. P. S.},
title = {Classification of {N}uclear {R}eceptors {B}ased on {A}mino {A}cid
{C}omposition and {D}ipeptide {C}omposition},
journal = {J. {B}iol. {C}hem.},
year = {2004},
volume = {279},
pages = {23262-23266},
number = {22},
abstract = {Nuclear receptors are key transcription factors that regulate crucial
gene networks responsible for cell growth, differentiation, and homeostasis.
{N}uclear receptors form a superfamily of phylogenetically related
proteins and control functions associated with major diseases (e.g.
diabetes, osteoporosis, and cancer). {I}n this study, a novel method
has been developed for classifying the subfamilies of nuclear receptors.
{T}he classification was achieved on the basis of amino acid and
dipeptide composition from a sequence of receptors using support
vector machines. {T}he training and testing was done on a non-redundant
data set of 282 proteins obtained from the {N}uclea{RDB} data base
(1). {T}he performance of all classifiers was evaluated using a 5-fold
cross validation test. {I}n the 5-fold cross-validation, the data
set was randomly partitioned into five equal sets and evaluated five
times on each distinct set while keeping the remaining four sets
for training. {I}t was found that different subfamilies of nuclear
receptors were quite closely correlated in terms of amino acid composition
as well as dipeptide composition. {T}he overall accuracy of amino
acid composition-based and dipeptide compositionbased classifiers
were 82.6 and 97.5%, respectively. {T}herefore, our results prove
that different subfamilies of nuclear receptors are predictable with
considerable accuracy using amino acid or dipeptide composition.
{F}urthermore, based on above approach, an online web service, {NR}pred,
was developed, which is available at www.imtech.res.in/raghava/nrpred.},
doi = {10.1074/jbc.M401932200},
eprint = {http://www.jbc.org/cgi/reprint/279/22/23262.pdf},
pdf = {../local/Bhasin2004Classification.pdf},
file = {Bhasin2004Classification.pdf:local/Bhasin2004Classification.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1074/jbc.M401932200}
}
@article{Bhasin2004ESLpred,
author = {Bhasin, M. and Raghava, G. P. S.},
title = {{{ESL}pred: {SVM}}-based method for subcellular localization of eukaryotic
proteins using dipeptide composition and {{PSI}-{BLAST}}},
journal = {Nucl. {A}cids {R}es.},
year = {2004},
volume = {32},
pages = {W414-419},
number = {Suppl. 2},
abstract = {Automated prediction of subcellular localization of proteins is an
important step in the functional annotation of genomes. {T}he existing
subcellular localization prediction methods are based on either amino
acid composition or {N}-terminal characteristics of the proteins.
{I}n this paper, support vector machine ({SVM}) has been used to
predict the subcellular location of eukaryotic proteins from their
different features such as amino acid composition, dipeptide composition
and physico-chemical properties. {T}he {SVM} module based on dipeptide
composition performed better than the {SVM} modules based on amino
acid composition or physico-chemical properties. {I}n addition, {PSI}-{BLAST}
was also used to search the query sequence against the dataset of
proteins (experimentally annotated proteins) to predict its subcellular
location. {I}n order to improve the prediction accuracy, we developed
a hybrid module using all features of a protein, which consisted
of an input vector of 458 dimensions (400 dipeptide compositions,
33 properties, 20 amino acid compositions of the protein and 5 from
{PSI}-{BLAST} output). {U}sing this hybrid approach, the prediction
accuracies of nuclear, cytoplasmic, mitochondrial and extracellular
proteins reached 95.3, 85.2, 68.2 and 88.9%, respectively. {T}he
overall prediction accuracy of {SVM} modules based on amino acid
composition, physico-chemical properties, dipeptide composition and
the hybrid approach was 78.1, 77.8, 82.9 and 88.0%, respectively.
{T}he accuracy of all the modules was evaluated using a 5-fold cross-validation
technique. {A}ssigning a reliability index (reliability index > or
=3), 73.5% of prediction can be made with an accuracy of 96.4%. {B}ased
on the above approach, an online web server {ESL}pred was developed,
which is available at http://www.imtech.res.in/raghava/eslpred/.},
doi = {10.1093/nar/gkh350},
eprint = {http://nar.oupjournals.org/cgi/reprint/32/suppl_2/W414.pdf},
pdf = {../local/Bhasin2004ESLpred.pdf},
file = {Bhasin2004ESLpred.pdf:local/Bhasin2004ESLpred.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://nar.oupjournals.org/cgi/content/abstract/32/suppl_2/W414}
}
@article{Bhasin2004GPCRpred,
author = {Bhasin, M. and Raghava, G. P. S.},
title = {{{GPCR}pred}: an {SVM}-based method for prediction of families and
subfamilies of {G}-protein coupled receptors},
journal = {Nucl. {A}cids {R}es.},
year = {2004},
volume = {32},
pages = {W383-389},
number = {Supp.2},
abstract = {G-protein coupled receptors ({GPCR}s) belong to one of the largest
superfamilies of membrane proteins and are important targets for
drug design. {I}n this study, a support vector machine ({SVM})-based
method, {GPCR}pred, has been developed for predicting families and
subfamilies of {GPCR}s from the dipeptide composition of proteins.
{T}he dataset used in this study for training and testing was obtained
from http://www.soe.ucsc.edu/research/compbio/gpcr/. {T}he method
classified {GPCR}s and non-{GPCR}s with an accuracy of 99.5% when
evaluated using 5-fold cross-validation. {T}he method is further
able to predict five major classes or families of {GPCR}s with an
overall {M}atthew's correlation coefficient ({MCC}) and accuracy
of 0.81 and 97.5% respectively. {I}n recognizing the subfamilies
of the rhodopsin-like family, the method achieved an average {MCC}
and accuracy of 0.97 and 97.3% respectively. {T}he method achieved
overall accuracy of 91.3% and 96.4% at family and subfamily level
respectively when evaluated on an independent/blind dataset of 650
{GPCR}s. {A} server for recognition and classification of {GPCR}s
based on multiclass {SVM}s has been set up at http://www.imtech.res.in/raghava/gpcrpred/.
{W}e have also suggested subfamilies for 42 sequences which were
previously identified as unclassified {C}lass{A} {GPCR}s. {T}he supplementary
information is available at http://www.imtech.res.in/raghava/gpcrpred/info.html.},
doi = {10.1093/nar/gkh416},
eprint = {http://nar.oupjournals.org/cgi/reprint/32/suppl_2/W383.pdf},
pdf = {../local/Bhasin2004GPCRpred.pdf},
file = {Bhasin2004GPCRpred.pdf:local/Bhasin2004GPCRpred.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1093/nar/gkh416}
}
@article{Bhasin2004Prediction,
author = {Bhasin, M. and Raghava, G. P. S.},
title = {Prediction of {CTL} epitopes using {QM}, {SVM} and {ANN} techniques},
journal = {Vaccine},
year = {2004},
volume = {22},
pages = {3195-3204},
number = {23-24},
abstract = {Cytotoxic {T} lymphocyte ({CTL}) epitopes are potential candidates
for subunit vaccine design for various diseases. {M}ost of the existing
{T} cell epitope prediction methods are indirect methods that predict
{MHC} class {I} binders instead of {CTL} epitopes. {I}n this study,
a systematic attempt has been made to develop a direct method for
predicting {CTL} epitopes from an antigenic sequence. {T}his method
is based on quantitative matrix ({QM}) and machine learning techniques
such as {S}upport {V}ector {M}achine ({SVM}) and {A}rtificial {N}eural
{N}etwork ({ANN}). {T}his method has been trained and tested on non-redundant
dataset of {T} cell epitopes and non-epitopes that includes 1137
experimentally proven {MHC} class {I} restricted {T} cell epitopes.
{T}he accuracy of {QM}-, {ANN}- and {SVM}-based methods was 70.0,
72.2 and 75.2%, respectively. {T}he performance of these methods
has been evaluated through {L}eave {O}ne {O}ut {C}ross-{V}alidation
({LOOCV}) at a cutoff score where sensitivity and specificity was
nearly equal. {F}inally, both machine-learning methods were used
for consensus and combined prediction of {CTL} epitopes. {T}he performances
of these methods were evaluated on blind dataset where machine learning-based
methods perform better than {QM}-based method. {W}e also demonstrated
through subgroup analysis that our methods can discriminate between
{T}-cell epitopes and {MHC} binders (non-epitopes). {I}n brief this
method allows prediction of {CTL} epitopes using {QM}, {SVM}, {ANN}
approaches. {T}he method also facilitates prediction of {MHC} restriction
in predicted {T} cell epitopes.},
doi = {10.1016/j.vaccine.2004.02.005},
pdf = {../local/Bhasin2004Prediction.pdf},
file = {Bhasin2004Prediction.pdf:local/Bhasin2004Prediction.pdf:PDF},
keywords = {biosvm immunoinformatics},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/j.vaccine.2004.02.005}
}
@article{Bhasin2004SVM,
author = {Bhasin, M. and Raghava, G. P. S.},
title = {S{VM} based method for predicting {{HLA}-{DRB}1*0401} binding peptides
in an antigen sequence},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {421-423},
number = {3},
abstract = {Summary: {P}rediction of peptides binding with {MHC} class {II} allele
{HLA}-{DRB}1*0401 can effectively reduce the number of experiments
required for identifying helper {T} cell epitopes. {T}his paper describes
support vector machine ({SVM}) based method developed for identifying
{HLA}-{DRB}1*0401 binding peptides in an antigenic sequence. {SVM}
was trained and tested on large and clean data set consisting of
567 binders and equal number of non-binders. {T}he accuracy of the
method was 86% when evaluated through 5-fold cross-validation technique.
{A}vailable: {A} web server {HLA}-{DR}4{P}red based on above approach
is available at http://www.imtech.res.in/raghava/hladr4pred/ and
http://bioinformatics.uams.edu/mirror/hladr4pred/ ({M}irror {S}ite).
{S}upplementary information: http://www.imtech.res.in/raghava/hladr4pred/info.html},
pdf = {../local/Bhasin2004SVM.pdf},
file = {Bhasin2004SVM.pdf:local/Bhasin2004SVM.pdf:PDF},
keywords = {biosvm immunoinformatics},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/3/421}
}
@article{Bock2003Whole-proteome,
author = {Bock, J. R. and Gough, D. A.},
title = {Whole-proteome interaction mining},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {125-134},
number = {1},
abstract = {Motivation: {A} major post-genomic scientific and technological pursuit
is to describe the functions performed by the proteins encoded by
the genome. {O}ne strategy is to first identify the protein-protein
interactions in a proteome, then determine pathways and overall structure
relating these interactions, and finally to statistically infer functional
roles of individual proteins. {A}lthough huge amounts of genomic
data are at hand, current experimental protein interaction assays
must overcome technical problems to scale-up for high-throughput
analysis. {I}n the meantime, bioinformatics approaches may help bridge
the information gap required for inference of protein function. {I}n
this paper, a previously described data mining approach to prediction
of protein-protein interactions ({B}ock and {G}ough, 2001, {B}ioinformatics,
17, 455-460) is extended to interaction mining on a proteome-wide
scale. {A}n algorithm (the phylogenetic bootstrap) is introduced,
which suggests traversal of a phenogram, interleaving rounds of computation
and experiment, to develop a knowledge base of protein interactions
in genetically-similar organisms. {R}esults: {T}he interaction mining
approach was demonstrated by building a learning system based on
1,039 experimentally validated protein-protein interactions in the
human gastric bacterium {H}elicobacter pylori. {A}n estimate of the
generalization performance of the classifier was derived from 10-fold
cross-validation, which indicated expected upper bounds on precision
of 80% and sensitivity of 69% when applied to related organisms.
{O}ne such organism is the enteric pathogen {C}ampylobacter jejuni,
in which comprehensive machine learning prediction of all possible
pairwise protein-protein interactions was performed. {T}he resulting
network of interactions shares an average protein connectivity characteristic
in common with previous investigations reported in the literature,
offering strong evidence supporting the biological feasibility of
the hypothesized map. {F}or inferences about complete proteomes in
which the number of pairwise non-interactions is expected to be much
larger than the number of actual interactions, we anticipate that
the sensitivity will remain the same but precision may decrease.
{W}e present specific biological examples of two subnetworks of protein-protein
interactions in {C}. jejuni resulting from the application of this
approach, including elements of a two-component signal transduction
systems for thermoregulation, and a ferritin uptake network. {C}ontact:
dgough@bioeng.ucsd.edu},
pdf = {../local/Bock2003Whole-proteome.pdf},
file = {Bock2003Whole-proteome.pdf:local/Bock2003Whole-proteome.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/1/125}
}
@article{Bock2002New,
author = {Bock, J. R. and Gough, D. A.},
title = {A {N}ew {M}ethod to {E}stimate {L}igand-{R}eceptor {E}nergetics},
journal = {Mol {C}ell {P}roteomics},
year = {2002},
volume = {1},
pages = {904-910},
number = {11},
abstract = {In the discovery of new drugs, lead identification and optimization
have assumed critical importance given the number of drug targets
generated from genetic, genomics, and proteomic technologies. {H}igh-throughput
experimental screening assays have been complemented recently by
"virtual screening" approaches to identify and filter potential ligands
when the characteristics of a target receptor structure of interest
are known. {V}irtual screening mandates a reliable procedure for
automatic ranking of structurally distinct ligands in compound library
databases. {C}omputing a rank score requires the accurate prediction
of binding affinities between these ligands and the target. {M}any
current scoring strategies require information about the target three-dimensional
structure. {I}n this study, a new method to estimate the free binding
energy between a ligand and receptor is proposed. {W}e extend a central
idea previously reported ({B}ock, {J}. {R}., and {G}ough, {D}. {A}.
(2001) {P}redicting protein-protein interactions from primary structure.
{B}ioinformatics 17, 455-460; {B}ock, {J}. {R}., and {G}ough, {D}.
{A}. (2002) {W}hole-proteome interaction mining. {B}ioinformatics,
in press) that uses simple descriptors to represent biomolecules
as input examples to train a support vector machine ({S}mola, {A}.
{J}., and {S}cholkopf, {B}. (1998) {A} {T}utorial on {S}upport {V}ector
{R}egression, {N}euro{COLT} {T}echnical {R}eport {NC}-{TR}-98-030,
{R}oyal {H}olloway {C}ollege, {U}niversity of {L}ondon, {UK}) and
the application of the trained system to previously unseen pairs,
estimating their propensity for interaction. {H}ere we seek to learn
the function that maps features of a receptor-ligand pair onto their
equilibrium free binding energy. {T}hese features do not comprise
any direct information about the three-dimensional structures of
ligand or target. {I}n cross-validation experiments, it is demonstrated
that objective measurements of prediction error rate and rank-ordering
statistics are competitive with those of several other investigations,
most of which depend on three-dimensional structural data. {T}he
size of the sample (n = 2,671) indicates that this approach is robust
and may have widespread applicability beyond restricted families
of receptor types. {I}t is concluded that newly sequenced proteins,
or those for which three-dimensional crystal structures are not easily
obtained, can be rapidly analyzed for their binding potential against
a library of ligands using this methodology.},
pdf = {../local/Bock2002New.pdf},
file = {Bock2002New.pdf:local/Bock2002New.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.mcponline.org/cgi/content/abstract/1/11/904}
}
@article{Bock2001Predicting,
author = {Bock, J. R. and Gough, D. A.},
title = {Predicting protein-protein interactions from primary structure},
journal = {Bioinformatics},
year = {2001},
volume = {17},
pages = {455--460},
number = {5},
pdf = {../local/bock01.pdf},
file = {bock01.pdf:local/bock01.pdf:PDF},
keywords = {biosvm},
subject = {biokernel},
url = {http://bioinformatics.oupjournals.org/cgi/reprint/17/5/455.pdf}
}
@article{Bordner2005Statistical,
author = {Andrew J Bordner and Ruben Abagyan},
title = {Statistical analysis and prediction of protein-protein interfaces.},
journal = {Proteins},
year = {2005},
volume = {60},
pages = {353-66},
number = {3},
month = {Aug},
abstract = {Predicting protein-protein interfaces from a three-dimensional structure
is a key task of computational structural proteomics. {I}n contrast
to geometrically distinct small molecule binding sites, protein-protein
interface are notoriously difficult to predict. {W}e generated a
large nonredundant data set of 1494 true protein-protein interfaces
using biological symmetry annotation where necessary. {T}he data
set was carefully analyzed and a {S}upport {V}ector {M}achine was
trained on a combination of a new robust evolutionary conservation
signal with the local surface properties to predict protein-protein
interfaces. {F}ivefold cross validation verifies the high sensitivity
and selectivity of the model. {A}s much as 97\% of the predicted
patches had an overlap with the true interface patch while only 22\%
of the surface residues were included in an average predicted patch.
{T}he model allowed the identification of potential new interfaces
and the correction of mislabeled oligomeric states.},
doi = {10.1002/prot.20433},
pdf = {../local/Bordner2005Statistical.pdf},
file = {Bordner2005Statistical.pdf:local/Bordner2005Statistical.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1002/prot.20433}
}
@article{Borgwardt2005Protein,
author = {Borgwardt, K.M. and Ong, C.S. and Sch{\"o}nauer, S. and Vishwanathan,
S.V.N. and Smola, A.J. and Kriegel, H.-P.},
title = {Protein function prediction via graph kernels.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {i47-i56},
number = {Suppl. 1},
month = {Jun},
abstract = {M{OTIVATION}: {C}omputational approaches to protein function prediction
infer protein function by finding proteins with similar sequence,
structure, surface clefts, chemical properties, amino acid motifs,
interaction partners or phylogenetic profiles. {W}e present a new
approach that combines sequential, structural and chemical information
into one graph model of proteins. {W}e predict functional class membership
of enzymes and non-enzymes using graph kernels and support vector
machine classification on these protein graphs. {RESULTS}: {O}ur
graph model, derivable from protein sequence and structure only,
is competitive with vector models that require additional protein
information, such as the size of surface pockets. {I}f we include
this extra information into our graph model, our classifier yields
significantly higher accuracy levels than the vector models. {H}yperkernels
allow us to select and to optimally combine the most relevant node
attributes in our protein graphs. {W}e have laid the foundation for
a protein function prediction system that integrates protein information
from various sources efficiently and effectively. {AVAILABILITY}:
{M}ore information available via www.dbs.ifi.lmu.de/{M}itarbeiter/borgwardt.html.
{CONTACT}: borgwardt@dbs.ifi.lmu.de.},
doi = {10.1093/bioinformatics/bti1007},
pdf = {../local/Borgwardt2005Protein.pdf},
file = {Borgwardt2005Protein.pdf:local/Borgwardt2005Protein.pdf:PDF},
keywords = {biosvm},
pii = {21/suppl_1/i47},
url = {http://dx.doi.org/10.1093/bioinformatics/bti1007}
}
@article{Bradford2005Improved,
author = {James R Bradford and David R Westhead},
title = {Improved prediction of protein-protein binding sites using a support
vector machines approach.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {1487-94},
number = {8},
month = {Apr},
abstract = {M{OTIVATION}: {S}tructural genomics projects are beginning to produce
protein structures with unknown function, therefore, accurate, automated
predictors of protein function are required if all these structures
are to be properly annotated in reasonable time. {I}dentifying the
interface between two interacting proteins provides important clues
to the function of a protein and can reduce the search space required
by docking algorithms to predict the structures of complexes. {RESULTS}:
{W}e have combined a support vector machine ({SVM}) approach with
surface patch analysis to predict protein-protein binding sites.
{U}sing a leave-one-out cross-validation procedure, we were able
to successfully predict the location of the binding site on 76\%
of our dataset made up of proteins with both transient and obligate
interfaces. {W}ith heterogeneous cross-validation, where we trained
the {SVM} on transient complexes to predict on obligate complexes
(and vice versa), we still achieved comparable success rates to the
leave-one-out cross-validation suggesting that sufficient properties
are shared between transient and obligate interfaces. {AVAILABILITY}:
{A} web application based on the method can be found at http://www.bioinformatics.leeds.ac.uk/ppi_pred.
{T}he dataset of 180 proteins used in this study is also available
via the same web site. {CONTACT}: westhead@bmb.leeds.ac.uk {SUPPLEMENTARY}
{INFORMATION}: http://www.bioinformatics.leeds.ac.uk/ppi-pred/supp-material.},
doi = {10.1093/bioinformatics/bti242},
pdf = {../local/Bradford2005Improved.pdf},
file = {Bradford2005Improved.pdf:local/Bradford2005Improved.pdf:PDF},
keywords = {biosvm},
pii = {bti242},
url = {http://dx.doi.org/10.1093/bioinformatics/bti242}
}
@article{Briem2005Classifying,
author = {Hans Briem and Judith G{\"u}nther},
title = {Classifying "kinase inhibitor-likeness" by using machine-learning
methods.},
journal = {ChemBioChem},
year = {2005},
volume = {6},
pages = {558-66},
number = {3},
month = {Mar},
abstract = {By using an in-house data set of small-molecule structures, encoded
by {G}hose-{C}rippen parameters, several machine learning techniques
were applied to distinguish between kinase inhibitors and other molecules
with no reported activity on any protein kinase. {A}ll four approaches
pursued--support-vector machines ({SVM}), artificial neural networks
({ANN}), k nearest neighbor classification with {GA}-optimized feature
selection ({GA}/k{NN}), and recursive partitioning ({RP})--proved
capable of providing a reasonable discrimination. {N}evertheless,
substantial differences in performance among the methods were observed.
{F}or all techniques tested, the use of a consensus vote of the 13
different models derived improved the quality of the predictions
in terms of accuracy, precision, recall, and {F}1 value. {S}upport-vector
machines, followed by the {GA}/k{NN} combination, outperformed the
other techniques when comparing the average of individual models.
{B}y using the respective majority votes, the prediction of neural
networks yielded the highest {F}1 value, followed by {SVM}s.},
doi = {10.1002/cbic.200400109},
pdf = {../local/Briem2005Classifying.pdf},
file = {Briem2005Classifying.pdf:local/Briem2005Classifying.pdf:PDF},
keywords = {biosvm chemoinformatics},
url = {http://dx.doi.org/10.1002/cbic.200400109}
}
@article{Brown2000Knowledge-based,
author = {Brown, M. P. and Grundy, W. N. and Lin, D. and Cristianini, N. and
Sugnet, C. W. and Furey, T. S. and Ares, M. and Haussler, D.},
title = {Knowledge-based analysis of microarray gene expression data by using
support vector machines.},
journal = {Proc. {N}atl. {A}cad. {S}ci. {USA}},
year = {2000},
volume = {97},
pages = {262-7},
number = {1},
month = {Jan},
abstract = {We introduce a method of functionally classifying genes by using gene
expression data from {DNA} microarray hybridization experiments.
{T}he method is based on the theory of support vector machines ({SVM}s).
{SVM}s are considered a supervised computer learning method because
they exploit prior knowledge of gene function to identify unknown
genes of similar function from expression data. {SVM}s avoid several
problems associated with unsupervised clustering methods, such as
hierarchical clustering and self-organizing maps. {SVM}s have many
mathematical features that make them attractive for gene expression
analysis, including their flexibility in choosing a similarity function,
sparseness of solution when dealing with large data sets, the ability
to handle large feature spaces, and the ability to identify outliers.
{W}e test several {SVM}s that use different similarity metrics, as
well as some other supervised learning methods, and find that the
{SVM}s best identify sets of genes with a common function using expression
data. {F}inally, we use {SVM}s to predict functional roles for uncharacterized
yeast {ORF}s based on their expression data.},
pdf = {../local/Brown2000Knowledge-based.pdf},
file = {Brown2000Knowledge-based.pdf:local/Brown2000Knowledge-based.pdf:PDF},
keywords = {biosvm microarray},
url = {http://www.pnas.org/cgi/content/abstract/97/1/262}
}
@article{Bunescu2005Comparative,
author = {Bunescu, R. and Ge, R. and Kate, R. J. and Marcotte, E. M. and Mooney,
R. J. and Ramani, A. K. and Wong, Y. W.},
title = {Comparative experiments on learning information extractors for proteins
and their interactions.},
journal = {Artif. {I}ntell. {M}ed.},
year = {2005},
volume = {33},
pages = {139-55},
number = {2},
month = {Feb},
abstract = {O{BJECTIVE}: {A}utomatically extracting information from biomedical
text holds the promise of easily consolidating large amounts of biological
knowledge in computer-accessible form. {T}his strategy is particularly
attractive for extracting data relevant to genes of the human genome
from the 11 million abstracts in {M}edline. {H}owever, extraction
efforts have been frustrated by the lack of conventions for describing
human genes and proteins. {W}e have developed and evaluated a variety
of learned information extraction systems for identifying human protein
names in {M}edline abstracts and subsequently extracting information
on interactions between the proteins. {METHODS} {AND} {MATERIAL}:
{W}e used a variety of machine learning methods to automatically
develop information extraction systems for extracting information
on gene/protein name, function and interactions from {M}edline abstracts.
{W}e present cross-validated results on identifying human proteins
and their interactions by training and testing on a set of approximately
1000 manually-annotated {M}edline abstracts that discuss human genes/proteins.
{RESULTS}: {W}e demonstrate that machine learning approaches using
support vector machines and maximum entropy are able to identify
human proteins with higher accuracy than several previous approaches.
{W}e also demonstrate that various rule induction methods are able
to identify protein interactions with higher precision than manually-developed
rules. {CONCLUSION}: {O}ur results show that it is promising to use
machine learning to automatically build systems for extracting information
from biomedical text. {T}he results also give a broad picture of
the relative strengths of a wide variety of methods when tested on
a reasonably large human-annotated corpus.},
doi = {10.1016/j.artmed.2004.07.016},
pdf = {../local/Bunescu2005Comparative.pdf},
file = {Bunescu2005Comparative.pdf:local/Bunescu2005Comparative.pdf:PDF},
keywords = {biosvm},
pii = {S0933-3657(04)00131-9},
url = {http://dx.doi.org/10.1016/j.artmed.2004.07.016}
}
@article{Burbidge2001Drug,
author = {Burbidge, R. and Trotter, M. and Buxton, B. and Holden, S.},
title = {Drug design by machine learning: support vector machines for pharmaceutical
data analysis},
journal = {Comput. {C}hem.},
year = {2001},
volume = {26},
pages = {4--15},
number = {1},
month = {December},
pdf = {../local/burb01.pdf},
file = {burb01.pdf:local/burb01.pdf:PDF},
keywords = {biosvm chemoinformatics},
subject = {qsar},
url = {http://stats.ma.ic.ac.uk/~rdb/pubs/candc-aisb00-rbmt-final.pdf}
}
@article{Burckin2005Exploring,
author = {Burckin, T. and Nagel, R. and Mandel-Gutfreund, Y. and Shiue, L.
and Clark, T. A. and Chong, J.-L. and Chang, T.-H. and Squazzo, S.
and Hartzog, G. and Ares, M.},
title = {Exploring functional relationships between components of the gene
expression machinery.},
journal = {Nat. {S}truct. {M}ol. {B}iol.},
year = {2005},
volume = {12},
pages = {175-82},
number = {2},
month = {Feb},
abstract = {Eukaryotic gene expression requires the coordinated activity of many
macromolecular machines including transcription factors and {RNA}
polymerase, the spliceosome, m{RNA} export factors, the nuclear pore,
the ribosome and decay machineries. {Y}east carrying mutations in
genes encoding components of these machineries were examined using
microarrays to measure changes in both pre-m{RNA} and m{RNA} levels.
{W}e used these measurements as a quantitative phenotype to ask how
steps in the gene expression pathway are functionally connected.
{A} multiclass support vector machine was trained to recognize the
gene expression phenotypes caused by these mutations. {I}n several
cases, unexpected phenotype assignments by the computer revealed
functional roles for specific factors at multiple steps in the gene
expression pathway. {T}he ability to resolve gene expression pathway
phenotypes provides insight into how the major machineries of gene
expression communicate with each other.},
doi = {10.1038/nsmb891},
pdf = {../local/Burckin2005Exploring.pdf},
file = {Burckin2005Exploring.pdf:local/Burckin2005Exploring.pdf:PDF},
keywords = {biosvm microarray},
pii = {nsmb891},
url = {http://dx.doi.org/10.1038/nsmb891}
}
@article{Busuttil2004Support,
author = {Busuttil, S. and Abela, J. and Pace, G. J.},
title = {Support vector machines with profile-based kernels for remote protein
homology detection.},
journal = {Genome {I}nform {S}er {W}orkshop {G}enome {I}nform},
year = {2004},
volume = {15},
pages = {191-200},
number = {2},
abstract = {Two new techniques for remote protein homology detection particulary
suited for sparse data are introduced. {T}hese methods are based
on position specific scoring matrices or profiles and use a support
vector machine ({SVM}) for discrimination. {T}he performance on standard
benchmarks outperforms previous non-discriminative techniques and
is comparable to that of other {SVM}-based methods while giving distinct
advantages.},
pdf = {../local/Busuttil2004Support.pdf},
file = {Busuttil2004Support.pdf:local/Busuttil2004Support.pdf:PDF},
keywords = {biosvm},
url = {http://www.jsbi.org/journal/GIW04/GIW04F020.html}
}
@article{Byvatov2003Comparison,
author = {Byvatov, E. and Fechner, U. and Sadowski, J. and Schneider, G.},
title = {Comparison of support vector machine and artificial neural network
systems for drug/nondrug classification.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2003},
volume = {43},
pages = {1882-9},
number = {6},
abstract = {Support vector machine ({SVM}) and artificial neural network ({ANN})
systems were applied to a drug/nondrug classification problem as
an example of binary decision problems in early-phase virtual compound
filtering and screening. {T}he results indicate that solutions obtained
by {SVM} training seem to be more robust with a smaller standard
error compared to {ANN} training. {G}enerally, the {SVM} classifier
yielded slightly higher prediction accuracy than {ANN}, irrespective
of the type of descriptors used for molecule encoding, the size of
the training data sets, and the algorithm employed for neural network
training. {T}he performance was compared using various different
descriptor sets and descriptor combinations based on the 120 standard
{G}hose-{C}rippen fragment descriptors, a wide range of 180 different
properties and physicochemical descriptors from the {M}olecular {O}perating
{E}nvironment ({MOE}) package, and 225 topological pharmacophore
({CATS}) descriptors. {F}or the complete set of 525 descriptors cross-validated
classification by {SVM} yielded 82\% correct predictions ({M}atthews
cc = 0.63), whereas {ANN} reached 80\% correct predictions ({M}atthews
cc = 0.58). {A}lthough {SVM} outperformed the {ANN} classifiers with
regard to overall prediction accuracy, both methods were shown to
complement each other, as the sets of true positives, false positives
(overprediction), true negatives, and false negatives (underprediction)
produced by the two classifiers were not identical. {T}he theory
of {SVM} and {ANN} training is briefly reviewed.},
doi = {10.1021/ci0341161},
pdf = {../local/Byvatov2003Comparison.pdf},
file = {Byvatov2003Comparison.pdf:local/Byvatov2003Comparison.pdf:PDF},
keywords = {biosvm chemoinformatics},
url = {http://dx.doi.org/10.1021/ci0341161}
}
@article{Byvatov2004SVM-based,
author = {Evgeny Byvatov and Gisbert Schneider},
title = {S{VM}-based feature selection for characterization of focused compound
collections.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2004},
volume = {44},
pages = {993-9},
number = {3},
abstract = {Artificial neural networks, the support vector machine ({SVM}), and
other machine learning methods for the classification of molecules
are often considered as a "black box", since the molecular features
that are most relevant for a given classifier are usually not presented
in a human-interpretable form. {W}e report on an {SVM}-based algorithm
for the selection of relevant molecular features from a trained classifier
that might be important for an understanding of ligand-receptor interactions.
{T}he original {SVM} approach was extended to allow for feature selection.
{T}he method was applied to characterize focused libraries of enzyme
inhibitors. {A} comparison with classical {K}olmogorov-{S}mirnov
({KS})-based feature selection was performed. {I}n most of the applications
the {SVM} method showed sustained classification accuracy, thereby
relying on a smaller number of molecular features than {KS}-based
classifiers. {I}n one case both methods produced comparable results.
{L}imiting the calculation of descriptors to only the most relevant
ones for a certain biological activity can also be used to speed
up high-throughput virtual screening.},
doi = {10.1021/ci0342876},
pdf = {../local/Byvatov2004SVM-based.pdf},
file = {Byvatov2004SVM-based.pdf:local/Byvatov2004SVM-based.pdf:PDF},
keywords = {biosvm chemoinformatics featureselection},
url = {http://dx.doi.org/10.1021/ci0342876}
}
@article{Byvatov2003Support,
author = {E. Byvatov and G. Schneider},
title = {Support vector machine applications in bioinformatics.},
journal = {Appl {B}ioinformatics},
year = {2003},
volume = {2},
pages = {67-77},
number = {2},
abstract = {The support vector machine ({SVM}) approach represents a data-driven
method for solving classification tasks. {I}t has been shown to produce
lower prediction error compared to classifiers based on other methods
like artificial neural networks, especially when large numbers of
features are considered for sample description. {I}n this review,
the theory and main principles of the {SVM} approach are outlined,
and successful applications in traditional areas of bioinformatics
research are described. {C}urrent developments in techniques related
to the {SVM} approach are reviewed which might become relevant for
future functional genomics and chemogenomics projects. {I}n a comparative
study, we developed neural network and {SVM} models to identify small
organic molecules that potentially modulate the function of {G}-protein
coupled receptors. {T}he {SVM} system was able to correctly classify
approximately 90\% of the compounds in a cross-validation study yielding
a {M}atthews correlation coefficient of 0.78. {T}his classifier can
be used for fast filtering of compound libraries in virtual screening
applications.},
keywords = {biosvm}
}
@article{Cai2004Enzyme,
author = {Cai, C.Z. and Han, L.Y. and Ji, Z.L. and Chen, Y.Z.},
title = {Enzyme family classification by support vector machines.},
journal = {Proteins},
year = {2004},
volume = {55},
pages = {66-76},
number = {1},
abstract = {One approach for facilitating protein function prediction is to classify
proteins into functional families. {R}ecent studies on the classification
of {G}-protein coupled receptors and other proteins suggest that
a statistical learning method, {S}upport vector machines ({SVM}),
may be potentially useful for protein classification into functional
families. {I}n this work, {SVM} is applied and tested on the classification
of enzymes into functional families defined by the {E}nzyme {N}omenclature
{C}ommittee of {IUBMB}. {SVM} classification system for each family
is trained from representative enzymes of that family and seed proteins
of {P}fam curated protein families. {T}he classification accuracy
for enzymes from 46 families and for non-enzymes is in the range
of 50.0% to 95.7% and 79.0% to 100% respectively. {T}he corresponding
{M}atthews correlation coefficient is in the range of 54.1% to 96.1%.
{M}oreover, 80.3% of the 8,291 correctly classified enzymes are uniquely
classified into a specific enzyme family by using a scoring function,
indicating that {SVM} may have certain level of unique prediction
capability. {T}esting results also suggest that {SVM} in some cases
is capable of classification of distantly related enzymes and homologous
enzymes of different functions. {E}ffort is being made to use a more
comprehensive set of enzymes as training sets and to incorporate
multi-class {SVM} classification systems to further enhance the unique
prediction accuracy. {O}ur results suggest the potential of {SVM}
for enzyme family classification and for facilitating protein function
prediction. {O}ur software is accessible at http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi.},
doi = {10.1002/prot.20045},
pdf = {../local/Cai2004Enzyme.pdf},
file = {Cai2004Enzyme.pdf:local/Cai2004Enzyme.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/prot.20045}
}
@article{Cai2003Protein,
author = {Cai, C.Z. and Wang, W.L. and Sun, L.Z. and Chen, Y.Z.},
title = {Protein function classification via support vector machine approach.},
journal = {Math. {B}iosci.},
year = {2003},
volume = {185},
pages = {111-122},
number = {2},
abstract = {Support vector machine ({SVM}) is introduced as a method for the classification
of proteins into functionally distinguished classes. {S}tudies are
conducted on a number of protein classes including {RNA}-binding
proteins; protein homodimers, proteins responsible for drug absorption,
proteins involved in drug distribution and excretion, and drug metabolizing
enzymes. {T}esting accuracy for the classification of these protein
classes is found to be in the range of 84-96%. {T}his suggests the
usefulness of {SVM} in the classification of protein functional classes
and its potential application in protein function prediction.},
doi = {10.1016/S0025-5564(03)00096-8},
pdf = {../local/Cai2003Protein.pdf},
file = {Cai2003Protein.pdf:local/Cai2003Protein.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Cai2003SVM-Prot,
author = {C. Z. Cai and L. Y. Han and Z. L. Ji and X. Chen and Y. Z. Chen},
title = {S{VM}-{P}rot: {W}eb-based support vector machine software for functional
classification of a protein from its primary sequence.},
journal = {Nucleic {A}cids {R}es},
year = {2003},
volume = {31},
pages = {3692-7},
number = {13},
month = {Jul},
abstract = {Prediction of protein function is of significance in studying biological
processes. {O}ne approach for function prediction is to classify
a protein into functional family. {S}upport vector machine ({SVM})
is a useful method for such classification, which may involve proteins
with diverse sequence distribution. {W}e have developed a web-based
software, {SVMP}rot, for {SVM} classification of a protein into functional
family from its primary sequence. {SVMP}rot classification system
is trained from representative proteins of a number of functional
families and seed proteins of {P}fam curated protein families. {I}t
currently covers 54 functional families and additional families will
be added in the near future. {T}he computed accuracy for protein
family classification is found to be in the range of 69.1-99.6\%.
{SVMP}rot shows a certain degree of capability for the classification
of distantly related proteins and homologous proteins of different
function and thus may be used as a protein function prediction tool
that complements sequence alignment methods. {SVMP}rot can be accessed
at http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi.},
pdf = {../local/Cai2003SVM-Prot.pdf},
file = {Cai2003SVM-Prot.pdf:local/Cai2003SVM-Prot.pdf:PDF},
keywords = {biosvm},
url = {http://nar.oxfordjournals.org/cgi/content/abstract/31/13/3692}
}
@article{Cai2003Supportc,
author = {Cai, Y.D. and Feng, K.Y. and Li, Y.X. and Chou, K.C.},
title = {Support vector machine for predicting alpha-turn types.},
journal = {Peptides},
year = {2003},
volume = {24},
pages = {629-630},
number = {4},
abstract = {Tight turns play an important role in globular proteins from both
the structural and functional points of view. {O}f tight turns, beta-turns
and gamma-turns have been extensively studied, but alpha-turns were
little investigated. {R}ecently, a systematic search for alpha-turns
classified alpha-turns into nine different types according to their
backbone trajectory features. {I}n this paper, {S}upport {V}ector
{M}achines ({SVM}s), a new machine learning method, is proposed for
predicting the alpha-turn types in proteins. {T}he high rates of
correct prediction imply that that the formation of different alpha-turn
types is evidently correlated with the sequence of a pentapeptide,
and hence can be approximately predicted based on the sequence information
of the pentapeptide alone, although the incorporation of its interaction
with the other part of a protein, the so-called "long distance interaction",
will further improve the prediction quality.},
doi = {10.1016/S0196-9781(03)00100-1},
pdf = {../local/Cai2003Supportc.pdf},
file = {Cai2003Supportc.pdf:local/Cai2003Supportc.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/S0196-9781(03)00100-1}
}
@article{Cai2003Supportd,
author = {Cai, Y.D. and Lin, S.L.},
title = {Support vector machines for predicting r{RNA}-, {RNA}-, and {DNA}-binding
proteins from amino acid sequence.},
journal = {Biochim. {B}iophys. {A}cta},
year = {2003},
volume = {1648},
pages = {127-133},
number = {1-2},
abstract = {Classification of gene function remains one of the most important
and demanding tasks in the post-genome era. {M}ost of the current
predictive computer methods rely on comparing features that are essentially
linear to the protein sequence. {H}owever, features of a protein
nonlinear to the sequence may also be predictive to its function.
{M}achine learning methods, for instance the {S}upport {V}ector {M}achines
({SVM}s), are particularly suitable for exploiting such features.
{I}n this work we introduce {SVM} and the pseudo-amino acid composition,
a collection of nonlinear features extractable from protein sequence,
to the field of protein function prediction. {W}e have developed
prototype {SVM}s for binary classification of r{RNA}-, {RNA}-, and
{DNA}-binding proteins. {U}sing a protein's amino acid composition
and limited range correlation of hydrophobicity and solvent accessible
surface area as input, each of the {SVM}s predicts whether the protein
belongs to one of the three classes. {I}n self-consistency and cross-validation
tests, which measures the success of learning and prediction, respectively,
the r{RNA}-binding {SVM} has consistently achieved >95% accuracy.
{T}he {RNA}- and {DNA}-binding {SVM}s demonstrate more diverse accuracy,
ranging from approximately 76% to approximately 97%. {A}nalysis of
the test results suggests the directions of improving the {SVM}s.},
doi = {10.1016/S1570-9639(03)00112-2},
pdf = {../local/Cai2003Supportd.pdf},
file = {Cai2003Supportd.pdf:local/Cai2003Supportd.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/S1570-9639(03)00112-2}
}
@article{Cai2003Supporta,
author = {Cai, Y.D. and Lin, S.L. and Chou, K.C.},
title = {Support vector machines for prediction of protein signal sequences
and their cleavage sites},
journal = {Peptides},
year = {2003},
volume = {24},
pages = {159-161},
number = {1},
abstract = {Given a nascent protein sequence, how can one predict its signal peptide
or "{Z}ipcode" sequence? {T}his is an important problem for scientists
to use signal peptides as a vehicle to find new drugs or to reprogram
cells for gene therapy (see, e.g. [7] {K}.{C}. {C}hou, {C}urrent
{P}rotein and {P}eptide {S}cience 2002;3:615?22). {I}n this paper,
support vector machines ({SVM}s), a new machine learning method,
is applied to approach this problem. {T}he overall rate of correct
prediction for 1939 secretary proteins and 1440 nonsecretary proteins
was over 91%. {I}t has not escaped our attention that the new method
may also serve as a useful tool for further investigating many unclear
details regarding the molecular mechanism of the {ZIP} code protein-sorting
system in cells.},
doi = {10.1016/S0196-9781(02)00289-9},
pdf = {../local/Cai2003Supporta.pdf},
file = {Cai2003Supporta.pdf:local/Cai2003Supporta.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Cai2003Prediction,
author = {Cai, Y.D. and Liu, X.J. and Li, Y.X. and Xu, X.B. and Chou, K.C.},
title = {Prediction of beta-turns with learning machines.},
journal = {Peptides},
year = {2003},
volume = {24},
pages = {665-669},
number = {5},
abstract = {The support vector machine approach was introduced to predict the
beta-turns in proteins. {T}he overall self-consistency rate by the
re-substitution test for the training or learning dataset reached
100%. {B}oth the training dataset and independent testing dataset
were taken from {C}hou [{J}. {P}ept. {R}es. 49 (1997) 120]. {T}he
success prediction rates by the jackknife test for the beta-turn
subset of 455 tetrapeptides and non-beta-turn subset of 3807 tetrapeptides
in the training dataset were 58.1 and 98.4%, respectively. {T}he
success rates with the independent dataset test for the beta-turn
subset of 110 tetrapeptides and non-beta-turn subset of 30,231 tetrapeptides
were 69.1 and 97.3%, respectively. {T}he results obtained from this
study support the conclusion that the residue-coupled effect along
a tetrapeptide is important for the formation of a beta-turn.},
doi = {10.1016/S0196-9781(03)00133-5},
pdf = {../local/Cai2003Prediction.pdf},
file = {Cai2003Prediction.pdf:local/Cai2003Prediction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/S0196-9781(03)00133-5}
}
@article{Cai2003Supportb,
author = {Cai, Y.D. and Liu, X.J. and Xu, X.B. and Chou, K.C.},
title = {Support vector machines for prediction of protein domain structural
class.},
journal = {J. {T}heor. {B}iol.},
year = {2003},
volume = {221},
pages = {115-120},
number = {1},
abstract = {The support vector machines ({SVM}s) method was introduced for predicting
the structural class of protein domains. {T}he results obtained through
the self-consistency test, jack-knife test, and independent dataset
test have indicated that the current method and the elegant component-coupled
algorithm developed by {C}hou and co-workers, if effectively complemented
with each other, may become a powerful tool for predicting the structural
class of protein domains.},
doi = {10.1006/jtbi.2003.3179},
pdf = {../local/Cai2003Supportb.pdf},
file = {Cai2003Supportb.pdf:local/Cai2003Supportb.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1006/jtbi.2003.3179}
}
@article{Cai2002Supporta,
author = {Cai, Y.D. and Liu, X.J. and Xu, X.B. and Chou, K.C.},
title = {Support {V}ector {M}achines for predicting {HIV} protease cleavage
sites in protein.},
journal = {J. {C}omput. {C}hem.},
year = {2002},
volume = {23},
pages = {267-274},
number = {2},
abstract = {Knowledge of the polyprotein cleavage sites by {HIV} protease will
refine our understanding of its specificity, and the information
thus acquired is useful for designing specific and efficient {HIV}
protease inhibitors. {T}he pace in searching for the proper inhibitors
of {HIV} protease will be greatly expedited if one can find an accurate,
robust, and rapid method for predicting the cleavage sites in proteins
by {HIV} protease. {I}n this article, a {S}upport {V}ector {M}achine
is applied to predict the cleavability of oligopeptides by proteases
with multiple and extended specificity subsites. {W}e selected {HIV}-1
protease as the subject of the study. {T}wo hundred ninety-nine oligopeptides
were chosen for the training set, while the other 63 oligopeptides
were taken as a test set. {B}ecause of its high rate of self-consistency
(299/299 = 100%), a good result in the jackknife test (286/299 95%)
and correct prediction rate (55/63 = 87%), it is expected that the
{S}upport {V}ector {M}achine method can be referred to as a useful
assistant technique for finding effective inhibitors of {HIV} protease,
which is one of the targets in designing potential drugs against
{AIDS}. {T}he principle of the {S}upport {V}ector {M}achine method
can also be applied to analyzing the specificity of other multisubsite
enzymes.},
doi = {10.1002/jcc.10017},
pdf = {../local/local},
file = {local:local/:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/jcc.10017}
}
@article{Cai2002Supportb,
author = {Cai, Y.D. and Liu, X.J. and Xu, X.B. and Chou, K.C.},
title = {Support vector machines for predicting the specificity of {{G}al{NA}c}-transferase},
journal = {Peptides},
year = {2002},
volume = {23},
pages = {205-208},
abstract = {Support {V}ector {M}achines ({SVM}s) which is one kind of learning
machines, was applied to predict the specificity of {G}al{NA}c-transferase.
{T}he examination for the self-consistency and the jackknife test
of the {SVM}s method were tested for the training dataset (305 oligopeptides),
the correct rate of self-consistency and jackknife test reaches 100%
and 84.9%, respectively. {F}urthermore, the prediction of the independent
testing dataset (30 oligopeptides) was tested, the rate reaches 76.67%.},
doi = {10.1016/S0196-9781(01)00597-6},
pdf = {../local/Cai2002Supportb.pdf},
file = {Cai2002Supportb.pdf:local/Cai2002Supportb.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/S0196-9781(01)00597-6}
}
@article{Cai2002Supportc,
author = {Cai, Y.D. and Liu, X.J. and Xu, X.B. and Chou, K.C.},
title = {Support vector machines for the classification and prediction of
beta-turn types},
journal = {J. {P}ept. {S}ci.},
year = {2002},
volume = {8},
pages = {297-301},
number = {7},
abstract = {The support vector machines ({SVM}s) method is proposed because it
can reflect the sequence-coupling effect for a tetrapeptide in not
only a beta-turn or non-beta-turn, but also in different types of
beta-turn. {T}he results of the model for 6022 tetrapeptides indicate
that the rates of self-consistency for beta-turn types {I}, {I}',
{II}, {II}', {VI} and {VIII} and non-beta-turns are 99.92%, 96.8%,
98.02%, 97.75%, 100%, 97.19% and 100%, respectively. {U}sing these
training data, the rate of correct prediction by the {SVM}s for a
given protein: rubredoxin (54 residues. 51 tetrapeptides) which includes
12 beta-turn type {I} tetrapeptides, 1 beta-turn type {II} tetrapeptide
and 38 non-beta-turns reached 82.4%. {T}he high quality of prediction
of the {SVM}s implies that the formation of different beta-turn types
or non-beta-turns is considerably correlated with the sequence of
a tetrapeptide. {T}he {SVM}s can save {CPU} time and avoid the overfitting
problem compared with the neural network method.},
doi = {10.1002/psc.401},
pdf = {../local/local},
file = {local:local/:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/psc.401}
}
@article{Cai2000Support,
author = {Cai, Y.D. and Liu, X.J. and Xu, X.B. and Chou, K.C.},
title = {Support vector machines for prediction of protein subcellular location},
journal = {Mol. {C}ell {B}iol. {R}es. {C}ommun.},
year = {2000},
volume = {4},
pages = {230-234},
number = {4},
abstract = {Support {V}ector {M}achine ({SVM}), which is one kind of learning
machines, was applied to predict the subcellular location of proteins
from their amino acid composition. {I}n this research, the proteins
are classified into the following 12 groups: (1) chloroplast, (2)
cytoplasm, (3) cytoskeleton, (4) endoplasmic reticulum, (5) extracall,
(6) {G}olgi apparatus, (7) lysosome, (8) mitochondria, (9) nucleus,
(10) peroxisome, (11) plasma membrane, and (12) vacuole, which have
covered almost all the organelles and subcellular compartments in
an animal or plant cell. {T}he examination for the self-consistency
and the jackknife test of the {SVM}s method was tested for the three
sets: 2022 proteins, 2161 proteins, and 2319 proteins. {A}s a result,
the correct rate of self-consistency and jackknife test reaches 91
and 82% for 2022 proteins, 89 and 75% for 2161 proteins, and 85 and
73% for 2319 proteins, respectively. {F}urthermore, the predicting
rate was tested by the three independent testing datasets containing
2240 proteins, 2513 proteins, and 2591 proteins. {T}he correct prediction
rates reach 82, 75, and 73% for 2240 proteins, 2513 proteins, and
2591 proteins, respectively.},
doi = {10.1006/mcbr.2001.0285},
pdf = {../local/local},
file = {local:local/:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1006/mcbr.2001.0285}
}
@article{Cai2004Application,
author = {Cai, Y.D. and Ricardo, P.W. and Jen, C.H. and Chou, K.C.},
title = {Application of {SVM} to predict membrane protein types.},
journal = {J. {T}heor. {B}iol.},
year = {2004},
volume = {226},
pages = {373-376},
number = {4},
abstract = {As a continuous effort to develop automated methods for predicting
membrane protein types that was initiated by {C}hou and {E}lrod ({PROTEINS}:
{S}tructure, {F}unction, and {G}enetics, 1999, 34, 137-153), the
support vector machine ({SVM}) is introduced. {R}esults obtained
through re-substitution, jackknife, and independent data set tests,
respectively, have indicated that the {SVM} approach is quite a promising
one, suggesting that the covariant discriminant algorithm ({C}hou
and {E}lrod, {P}rotein {E}ng. 12 (1999) 107) and {SVM}, if effectively
complemented with each other, will become a powerful tool for predicting
membrane protein types and the other protein attributes as well.},
doi = {10.1016/j.jtbi.2003.08.015},
pdf = {../local/Cai2004Application.pdf},
file = {Cai2004Application.pdf:local/Cai2004Application.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/j.jtbi.2003.08.015}
}
@article{Cai2004Identify,
author = {Cai, Y.D. and Zhou, G.P. and Jen, C.H. and Lin, S.L. and Chou, K.C.},
title = {Identify catalytic triads of serine hydrolases by support vector
machines.},
journal = {J. {T}heor. {B}iol.},
year = {2004},
volume = {228},
pages = {551-557},
number = {4},
abstract = {The core of an enzyme molecule is its active site from the viewpoints
of both academic research and industrial application. {T}o reveal
the structural and functional mechanism of an enzyme, one needs to
know its active site; to conduct structure-based drug design by regulating
the function of an enzyme, one needs to know the active site and
its microenvironment as well. {G}iven the atomic coordinates of an
enzyme molecule, how can we predict its active site? {T}o tackle
such a problem, a distance group approach was proposed and the support
vector machine algorithm applied to predict the catalytic triad of
serine hydrolase family. {T}he success rate by jackknife test for
the 139 serine hydrolases was 85%, implying that the method is quite
promising and may become a useful tool in structural bioinformatics.},
doi = {10.1016/j.jtbi.2004.02.019},
pdf = {../local/Cai2004Identify.pdf},
file = {Cai2004Identify.pdf:local/Cai2004Identify.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/j.jtbi.2004.02.019}
}
@article{Cai2004Prediction,
author = {Yu-Dong Cai and Andrew J Doig},
title = {Prediction of {S}accharomyces cerevisiae protein functional class
from functional domain composition.},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {1292-300},
number = {8},
month = {May},
abstract = {M{OTIVATION}: {A} key goal of genomics is to assign function to genes,
especially for orphan sequences. {RESULTS}: {W}e compared the clustered
functional domains in the {SBASE} database to each protein sequence
using {BLASTP}. {T}his representation for a protein is a vector,
where each of the non-zero entries in the vector indicates a significant
match between the sequence of interest and the {SBASE} domain. {T}he
machine learning methods nearest neighbour algorithm ({NNA}) and
support vector machines are used for predicting protein functional
classes from this information. {W}e find that the best results are
found using the {SBASE}-{A} database and the {NNA}, namely 72\% accuracy
for 79\% coverage. {W}e tested an assigning function based on searching
for {I}nter{P}ro sequence motifs and by taking the most significant
{BLAST} match within the dataset. {W}e applied the functional domain
composition method to predict the functional class of 2018 currently
unclassified yeast open reading frames. {AVAILABILITY}: {A} program
for the prediction method, that uses {NNA} called {F}unctional {C}lass
{P}rediction based on {F}unctional {D}omains ({FCPFD}) is available
and can be obtained by contacting {Y}.{D}.{C}ai at y.cai@umist.ac.uk},
doi = {10.1093/bioinformatics/bth085},
pdf = {../local/Cai2004Prediction.pdf},
file = {Cai2004Prediction.pdf:local/Cai2004Prediction.pdf:PDF},
keywords = {biosvm},
pii = {bth085},
url = {http://dx.doi.org/10.1093/bioinformatics/bth085}
}
@article{Cai2002Support,
author = {Cai, Y.-D. and Liu, X.-J. and Xu, X.-B. and Chou, K.-C.},
title = {Support vector machines for prediction of protein subcellular location
by incorporating quasi-sequence-order effect},
journal = {J. {C}ell. {B}iochem.},
year = {2002},
volume = {84},
pages = {343-348},
number = {2},
abstract = {Support {V}ector {M}achine ({SVM}), which is one class of learning
machines, was applied to predict the subcellular location of proteins
by incorporating the quasi-sequence-order effect ({C}hou [2000] {B}iochem.
{B}iophys. {R}es. {C}ommun. 278:477-483). {I}n this study, the proteins
are classified into the following 12 groups: (1) chloroplast, (2)
cytoplasm, (3) cytoskeleton, (4) endoplasmic reticulum, (5) extracellular,
(6) {G}olgi apparatus, (7) lysosome, (8) mitochondria, (9) nucleus,
(10) peroxisome, (11) plasma membrane, and (12) vacuole, which account
for most organelles and subcellular compartments in an animal or
plant cell. {E}xaminations for self-consistency and jackknife testing
of the {SVM}s method were conducted for three sets consisting of
1,911, 2,044, and 2,191 proteins. {T}he correct rates for self-consistency
and the jackknife test values achieved with these protein sets were
94 and 83% for 1,911 proteins, 92 and 78% for 2,044 proteins, and
89 and 75% for 2,191 proteins, respectively. {F}urthermore, tests
for correct prediction rates were undertaken with three independent
testing datasets containing 2,148 proteins, 2,417 proteins, and 2,494
proteins producing values of 84, 77, and 74%, respectively.},
doi = {10.1002/jcb.10030},
pdf = {../local/Cai2002Support.pdf},
file = {Cai2002Support.pdf:local/Cai2002Support.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/jcb.10030}
}
@article{Cai2002Prediction,
author = {Cai, Y.-D. and Liu, X.-J. and Xu, X.-B. and Zhou, G.-P.},
title = {Prediction of protein structural classes by support vector machines.},
journal = {Comput. {C}hem.},
year = {2002},
volume = {26},
pages = {293-296},
number = {3},
abstract = {In this paper, we apply a new machine learning method which is called
support vector machine to approach the prediction of protein structural
class. {T}he support vector machine method is performed based on
the database derived from {SCOP} which is based upon domains of known
structure and the evolutionary relationships and the principles that
govern their 3{D} structure. {A}s a result, high rates of both self-consistency
and jackknife test are obtained. {T}his indicates that the structural
class of a protein inconsiderably correlated with its amino and composition,
and the support vector machine can be referred as a powerful computational
tool for predicting the structural classes of proteins.},
doi = {10.1016/S0097-8485(01)00113-9},
pdf = {../local/Cai2002Prediction.pdf},
file = {Cai2002Prediction.pdf:local/Cai2002Prediction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/S0097-8485(01)00113-9}
}
@article{Cai2001Support,
author = {Cai, Y.-D. and Liu, X.-J. and Xu, X.-B. and Zhou, G.-P.},
title = {Support {V}ector {M}achines for predicting protein structural class},
journal = {B{MC} {B}ioinformatics},
year = {2001},
volume = {2},
pages = {3},
number = {3},
abstract = {Background {W}e apply a new machine learning method, the so-called
{S}upport {V}ector {M}achine method, to predict the protein structural
class. {S}upport {V}ector {M}achine method is performed based on
the database derived from {SCOP}, in which protein domains are classified
based on known structures and the evolutionary relationships and
the principles that govern their 3-{D} structure. {R}esults {H}igh
rates of both self-consistency and jackknife tests are obtained.
{T}he good results indicate that the structural class of a protein
is considerably correlated with its amino acid composition. {C}onclusions
{I}t is expected that the {S}upport {V}ector {M}achine method and
the elegant component-coupled method, also named as the covariant
discrimination algorithm, if complemented with each other, can provide
a powerful computational tool for predicting the structural classes
of proteins.},
doi = {10.1186/1471-2105-2-3},
pdf = {../local/Cai2001Support.pdf},
file = {Cai2001Support.pdf:local/Cai2001Support.pdf:PDF},
keywords = {biosvm},
owner = {vert},
url = {http://www.biomedcentral.com/1471-2105/2/3/abstract}
}
@article{Cai2003Support,
author = {Cai, Y.-D. and Zhou, G.-P. and Chou, K.-C.},
title = {Support {V}ector {M}achines for {P}redicting {M}embrane {P}rotein
{T}ypes by {U}sing {F}unctional {D}omain {C}omposition},
journal = {Biophys. {J}.},
year = {2003},
volume = {84},
pages = {3257-3263},
number = {5},
abstract = {Membrane proteins are generally classified into the following five
types: 1), type {I} membrane protein; 2), type {II} membrane protein;
3), multipass transmembrane proteins; 4), lipid chain-anchored membrane
proteins; and 5), {GPI}-anchored membrane proteins. {I}n this article,
based on the concept of using the functional domain composition to
define a protein, the {S}upport {V}ector {M}achine algorithm is developed
for predicting the membrane protein type. {H}igh success rates are
obtained by both the self-consistency and jackknife tests. {T}he
current approach, complemented with the powerful covariant discriminant
algorithm based on the pseudo-amino acid composition that has incorporated
quasi-sequence-order effect as recently proposed by {K}. {C}. {C}hou
(2001), may become a very useful high-throughput tool in the area
of bioinformatics and proteomics.},
pdf = {../local/Cai2003Support.pdf},
file = {Cai2003Support.pdf:local/Cai2003Support.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.biophysj.org/cgi/content/abstract/84/5/3257}
}
@article{Camps-Valls2004Profiled,
author = {Camps-Valls, G. and Chalk, A.M. and Serrano-Lopez, A.J. and Martin-Guerrero,
J.D. and Sonnhammer, E.L.},
title = {Profiled support vector machines for antisense oligonucleotide efficacy
prediction.},
journal = {B{MC} {B}ioinformatics},
year = {2004},
volume = {5},
pages = {135},
number = {135},
abstract = {Background {T}his paper presents the use of {S}upport {V}ector {M}achines
({SVM}s) for prediction and analysis of antisense oligonucleotide
({AO}) efficacy. {T}he collected database comprises 315 {AO} molecules
including 68 features each, inducing a problem well-suited to {SVM}s.
{T}he task of feature selection is crucial given the presence of
noisy or redundant features, and the well-known problem of the curse
of dimensionality. {W}e propose a two-stage strategy to develop an
optimal model: (1) feature selection using correlation analysis,
mutual information, and {SVM}-based recursive feature elimination
({SVM}-{RFE}), and (2) {AO} prediction using standard and profiled
{SVM} formulations. {A} profiled {SVM} gives different weights to
different parts of the training data to focus the training on the
most important regions. {R}esults {I}n the first stage, the {SVM}-{RFE}
technique was most efficient and robust in the presence of low number
of samples and high input space dimension. {T}his method yielded
an optimal subset of 14 representative features, which were all related
to energy and sequence motifs. {T}he second stage evaluated the performance
of the predictors (overall correlation coefficient between observed
and predicted efficacy, r; mean error, {ME}; and root-mean-square-error,
{RMSE}) using 8-fold and minus-one-{RNA} cross-validation methods.
{T}he profiled {SVM} produced the best results (r = 0.44, {ME} =
0.022, and {RMSE}= 0.278) and predicted high (>75% inhibition of
gene expression) and low efficacy (<25%) {AO}s with a success rate
of 83.3% and 82.9%, respectively, which is better than by previous
approaches. {A} web server for {AO} prediction is available online
at http://aosvm.cgb.ki.se/. {C}onclusions {T}he {SVM} approach is
well suited to the {AO} prediction problem, and yields a prediction
accuracy superior to previous methods. {T}he profiled {SVM} was found
to perform better than the standard {SVM}, suggesting that it could
lead to improvements in other prediction problems as well.},
doi = {10.1186/1471-2105-5-135},
pdf = {../local/Camps-Valls2004Profiled.pdf},
file = {Camps-Valls2004Profiled.pdf:local/Camps-Valls2004Profiled.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.biomedcentral.com/1471-2105/5/135}
}
@article{Capriotti2005I-Mutant,
author = {Capriotti, E. and Fariselli, P. and Casadio, R.},
title = {I-{M}utant2.0: predicting stability changes upon mutation from the
protein sequence or structure.},
journal = {Nucleic {A}cids {R}es.},
year = {2005},
volume = {33},
pages = {W306-10},
number = {Web Server issue},
month = {Jul},
abstract = {I-{M}utant2.0 is a support vector machine ({SVM})-based tool for the
automatic prediction of protein stability changes upon single point
mutations. {I}-{M}utant2.0 predictions are performed starting either
from the protein structure or, more importantly, from the protein
sequence. {T}his latter task, to the best of our knowledge, is exploited
for the first time. {T}he method was trained and tested on a data
set derived from {P}ro{T}herm, which is presently the most comprehensive
available database of thermodynamic experimental data of free energy
changes of protein stability upon mutation under different conditions.
{I}-{M}utant2.0 can be used both as a classifier for predicting the
sign of the protein stability change upon mutation and as a regression
estimator for predicting the related {D}elta{D}elta{G} values. {A}cting
as a classifier, {I}-{M}utant2.0 correctly predicts (with a cross-validation
procedure) 80\% or 77\% of the data set, depending on the usage of
structural or sequence information, respectively. {W}hen predicting
{D}elta{D}elta{G} values associated with mutations, the correlation
of predicted with expected/experimental values is 0.71 (with a standard
error of 1.30 kcal/mol) and 0.62 (with a standard error of 1.45 kcal/mol)
when structural or sequence information are respectively adopted.
{O}ur web interface allows the selection of a predictive mode that
depends on the availability of the protein structure and/or sequence.
{I}n this latter case, the web server requires only pasting of a
protein sequence in a raw format. {W}e therefore introduce {I}-{M}utant2.0
as a unique and valuable helper for protein design, even when the
protein structure is not yet known with atomic resolution. {A}vailability:
http://gpcr.biocomp.unibo.it/cgi/predictors/{I}-{M}utant2.0/{I}-{M}utant2.0.cgi.},
doi = {10.1093/nar/gki375},
pdf = {../local/local},
file = {local:local/:PDF},
keywords = {biosvm},
pii = {33/suppl_2/W306},
url = {http://dx.doi.org/10.1093/nar/gki375}
}
@article{Carter2001computational,
author = {Carter, R. J. and Dubchak, I. and Holbrook, S. R.},
title = {A computational approach to identify genes for functional {{RNA}s}
in genomic sequences},
journal = {Nucl. {A}cids {R}es.},
year = {2001},
volume = {29},
pages = {3928-3938},
number = {19},
abstract = {Currently there is no successful computational approach for identification
of genes encoding novel functional {RNA}s (f{RNA}s) in genomic sequences.
{W}e have developed a machine learning approach using neural networks
and support vector machines to extract common features among known
{RNA}s for prediction of new {RNA} genes in the unannotated regions
of prokaryotic and archaeal genomes. {T}he {E}scherichia coli genome
was used for development, but we have applied this method to several
other bacterial and archaeal genomes. {N}etworks based on nucleotide
composition were 80-90% accurate in jackknife testing experiments
for bacteria and 90-99% for hyperthermophilic archaea. {W}e also
achieved a significant improvement in accuracy by combining these
predictions with those obtained using a second set of parameters
consisting of known {RNA} sequence motifs and the calculated free
energy of folding. {S}everal known f{RNA}s not included in the training
datasets were identified as well as several hundred predicted novel
{RNA}s. {T}hese studies indicate that there are many unidentified
{RNA}s in simple genomes that can be predicted computationally as
a precursor to experimental study. {P}ublic access to our {RNA} gene
predictions and an interface for user predictions is available via
the web.},
pdf = {../local/Carter2001computational.pdf},
file = {Carter2001computational.pdf:local/Carter2001computational.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://nar.oupjournals.org/cgi/content/abstract/29/19/3928}
}
@article{Chen2004Prediction,
author = {Chen, Y.C. and Lin, Y.S. and Lin, C.J. and Hwang, J.K.},
title = {Prediction of the bonding states of cysteines using the support vector
machines based on multiple feature vectors and cysteine state sequences},
journal = {Proteins},
year = {2004},
volume = {55},
pages = {1036-1042},
number = {4},
abstract = {The support vector machine ({SVM}) method is used to predict the bonding
states of cysteines. {B}esides using local descriptors such as the
local sequences, we include global information, such as amino acid
compositions and the patterns of the states of cysteines (bonded
or nonbonded), or cysteine state sequences, of the proteins. {W}e
found that {SVM} based on local sequences or global amino acid compositions
yielded similar prediction accuracies for the data set comprising
4136 cysteine-containing segments extracted from 969 nonhomologous
proteins. {H}owever, the {SVM} method based on multiple feature vectors
(combining local sequences and global amino acid compositions) significantly
improves the prediction accuracy, from 80% to 86%. {I}f coupled with
cysteine state sequences, {SVM} based on multiple feature vectors
yields 90% in overall prediction accuracy and a 0.77 {M}atthews correlation
coefficient, around 10% and 22% higher than the corresponding values
obtained by {SVM} based on local sequence information.},
doi = {10.1002/prot.20079},
pdf = {../local/Chen2004Prediction.pdf},
file = {Chen2004Prediction.pdf:local/Chen2004Prediction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/Chen2004Prediction.pdf}
}
@article{Chen2005Understanding,
author = {Chen, Y. and Xu, D.},
title = {Understanding protein dispensability through machine-learning analysis
of high-throughput data},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {575-581},
month = {Mar},
abstract = {Motivation: {P}rotein dispensability is fundamental to understanding
of gene function and evolution. {R}ecent advances in generating high-throughput
data such as genomic sequence data, protein-protein interaction data,
gene-expression data, and growth-rate data of mutants allow us to
investigate protein dispensability systematically at the genome scale.{R}esults:
{I}n our studies, protein dispensability is represented as a fitness
score that is measured by the growth rate of gene-deletion mutants.
{T}hrough analyses of high-throughput data in yeast {S}accharomyces
cerevisia, we found that a protein's dispensability had significant
correlations with its evolutionary rate and duplication rate, as
well as its connectivity in protein-protein interaction network and
gene-expression correlation network. {N}eural network and support
vector machine were applied to predict protein dispensability through
high-throughput data. {O}ur studies shed some lights on global characteristics
of protein dispensability and evolution.{A}vailability: {T}he original
datasets for protein dispensability analysis and prediction, together
with related scripts, are available at http://digbio.missouri.edu/~ychen/{P}ro{D}ispen/.},
doi = {10.1093/bioinformatics/bti058},
pdf = {../local/Chen2005Understanding.pdf},
file = {Chen2005Understanding.pdf:local/Chen2005Understanding.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1093/bioinformatics/bti058}
}
@article{Chou2002Using,
author = {Chou, K.-C. and Cai, Y.-D.},
title = {Using {F}unctional {D}omain {C}omposition and {S}upport {V}ector
{M}achines for {P}rediction of {P}rotein {S}ubcellular {L}ocation},
journal = {J. {B}iol. {C}hem.},
year = {2002},
volume = {277},
pages = {45765-45769},
number = {48},
abstract = {Proteins are generally classified into the following 12 subcellular
locations: 1) chloroplast, 2) cytoplasm, 3) cytoskeleton, 4) endoplasmic
reticulum, 5) extracellular, 6) {G}olgi apparatus, 7) lysosome, 8)
mitochondria, 9) nucleus, 10) peroxisome, 11) plasma membrane, and
12) vacuole. {B}ecause the function of a protein is closely correlated
with its subcellular location, with the rapid increase in new protein
sequences entering into databanks, it is vitally important for both
basic research and pharmaceutical industry to establish a high throughput
tool for predicting protein subcellular location. {I}n this paper,
a new concept, the so-called "functional domain composition" is introduced.
{B}ased on the novel concept, the representation for a protein can
be defined as a vector in a high-dimensional space, where each of
the clustered functional domains derived from the protein universe
serves as a vector base. {W}ith such a novel representation for a
protein, the support vector machine ({SVM}) algorithm is introduced
for predicting protein subcellular location. {H}igh success rates
are obtained by the self-consistency test, jackknife test, and independent
dataset test, respectively. {T}he current approach not only can play
an important complementary role to the powerful covariant discriminant
algorithm based on the pseudo amino acid composition representation
({C}hou, {K}. {C}. (2001) {P}roteins {S}truct. {F}unct. {G}enet.
43, 246-255; {C}orrection (2001) {P}roteins {S}truct. {F}unct. {G}enet.
44, 60), but also may greatly stimulate the development of this area.},
pdf = {../local/Chou2002Using.pdf},
file = {Chou2002Using.pdf:local/Chou2002Using.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.jbc.org/cgi/content/abstract/277/48/45765}
}
@article{Chow2001Identifying,
author = {M. L. Chow and E. J. Moler and I. S. Mian},
title = {Identifying marker genes in transcription profiling data using a
mixture of feature relevance experts.},
journal = {Physiol. {G}enomics},
year = {2001},
volume = {5},
pages = {99-111},
number = {2},
month = {Mar},
abstract = {Transcription profiling experiments permit the expression levels of
many genes to be measured simultaneously. {G}iven profiling data
from two types of samples, genes that most distinguish the samples
(marker genes) are good candidates for subsequent in-depth experimental
studies and developing decision support systems for diagnosis, prognosis,
and monitoring. {T}his work proposes a mixture of feature relevance
experts as a method for identifying marker genes and illustrates
the idea using published data from samples labeled as acute lymphoblastic
and myeloid leukemia ({ALL}, {AML}). {A} feature relevance expert
implements an algorithm that calculates how well a gene distinguishes
samples, reorders genes according to this relevance measure, and
uses a supervised learning method [here, support vector machines
({SVM}s)] to determine the generalization performances of different
nested gene subsets. {T}he mixture of three feature relevance experts
examined implement two existing and one novel feature relevance measures.
{F}or each expert, a gene subset consisting of the top 50 genes distinguished
{ALL} from {AML} samples as completely as all 7,070 genes. {T}he
125 genes at the union of the top 50s are plausible markers for a
prototype decision support system. {C}hromosomal aberration and other
data support the prediction that the three genes at the intersection
of the top 50s, cystatin {C}, azurocidin, and adipsin, are good targets
for investigating the basic biology of {ALL}/{AML}. {T}he same data
were employed to identify markers that distinguish samples based
on their labels of {T} cell/{B} cell, peripheral blood/bone marrow,
and male/female. {S}elenoprotein {W} may discriminate {T} cells from
{B} cells. {R}esults from analysis of transcription profiling data
from tumor/nontumor colon adenocarcinoma samples support the general
utility of the aforementioned approach. {T}heoretical issues such
as choosing {SVM} kernels and their parameters, training and evaluating
feature relevance experts, and the impact of potentially mislabeled
samples on marker identification (feature selection) are discussed.},
pdf = {../local/Chow2001Identifying.pdf},
file = {Chow2001Identifying.pdf:local/Chow2001Identifying.pdf:PDF},
keywords = {biosvm},
pii = {5/2/99},
url = {http://physiolgenomics.physiology.org/cgi/content/abstract/5/2/99}
}
@article{Collier2004Comparison,
author = {Nigel Collier and Koichi Takeuchi},
title = {Comparison of character-level and part of speech features for name
recognition in biomedical texts.},
journal = {J {B}iomed {I}nform},
year = {2004},
volume = {37},
pages = {423-35},
number = {6},
month = {Dec},
abstract = {The immense volume of data which is now available from experiments
in molecular biology has led to an explosion in reported results
most of which are available only in unstructured text format. {F}or
this reason there has been great interest in the task of text mining
to aid in fact extraction, document screening, citation analysis,
and linkage with large gene and gene-product databases. {I}n particular
there has been an intensive investigation into the named entity ({NE})
task as a core technology in all of these tasks which has been driven
by the availability of high volume training sets such as the {GENIA}
v3.02 corpus. {D}espite such large training sets accuracy for biology
{NE} has proven to be consistently far below the high levels of performance
in the news domain where {F} scores above 90 are commonly reported
which can be considered near to human performance. {W}e argue that
it is crucial that more rigorous analysis of the factors that contribute
to the model's performance be applied to discover where the underlying
limitations are and what our future research direction should be.
{O}ur investigation in this paper reports on variations of two widely
used feature types, part of speech ({POS}) tags and character-level
orthographic features, and makes a comparison of how these variations
influence performance. {W}e base our experiments on a proven state-of-the-art
model, support vector machines using a high quality subset of 100
annotated {MEDLINE} abstracts. {E}xperiments reveal that the best
performing features are orthographic features with {F} score of 72.6.
{A}lthough the {B}rill tagger trained in-domain on the {GENIA} v3.02p
{POS} corpus gives the best overall performance of any {POS} tagger,
at an {F} score of 68.6, this is still significantly below the orthographic
features. {I}n combination these two features types appear to interfere
with each other and degrade performance slightly to an {F} score
of 72.3.},
doi = {10.1016/j.jbi.2004.08.008},
pdf = {../local/Collier2004Comparison.pdf},
file = {Collier2004Comparison.pdf:local/Collier2004Comparison.pdf:PDF},
keywords = {biosvm nlp},
pii = {S1532-0464(04)00088-7},
url = {http://dx.doi.org/10.1016/j.jbi.2004.08.008}
}
@article{Cui2004Esub8,
author = {Cui, Q. and Jiang, T. and Liu, B. and Ma, S.},
title = {Esub8: {A} novel tool to predict protein subcellular localizations
in eukaryotic organisms},
journal = {B{MC} {B}ioinformatics},
year = {2004},
volume = {5},
pages = {66},
number = {66},
abstract = {Background {S}ubcellular localization of a new protein sequence is
very important and fruitful for understanding its function. {A}s
the number of new genomes has dramatically increased over recent
years, a reliable and efficient system to predict protein subcellular
location is urgently needed. {R}esults {E}sub8 was developed to predict
protein subcellular localizations for eukaryotic proteins based on
amino acid composition. {I}n this research, the proteins are classified
into the following eight groups: chloroplast, cytoplasm, extracellular,
{G}olgi apparatus, lysosome, mitochondria, nucleus and peroxisome.
{W}e know subcellular localization is a typical classification problem;
consequently, a one-against-one (1-v-1) multi-class support vector
machine was introduced to construct the classifier. {U}nlike previous
methods, ours considers the order information of protein sequences
by a different method. {O}ur method is tested in three subcellular
localization predictions for prokaryotic proteins and four subcellular
localization predictions for eukaryotic proteins on {R}einhardt's
dataset. {T}he results are then compared to several other methods.
{T}he total prediction accuracies of two tests are both 100% by a
self-consistency test, and are 92.9% and 84.14% by the jackknife
test, respectively. {E}sub8 also provides excellent results: the
total prediction accuracies are 100% by a self-consistency test and
87% by the jackknife test. {C}onclusions {O}ur method represents
a different approach for predicting protein subcellular localization
and achieved a satisfactory result; furthermore, we believe {E}sub8
will be a useful tool for predicting protein subcellular localizations
in eukaryotic organisms.},
doi = {10.1186/1471-2105-5-66},
pdf = {../local/Cui2004Esub8.pdf},
file = {Cui2004Esub8.pdf:local/Cui2004Esub8.pdf:PDF},
keywords = {biosvm},
owner = {vert},
url = {http://www.biomedcentral.com/1471-2105/5/66}
}
@article{Cuturi2005context-tree,
author = {Cuturi, M. and Vert, J.-P.},
title = {The context-tree kernel for strings},
journal = {Neural {N}etwork.},
year = {2005},
volume = {18},
pages = {1111-1123},
number = {4},
abstract = {We propose a new kernel for strings which borrows ideas and techniques
from information theory and data compression. {T}his kernel can be
used in combination with any kernel method, in particular {S}upport
{V}ector {M}achines for string classi- fication, with notable applications
in proteomics. {B}y using a {B}ayesian averaging framework with conjugate
priors on a class of {M}arkovian models known as prob- abilistic
suffix trees or context-trees, we compute the value of this kernel
in linear time and space while only using the information contained
in the spectrum of the considered strings. {T}his is ensured through
an adaptation of a compression method known as the context-tree weighting
algorithm. {E}ncouraging classification results are reported on a
standard protein homology detection experiment, showing that the
context-tree kernel performs well with respect to other state-of-the-art
methods while using no biological prior knowledge.},
doi = {10.1016/j.neunet.2005.07.010},
pdf = {../local/Cuturi2005context-tree.pdf},
file = {Cuturi2005context-tree.pdf:local/Cuturi2005context-tree.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1016/j.neunet.2005.07.010}
}
@inproceedings{Cuturi2004mutual,
author = {Cuturi, M. and Vert, J.-P.},
title = {A mutual information kernel for strings},
booktitle = {Proceedings of {IJCNN} 2004},
year = {2004},
pages = {1904-1910},
pdf = {../local/ijcnn04.pdf:http\://cg.ensmp.fr/~vert/publi/04ijcnn/ijcnn04.pdf:PDF;ijcnn04.pdf:http\},
file = {ijcnn04.pdf:http\://cg.ensmp.fr/~vert/publi/04ijcnn/ijcnn04.pdf:PDF;ijcnn04.pdf:http\://cg.ensmp.fr/~vert/publi/04ijcnn/ijcnn04.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@article{Degroeve2002Feature,
author = {Degroeve, S. and De Baets, B. and Van de Peer, Y. and Rouze, P.},
title = {Feature subset selection for splice site prediction},
journal = {Bioinformatics},
year = {2002},
volume = {18},
pages = {S75-S83},
number = {Suppl. 1},
abstract = {Motivation: {T}he large amount of available annotated {A}rabidopsis
thaliana sequences allows the induction of splice site prediction
models with supervised learning algorithms (see {H}aussler (1998)
for a review and references). {T}hese algorithms need information
sources or features from which the models can be computed. {F}or
splice site prediction, the features we consider in this study are
the presence or absence of certain nucleotides in close proximity
to the splice site. {S}ince it is not known how many and which nucleotides
are relevant for splice site prediction, the set of features is chosen
large enough such that the probability that all relevant information
sources are in the set is very high. {U}sing only those features
that are relevant for constructing a splice site prediction system
might improve the system and might also provide us with useful biological
knowledge. {U}sing fewer features will of course also improve the
prediction speed of the system. {R}esults: {A} wrapper-based feature
subset selection algorithm using a support vector machine or a naive
{B}ayes prediction method was evaluated against the traditional method
for selecting features relevant for splice site prediction. {O}ur
results show that this wrapper approach selects features that improve
the performance against the use of all features and against the use
of the features selected by the traditional method. {A}vailability:
{T}he data and additional interactive graphs on the selected feature
subsets are available at http://www.psb.rug.ac.be/gps {C}ontact:
svgro@gengenp.rug.ac.be yvdp@gengenp.rug.ac.be},
pdf = {../local/Degroeve2002Feature.pdf},
file = {Degroeve2002Feature.pdf:local/Degroeve2002Feature.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/18/suppl_2/S75}
}
@article{Degroeve2005SpliceMachine,
author = {Degroeve, S. and Saeys, Y. and De Baets, B. and Rouze, P. and Van
de Peer, Y.},
title = {{{S}plice{M}achine}: predicting splice sites from high-dimensional
local context representations},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {1332-1338},
abstract = {Motivation: {I}n this age of complete genome sequencing, finding the
location and structure of genes is crucial for further molecular
research. {T}he accurate prediction of intron boundaries largely
facilitates the correct prediction of gene structure in nuclear genomes.
{M}any tools for localizing these boundaries on {DNA} sequences have
been developed and are available to researchers through the internet.
{N}evertheless, these tools still make many false positive predictions.{R}esults:
{T}his manuscript presents a novel publicly available splice site
prediction tool named {S}plice{M}achine that (i) shows state-of-the-art
prediction performance on {A}rabidopsis thaliana and human sequences,
(ii) performs a computationally fast annotation, and (iii) can be
trained by the user on its own data.{A}vailability: {R}esults, figures
and software are available at http://bioinformatics.psb.ugent.be/supplementary_data/.},
doi = {10.1093/bioinformatics/bti166},
pdf = {../local/Degroeve2005SpliceMachine.pdf},
file = {Degroeve2005SpliceMachine.pdf:local/Degroeve2005SpliceMachine.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/bti166v1}
}
@inproceedings{Deshpande2002Evaluation,
author = {Deshpande, M. and Karypis, G.},
title = {Evaluation of {T}echniques for {C}lassifying {B}iological {S}equences},
booktitle = {P{AKDD} '02: {P}roceedings of the 6th {P}acific-{A}sia {C}onference
on {A}dvances in {K}nowledge {D}iscovery and {D}ata {M}ining},
year = {2002},
pages = {417--431},
publisher = {Springer Verlag},
abstract = {In recent years we have witnessed an exponential increase in the amount
of biological information, either {DNA} or protein sequences, that
has become available in public databases. {T}his has been followed
by an increased interest in developing computational techniques to
automatically classify these large volumes of sequence data into
various categories corresponding to either their role in the chromosomes,
their structure, and/or their function. {I}n this paper we evaluate
some of the widely-used sequence classification algorithms and develop
a framework for modeling sequences in a fashion so that traditional
machine learning algorithms, such as support vector machines, can
be applied easily. {O}ur detailed experimental evaluation shows that
the {SVM}-based approaches are able to achieve higher classification
accuracy compared to the more traditional sequence classification
algorithms such as {M}arkov model based techniques and {K}-nearest
neighbor based approaches.},
pdf = {../local/Deshpande2002Evaluation.pdf},
file = {Deshpande2002Evaluation.pdf:local/Deshpande2002Evaluation.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Ding2001Multi-class,
author = {Ding, C.H.Q. and Dubchak, I.},
title = {Multi-class protein fold recognition using support vector machines
and neural networks},
journal = {Bioinformatics},
year = {2001},
volume = {17},
pages = {349--358},
abstract = {Motivation: {P}rotein fold recognition is an important approach to
structure discovery without relying on sequence similarity. {W}e
study this approach with new multi-class classification methods and
examined many issues important for a practical recognition system.
{R}esults: {M}ost current discriminative methods for protein fold
prediction use the one-against-others method, which has the well-known
?{F}alse {P}ositives? problem. {W}e investigated two new methods:
the unique one-against-others and the all-against-all methods. {B}oth
improve prediction accuracy by 14?110% on a dataset containing 27
{SCOP} folds. {W}e used the {S}upport {V}ector {M}achine ({SVM})
and the {N}eural {N}etwork ({NN}) learning methods as base classifiers.
{SVM}s converges fast and leads to high accuracy. {W}hen scores of
multiple parameter datasets are combined, majority voting reduces
noise and increases recognition accuracy. {W}e examined many issues
involved with large number of classes, including dependencies of
prediction accuracy on the number of folds and on the number of representatives
in a fold. {O}verall, recognition systems achieve 56% fold prediction
accuracy on a protein test dataset, where most of the proteins have
below 25% sequence identity with the proteins used in training. {S}upplementary
information: {T}he protein parameter datasets used in this paper
are available online (http://www.nersc.gov/~cding/protein).},
pdf = {../local/Ding2001Multi-class.pdf},
file = {Ding2001Multi-class.pdf:local/Ding2001Multi-class.pdf:PDF},
keywords = {biosvm},
subject = {biokernel},
url = {http://bioinformatics.oupjournals.org/cgi/reprint/17/4/349.pdf}
}
@article{Dobson2005Predicting,
author = {Dobson, P.D. and Doig, A.J.},
title = {Predicting enzyme class from protein structure without alignments},
journal = {J. {M}ol. {B}iol.},
year = {2005},
volume = {345},
pages = {187-199},
number = {1},
month = {Jan},
abstract = {Methods for predicting protein function from structure are becoming
more important as the rate at which structures are solved increases
more rapidly than experimental knowledge. {A}s a result, protein
structures now frequently lack functional annotations. {T}he majority
of methods for predicting protein function are reliant upon identifying
a similar protein and transferring its annotations to the query protein.
{T}his method fails when a similar protein cannot be identified,
or when any similar proteins identified also lack reliable annotations.
{H}ere, we describe a method that can assign function from structure
without the use of algorithms reliant upon alignments. {U}sing simple
attributes that can be calculated from any crystal structure, such
as secondary structure content, amino acid propensities, surface
properties and ligands, we describe each enzyme in a non-redundant
set. {T}he set is split according to {E}nzyme {C}lassification ({EC})
number. {W}e combine the predictions of one-class versus one-class
support vector machine models to make overall assignments of {EC}
number to an accuracy of 35% with the top-ranked prediction, rising
to 60% accuracy with the top two ranks. {I}n doing so we demonstrate
the utility of simple structural attributes in protein function prediction
and shed light on the link between structure and function. {W}e apply
our methods to predict the function of every currently unclassified
protein in the {P}rotein {D}ata {B}ank.},
doi = {10.1016/j.jmb.2004.10.024},
pdf = {../local/Dobson2005Predicting.pdf},
file = {Dobson2005Predicting.pdf:local/Dobson2005Predicting.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/j.jmb.2004.10.024}
}
@article{Dobson2003Distinguishing,
author = {Dobson, P.D. and Doig, A.J.},
title = {Distinguishing enzyme structures from non-enzymes without alignments},
journal = {J. {M}ol. {B}iol.},
year = {2003},
volume = {330},
pages = {771-783},
number = {4},
abstract = {The ability to predict protein function from structure is becoming
increasingly important as the number of structures resolved is growing
more rapidly than our capacity to study function. {C}urrent methods
for predicting protein function are mostly reliant on identifying
a similar protein of known function. {F}or proteins that are highly
dissimilar or are only similar to proteins also lacking functional
annotations, these methods fail. {H}ere, we show that protein function
can be predicted as enzymatic or not without resorting to alignments.
{W}e describe 1178 high-resolution proteins in a structurally non-redundant
subset of the {P}rotein {D}ata {B}ank using simple features such
as secondary-structure content, amino acid propensities, surface
properties and ligands. {T}he subset is split into two functional
groupings, enzymes and non-enzymes. {W}e use the support vector machine-learning
algorithm to develop models that are capable of assigning the protein
class. {V}alidation of the method shows that the function can be
predicted to an accuracy of 77% using 52 features to describe each
protein. {A}n adaptive search of possible subsets of features produces
a simplified model based on 36 features that predicts at an accuracy
of 80%. {W}e compare the method to sequence-based methods that also
avoid calculating alignments and predict a recently released set
of unrelated proteins. {T}he most useful features for distinguishing
enzymes from non-enzymes are secondary-structure content, amino acid
frequencies, number of disulphide bonds and size of the largest cleft.
{T}his method is applicable to any structure as it does not require
the identification of sequence or structural similarity to a protein
of known function.},
doi = {10.1016/S0022-2836(03)00628-4},
pdf = {../local/Dobson2003Distinguishing.pdf},
file = {Dobson2003Distinguishing.pdf:local/Dobson2003Distinguishing.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/S0022-2836(03)00628-4}
}
@article{Donaldson2003PreBIND,
author = {Donaldson, I. and Martin, J. and de Bruijn, B. and Wolting, C. and
Lay, V. and Tuekam, B. and Zhang, S. and Baskin, B. and Bader, G.D.
and Michalickova, K. and Pawson, T. and Hogue, C.W.V. },
title = {{{P}re{BIND}} and {T}extomy - mining the biomedical literature for
protein-protein interactions using a support vector machine},
journal = {B{MC} {B}ioinformatics},
year = {2003},
volume = {4},
pages = {11},
number = {1},
month = {Mar},
abstract = {Background {T}he majority of experimentally verified molecular interaction
and biological pathway data are present in the unstructured text
of biomedical journal articles where they are inaccessible to computational
methods. {T}he {B}iomolecular interaction network database ({BIND})
seeks to capture these data in a machine-readable format. {W}e hypothesized
that the formidable task-size of backfilling the database could be
reduced by using {S}upport {V}ector {M}achine technology to first
locate interaction information in the literature. {W}e present an
information extraction system that was designed to locate protein-protein
interaction data in the literature and present these data to curators
and the public for review and entry into {BIND}. {R}esults {C}ross-validation
estimated the support vector machine's test-set precision, accuracy
and recall for classifying abstracts describing interaction information
was 92%, 90% and 92% respectively. {W}e estimated that the system
would be able to recall up to 60% of all non-high throughput interactions
present in another yeast-protein interaction database. {F}inally,
this system was applied to a real-world curation problem and its
use was found to reduce the task duration by 70% thus saving 176
days. {C}onclusions {M}achine learning methods are useful as tools
to direct interaction and pathway database back-filling; however,
this potential can only be realized if these techniques are coupled
with human review and entry into a factual database such as {BIND}.
{T}he {P}re{BIND} system described here is available to the public
at http://bind.ca. {C}urrent capabilities allow searching for human,
mouse and yeast protein-interaction information.},
doi = {10.1186/1471-2105-4-11},
pdf = {../local/Donaldson2003PreBIND.pdf},
file = {Donaldson2003PreBIND.pdf:local/Donaldson2003PreBIND.pdf:PDF},
keywords = {biosvm},
owner = {vert},
url = {http://www.biomedcentral.com/1471-2105/4/11/abstract}
}
@article{Doniger2002Predicting,
author = {Doniger, S. and Hofmann, T. and Yeh, J.},
title = {Predicting {CNS} permeability of drug molecules: comparison of neural
network and support vector machine algorithms},
journal = {J. {C}omput. {B}iol.},
year = {2002},
volume = {9},
pages = {849-864},
number = {6},
abstract = {Two different machine-learning algorithms have been used to predict
the blood-brain barrier permeability of different classes of molecules,
to develop a method to predict the ability of drug compounds to penetrate
the {CNS}. {T}he first algorithm is based on a multilayer perceptron
neural network and the second algorithm uses a support vector machine.
{B}oth algorithms are trained on an identical data set consisting
of 179 {CNS} active molecules and 145 {CNS} inactive molecules. {T}he
training parameters include molecular weight, lipophilicity, hydrogen
bonding, and other variables that govern the ability of a molecule
to diffuse through a membrane. {T}he results show that the support
vector machine outperforms the neural network. {B}ased on over 30
different validation sets, the {SVM} can predict up to 96% of the
molecules correctly, averaging 81.5% over 30 test sets, which comprised
of equal numbers of {CNS} positive and negative molecules. {T}his
is quite favorable when compared with the neural network's average
performance of 75.7% with the same 30 test sets. {T}he results of
the {SVM} algorithm are very encouraging and suggest that a classification
tool like this one will prove to be a valuable prediction approach.},
doi = {10.1089/10665270260518317},
pdf = {../local/Doniger2002Predicting.pdf},
file = {Doniger2002Predicting.pdf:local/Doniger2002Predicting.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Dror2005Accurate,
author = {Dror, G. and Sorek, R. and Shamir, R.},
title = {Accurate identification of alternatively spliced exons using support
vector machine},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {897-901},
number = {7},
month = {Apr},
abstract = {Motivation: {A}lternative splicing is a major component of the regulation
acting on mammalian transcriptomes. {I}t is estimated that over half
of all human genes have more than one splice variant. {P}revious
studies have shown that alternatively spliced exons possess several
features that distinguish them from constitutively spliced ones.
{R}ecently, we have demonstrated that such features can be used to
distinguish alternative from constitutive exons. {I}n the current
study we use advanced machine learning methods to generate robust
alternative exons classifier.{R}esults: {W}e extracted several hundred
local sequence features of constitutive as well as alternative exons.
{U}sing feature selection methods we find seven attributes that are
dominant for the task of classification. {S}everal less informative
features help to slightly increase the performance of the classifier.
{T}he classifier achieves a true positive rate of 50% for a false
positive rate of 0.5%. {T}his result enables one to reliably identify
alternatively spliced exons in exon databases that are believed to
be dominated by constitutive exons.{A}vailability: {U}pon request
from the authors.},
doi = {10.1093/bioinformatics/bti132},
pdf = {../local/Dror2005Accurate.pdf},
file = {Dror2005Accurate.pdf:local/Dror2005Accurate.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/bti132v1}
}
@article{Dubey2005Support,
author = {Anshul Dubey and Matthew J Realff and Jay H Lee and Andreas S Bommarius},
title = {Support vector machines for learning to identify the critical positions
of a protein.},
journal = {J {T}heor {B}iol},
year = {2005},
volume = {234},
pages = {351-61},
number = {3},
month = {Jun},
abstract = {A method for identifying the positions in the amino acid sequence,
which are critical for the catalytic activity of a protein using
support vector machines ({SVM}s) is introduced and analysed. {SVM}s
are supported by an efficient learning algorithm and can utilize
some prior knowledge about the structure of the problem. {T}he amino
acid sequences of the variants of a protein, created by inducing
mutations, along with their fitness are required as input data by
the method to predict its critical positions. {T}o investigate the
performance of this algorithm, variants of the beta-lactamase enzyme
were created in silico using simulations of both mutagenesis and
recombination protocols. {R}esults from literature on beta-lactamase
were used to test the accuracy of this method. {I}t was also compared
with the results from a simple search algorithm. {T}he algorithm
was also shown to be able to predict critical positions that can
tolerate two different amino acids and retain function.},
doi = {10.1016/j.jtbi.2004.11.037},
pdf = {../local/Dubey2005Support.pdf},
file = {Dubey2005Support.pdf:local/Dubey2005Support.pdf:PDF},
keywords = {biosvm},
pii = {S0022-5193(04)00585-5},
url = {http://dx.doi.org/10.1016/j.jtbi.2004.11.037}
}
@article{Donnes2002Prediction,
author = {D{\"o}nnes, P. and Elofsson, A.},
title = {Prediction of {MHC} class {I} binding peptides, using {SVMHC}},
journal = {B{MC} {B}ioinformatics},
year = {2002},
volume = {3},
pages = {25},
number = {1},
month = {Sep},
abstract = {Background {T}-cells are key players in regulating a specific immune
response. {A}ctivation of cytotoxic {T}-cells requires recognition
of specific peptides bound to {M}ajor {H}istocompatibility {C}omplex
({MHC}) class {I} molecules. {MHC}-peptide complexes are potential
tools for diagnosis and treatment of pathogens and cancer, as well
as for the development of peptide vaccines. {O}nly one in 100 to
200 potential binders actually binds to a certain {MHC} molecule,
therefore a good prediction method for {MHC} class {I} binding peptides
can reduce the number of candidate binders that need to be synthesized
and tested. {R}esults {H}ere, we present a novel approach, {SVMHC},
based on support vector machines to predict the binding of peptides
to {MHC} class {I} molecules. {T}his method seems to perform slightly
better than two profile based methods, {SYFPEITHI} and {HLA}_{BIND}.
{T}he implementation of {SVMHC} is quite simple and does not involve
any manual steps, therefore as more data become available it is trivial
to provide prediction for more {MHC} types. {SVMHC} currently contains
prediction for 26 {MHC} class {I} types from the {MHCPEP} database
or alternatively 6 {MHC} class {I} types from the higher quality
{SYFPEITHI} database. {T}he prediction models for these {MHC} types
are implemented in a public web service available at http://www.sbc.su.se/svmhc/.
{C}onclusions {P}rediction of {MHC} class {I} binding peptides using
{S}upport {V}ector {M}achines, shows high performance and is easy
to apply to a large number of {MHC} class {I} types. {A}s more peptide
data are put into {MHC} databases, {SVMHC} can easily be updated
to give prediction for additional {MHC} class {I} types. {W}e suggest
that the number of binding peptides needed for {SVM} training is
at least 20 sequences.},
doi = {10.1186/1471-2105-3-25},
pdf = {../local/Donnes2002Prediction.pdf},
file = {Donnes2002Prediction.pdf:local/Donnes2002Prediction.pdf:PDF},
keywords = {biosvm immunoinformatics},
owner = {vert},
url = {http://www.biomedcentral.com/1471-2105/3/25/abstract}
}
@article{Donnes2005Integrated,
author = {D{\"o}nnes, P. and Kohlbacher, O.},
title = {Integrated modeling of the major events in the {MHC} class {I} antigen
processing pathway.},
journal = {Protein {S}ci.},
year = {2005},
volume = {14},
pages = {2132-2140},
month = {Jun},
abstract = {Rational design of epitope-driven vaccines is a key goal of immunoinformatics.
{T}ypically, candidate selection relies on the prediction of {MHC}-peptide
binding only, as this is known to be the most selective step in the
{MHC} class {I} antigen processing pathway. {H}owever, proteasomal
cleavage and transport by the transporter associated with antigen
processing ({TAP}) are essential steps in antigen processing as well.
{W}hile prediction methods exist for the individual steps, no method
has yet offered an integrated prediction of all three major processing
events. {H}ere we present {WAPP}, a method combining prediction of
proteasomal cleavage, {TAP} transport, and {MHC} binding into a single
prediction system. {T}he proteasomal cleavage site prediction employs
a new matrix-based method that is based on experimentally verified
proteasomal cleavage sites. {S}upport vector regression is used for
predicting peptides transported by {TAP}. {MHC} binding is the last
step in the antigen processing pathway and was predicted using a
support vector machine method, {SVMHC}. {T}he individual methods
are combined in a filtering approach mimicking the natural processing
pathway. {WAPP} thus predicts peptides that are cleaved by the proteasome
at the {C} terminus, transported by {TAP}, and show significant affinity
to {MHC} class {I} molecules. {T}his results in a decrease in false
positive rates compared to {MHC} binding prediction alone. {C}ompared
to prediction of {MHC} binding only, we report an increased overall
accuracy and a lower rate of false positive predictions for the {HLA}-{A}*0201,
{HLA}-{B}*2705, {HLA}-{A}*01, and {HLA}-{A}*03 alleles using {WAPP}.
{T}he method is available online through our prediction server at
http://www-bs.informatik.uni-tuebingen.de/{WAPP}.},
doi = {10.1110/ps.051352405},
pdf = {../local/Donnes2005Integrated.pdf},
file = {Donnes2005Integrated.pdf:local/Donnes2005Integrated.pdf:PDF},
keywords = {biosvm immunoinformatics},
pii = {ps.051352405},
url = {http://dx.doi.org/10.1110/ps.051352405}
}
@article{Fong2004Predicting,
author = {Fong, J. H. and Keating, A. E. and Singh, M.},
title = {Predicting specificity in b{ZIP} coiled-coil protein interactions},
journal = {Genome {B}iol.},
year = {2004},
volume = {5},
number = {R11},
abstract = {We present a method for predicting protein-protein interactions mediated
by the coiled-coil motif. {W}hen tested on interactions between nearly
all human and yeast b{ZIP} proteins, our method identifies 70% of
strong interactions while maintaining that 92% of predictions are
correct. {F}urthermore, cross-validation testing shows that including
the b{ZIP} experimental data significantly improves performance.
{O}ur method can be used to predict b{ZIP} interactions in other
genomes and is a promising approach for predicting coiled-coil interactions
more generally.},
pdf = {../local/Fong2004Predicting.pdf},
file = {Fong2004Predicting.pdf:local/Fong2004Predicting.pdf:PDF},
keywords = {biosvm},
owner = {vert},
url = {http://genomebiology.com/2004/5/2/R11}
}
@article{Friedel2005Support,
author = {Friedel, C. C. and Jahn, K. H. V. and Sommer, S. and Rudd, S. and
Mewes, H. W. and Tetko, I. V.},
title = {Support vector machines for separation of mixed plant-pathogen {EST}
collections based on codon usage},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {1383-1388},
abstract = {Motivation: {D}iscovery of host and pathogen genes expressed at the
plant-pathogen interface often requires the construction of mixed
libraries that contain sequences from both genomes. {S}equence identification
requires high-throughput and reliable classification of genome origin.
{W}hen using single-pass c{DNA} sequences difficulties arise from
the short sequence length, the lack of sufficient taxonomically relevant
sequence data in public databases and ambiguous sequence homology
between plant and pathogen genes.{R}esults: {A} novel method is described,
which is independent of the availability of homologous genes and
relies on subtle differences in codon usage between plant and fungal
genes. {W}e used support vector machines ({SVM}s) to identify the
probable origin of sequences. {SVM}s were compared to several other
machine learning techniques and to a probabilistic algorithm ({PF}-{IND},
{M}aor et al., 2003) for {EST} classification also based on codon
bias differences. {O}ur software ({ECLAT}) has achieved a classification
accuracy of 93.1% on a test set of 3217 {EST} sequences from {H}.
vulgare and {B}. graminis, which is a significant improvement compared
to {PF}-{IND} (prediction accuracy of 81.2% on the same test set).
{EST} sequences with at least 50 nt of coding sequence can be classified
by {ECLAT} with high confidence. {ECLAT} allows training of classifiers
for any host-pathogen combination for which there are sufficient
classified training sequences.{A}vailability: {ECLAT} is freely available
on the internet (http://mips.gsf.de/proj/est) or on request as a
standalone version.},
doi = {10.1093/bioinformatics/bti200},
pdf = {../local/Friedel2005Support.pdf},
file = {Friedel2005Support.pdf:local/Friedel2005Support.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/bti200v1}
}
@article{Fritz2002Microarray-based,
author = {Fritz, B. and Schubert, F. and Wrobel, G. and Schwaenen, C. and Wessendorf,
S. and Nessling, M. and Korz, C. and Rieker, R. J. and Montgomery,
K. and Kucherlapati, R. and Mechtersheimer, G. and Eils, R. and Joos,
S. and Lichter, P.},
title = {Microarray-based {C}opy {N}umber and {E}xpression {P}rofiling in
{D}edifferentiated and {P}leomorphic {L}iposarcoma},
journal = {Cancer {R}es.},
year = {2002},
volume = {62},
pages = {2993-2998},
number = {11},
abstract = {Sixteen dedifferentiated and pleomorphic liposarcomas were analyzed
by comparative genomic hybridization ({CGH}) to genomic microarrays
(matrix-{CGH}), c{DNA}-derived microarrays for expression profiling,
and by quantitative {PCR}. {M}atrix-{CGH} revealed copy number gains
of numerous oncogenes, i.e., {CCND}1, {MDM}2, {GLI}, {CDK}4, {MYB},
{ESR}1, and {AIB}1, several of which correlate with a high level
of transcripts from the respective gene. {I}n addition, a number
of genes were found differentially expressed in dedifferentiated
and pleomorphic liposarcomas. {A}pplication of dedicated clustering
algorithms revealed that both tumor subtypes are clearly separated
by the genomic profiles but only with a lesser power by the expression
profiles. {U}sing a support vector machine, a subset of five clones
was identified as "class discriminators." {T}hus, for the distinction
of these types of liposarcomas, genomic profiling appears to be more
advantageous than {RNA} expression analysis.},
pdf = {../local/Fritz2002Microarray-based.pdf},
file = {Fritz2002Microarray-based.pdf:local/Fritz2002Microarray-based.pdf:PDF},
keywords = {biosvm, cgh},
owner = {jeanphilippevert},
url = {http://cancerres.aacrjournals.org/cgi/content/abstract/62/11/2993}
}
@article{Furey2000Support,
author = {Furey, T. S. and Cristianini, N. and Duffy, N. and Bednarski, D.
W. and Schummer, M. and Haussler, D.},
title = {Support vector machine classification and validation of cancer tissue
samples using microarray expression data},
journal = {Bioinformatics},
year = {2000},
volume = {16},
pages = {906-914},
number = {10},
month = {Oct},
abstract = {Motivation: {DNA} microarray experiments generating thousands of gene
expression measurements, are being used to gather information from
tissue and cell samples regarding gene expression differences that
will be useful in diagnosing disease. {W}e have developed a new method
to analyse this kind of data using support vector machines ({SVM}s).
{T}his analysis consists of both classification of the tissue samples,
and an exploration of the data for mis-labeled or questionable tissue
results. {R}esults: {W}e demonstrate the method in detail on samples
consisting of ovarian cancer tissues, normal ovarian tissues, and
other normal tissues. {T}he dataset consists of expression experiment
results for 97802 c{DNA}s for each tissue. {A}s a result of computational
analysis, a tissue sample is discovered and confirmed to be wrongly
labeled. {U}pon correction of this mistake and the removal of an
outlier, perfect classification of tissues is achieved, but not with
high confidence. {W}e identify and analyse a subset of genes from
the ovarian dataset whose expression is highly differentiated between
the types of tissues. {T}o show robustness of the {SVM} method, two
previously published datasets from other types of tissues or cells
are analysed. {T}he results are comparable to those previously obtained.
{W}e show that other machine learning methods also perform comparably
to the {SVM} on many of those datasets. {A}vailability: {T}he {SVM}
software is available at http://www.cs.columbia.edu/~bgrundy/svm.
{C}ontact: booch@cse.ucsc.edu},
pdf = {../local/Furey2000Support.pdf},
file = {Furey2000Support.pdf:local/Furey2000Support.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/16/10/906}
}
@article{Furlanello2003Entropy-based,
author = {Furlanello, C. and Serafini, M. and Merler, S. and Jurman, G.},
title = {Entropy-based gene ranking without selection bias for the predictive
classification of microarray data},
journal = {B{MC} {B}ioinformatics},
year = {2003},
volume = {4},
number = {54},
abstract = {Background {W}e describe the {E}-{RFE} method for gene ranking, which
is useful for the identification of markers in the predictive classification
of array data. {T}he method supports a practical modeling scheme
designed to avoid the construction of classification rules based
on the selection of too small gene subsets (an effect known as the
selection bias, in which the estimated predictive errors are too
optimistic due to testing on samples already considered in the feature
selection process). {R}esults {W}ith {E}-{RFE}, we speed up the recursive
feature elimination ({RFE}) with {SVM} classifiers by eliminating
chunks of uninteresting genes using an entropy measure of the {SVM}
weights distribution. {A}n optimal subset of genes is selected according
to a two-strata model evaluation procedure: modeling is replicated
by an external stratified-partition resampling scheme, and, within
each run, an internal {K}-fold cross-validation is used for {E}-{RFE}
ranking. {A}lso, the optimal number of genes can be estimated according
to the saturation of {Z}ipf's law profiles. {C}onclusions {W}ithout
a decrease of classification accuracy, {E}-{RFE} allows a speed-up
factor of 100 with respect to standard {RFE}, while improving on
alternative parametric {RFE} reduction strategies. {T}hus, a process
for gene selection and error estimation is made practical, ensuring
control of the selection bias, and providing additional diagnostic
indicators of gene importance.},
doi = {10.1186/1471-2105-4-54},
pdf = {../local/Furlanello2003Entropy-based.pdf},
file = {Furlanello2003Entropy-based.pdf:local/Furlanello2003Entropy-based.pdf:PDF},
keywords = {biosvm},
owner = {vert},
url = {http://www.biomedcentral.com/1471-2105/4/54}
}
@article{Gangal2005Human,
author = {Rajeev Gangal and Pankaj Sharma},
title = {Human pol {II} promoter prediction: time series descriptors and machine
learning.},
journal = {Nucleic {A}cids {R}es},
year = {2005},
volume = {33},
pages = {1332-6},
number = {4},
abstract = {Although several in silico promoter prediction methods have been developed
to date, they are still limited in predictive performance. {T}he
limitations are due to the challenge of selecting appropriate features
of promoters that distinguish them from non-promoters and the generalization
or predictive ability of the machine-learning algorithms. {I}n this
paper we attempt to define a novel approach by using unique descriptors
and machine-learning methods for the recognition of eukaryotic polymerase
{II} promoters. {I}n this study, non-linear time series descriptors
along with non-linear machine-learning algorithms, such as support
vector machine ({SVM}), are used to discriminate between promoter
and non-promoter regions. {T}he basic idea here is to use descriptors
that do not depend on the primary {DNA} sequence and provide a clear
distinction between promoter and non-promoter regions. {T}he classification
model built on a set of 1000 promoter and 1500 non-promoter sequences,
showed a 10-fold cross-validation accuracy of 87\% and an independent
test set had an accuracy >85\% in both promoter and non-promoter
identification. {T}his approach correctly identified all 20 experimentally
verified promoters of human chromosome 22. {T}he high sensitivity
and selectivity indicates that n-mer frequencies along with non-linear
time series descriptors, such as {L}yapunov component stability and
{T}sallis entropy, and supervised machine-learning methods, such
as {SVM}s, can be useful in the identification of pol {II} promoters.},
doi = {10.1093/nar/gki271},
pdf = {../local/Gangal2005Human.pdf},
file = {Gangal2005Human.pdf:local/Gangal2005Human.pdf:PDF},
keywords = {biosvm},
pii = {33/4/1332},
url = {http://dx.doi.org/10.1093/nar/gki271}
}
@article{Gardy2005PSORTb,
author = {Gardy, J. L. and Laird, M. R. and Chen, F. and Rey, S. and Walsh,
C. J. and Ester, M. and Brinkman, F. S. L.},
title = {{{PSORT}b v.2.0}: expanded prediction of bacterial protein subcellular
localization and insights gained from comparative proteome analysis},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {617-623},
number = {5},
month = {Mar},
abstract = {Motivation: {PSORT}b v.1.1 is the most precise bacterial localization
prediction tool available. {H}owever the program's predictive coverage
and recall are low and the method is only applicable to {G}ram-negative
bacteria. {T}he goals of the present work were: increase {PSORT}b's
coverage while maintaining the existing precision level, expand it
to include {G}ram-positive bacteria, and then carry out a comparative
analysis of localization.{R}esults: {A}n expanded database of proteins
of known localization and new modules using frequent subsequence-based
support vector machines were introduced into {PSORT}b v.2.0. {T}he
program attains a precision of 96% for {G}ram-positive and {G}ram-negative
bacteria and predictive coverage comparable to other tools for whole
proteome analysis. {W}e show that the proportion of proteins at each
localization is remarkably consistent across species, even in species
with varying proteome size.{A}vailability: {W}eb-based version: http://www.psort.org/psortb.
{S}tandalone version: {A}vailable through the website under {GNU}
{G}eneral {P}ublic {L}icense.{S}upplementary {I}nformation: http://www.psort.org/psortb/supplementaryinfo.html.},
doi = {10.1093/bioinformatics/bti057},
pdf = {../local/Gardy2005PSORTb.pdf},
file = {Gardy2005PSORTb.pdf:local/Gardy2005PSORTb.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1093/bioinformatics/bti057}
}
@article{Garg2005SVM-based,
author = {Garg, A. and Bhasin, M. and Raghava, G.P.},
title = {S{VM}-based method for subcellular localization of human proteins
using amino acid compositions, their order and similarity search},
journal = {J. {B}iol. {C}hem.},
year = {2005},
volume = {280},
pages = {14427-32},
number = {15},
month = {Apr},
abstract = {Here we report a systematic approach for predicting subcellular localization
(cytoplasm, mitochondrial, nuclear and plasma membrane) of human
proteins. {F}irstly, {SVM} based modules for predicting subcellular
localization using traditional amino acid and dipeptide (i+1) composition
achieved overall accuracy of 76.6% and 77.8%, respectively. {PSI}-{BLAST}
when carried out using similarity-based search against non-redundant
database of experimentally annotated proteins yielded 73.3% accuracy.
{T}o gain further insight, hybrid module (hybrid1) was developed
based on amino acid composition, dipeptide composition, and similarity
information and attained better accuracy of 84.9%. {I}n addition,
{SVM} module based on different higher order dipeptide i.e. i+2,
i+3, and i+4 were also constructed for the prediction of subcellular
localization of human proteins and overall accuracy of 79.7%, 77.5%
and 77.1% was accomplished respectively. {F}urthermore, another {SVM}
module hybrid2 was developed using traditional dipeptide (i+1) and
higher order dipeptide (i+2, i+3, and i+4) compositions, which gave
an overall accuracy of 81.3%. {W}e also developed {SVM} module hybrid3
based on amino acid composition, traditional and higher order dipeptide
compositions and {PSI}-{BLAST} output and achieved an overall accuracy
of 84.4%. {A} web server {HSLP}red (http://www.imtech.res.in/raghava/hslpred/
or http://bioinformatics.uams.edu/raghava/hslpred/) has been designed
to predict subcellular localization of human proteins using the above
approaches.},
doi = {10.1074/jbc.M411789200},
pdf = {../local/Garg2005SVM-based.pdf},
file = {Garg2005SVM-based.pdf:local/Garg2005SVM-based.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1074/jbc.M411789200}
}
@article{Gaudan2005Resolving,
author = {Gaudan, S. and Kirsch, H. and Rebholz-Schuhmann, D.},
title = {Resolving abbreviations to their senses in {M}edline.},
journal = {Bioinformatics},
year = {2005},
month = {Jul},
abstract = {M{OTIVATION}: {B}iological literature contains many abbreviations
with one particular sense in each document. {H}owever, most abbreviations
do not have a unique sense across the literature. {F}urthermore,
many documents do not contain the long-forms of the abbreviations.
{R}esolving an abbreviation in a document consists of retrieving
its sense in use. {A}bbreviation resolution improves accuracy of
document retrieval engines and of information extraction systems.
{RESULTS}: {W}e combine an automatic analysis of {M}edline abstracts
and linguistic methods to build a dictionary of abbreviation/sense
pairs. {T}he dictionary is used for the resolution of abbreviations
occurring with their long-forms. {A}mbiguous global abbreviations
are resolved using {S}upport {V}ector {M}achines that have been trained
on the context of each instance of the abbreviation/sense pairs,
previously extracted for the dictionary setup. {T}he system disambiguates
abbreviations with a precision of 98.9\% for a recall of 98.2\% (98.5\%
accuracy). {T}his performance is superior in comparison to previously
reported research work. {AVAILABILITY}: {T}he abbreviation resolution
module is available at http://www.ebi.ac.uk/{R}ebholz/software.html.},
doi = {10.1093/bioinformatics/bti586},
pdf = {../local/Gaudan2005Resolving.pdf},
file = {Gaudan2005Resolving.pdf:local/Gaudan2005Resolving.pdf:PDF},
keywords = {biosvm nlp},
pii = {bti586},
url = {http://dx.doi.org/10.1093/bioinformatics/bti586}
}
@article{Gomez2003Learning,
author = {Gomez, S. M. and Noble, W. S. and Rzhetsky, A.},
title = {Learning to predict protein-protein interactions from protein sequences},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {1875-1881},
number = {15},
abstract = {In order to understand the molecular machinery of the cell, we need
to know about the multitude of protein-protein interactions that
allow the cell to function. {H}igh-throughput technologies provide
some data about these interactions, but so far that data is fairly
noisy. {T}herefore, computational techniques for predicting protein-protein
interactions could be of significant value. {O}ne approach to predicting
interactions in silico is to produce from first principles a detailed
model of a candidate interaction. {W}e take an alternative approach,
employing a relatively simple model that learns dynamically from
a large collection of data. {I}n this work, we describe an attraction-repulsion
model, in which the interaction between a pair of proteins is represented
as the sum of attractive and repulsive forces associated with small,
domain- or motif-sized features along the length of each protein.
{T}he model is discriminative, learning simultaneously from known
interactions and from pairs of proteins that are known (or suspected)
not to interact. {T}he model is efficient to compute and scales well
to very large collections of data. {I}n a cross-validated comparison
using known yeast interactions, the attraction-repulsion method performs
better than several competing techniques.},
pdf = {../local/Gomez2003Learning.pdf},
file = {Gomez2003Learning.pdf:local/Gomez2003Learning.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/15/1875}
}
@article{Gordon2003Sequence,
author = {Gordon, L. and Chervonenkis, A. Y. and Gammerman, A. J. and Shahmuradov,
I. A. and Solovyev, V. V.},
title = {Sequence alignment kernel for recognition of promoter regions},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {1964-1971},
number = {15},
abstract = {In this paper we propose a new method for recognition of prokaryotic
promoter regions with startpoints of transcription. {T}he method
is based on {S}equence {A}lignment {K}ernel, a function reflecting
the quantitative measure of match between two sequences. {T}his kernel
function is further used in {D}ual {SVM}, which performs the recognition.
{S}everal recognition methods have been trained and tested on positive
data set, consisting of 669 {sigma}70-promoter regions with known
transcription startpoints of {E}scherichia coli and two negative
data sets of 709 examples each, taken from coding and non-coding
regions of the same genome. {T}he results show that our method performs
well and achieves 16.5% average error rate on positive & coding negative
data and 18.6% average error rate on positive & non-coding negative
data. {A}vailability:{T}he demo version of our method is accessible
from our website http://mendel.cs.rhul.ac.uk/},
pdf = {../local/Gordon2003Sequence.pdf},
file = {Gordon2003Sequence.pdf:local/Gordon2003Sequence.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/15/1964}
}
@article{Guermeur2002Combining,
author = {Guermeur, Y.},
title = {Combining {D}iscriminant {M}odels with {N}ew {M}ulti-{C}lass {SVM}s},
journal = {Pattern {A}nal. {A}ppl.},
year = {2002},
volume = {5},
pages = {168-179},
number = {2},
abstract = {The idea of performing model combination, instead of model selection,
has a long theoretical background in statistics. {H}owever, making
use of theoretical results is ordinarily subject to the satisfaction
of strong hypotheses (weak error correlation, availability of large
training sets, possibility to rerun the training procedure an arbitrary
number of times, etc.). {I}n contrast, the practitioner is frequently
faced with the problem of combining a given set of pre-trained classifiers,
with highly correlated errors, using only a small training sample.
{O}verfitting is then the main risk, which cannot be overcome but
with a strict complexity control of the combiner selected. {T}his
suggests that {SVM}s should be well suited for these difficult situations.
{I}nvestigating this idea, we introduce a family of multi-class {SVM}s
and assess them as ensemble methods on a real-world problem. {T}his
task, protein secondary structure prediction, is an open problem
in biocomputing for which model combination appears to be an issue
of central importance. {E}xperimental evidence highlights the gain
in quality resulting from combining some of the most widely used
prediction methods with our {SVM}s rather than with the ensemble
methods traditionally used in the field. {T}he gain increases when
the outputs of the combiners are post-processed with a {DP} algorithm.},
doi = {10.1007/s100440200015},
pdf = {../local/Guermeur2002Combining.pdf},
file = {Guermeur2002Combining.pdf:local/Guermeur2002Combining.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1007/s100440200015}
}
@incollection{Guermeur2004kernel,
author = {Guermeur, Y. and Lifschitz, A. and Vert, R.},
title = {A kernel for protein secondary structure prediction},
booktitle = {Kernel {M}ethods in {C}omputational {B}iology},
publisher = {MIT Press},
year = {2004},
editor = {Sch{\"o}lkopf, B. and Tsuda, K. and Vert, J.P.},
pages = {193-206},
keywords = {biosvm},
owner = {vert}
}
@article{Guermeur2004Combining,
author = {Guermeur, Y. and Pollastri, G. and Elisseeff, A. and Zelus, D. and
Paugam-Moisy, H. and Baldi, P.},
title = {Combining protein secondary structure prediction models with ensemble
methods of optimal complexity},
journal = {Neurocomputing},
year = {2004},
volume = {56},
pages = {305-327},
abstract = {Many sophisticated methods are currently available to perform protein
secondary structure prediction. {S}ince they are frequently based
on different principles, and different knowledge sources, significant
benefits can be expected from combining them. {H}owever, the choice
of an appropriate combiner appears to be an issue in its own right.
{T}he first difficulty to overcome when combining prediction methods
is overfitting. {T}his is the reason why we investigate the implementation
of {S}upport {V}ector {M}achines to perform the task. {A} family
of multi-class {SVM}s is introduced. {T}wo of these machines are
used to combine some of the current best protein secondary structure
prediction methods. {T}heir performance is consistently superior
to the performance of the ensemble methods traditionally used in
the field. {T}hey also outperform the decomposition approaches based
on bi-class {SVM}s. {F}urthermore, initial experimental evidence
suggests that their outputs could be processed by the biologist to
perform higher-level treatments.},
doi = {10.1016/j.neucom.2003.10.004},
pdf = {../local/Guermeur2004Combining.pdf},
file = {Guermeur2004Combining.pdf:local/Guermeur2004Combining.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/j.neucom.2003.10.004}
}
@article{Guo2004novel,
author = {Guo, J. and Chen, H. and Sun, Z. and Lin, Y.},
title = {A novel method for protein secondary structure prediction using dual-layer
{SVM} and profiles},
journal = {Proteins},
year = {2004},
volume = {54},
pages = {738-743},
number = {4},
abstract = {A high-performance method was developed for protein secondary structure
prediction based on the dual-layer support vector machine ({SVM})
and position-specific scoring matrices ({PSSM}s). {SVM} is a new
machine learning technology that has been successfully applied in
solving problems in the field of bioinformatics. {T}he {SVM}'s performance
is usually better than that of traditional machine learning approaches.
{T}he performance was further improved by combining {PSSM} profiles
with the {SVM} analysis. {T}he {PSSM}s were generated from {PSI}-{BLAST}
profiles, which contain important evolution information. {T}he final
prediction results were generated from the second {SVM} layer output.
{O}n the {CB}513 data set, the three-state overall per-residue accuracy,
{Q}3, reached 75.2%, while segment overlap ({SOV}) accuracy increased
to 80.0%. {O}n the {CB}396 data set, the {Q}3 of our method reached
74.0% and the {SOV} reached 78.1%. {A} web server utilizing the method
has been constructed and is available at http://www.bioinfo.tsinghua.edu.cn/pmsvm.},
doi = {10.1002/prot.10634Â },
pdf = {../local/Guo2004novel.pdf},
file = {Guo2004novel.pdf:local/Guo2004novel.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/prot.10634Â }
}
@article{Guo2005novel,
author = {Ting Guo and Yanxin Shi and Zhirong Sun},
title = {A novel statistical ligand-binding site predictor: application to
{ATP}-binding sites.},
journal = {Protein {E}ng {D}es {S}el},
year = {2005},
volume = {18},
pages = {65-70},
number = {2},
month = {Feb},
abstract = {Structural genomics initiatives are leading to rapid growth in newly
determined protein 3{D} structures, the functional characterization
of which may still be inadequate. {A}s an attempt to provide insights
into the possible roles of the emerging proteins whose structures
are available and/or to complement biochemical research, a variety
of computational methods have been developed for the screening and
prediction of ligand-binding sites in raw structural data, including
statistical pattern classification techniques. {I}n this paper, we
report a novel statistical descriptor (the {O}riented {S}hell {M}odel)
for protein ligand-binding sites, which utilizes the distance and
angular position distribution of various structural and physicochemical
features present in immediate proximity to the center of a binding
site. {U}sing the support vector machine ({SVM}) as the classifier,
our model identified 69\% of the {ATP}-binding sites in whole-protein
scanning tests and in eukaryotic proteins the accuracy is particularly
high. {W}e propose that this feature extraction and machine learning
procedure can screen out ligand-binding-capable protein candidates
and can yield valuable biochemical information for individual proteins.},
doi = {10.1093/protein/gzi006},
pdf = {../local/Guo2005novel.pdf},
file = {Guo2005novel.pdf:local/Guo2005novel.pdf:PDF},
keywords = {biosvm},
pii = {gzi006},
url = {http://dx.doi.org/10.1093/protein/gzi006}
}
@article{Gururaja2003Multiple,
author = {Gururaja, T. and Li, W. and Noble, W.S. and Payan, D.G. and Anderson,
D.C.},
title = {Multiple functional categories of proteins identified in an in vitro
cellular ubiquitin affinity extract using shotgun peptide sequencing},
journal = {J {P}roteome {R}es},
year = {2003},
volume = {2},
pages = {394-404},
number = {394-404},
abstract = {Using endogenous human cellular ubiquitin system enzymes and added
his-tagged ubiquitin, {ATP}, and an {ATP}-regenerating system, we
labelled cellular proteins with hexahistidine tagged ubiquitin in
vitro. {L}abeling was dependent on {ATP} and the {ATP} recycling
system, on the proteasome inhibitor {MG}132 and the ubiquitin protease
inhibitor ubiquitin aldehyde, and was inhibited by iodoacetamide.
{L}abeled proteins were affinity extracted in quadruplicate and tryptic
peptides identifed by 2{D} capillary {LC}/{MS}/{MS} comb9ined with
{SEQUEST} and {MEDUSA} analyses. {S}upport vector machine analyais
of the mass spectrometry data allowed prediction of correct matches
between mass spectrometry data and peptide sequences. {O}verall,
144 proteins were identified by peptides predicted to be correctly
sequenced, and 113 were identified by at least three peptides or
one or two peptides with at least an 80% chance of being correct.
{I}dentified proteins included 22 proteasome subunits or associated
proteins, 18 {E}1, {E}2 or {E}3 ubiquitin system enzymes or related
proteins, and four ubiquitin domain proteins. {S}eventeen directly
ubiquitinated proteins or proteins associated with the ubiquitin
system were identified. {F}unctional clusters of other proteins included
redox enzymes, proteins associated with endocytosis, cytoskeletal
proteins, {DNA} damage or repair related proteins, calcium binding
proteins, and splicing factor and related proteins, suggesting that
in vitro ubiquitination is not random, and that these functions may
be regulated by the ubiquitin system. {T}his map of cellular ubiquitinated
proteins and their interacting proteins will be useful for further
studies of ubiquitin system function.},
pdf = {../local/Gururaja2003Multiple.pdf},
file = {Gururaja2003Multiple.pdf:local/Gururaja2003Multiple.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Guyon2002Gene,
author = {Guyon, I. and Weston, J. and Barnhill, S. and Vapnik, V.},
title = {Gene selection for cancer classification using support vector machines},
journal = {Mach. Learn.},
year = {2002},
volume = {46},
pages = {389-422},
number = {1/3},
month = {Jan},
abstract = {D{NA} micro-arrays now permit scientists to screen thousands of genes
simultaneously and determine whether those genes are active, hyperactive
or silent in normal or cancerous tissue. {B}ecause these new micro-array
devices generate bewildering amounts of raw data, new analytical
methods must be developed to sort out whether cancer tissues have
distinctive signatures of gene expression over normal tissues or
other types of cancer tissues. {I}n this paper, we address the problem
of selection of a small subset of genes from broad patterns of gene
expression data, recorded on {DNA} micro-arrays. {U}sing available
training examples from cancer and normal patients, we build a classifier
suitable for genetic diagnosis, as well as drug discovery. {P}revious
attempts to address this problem select genes with correlation techniques.
{W}e propose a new method of gene selection utilizing {S}upport {V}ector
{M}achine methods based on {R}ecursive {F}eature {E}limination ({RFE}).
{W}e demonstrate experimentally that the genes selected by our techniques
yield better classification performance and are biologically relevant
to cancer. {I}n contrast with the baseline method, our method eliminates
gene redundancy automatically and yields better and more compact
gene subsets. {I}n patients with leukemia our method discovered 2
genes that yield zero leave-one-out error, while 64 genes are necessary
for the baseline method to get the best result (one leave-one-out
error). {I}n the colon cancer database, using only 4 genes our method
is 98% accurate, while the baseline method is only 86% accurate.},
pdf = {../local/Guyon2002Gene.pdf},
file = {Guyon2002Gene.pdf:local/Guyon2002Gene.pdf:PDF},
keywords = {biosvm},
subject = {biokernel},
url = {http://homepages.nyu.edu/~jaw281/genesel.pdf}
}
@article{Gartner2004Kernels,
author = {G{\"a}rtner, T. and Lloyd, J.W. and Flach, P.A.},
title = {Kernels and Distances for Structured Data},
journal = {Mach. Learn.},
year = {2004},
volume = {57},
pages = {205-232},
number = {3},
abstract = {This paper brings together two strands of machine learning of increasing
importance: kernel methods and highly structured data. We propose
a general method for constructing a kernel following the syntactic
structure of the data, as defined by its type signature in a higher-order
logic. Our main theoretical result is the positive definiteness of
any kernel thus defined. We report encouraging experimental results
on a range of real-world data sets. By converting our kernel to a
distance pseudo-metric for 1-nearest neighbour, we were able to improve
the best accuracy from the literature on the Diterpene data set by
more than 10%.},
doi = {10.1023/B:MACH.0000039777.23772.30},
keywords = {biosvm},
timestamp = {2006.07.11},
url = {http://dx.doi.org/10.1023/B:MACH.0000039777.23772.30}
}
@article{Haferlach2005AML,
author = {Torsten Haferlach and Alexander Kohlmann and Susanne Schnittger and
Martin Dugas and Wolfgang Hiddemann and Wolfgang Kern and Claudia
Schoch},
title = {A{ML} {M}3 and {AML} {M}3 variant each have a distinct gene expression
signature but also share patterns different from other genetically
defined {AML} subtypes.},
journal = {Genes {C}hromosomes {C}ancer},
year = {2005},
volume = {43},
pages = {113-27},
number = {2},
month = {Jun},
abstract = {Acute promyelocytic leukemia ({APL}) with t(15;17) appears in two
phenotypes: {AML} {M}3, with abnormal promyelocytes showing heavy
granulation and bundles of {A}uer rods, and {AML} {M}3 variant ({M}3v),
with non- or hypogranular cytoplasm and a bilobed nucleus. {W}e investigated
the global gene expression profiles of 35 {APL} patients (19 {AML}
{M}3, 16 {AML} {M}3v) by using high-density {DNA}-oligonucleotide
microarrays. {F}irst, an unsupervised approach clearly separated
{APL} samples from other {AML}s characterized genetically as t(8;21)
(n = 35), inv(16) (n = 35), or t(11q23)/{MLL} (n = 35) or as having
a normal karyotype (n = 50). {S}econd, we found genes with functional
relevance for blood coagulation that were differentially expressed
between {APL} and other {AML}s. {F}urthermore, a supervised pairwise
comparison between {M}3 and {M}3v revealed differential expression
of genes that encode for biological functions and pathways such as
granulation and maturation of hematologic cells, explaining morphologic
and clinical differences. {D}iscrimination between {M}3 and {M}3v
based on gene signatures showed a median classification accuracy
of 90\% by use of 10-fold {CV} and support vector machines. {A}dditional
molecular mutations such as {FLT}3-{LM}, which were significantly
more frequent in {M}3v than in {M}3 ({P} < 0.0001), may partly contribute
to the different phenotypes. {H}owever, linear regression analysis
demonstrated that genes differentially expressed between {M}3 and
{M}3v did not correlate with {FLT}3-{LM}.},
doi = {10.1002/gcc.20175},
pdf = {../local/Haferlach2005AML.pdf},
file = {Haferlach2005AML.pdf:local/Haferlach2005AML.pdf:PDF},
keywords = {biosvm microarray},
url = {http://dx.doi.org/10.1002/gcc.20175}
}
@article{Haferlach2005global,
author = {Torsten Haferlach and Alexander Kohlmann and Susanne Schnittger and
Martin Dugas and Wolfgang Hiddemann and Wolfgang Kern and Claudia
Schoch},
title = {A global approach to the diagnosis of leukemia using gene expression
profiling.},
journal = {Blood},
year = {2005},
volume = {106},
pages = {1189-1198},
number = {4},
month = {Aug},
abstract = {Accurate diagnosis and classification of leukemias are the bases for
the appropriate management of patients. {T}he diagnostic accuracy
and efficiency of present methods may be improved by the use of microarrays
for gene expression profiling. {W}e analyzed gene expression profiles
in bone marrow and peripheral blood samples from 937 patients with
all clinically relevant leukemia subtypes (n=892) and non-leukemic
controls (n=45) by {U}133{A} and {B} {G}ene{C}hips ({A}ffymetrix).
{F}or each subgroup differentially expressed genes were calculated.
{C}lass prediction was performed using support vector machines. {P}rediction
accuracies were estimated by 10-fold cross validation and assessed
for robustness in a 100-fold resampling approach using randomly chosen
test-sets consisting of 1/3 of the samples. {A}pplying the top 100
genes of each subgroup an overall prediction accuracy of 95.1\% was
achieved which was confirmed by resampling (median, 93.8\%; 95\%
confidence interval, 91.4\%-95.8\%). {I}n particular, {AML} with
t(15;17), t(8;21), or inv(16), {CLL}, and {P}ro-{B}-{ALL} with t(11q23)
were classified with 100\% sensitivity and 100\% specificity. {A}ccordingly,
cluster analysis completely separated all of the 13 subgroups analyzed.
{G}ene expression profiling can predict all clinically relevant subentities
of leukemia with high accuracy.},
doi = {10.1182/blood-2004-12-4938},
pdf = {../local/Haferlach2005global.pdf},
file = {Haferlach2005global.pdf:local/Haferlach2005global.pdf:PDF},
keywords = {biosvm microarray},
pii = {2004-12-4938},
url = {http://dx.doi.org/10.1182/blood-2004-12-4938}
}
@article{Hakenberg2005Systematic,
author = {Jörg Hakenberg and Steffen Bickel and Conrad Plake and Ulf Brefeld
and Hagen Zahn and Lukas Faulstich and Ulf Leser and Tobias Scheffer},
title = {Systematic feature evaluation for gene name recognition.},
journal = {B{MC} {B}ioinformatics},
year = {2005},
volume = {6 Suppl 1},
pages = {S9},
abstract = {In task 1{A} of the {B}io{C}re{A}t{I}v{E} evaluation, systems had
to be devised that recognize words and phrases forming gene or protein
names in natural language sentences. {W}e approach this problem by
building a word classification system based on a sliding window approach
with a {S}upport {V}ector {M}achine, combined with a pattern-based
post-processing for the recognition of phrases. {T}he performance
of such a system crucially depends on the type of features chosen
for consideration by the classification method, such as pre- or postfixes,
character n-grams, patterns of capitalization, or classification
of preceding or following words. {W}e present a systematic approach
to evaluate the performance of different feature sets based on recursive
feature elimination, {RFE}. {B}ased on a systematic reduction of
the number of features used by the system, we can quantify the impact
of different feature sets on the results of the word classification
problem. {T}his helps us to identify descriptive features, to learn
about the structure of the problem, and to design systems that are
faster and easier to understand. {W}e observe that the {SVM} is robust
to redundant features. {RFE} improves the performance by 0.7\%, compared
to using the complete set of attributes. {M}oreover, a performance
that is only 2.3\% below this maximum can be obtained using fewer
than 5\% of the features.},
doi = {10.1186/1471-2105-6-S1-S9},
pdf = {../local/Hakenberg2005Systematic.pdf},
file = {Hakenberg2005Systematic.pdf:local/Hakenberg2005Systematic.pdf:PDF},
keywords = {biosvm},
pii = {1471-2105-6-S1-S9},
url = {http://dx.doi.org/10.1186/1471-2105-6-S1-S9}
}
@article{Hakenberg2004Finding,
author = {Hakenberg, J. and Schmeier ,S. and Kowald, A. and Klipp, E. and Leser,
U.},
title = {Finding kinetic parameters using text mining.},
journal = {O{MICS}},
year = {2004},
volume = {8},
pages = {131-152},
number = {2},
abstract = {The mathematical modeling and description of complex biological processes
has become more and more important over the last years. {S}ystems
biology aims at the computational simulation of complex systems,
up to whole cell simulations. {A}n essential part focuses on solving
a large number of parameterized differential equations. {H}owever,
measuring those parameters is an expensive task, and finding them
in the literature is very laborious. {W}e developed a text mining
system that supports researchers in their search for experimentally
obtained parameters for kinetic models. {O}ur system classifies full
text documents regarding the question whether or not they contain
appropriate data using a support vector machine. {W}e evaluated our
approach on a manually tagged corpus of 800 documents and found that
it outperforms keyword searches in abstracts by a factor of five
in terms of precision.},
pdf = {../local/Hakenberg2004Finding.pdf},
file = {Hakenberg2004Finding.pdf:local/Hakenberg2004Finding.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.liebertonline.com/doi/abs/10.1089%2F1536231041388366}
}
@article{Han2004Predicting,
author = {Han, L.Y. and Cai, C.Z. and Ji, Z.L. and Cao, Z.W. and Cui, J. and
Chen, Y.Z.},
title = {Predicting functional family of novel enzymes irrespective of sequence
similarity: a statistical learning approach.},
journal = {Nucl. {A}cids {R}es.},
year = {2004},
volume = {32},
pages = {6437-6444},
number = {21},
abstract = {The function of a protein that has no sequence homolog of known function
is difficult to assign on the basis of sequence similarity. {T}he
same problem may arise for homologous proteins of different functions
if one is newly discovered and the other is the only known protein
of similar sequence. {I}t is desirable to explore methods that are
not based on sequence similarity. {O}ne approach is to assign functional
family of a protein to provide useful hint about its function. {S}everal
groups have employed a statistical learning method, support vector
machines ({SVM}s), for predicting protein functional family directly
from sequence irrespective of sequence similarity. {T}hese studies
showed that {SVM} prediction accuracy is at a level useful for functional
family assignment. {B}ut its capability for assignment of distantly
related proteins and homologous proteins of different functions has
not been critically and adequately assessed. {H}ere {SVM} is tested
for functional family assignment of two groups of enzymes. {O}ne
consists of 50 enzymes that have no homolog of known function from
{PSI}-{BLAST} search of protein databases. {T}he other contains eight
pairs of homologous enzymes of different families. {SVM} correctly
assigns 72% of the enzymes in the first group and 62% of the enzyme
pairs in the second group, suggesting that it is potentially useful
for facilitating functional study of novel proteins. {A} web version
of our software, {SVMP}rot, is accessible at http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi.},
doi = {10.1093/nar/gkh984},
pdf = {../local/Han2004Predicting.pdf},
file = {Han2004Predicting.pdf:local/Han2004Predicting.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1093/nar/gkh984}
}
@article{Han2005Prediction,
author = {Han, L.Y. and Cai, C.Z. and Ji, Z.L. and Chen, Y.Z.},
title = {Prediction of functional class of novel viral proteins by a statistical
learning method irrespective of sequence similarity},
journal = {Virology},
year = {2005},
volume = {331},
pages = {136-143},
number = {1},
abstract = {The function of a substantial percentage of the putative protein-coding
open reading frames ({ORF}s) in viral genomes is unknown. {A}s their
sequence is not similar to that of proteins of known function, the
function of these {ORF}s cannot be assigned on the basis of sequence
similarity. {M}ethods complement or in combination with sequence
similarity-based approaches are being explored. {T}he web-based software
{SVMP}rot () to some extent assigns protein functional family irrespective
of sequence similarity and has been found to be useful for studying
distantly related proteins [{C}ai, {C}.{Z}., {H}an, {L}.{Y}., {J}i,
{Z}.{L}., {C}hen, {X}., {C}hen, {Y}.{Z}., 2003. {SVM}-{P}rot: web-based
support vector machine software for functional classification of
a protein from its primary sequence. {N}ucleic {A}cids {R}es. 31(13):
3692-3697]. {H}ere 25 novel viral proteins are selected to test the
capability of {SVMP}rot for functional family assignment of viral
proteins whose function cannot be confidently predicted on by sequence
similarity methods at present. {T}hese proteins are without a sequence
homolog in the {S}wissprot database, with its precise function provided
in the literature, and not included in the training sets of {SVMP}rot.
{T}he predicted functional classes of 72% of these proteins match
the literature-described function, which is compared to the overall
accuracy of 87% for {SVMP}rot functional class assignment of 34582
proteins. {T}his suggests that {SVMP}rot to some extent is capable
of functional class assignment irrespective of sequence similarity
and it is potentially useful for facilitating functional study of
novel viral proteins.},
doi = {10.1016/j.virol.2004.10.020},
pdf = {../local/Han2005Prediction.pdf},
file = {Han2005Prediction.pdf:local/Han2005Prediction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/j.virol.2004.10.020}
}
@article{Han2004Prediction,
author = {Han, L.Y. and Cai, C.Z. and Lo, S.L. and Chung, M.C. and Chen, Y.Z.},
title = {Prediction of {RNA}-binding proteins from primary sequence by a support
vector machine approach.},
journal = {R{NA}},
year = {2004},
volume = {10},
pages = {355-368},
number = {3},
abstract = {Elucidation of the interaction of proteins with different molecules
is of significance in the understanding of cellular processes. {C}omputational
methods have been developed for the prediction of protein-protein
interactions. {B}ut insufficient attention has been paid to the prediction
of protein-{RNA} interactions, which play central roles in regulating
gene expression and certain {RNA}-mediated enzymatic processes. {T}his
work explored the use of a machine learning method, support vector
machines ({SVM}), for the prediction of {RNA}-binding proteins directly
from their primary sequence. {B}ased on the knowledge of known {RNA}-binding
and non-{RNA}-binding proteins, an {SVM} system was trained to recognize
{RNA}-binding proteins. {A} total of 4011 {RNA}-binding and 9781
non-{RNA}-binding proteins was used to train and test the {SVM} classification
system, and an independent set of 447 {RNA}-binding and 4881 non-{RNA}-binding
proteins was used to evaluate the classification accuracy. {T}esting
results using this independent evaluation set show a prediction accuracy
of 94.1%, 79.3%, and 94.1% for r{RNA}-, m{RNA}-, and t{RNA}-binding
proteins, and 98.7%, 96.5%, and 99.9% for non-r{RNA}-, non-m{RNA}-,
and non-t{RNA}-binding proteins, respectively. {T}he {SVM} classification
system was further tested on a small class of sn{RNA}-binding proteins
with only 60 available sequences. {T}he prediction accuracy is 40.0%
and 99.9% for sn{RNA}-binding and non-sn{RNA}-binding proteins, indicating
a need for a sufficient number of proteins to train {SVM}. {T}he
{SVM} classification systems trained in this work were added to our
{W}eb-based protein functional classification software {SVMP}rot,
at http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi. {O}ur study suggests
the potential of {SVM} as a useful tool for facilitating the prediction
of protein-{RNA} interactions.},
pdf = {../local/Han2004Prediction.pdf},
file = {Han2004Prediction.pdf:local/Han2004Prediction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.rnajournal.org/cgi/content/abstract/10/3/355}
}
@article{Han2005Fold,
author = {Sangjo Han and Byung-Chul Lee and Seung Taek Yu and Chan-Seok Jeong
and Soyoung Lee and Dongsup Kim},
title = {Fold recognition by combining profile-profile alignment and support
vector machine.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {2667-73},
number = {11},
month = {Jun},
abstract = {M{OTIVATION}: {C}urrently, the most accurate fold-recognition method
is to perform profile-profile alignments and estimate the statistical
significances of those alignments by calculating {Z}-score or {E}-value.
{A}lthough this scheme is reliable in recognizing relatively close
homologs related at the family level, it has difficulty in finding
the remote homologs that are related at the superfamily or fold level.
{RESULTS}: {I}n this paper, we present an alternative method to estimate
the significance of the alignments. {T}he alignment between a query
protein and a template of length n in the fold library is transformed
into a feature vector of length n + 1, which is then evaluated by
support vector machine ({SVM}). {T}he output from {SVM} is converted
to a posterior probability that a query sequence is related to a
template, given {SVM} output. {R}esults show that a new method shows
significantly better performance than {PSI}-{BLAST} and profile-profile
alignment with {Z}-score scheme. {W}hile {PSI}-{BLAST} and {Z}-score
scheme detect 16 and 20\% of superfamily-related proteins, respectively,
at 90\% specificity, a new method detects 46\% of these proteins,
resulting in more than 2-fold increase in sensitivity. {M}ore significantly,
at the fold level, a new method can detect 14\% of remotely related
proteins at 90\% specificity, a remarkable result considering the
fact that the other methods can detect almost none at the same level
of specificity.},
doi = {10.1093/bioinformatics/bti384},
pdf = {../local/Han2005Fold.pdf},
file = {Han2005Fold.pdf:local/Han2005Fold.pdf:PDF},
keywords = {biosvm},
pii = {bti384},
url = {http://dx.doi.org/10.1093/bioinformatics/bti384}
}
@techreport{Haussler1999Convolution,
author = {Haussler, D.},
title = {Convolution {K}ernels on {D}iscrete {S}tructures},
institution = {UC Santa Cruz},
year = {1999},
number = {UCSC-CRL-99-10},
abstract = {We introduce a new method of constructing kernels on sets whose elements
are discrete structures like strings, trees and graphs. {T}he method
can be applied iteratively to build a kernel on a infinite set from
kernels involving generators of the set. {T}he family of kernels
generated generalizes the family of radial basis kernels. {I}t can
also be used to define kernels in the form of joint {G}ibbs probability
distributions. {K}ernels can be built from hidden {M}arkov random
fields, generalized regular expressions, pair-{HMM}s, or {ANOVA}
decompositions. {U}ses of the method lead to open problems involving
the theory of infinitely divisible positive definite functions. {F}undamentals
of this theory and the theory of reproducing kernel {H}ilbert spaces
are reviewed and applied in establishing the validity of the method.},
pdf = {../local/Haussler1999Convolution.pdf},
file = {Haussler1999Convolution.pdf:local/Haussler1999Convolution.pdf:PDF},
keywords = {biosvm},
subject = {kernel}
}
@article{Helma2004Data,
author = {Helma, C. and Cramer, T. and Kramer, S. and De Raedt, L.},
title = {Data mining and machine learning techniques for the identification
of mutagenicity inducing substructures and structure activity relationships
of noncongeneric compounds},
journal = {J. Chem. Inf. Comput. Sci.},
year = {2004},
volume = {44},
pages = {1402-11},
number = {4},
abstract = {This paper explores the utility of data mining and machine learning
algorithms for the induction of mutagenicity structure-activity relationships
({SAR}s) from noncongeneric data sets. {W}e compare (i) a newly developed
algorithm ({MOLFEA}) for the generation of descriptors (molecular
fragments) for noncongeneric compounds with traditional {SAR} approaches
(molecular properties) and (ii) different machine learning algorithms
for the induction of {SAR}s from these descriptors. {I}n addition
we investigate the optimal parameter settings for these programs
and give an exemplary interpretation of the derived models. {T}he
predictive accuracies of models using {MOLFEA} derived descriptors
is approximately 10-15\%age points higher than those using molecular
properties alone. {U}sing both types of descriptors together does
not improve the derived models. {F}rom the applied machine learning
techniques the rule learner {PART} and support vector machines gave
the best results, although the differences between the learning algorithms
are only marginal. {W}e were able to achieve predictive accuracies
up to 78\% for 10-fold cross-validation. {T}he resulting models are
relatively easy to interpret and usable for predictive as well as
for explanatory purposes.},
doi = {10.1021/ci034254q},
pdf = {../local/Helma2004Data.pdf},
file = {Helma2004Data.pdf:local/Helma2004Data.pdf:PDF},
keywords = {biosvm chemoinformatics},
url = {http://dx.doi.org/10.1021/ci034254q}
}
@incollection{Hochreiter2004Gene,
author = {Hochreiter, S. and Obermayer, K.},
title = {Gene selection for microarray data},
booktitle = {Kernel {M}ethods in {C}omputational {B}iology},
publisher = {MIT Press},
year = {2004},
editor = {Schölkopf, B. and Tsuda, K. and Vert, J.P.},
pages = {319-355},
pdf = {../local/heterogeneous.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/heterogeneous.pdf:PDF;heterogeneous.pdf:http\},
file = {heterogeneous.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/heterogeneous.pdf:PDF;heterogeneous.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/heterogeneous.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@article{Hofmann2005Concept-based,
author = {Oliver Hofmann and Dietmar Schomburg},
title = {Concept-based annotation of enzyme classes.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {2059-66},
number = {9},
month = {May},
abstract = {M{OTIVATION}: {G}iven the explosive growth of biomedical data as well
as the literature describing results and findings, it is getting
increasingly difficult to keep up to date with new information. {K}eeping
databases synchronized with current knowledge is a time-consuming
and expensive task-one which can be alleviated by automatically gathering
findings from the literature using linguistic approaches. {W}e describe
a method to automatically annotate enzyme classes with disease-related
information extracted from the biomedical literature for inclusion
in such a database. {RESULTS}: {E}nzyme names for the 3901 enzyme
classes in the {BRENDA} database, a repository for quantitative and
qualitative enzyme information, were identified in more than 100,000
abstracts retrieved from the {P}ub{M}ed literature database. {P}hrases
in the abstracts were assigned to concepts from the {U}nified {M}edical
{L}anguage {S}ystem ({UMLS}) utilizing the {M}eta{M}ap program, allowing
for the identification of disease-related concepts by their semantic
fields in the {UMLS} ontology. {A}ssignments between enzyme classes
and diseases were created based on their co-occurrence within a single
sentence. {F}alse positives could be removed by a variety of filters
including minimum number of co-occurrences, removal of sentences
containing a negation and the classification of sentences based on
their semantic fields by a {S}upport {V}ector {M}achine. {V}erification
of the assignments with a manually annotated set of 1500 sentences
yielded favorable results of 92\% precision at 50\% recall, sufficient
for inclusion in a high-quality database. {AVAILABILITY}: {S}ource
code is available from the author upon request. {SUPPLEMENTARY} {INFORMATION}:
ftp.uni-koeln.de/institute/biochemie/pub/brenda/info/disease{S}upp.pdf.},
doi = {10.1093/bioinformatics/bti284},
pdf = {../local/Hofmann2005Concept-based.pdf},
file = {Hofmann2005Concept-based.pdf:local/Hofmann2005Concept-based.pdf:PDF},
keywords = {biosvm},
pii = {bti284},
url = {http://dx.doi.org/10.1093/bioinformatics/bti284}
}
@article{Hou2004Remote,
author = {Hou, Y. and Hsu, W. and Lee, M. L. and Bystroff, C.},
title = {Remote homolog detection using local sequence-structure correlations.},
journal = {Proteins},
year = {2004},
volume = {57},
pages = {518-530},
number = {3},
abstract = {Remote homology detection refers to the detection of structural homology
in proteins when there is little or no sequence similarity. {I}n
this article, we present a remote homolog detection method called
{SVM}-{HMMSTR} that overcomes the reliance on detectable sequence
similarity by transforming the sequences into strings of hidden {M}arkov
states that represent local folding motif patterns. {T}hese state
strings are transformed into fixed-dimension feature vectors for
input to a support vector machine. {T}wo sets of features are defined:
an order-independent feature set that captures the amino acid and
local structure composition; and an order-dependent feature set that
captures the sequential ordering of the local structures. {T}ests
using the {S}tructural {C}lassification of {P}roteins ({SCOP}) 1.53
data set show that the {SVM}-{HMMSTR} gives a significant improvement
over several current methods.},
doi = {10.1002/prot.20221},
pdf = {../local/Hou2004Remote.pdf},
file = {Hou2004Remote.pdf:local/Hou2004Remote.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Hou2003Efficient,
author = {Hou, Y. and Hsu, W. and Lee, M. L. and Bystroff, C.},
title = {Efficient remote homology detection using local structure},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {2294-2301},
number = {17},
abstract = {Motivation: {T}he function of an unknown biological sequence can often
be accurately inferred if we are able to map this unknown sequence
to its corresponding homologous family. {A}t present, discriminative
methods such as {SVM}-{F}isher and {SVM}-pairwise, which combine
support vector machine ({SVM}) and sequence similarity, are recognized
as the most accurate methods, with {SVM}-pairwise being the most
accurate. {H}owever, these methods typically encode sequence information
into their feature vectors and ignore the structure information.
{T}hey are also computationally inefficient. {B}ased on these observations,
we present an alternative method for {SVM}-based protein classification.
{O}ur proposed method, {SVM}-{I}-sites, utilizes structure similarity
for remote homology detection. {R}esult: {W}e run experiments on
the {S}tructural {C}lassification of {P}roteins 1.53 data set. {T}he
results show that {SVM}-{I}-sites is more efficient than {SVM}-pairwise.
{F}urther, we find that {SVM}-{I}-sites outperforms sequence-based
methods such as {PSI}-{BLAST}, {SAM}, and {SVM}-{F}isher while achieving
a comparable performance with {SVM}-pairwise. {A}vailability: {I}-sites
server is accessible through the web at http://www.bioinfo.rpi.edu.
{P}rograms are available upon request for academics. {L}icensing
agreements are available for commercial interests. {T}he framework
of encoding local structure into feature vector is available upon
request.},
pdf = {../local/Hou2003Efficient.pdf},
file = {Hou2003Efficient.pdf:local/Hou2003Efficient.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/17/2294}
}
@article{Hu2004Developing,
author = {Hu, C. and Li, X. and Liang, J.},
title = {Developing optimal non-linear scoring function for protein design},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {3080-3098},
number = {17},
abstract = {Motivation. {P}rotein design aims to identify sequences compatible
with a given protein fold but incompatible to any alternative folds.
{T}o select the correct sequences and to guide the search process,
a design scoring function is critically important. {S}uch a scoring
function should be able to characterize the global fitness landscape
of many proteins simultaneously. {R}esults: {T}o find optimal design
scoring functions, we introduce two geometric views and propose a
formulation using a mixture of non-linear {G}aussian kernel functions.
{W}e aim to solve a simplified protein sequence design problem. {O}ur
goal is to distinguish each native sequence for a major portion of
representative protein structures from a large number of alternative
decoy sequences, each a fragment from proteins of different folds.
{O}ur scoring function discriminates perfectly a set of 440 native
proteins from 14 million sequence decoys. {W}e show that no linear
scoring function can succeed in this task. {I}n a blind test of unrelated
proteins, our scoring function misclassfies only 13 native proteins
out of 194. {T}his compares favorably with about three-four times
more misclassifications when optimal linear functions reported in
the literature are used. {W}e also discuss how to develop protein
folding scoring function. {A}vailability: {A}vailable on request
from the authors.},
doi = {10.1093/bioinformatics/bth369},
pdf = {../local/Hu2004Developing},
file = {Hu2004Developing:local/Hu2004Developing:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/17/3080}
}
@article{Hu2004Improved,
author = {Hu, H.J. and Pan, Y. and Harrison, R. and Tai, P.C.},
title = {Improved protein secondary structure prediction using support vector
machine with a new encoding scheme and an advanced tertiary classifier},
journal = {I{EEE} {T}rans. {N}anobioscience},
year = {2004},
volume = {3},
pages = {265-271},
number = {4},
abstract = {Prediction of protein secondary structures is an important problem
in bioinformatics and has many applications. {T}he recent trend of
secondary structure prediction studies is mostly based on the neural
network or the support vector machine ({SVM}). {T}he {SVM} method
is a comparatively new learning system which has mostly been used
in pattern recognition problems. {I}n this study, {SVM} is used as
a machine learning tool for the prediction of secondary structure
and several encoding schemes, including orthogonal matrix, hydrophobicity
matrix, {BLOSUM}62 substitution matrix, and combined matrix of these,
are applied and optimized to improve the prediction accuracy. {A}lso,
the optimal window length for six {SVM} binary classifiers is established
by testing different window sizes and our new encoding scheme is
tested based on this optimal window size via sevenfold cross validation
tests. {T}he results show 2% increase in the accuracy of the binary
classifiers when compared with the instances in which the classical
orthogonal matrix is used. {F}inally, to combine the results of the
six {SVM} binary classifiers, a new tertiary classifier which combines
the results of one-versus-one binary classifiers is introduced and
the performance is compared with those of existing tertiary classifiers.
{A}ccording to the results, the {Q}3 prediction accuracy of new tertiary
classifier reaches 78.8% and this is better than the best result
reported in the literature.},
pdf = {../local/Hu2004Improved.pdf},
file = {Hu2004Improved.pdf:local/Hu2004Improved.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Hua2005Optimal,
author = {Hua, J. and Xiong, Z. and Lowey, J. and Suh, E. and Dougherty, E.
R.},
title = {Optimal number of features as a function of sample size for various
classification rules},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {1509-1515},
number = {8},
month = {Apr},
note = {To appear},
abstract = {Motivation: {G}iven the joint feature-label distribution, increasing
the number of features always results in decreased classification
error; however, this is not the case when a classifier is designed
via a classification rule from sample data. {T}ypically (but not
always), for fixed sample size, the error of a designed classifier
decreases and then increases as the number of features grows. {T}he
potential downside of using too many features is most critical for
small samples, which are commonplace for gene-expression-based classifiers
for phenotype discrimination. {F}or fixed sample size and feature-label
distribution, the issue is to find an optimal number of features.{R}esults:
{S}ince only in rare cases is there a known distribution of the error
as a function of the number of features and sample size, this study
employs simulation for various feature-label distributions and classification
rules, and across a wide range of sample and feature-set sizes. {T}o
achieve the desired end, finding the optimal number of features as
a function of sample size, it employs massively parallel computation.
{S}even classifiers are treated: 3-nearest-neighbor, {G}aussian kernel,
linear support vector machine, polynomial support vector machine,
perceptron, regular histogram and linear discriminant analysis. {T}hree
{G}aussian-based models are considered: linear, nonlinear and bimodal.
{I}n addition, real patient data from a large breast-cancer study
is considered. {T}o mitigate the combinatorial search for finding
optimal feature sets, and to model the situation in which subsets
of genes are co-regulated and correlation is internal to these subsets,
we assume that the covariance matrix of the features is blocked,
with each block corresponding to a group of correlated features.
{A}ltogether there is a large number of error surfaces for the many
cases. {T}hese are provided in full on a companion web-site, which
is meant to serve as resource for those working with small-sample
classification.{A}vailability: {F}or the companion web-site, please
visit http://public.tgen.org/tamu/ofs/.},
doi = {10.1093/bioinformatics/bti171},
pdf = {../local/Hua2005Optimal.pdf},
file = {Hua2005Optimal.pdf:local/Hua2005Optimal.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/bti171v1}
}
@article{Hua2001Novel,
author = {Hua, S. and Sun, Z.},
title = {A {N}ovel {M}ethod of {P}rotein {S}econdary {S}tructure {P}rediction
with {H}igh {S}egment {O}verlap {M}easure: {S}upport {V}ector {M}achine
{A}pproach},
journal = {J. {M}ol. {B}iol.},
year = {2001},
volume = {308},
pages = {397--407},
number = {2},
month = {April},
doi = {10.1006/jmbi.2001.4580},
pdf = {../local/Hua2001Novel.pdf},
file = {Hua2001Novel.pdf:local/Hua2001Novel.pdf:PDF},
keywords = {biosvm},
subject = {biokernel}
}
@article{Hua2001Support,
author = {Hua, S. and Sun, Z.},
title = {Support vector machine approach for protein subcellular localization
prediction},
journal = {Bioinformatics},
year = {2001},
volume = {17},
pages = {721-728},
number = {8},
abstract = {Motivation: {S}ubcellular localization is a key functional characteristic
of proteins. {A} fully automatic and reliable prediction system for
protein subcellular localization is needed, especially for the analysis
of large-scale genome sequences. {R}esults: {I}n this paper, {S}upport
{V}ector {M}achine has been introduced to predict the subcellular
localization of proteins from their amino acid compositions. {T}he
total prediction accuracies reach 91.4% for three subcellular locations
in prokaryotic organisms and 79.4% for four locations in eukaryotic
organisms. {P}redictions by our approach are robust to errors in
the protein {N}-terminal sequences. {T}his new approach provides
superior prediction performance compared with existing algorithms
based on amino acid composition and can be a complementary method
to other existing methods based on sorting signals. {A}vailability:
{A} web server implementing the prediction method is available at
http://www.bioinfo.tsinghua.edu.cn/{S}ub{L}oc/. {C}ontact: sunzhr@mail.tsinghua.edu.cn;
huasj00@mails.tsinghua.edu.cn {S}upplementary information: {S}upplementary
material is available at http://www.bioinfo.tsinghua.edu.cn/{S}ub{L}oc},
pdf = {../local/Hua2001Support.pdf},
file = {Hua2001Support.pdf:local/Hua2001Support.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/17/8/721}
}
@inproceedings{Huan2004Accurate,
author = {Huan, J. and Wang, W. and Washington, A. and Prins, J. and Shah,
R. and Tropsha, A.},
title = {Accurate classification of protein structural families using coherent
subgraph analysis.},
booktitle = {Proceedings of the {P}acific {S}ymposium on {B}iocomputing 2002},
year = {2004},
pages = {411-422},
abstract = {Protein structural annotation and classification is an important problem
in bioinformatics. {W}e report on the development of an efficient
subgraph mining technique and its application to finding characteristic
substructural patterns within protein structural families. {I}n our
method, protein structures are represented by graphs where the nodes
are residues and the edges connect residues found within certain
distance from each other. {A}pplication of subgraph mining to proteins
is challenging for a number reasons: (1) protein graphs are large
and complex, (2) current protein databases are large and continue
to grow rapidly, and (3) only a small fraction of the frequent subgraphs
among the huge pool of all possible subgraphs could be significant
in the context of protein classification. {T}o address these challenges,
we have developed an information theoretic model called coherent
subgraph mining. {F}rom information theory, the entropy of a random
variable {X} measures the information content carried by {X} and
the {M}utual {I}nformation ({MI}) between two random variables {X}
and {Y} measures the correlation between {X} and {Y}. {W}e define
a subgraph {X} as coherent if it is strongly correlated with every
sufficiently large sub-subgraph {Y} embedded in it. {B}ased on the
{MI} metric, we have designed a search scheme that only reports coherent
subgraphs. {T}o determine the significance of coherent protein subgraphs,
we have conducted an experimental study in which all coherent subgraphs
were identified in several protein structural families annotated
in the {SCOP} database ({M}urzin et al, 1995). {T}he {S}upport {V}ector
{M}achine algorithm was used to classify proteins from different
families under the binary classification scheme. {W}e find that this
approach identifies spatial motifs unique to individual {SCOP} families
and affords excellent discrimination between families.},
pdf = {../local/Huan2004Accurate.pdf},
file = {Huan2004Accurate.pdf:local/Huan2004Accurate.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Huang2005Support,
author = {Jing Huang and Feng Shi},
title = {Support vector machines for predicting apoptosis proteins types.},
journal = {Acta {B}iotheor.},
year = {2005},
volume = {53},
pages = {39-47},
number = {1},
abstract = {Apoptosis proteins have a central role in the development and homeostasis
of an organism. {T}hese proteins are very important for understanding
the mechanism of programmed cell death, and their function is related
to their types. {A}ccording to the classification scheme by {Z}hou
and {D}octor (2003), the apoptosis proteins are categorized into
the following four types: (1) cytoplasmic protein; (2) plasma membrane-bound
protein; (3) mitochondrial inner and outer proteins; (4) other proteins.
{A} powerful learning machine, the {S}upport {V}ector {M}achine,
is applied for predicting the type of a given apoptosis protein by
incorporating the sqrt-amino acid composition effect. {H}igh success
rates were obtained by the re-substitute test (98/98 = 100 \%) and
the jackknife test (89/98 = 90.8\%).},
doi = {10.1007/s10441-005-7002-5},
pdf = {../local/Huang2005Support.pdf},
file = {Huang2005Support.pdf:local/Huang2005Support.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1007/s10441-005-7002-5}
}
@article{Huang2005CTKPred,
author = {Huang, N. and Chen, H. and Sun, Z.},
title = {C{TKP}red: an {SVM}-based method for the prediction and classification
of the cytokine superfamily.},
journal = {Protein {E}ng. {D}es. {S}el.},
year = {2005},
month = {Jun},
abstract = {Cell proliferation, differentiation and death are controlled by a
multitude of cell-cell signals and loss of this control has devastating
consequences. {P}rominent among these regulatory signals is the cytokine
superfamily, which has crucial functions in the development, differentiation
and regulation of immune cells. {I}n this study, a support vector
machine ({SVM})-based method was developed for predicting families
and subfamilies of cytokines using dipeptide composition. {T}he taxonomy
of the cytokine superfamily with which our method complies was described
in the {C}ytokine {F}amily c{DNA} {D}atabase (db{CFC}) and the dataset
used in this study for training and testing was obtained from the
db{CFC} and {S}tructural {C}lassification of {P}roteins ({SCOP}).
{T}he method classified cytokines and non-cytokines with an accuracy
of 92.5\% by 7-fold cross-validation. {T}he method is further able
to predict seven major classes of cytokine with an overall accuracy
of 94.7\%. {A} server for recognition and classification of cytokines
based on multi-class {SVM}s has been set up at http://bioinfo.tsinghua.edu.cn/~huangni/{CTKP}red/.},
doi = {10.1093/protein/gzi041},
pdf = {../local/Huang2005CTKPred.pdf},
file = {Huang2005CTKPred.pdf:local/Huang2005CTKPred.pdf:PDF},
keywords = {biosvm},
pii = {gzi041},
url = {http://dx.doi.org/10.1093/protein/gzi041}
}
@article{Huang2005Computation,
author = {Shao-Wei Huang and Jenn-Kang Hwang},
title = {Computation of conformational entropy from protein sequences using
the machine-learning method--application to the study of the relationship
between structural conservation and local structural stability.},
journal = {Proteins},
year = {2005},
volume = {59},
pages = {802-9},
number = {4},
month = {Jun},
abstract = {A complete protein sequence can usually determine a unique conformation;
however, the situation is different for shorter subsequences--some
of them are able to adopt unique conformations, independent of context;
while others assume diverse conformations in different contexts.
{T}he conformations of subsequences are determined by the interplay
between local and nonlocal interactions. {A} quantitative measure
of such structural conservation or variability will be useful in
the understanding of the sequence-structure relationship. {I}n this
report, we developed an approach using the support vector machine
method to compute the conformational variability directly from sequences,
which is referred to as the sequence structural entropy. {A}s a practical
application, we studied the relationship between sequence structural
entropy and the hydrogen exchange for a set of well-studied proteins.
{W}e found that the slowest exchange cores usually comprise amino
acids of the lowest sequence structural entropy. {O}ur results indicate
that structural conservation is closely related to the local structural
stability. {T}his relationship may have interesting implications
in the protein folding processes, and may be useful in the study
of the sequence-structure relationship.},
doi = {10.1002/prot.20462},
pdf = {../local/Huang2005Computation.pdf},
file = {Huang2005Computation.pdf:local/Huang2005Computation.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1002/prot.20462}
}
@article{Huang2005Gene,
author = {Huang, T. M. and Kecman, V.},
title = {Gene extraction for cancer diagnosis by support vector machines-{A}n
improvement.},
journal = {Artif. {I}ntell. {M}ed.},
year = {2005},
month = {Jul},
abstract = {O{BJECTIVE}:: {T}o improve the performance of gene extraction for
cancer diagnosis by recursive feature elimination with support vector
machines ({RFE}-{SVM}s): {A} cancer diagnosis by using the {DNA}
microarray data faces many challenges the most serious one being
the presence of thousands of genes and only several dozens (at the
best) of patient's samples. {T}hus, making any kind of classification
in high-dimensional spaces from a limited number of data is both
an extremely difficult and a prone to an error procedure. {T}he improved
{RFE}-{SVM}s is introduced and used here for an elimination of less
relevant genes and just for a reduction of the overall number of
genes used in a medical diagnostic. {METHODS}:: {T}he paper shows
why and how the, usually neglected, penalty parameter {C} and some
standard data preprocessing techniques (normalizing and scaling)
influence classification results and the gene selection of {RFE}-{SVM}s.
{T}he gene selected by {RFE}-{SVM}s is compared with eight other
gene selection algorithms implemented in the {R}ankgene software
to investigate whether there is any consensus among the algorithms,
so the scope of finding the right set of genes can be reduced. {RESULTS}::
{T}he improved {RFE}-{SVM}s is applied on the two benchmarking colon
and lymphoma cancer data sets with various {C} parameters and different
standard preprocessing techniques. {H}ere, decreasing {C} leads to
the smaller diagnosis error in comparisons to other known methods
applied to the benchmarking data sets. {W}ith an appropriate parameter
{C} and with a proper preprocessing procedure, the reduction in a
diagnosis error is as high as 36\%. {CONCLUSIONS}:: {T}he results
suggest that with a properly chosen parameter {C}, the extracted
genes and the constructed classifier will ensure less overfitting
of the training data leading to an increased accuracy in selecting
relevant genes. {F}inally, comparison in gene ranking obtained by
different algorithms shows that there is a significant consensus
among the various algorithms as to which set of genes is relevant.},
doi = {10.1016/j.artmed.2005.01.006},
pdf = {../local/Huang2005Gene.pdf},
file = {Huang2005Gene.pdf:local/Huang2005Gene.pdf:PDF},
keywords = {biosvm},
pii = {S0933-3657(05)00051-5},
url = {http://dx.doi.org/10.1016/j.artmed.2005.01.006}
}
@article{Hutter2004Prediction,
author = {Hutter, B. and Schaab, C. and Albrecht, S. and Borgmann, M. and Brunner,
N. A. and Freiberg, C. and Ziegelbauer, K. and Rock, C. O. and Ivanov,
I. and Loferer, H.},
title = {Prediction of {M}echanisms of {A}ction of {A}ntibacterial {C}ompounds
by {G}ene {E}xpression {P}rofiling},
journal = {Antimicrob. {A}gents {C}hemother.},
year = {2004},
volume = {48},
pages = {2838-2844},
number = {8},
month = {Aug},
abstract = {We have generated a database of expression profiles carrying the transcriptional
responses of the model organism {B}acillus subtilis following treatment
with 37 well-characterized antibacterial compounds of different classes.
{T}he database was used to build a predictor for the assignment of
the mechanisms of action ({M}o{A}s) of antibacterial compounds by
the use of support vector machines. {T}his predictor was able to
correctly classify the {M}o{A} class for most compounds tested. {F}urthermore,
we provide evidence that the in vivo {M}o{A} of hexachlorophene does
not match the {M}o{A} predicted from in vitro data, a situation frequently
faced in drug discovery. {A} database of this kind may facilitate
the prioritization of novel antibacterial entities in drug discovery
programs. {P}otential applications and limitations are discussed.},
doi = {10.1128/AAC.48.8.2838-2844.2004},
eprint = {http://aac.asm.org/cgi/reprint/48/8/2838.pdf},
pdf = {../local/Hutter2004Prediction.pdf},
file = {Hutter2004Prediction.pdf:local/Hutter2004Prediction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1128/AAC.48.8.2838-2844.2004}
}
@article{Jaakkola2000Discriminative,
author = {Jaakkola, T. and Diekhans, M. and Haussler, D.},
title = {A {D}iscriminative {F}ramework for {D}etecting {R}emote {P}rotein
{H}omologies},
journal = {J. {C}omput. {B}iol.},
year = {2000},
volume = {7},
pages = {95--114},
number = {1,2},
pdf = {../local/jaak00.pdf},
file = {jaak00.pdf:local/jaak00.pdf:PDF},
keywords = {biosvm},
subject = {biokernelcasp},
url = {http://www.cse.ucsc.edu/research/compbio/discriminative/Jaakola2-1998.ps}
}
@inproceedings{Jaakkola1999Using,
author = {Jaakkola, T. S. and Diekhans, M. and Haussler, D.},
title = {Using the {F}isher {K}ernel {M}ethod to {D}etect {R}emote {P}rotein
{H}omologies},
booktitle = {Proceedings of the {S}eventh {I}nternational {C}onference on {I}ntelligent
{S}ystems for {M}olecular {B}iology},
year = {1999},
pages = {149--158},
publisher = {AAAI Press},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@inproceedings{Jaakkola1999Exploiting,
author = {Jaakkola, T. S. and Haussler, D.},
title = {Exploiting generative models in discriminative classifiers},
booktitle = {Proc. of {T}enth {C}onference on {A}dvances in {N}eural {I}nformation
{P}rocessing {S}ystems},
year = {1999},
pdf = {../local/jaak99.pdf},
file = {jaak99.pdf:local/jaak99.pdf:PDF},
keywords = {biosvm},
subject = {kernel},
url = {http://www.cse.ucsc.edu/research/ml/papers/Jaakola.ps}
}
@article{Jarzab2005Gene,
author = {Barbara Jarzab and Malgorzata Wiench and Krzysztof Fujarewicz and
Krzysztof Simek and Michal Jarzab and Malgorzata Oczko-Wojciechowska
and Jan Wloch and Agnieszka Czarniecka and Ewa Chmielik and Dariusz
Lange and Agnieszka Pawlaczek and Sylwia Szpak and Elzbieta Gubala
and Andrzej Swierniak},
title = {Gene expression profile of papillary thyroid cancer: sources of variability
and diagnostic implications.},
journal = {Cancer {R}es.},
year = {2005},
volume = {65},
pages = {1587-97},
number = {4},
month = {Feb},
abstract = {The study looked for an optimal set of genes differentiating between
papillary thyroid cancer ({PTC}) and normal thyroid tissue and assessed
the sources of variability in gene expression profiles. {T}he analysis
was done by oligonucleotide microarrays ({G}ene{C}hip {HG}-{U}133{A})
in 50 tissue samples taken intraoperatively from 33 patients (23
{PTC} patients and 10 patients with other thyroid disease). {I}n
the initial group of 16 {PTC} and 16 normal samples, we assessed
the sources of variability in the gene expression profile by singular
value decomposition which specified three major patterns of variability.
{T}he first and the most distinct mode grouped transcripts differentiating
between tumor and normal tissues. {T}wo consecutive modes contained
a large proportion of immunity-related genes. {T}o generate a multigene
classifier for tumor-normal difference, we used support vector machines-based
technique (recursive feature replacement). {I}t included the following
19 genes: {DPP}4, {GJB}3, {ST}14, {SERPINA}1, {LRP}4, {MET}, {EVA}1,
{SPUVE}, {LGALS}3, {HBB}, {MKRN}2, {MRC}2, {IGSF}1, {KIAA}0830, {RXRG},
{P}4{HA}2, {CDH}3, {IL}13{RA}1, and {MTMR}4, and correctly discriminated
17 of 18 additional {PTC}/normal thyroid samples and all 16 samples
published in a previous microarray study. {S}elected novel genes
({LRP}4, {EVA}1, {TMPRSS}4, {QPCT}, and {SLC}34{A}2) were confirmed
by {Q}-{PCR}.{O}ur results prove that the gene expression signal
of {PTC} is easily detectable even when cancer cells do not prevail
over tumor stroma. {W}e indicate and separate the confounding variability
related to the immune response. {F}inally, we propose a potent molecular
classifier able to discriminate between {PTC} and nonmalignant thyroid
in more than 90\% of investigated samples.},
doi = {10.1158/0008-5472.CAN-04-3078},
pdf = {../local/Jarzab2005Gene.pdf},
file = {Jarzab2005Gene.pdf:local/Jarzab2005Gene.pdf:PDF},
keywords = {biosvm},
pii = {65/4/1587},
url = {http://dx.doi.org/10.1158/0008-5472.CAN-04-3078}
}
@article{Jiang-Ning2004Cooperativity,
author = {Jiang-Ning, S. and Wei-Jiang, L. and Wen-Bo, X.},
title = {Cooperativity of the oxidization of cysteines in globular proteins.},
journal = {J. {T}heor. {B}iol.},
year = {2004},
volume = {231},
pages = {85-95},
number = {1},
abstract = {Based on the 639 non-homologous proteins with 2910 cysteine-containing
segments of well-resolved three-dimensional structures, a novel approach
has been proposed to predict the disulfide-bonding state of cysteines
in proteins by constructing a two-stage classifier combining a first
global linear discriminator based on their amino acid composition
and a second local support vector machine classifier. {T}he overall
prediction accuracy of this hybrid classifier for the disulfide-bonding
state of cysteines in proteins has scored 84.1% and 80.1%, when measured
on cysteine and protein basis using the rigorous jack-knife procedure,
respectively. {I}t shows that whether cysteines should form disulfide
bonds depends not only on the global structural features of proteins
but also on the local sequence environment of proteins. {T}he result
demonstrates the applicability of this novel method and provides
comparable prediction performance compared with existing methods
for the prediction of the oxidation states of cysteines in proteins.},
doi = {10.1016/j.jtbi.2004.06.002},
pdf = {../local/Jiang-Ning2004Cooperativity.pdf},
file = {Jiang-Ning2004Cooperativity.pdf:local/Jiang-Ning2004Cooperativity.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/j.jtbi.2004.06.002}
}
@article{Jorissen2005Virtual,
author = {R. N. Jorissen and M. K. Gilson},
title = {Virtual screening of molecular databases using a support vector machine.},
journal = {J {C}hem {I}nf {M}odel},
year = {2005},
volume = {45},
pages = {549-61},
number = {3},
abstract = {The {S}upport {V}ector {M}achine ({SVM}) is an algorithm that derives
a model used for the classification of data into two categories and
which has good generalization properties. {T}his study applies the
{SVM} algorithm to the problem of virtual screening for molecules
with a desired activity. {I}n contrast to typical applications of
the {SVM}, we emphasize not classification but enrichment of actives
by using a modified version of the standard {SVM} function to rank
molecules. {T}he method employs a simple and novel criterion for
picking molecular descriptors and uses cross-validation to select
{SVM} parameters. {T}he resulting method is more effective at enriching
for active compounds with novel chemistries than binary fingerprint-based
methods such as binary kernel discrimination.},
doi = {10.1021/ci049641u},
pdf = {../local/Jorissen2005Virtual.pdf},
file = {Jorissen2005Virtual.pdf:local/Jorissen2005Virtual.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci049641u}
}
@article{Karchin2002Classifying,
author = {Karchin, R. and Karplus, K. and Haussler, D.},
title = {Classifying {G}-protein coupled receptors with support vector machines},
journal = {Bioinformatics},
year = {2002},
volume = {18},
pages = {147--159},
abstract = {Motivation: {T}he enormous amount of protein sequence data uncovered
by genome research has increased the demand for computer software
that can automate the recognition of new proteins. {W}e discuss the
relative merits of various automated methods for recognizing {G}-{P}rotein
{C}oupled {R}eceptors ({GPCR}s), a superfamily of cell membrane proteins.
{GPCR}s are found in a wide range of organisms and are central to
a cellular signalling network that regulates many basic physiological
processes. {T}hey are the focus of a significant amount of current
pharmaceutical research because they play a key role in many diseases.
{H}owever, their tertiary structures remain largely unsolved. {T}he
methods described in this paper use only primary sequence information
to make their predictions. {W}e compare a simple nearest neighbor
approach ({BLAST}), methods based on multiple alignments generated
by a statistical profile {H}idden {M}arkov {M}odel ({HMM}), and methods,
including {S}upport {V}ector {M}achines ({SVM}s), that transform
protein sequences into fixed-length feature vectors. {R}esults: {T}he
last is the most computationally expensive method, but our experiments
show that, for those interested in annotation-quality classification,
the results are worth the effort. {I}n two-fold cross-validation
experiments testing recognition of {GPCR} subfamilies that bind a
specific ligand (such as a histamine molecule), the errors per sequence
at the {M}inimum {E}rror {P}oint ({MEP}) were 13.7% for multi-class
{SVM}s, 17.1% for our {SVM}tree method of hierarchical multi-class
{SVM} classification, 25.5% for {BLAST}, 30% for profile {HMM}s,
and 49% for classification based on nearest neighbor feature vector
{K}ernel {N}earest {N}eighbor (kern{NN}). {T}he percentage of true
positives recognized before the first false positive was 65% for
both {SVM} methods, 13% for {BLAST}, 5% for profile {HMM}s and 4%
for kern{NN}. {A}vailability: {W}e have set up a web server for {GPCR}
subfamily classification based on hierarchical multi-class {SVM}s
at http://www.soe.ucsc.edu/research/compbio/gpcr-subclass. {B}y scanning
predicted peptides found in the human genome with the {SVM}tree server,
we have identified a large number of genes that encode {GPCR}s. {A}
list of our predictions for human {GPCR}s is available at http://www.soe.ucsc.edu/research/compbio/gpcr·hg/class·results.
{W}e also provide suggested subfamily classification for 18 sequences
previously identified as unclassified {C}lass {A} (rhodopsin-like)
{GPCR}s in {GPCRDB} ({H}orn et al. , {N}ucleic {A}cids {R}es. , 26,
277?281, 1998), available at http://www.soe.ucsc.edu/research/compbio/gpcr/class{A}·unclassified/},
comment = {Un papier intéressant sur l'utilisation du Fisher kernel pour classer
les GPCR, une famille de protéines importante pour l'industrie pharmaceutique.},
pdf = {../local/Karchin2002Classifying.pdf},
file = {Karchin2002Classifying.pdf:local/Karchin2002Classifying.pdf:PDF},
keywords = {fisher-kernel sequence-classification biosvm},
subject = {biokernel},
url = {http://bioinformatics.oupjournals.org/cgi/reprint/18/1/147}
}
@article{Karchin2005Improving,
author = {R. Karchin and L. Kelly and A. Sali},
title = {Improving functional annotation of non-synonomous {SNP}s with information
theory.},
journal = {Pac {S}ymp {B}iocomput},
year = {2005},
pages = {397-408},
abstract = {Automated functional annotation of ns{SNP}s requires that amino-acid
residue changes are represented by a set of descriptive features,
such as evolutionary conservation, side-chain volume change, effect
on ligand-binding, and residue structural rigidity. {I}dentifying
the most informative combinations of features is critical to the
success of a computational prediction method. {W}e rank 32 features
according to their mutual information with functional effects of
amino-acid substitutions, as measured by in vivo assays. {I}n addition,
we use a greedy algorithm to identify a subset of highly informative
features. {T}he method is simple to implement and provides a quantitative
measure for selecting the best predictive features given a set of
features that a human expert believes to be informative. {W}e demonstrate
the usefulness of the selected highly informative features by cross-validated
tests of a computational classifier, a support vector machine ({SVM}).
{T}he {SVM}'s classification accuracy is highly correlated with the
ranking of the input features by their mutual information. {T}wo
features describing the solvent accessibility of "wild-type" and
"mutant" amino-acid residues and one evolutionary feature based on
superfamily-level multiple alignments produce comparable overall
accuracy and 6\% fewer false positives than a 32-feature set that
considers physiochemical properties of amino acids, protein electrostatics,
amino-acid residue flexibility, and binding interactions.},
keywords = {biosvm}
}
@article{Karklin2005Classification,
author = {Karklin, Y. and Meraz, R. F. and Holbrook, S.R.},
title = {Classification of non-coding {RNA} using graph representations of
secondary structure.},
journal = {Pac. {S}ymp. {B}iocomput.},
year = {2005},
pages = {4-15},
abstract = {Some genes produce transcripts that function directly in regulatory,
catalytic, or structural roles in the cell. {T}hese non-coding {RNA}s
are prevalent in all living organisms, and methods that aid the understanding
of their functional roles are essential. {RNA} secondary structure,
the pattern of base-pairing, contains the critical information for
determining the three dimensional structure and function of the molecule.
{I}n this work we examine whether the basic geometric and topological
properties of secondary structure are sufficient to distinguish between
{RNA} families in a learning framework. {F}irst, we develop a labeled
dual graph representation of {RNA} secondary structure by adding
biologically meaningful labels to the dual graphs proposed by {G}an
et al [1]. {N}ext, we define a similarity measure directly on the
labeled dual graphs using the recently developed marginalized kernels
[2]. {U}sing this similarity measure, we were able to train {S}upport
{V}ector {M}achine classifiers to distinguish {RNA}s of known families
from random {RNA}s with similar statistics. {F}or 22 of the 25 families
tested, the classifier achieved better than 70\% accuracy, with much
higher accuracy rates for some families. {T}raining a set of classifiers
to automatically assign family labels to {RNA}s using a one vs. all
multi-class scheme also yielded encouraging results. {F}rom these
initial learning experiments, we suggest that the labeled dual graph
representation, together with kernel machine methods, has potential
for use in automated analysis and classification of uncharacterized
{RNA} molecules or efficient genome-wide screens for {RNA} molecules
from existing families.},
keywords = {biosvm},
url = {http://helix-web.stanford.edu/psb05/karklin.pdf}
}
@inproceedings{Kashima2003Marginalized,
author = {Kashima, H. and Tsuda, K. and Inokuchi, A.},
title = {Marginalized {K}ernels between {L}abeled {G}raphs},
booktitle = {Proceedings of the {T}wentieth {I}nternational {C}onference on {M}achine
{L}earning},
year = {2003},
editor = {Faucett, T. and Mishra, N.},
pages = {321-328},
address = {New York, NY, USA},
publisher = {AAAI Press},
pdf = {../local/Kashima2003Marginalized.pdf},
file = {Kashima2003Marginalized.pdf:local/Kashima2003Marginalized.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@incollection{Kashima2004Kernels,
author = {Kashima, H. and Tsuda, K. and Inokuchi, A.},
title = {Kernels for graphs},
booktitle = {Kernel {M}ethods in {C}omputational {B}iology},
publisher = {MIT Press},
year = {2004},
editor = {Sch{\"o}lkopf, B. and Tsuda, K. and Vert, J.P.},
pages = {155-170},
address = {The MIT Press, Cambridge, Massachussetts},
keywords = {biosvm chemoinformatics},
owner = {vert}
}
@article{Kim2004Predictiona,
author = {Kim, H. and Park, H.},
title = {Prediction of protein relative solvent accessibility with support
vector machines and long-range interaction 3{D} local descriptor},
journal = {Proteins},
year = {2004},
volume = {54},
pages = {557-562},
number = {3},
month = {Feb},
abstract = {The prediction of protein relative solvent accessibility gives us
helpful information for the prediction of tertiary structure of a
protein. {T}he {SVM}psi method, which uses support vector machines
({SVM}s), and the position-specific scoring matrix ({PSSM}) generated
from {PSI}-{BLAST} have been applied to achieve better prediction
accuracy of the relative solvent accessibility. {W}e have introduced
a three-dimensional local descriptor that contains information about
the expected remote contacts by both the long-range interaction matrix
and neighbor sequences. {M}oreover, we applied feature weights to
kernels in {SVM}s in order to consider the degree of significance
that depends on the distance from the specific amino acid. {R}elative
solvent accessibility based on a two state-model, for 25%, 16%, 5%,
and 0% accessibility are predicted at 78.7%, 80.7%, 82.4%, and 87.4%
accuracy, respectively. {T}hree-state prediction results provide
a 64.5% accuracy with 9%; 36% threshold. {T}he support vector machine
approach has successfully been applied for solvent accessibility
prediction by considering long-range interaction and handling unbalanced
data.},
doi = {10.1002/prot.10602},
pdf = {../local/Kim2004Predictiona.pdf},
file = {Kim2004Predictiona.pdf:local/Kim2004Predictiona.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/prot.10602}
}
@article{Kim2003Protein,
author = {Kim, H. and Park, H.},
title = {Protein secondary structure prediction based on an improved support
vector machines approach},
journal = {Protein {E}ng.},
year = {2003},
volume = {16},
pages = {553-560},
number = {8},
month = {Aug},
abstract = {The prediction of protein secondary structure is an important step
in the prediction of protein tertiary structure. {A} new protein
secondary structure prediction method, {SVM}psi, was developed to
improve the current level of prediction by incorporating new tertiary
classifiers and their jury decision system, and the {PSI}-{BLAST}
{PSSM} profiles. {A}dditionally, efficient methods to handle unbalanced
data and a new optimization strategy for maximizing the {Q}3 measure
were developed. {T}he {SVM}psi produces the highest published {Q}3
and {SOV}94 scores on both the {RS}126 and {CB}513 data sets to date.
{F}or a new {KP}480 set, the prediction accuracy of {SVM}psi was
{Q}3 = 78.5% and {SOV}94 = 82.8%. {M}oreover, the blind test results
for 136 non-redundant protein sequences which do not contain homologues
of training data sets were {Q}3 = 77.2% and {SOV}94 = 81.8%. {T}he
{SVM}psi results in {CASP}5 illustrate that it is another competitive
method to predict protein secondary structure.},
pdf = {../local/Kim2003Protein.pdf},
file = {Kim2003Protein.pdf:local/Kim2003Protein.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://peds.oupjournals.org/cgi/content/abstract/16/8/553}
}
@article{Kim2004Prediction,
author = {Kim, J. H. and Lee, J. and Oh, B. and Kimm, K. and Koh, I.},
title = {Prediction of phosphorylation sites using {SVM}s},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {3179-3184},
number = {17},
abstract = {Motivation: {P}hosphorylation is involved in diverse signal transduction
pathways. {B}y predicting phosphorylation sites and their kinases
from primary protein sequences, we can obtain much valuable information
that can form the basis for further research. {U}sing support vector
machines, we attempted to predict phosphorylation sites and the type
of kinase that acts at each site. {R}esults: {O}ur prediction system
was limited to phosphorylation sites catalyzed by four protein kinase
families and four protein kinase groups. {T}he accuracy of the predictions
ranged from 83 to 95% at the kinase family level, and 76-91% at the
kinase group level. {T}he prediction system used--{P}red{P}hospho--can
be applied to the functional study of proteins, and can help predict
the changes in phosphorylation sites caused by amino acid variations
at intra- and interspecies levels. {A}vailability: {P}red{P}hospho
is available at http://www.ngri.re.kr/proteo/{P}red{P}hospho.htm.
{S}upplementary information: http://www.ngri.re.kr/proteo/supplementary.doc},
doi = {10.1093/bioinformatics/bth382},
pdf = {../local/Kim2004Prediction.pdf},
file = {Kim2004Prediction.pdf:local/Kim2004Prediction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/17/3179}
}
@inproceedings{Kin2002Marginalized,
author = {Kin, T. and Tsuda, K. and Asai, K.},
title = {Marginalized kernels for {RNA} sequence data analysis},
booktitle = {Genome {I}nformatics 2002},
year = {2002},
editor = {Lathtop, R.H. and Nakai, K. and Miyano, S. and Takagi, T. and Kanehisa,
M.},
pages = {112-122},
publisher = {Universal Academic Press},
abstract = {We present novel kernels that measure similarity of two {RNA} sequences,
taking account of their secondary structures. {T}wo types of kernels
are presented. {O}ne is for {RNA} sequences with known secondary
structures, the other for those without known secondary structures.
{T}he latter employs stochastic context-free grammar ({SCFG}) for
estimating the secondary structure. {W}e call the latter the {\it
marginalized count kernel} ({MCK}). {W}e show computational experiments
for {MCK} using 74 sets of human t{RNA} sequence data: (i) kernel
principal component analysis ({PCA}) for visualizing t{RNA} similarities,
(ii) supervised classification with support vector machines ({SVM}s).
{B}oth types of experiment show promising results for {MCK}s.},
pdf = {../local/Kin2002Marginalized.pdf},
file = {Kin2002Marginalized.pdf:local/Kin2002Marginalized.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.jsbi.org/journal/GIW02/GIW02F012.html}
}
@article{Kohlmann2004Pediatric,
author = {Kohlmann, A. and Schoch, C. and Schnittger, S. and Dugas, M. and
Hiddemann, W. and Kern, W. and Haferlach, T.},
title = {Pediatric acute lymphoblastic leukemia ({ALL}) gene expression signatures
classify an independent cohort of adult {ALL} patients},
journal = {Leukemia},
year = {2004},
volume = {18},
pages = {63-71},
number = {1},
abstract = {Recent reports support a possible future application of gene expression
profiling for the diagnosis of leukemias. {H}owever, the robustness
of subtype-specific gene expression signatures has to be proven on
independent patient samples. {H}ere, we present gene expression data
of 34 adult acute lymphoblastic leukemia ({ALL}) patients ({A}ffymetrix
{U}133{A} microarrays). {S}upport {V}ector {M}achines ({SVM}s) were
applied to stratify our samples based on given gene lists reported
to predict {MLL}, {BCR}-{ABL}, and {T}-{ALL}, as well as {MLL} and
non-{MLL} gene rearrangement positive pediatric {ALL}. {I}n addition,
seven other {B}-precursor {ALL} cases not bearing t(9;22) or t(11q23)/{MLL}
chromosomal aberrations were analyzed. {U}sing top differentially
expressed genes, hierarchical cluster and principal component analyses
demonstrate that the genetically more heterogeneous {B}-precursor
{ALL} samples intercalate with {BCR}-{ABL}-positive cases, but were
clearly distinct from {T}-{ALL} and {MLL} profiles. {S}imilar expression
signatures were observed for both heterogeneous {B}-precursor {ALL}
and for {BCR}-{ABL}-positive cases. {A}s an unrelated laboratory,
we demonstrate that gene signatures defined for childhood {ALL} were
also capable of stratifying distinct subtypes in our cohort of adult
{ALL} patients. {A}s such, previously reported gene expression patterns
identified by microarray technology are validated and confirmed on
truly independent leukemia patient samples.},
doi = {10.1038/sj.leu.2403167},
pdf = {../local/Kohlmann2004Pediatric.pdf},
file = {Kohlmann2004Pediatric.pdf:local/Kohlmann2004Pediatric.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1038/sj.leu.2403167}
}
@article{Koike2004Prediction,
author = {Koike, A. and Takagi, T.},
title = {Prediction of protein-protein interaction sites using support vector
machines},
journal = {Protein {E}ng. {D}es. {S}el.},
year = {2004},
volume = {17},
pages = {165-173},
number = {2},
month = {Feb},
abstract = {The identification of protein-protein interaction sites is essential
for the mutant design and prediction of protein-protein networks.
{T}he interaction sites of residue units were predicted using support
vector machines ({SVM}) and the profiles of sequentially/spatially
neighboring residues, plus additional information. {W}hen only sequence
information was used, prediction performance was highest using the
feature vectors, sequentially neighboring profiles and predicted
interaction site ratios, which were calculated by {SVM} regression
using amino acid compositions. {W}hen structural information was
also used, prediction performance was highest using the feature vectors,
spatially neighboring residue profiles, accessible surface areas,
and the with/without protein interaction sites ratios predicted by
{SVM} regression and amino acid compositions. {I}n the latter case,
the precision at recall = 50% was 54-56% for a homo-hetero mixed
test set and >20% higher than for random prediction. {A}pproximately
30% of the residues wrongly predicted as interaction sites were the
closest sequentially/spatially neighboring on the interaction site
residues. {T}he predicted residues covered 86-87% of the actual interfaces
(96-97% of interfaces with over 20 residues). {T}his prediction performance
appeared to be slightly higher than a previously reported study.
{C}omparing the prediction accuracy of each molecule, it seems to
be easier to predict interaction sites for stable complexes.},
doi = {10.1093/protein/gzh020},
pdf = {../local/Koike2004Prediction.pdf},
file = {Koike2004Prediction.pdf:local/Koike2004Prediction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1093/protein/gzh020}
}
@article{Komura2005Multidimensional,
author = {Komura, D. and Nakamura, H. and Tsutsumi, S. and Aburatani, H. and
Ihara, S.},
title = {Multidimensional support vector machines for visualization of gene
expression data},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {439-444},
number = {4},
month = {Feb},
abstract = {Motivation: {S}ince {DNA} microarray experiments provide us with huge
amount of gene expression data, they should be analyzed with statistical
methods to extract the meanings of experimental results. {S}ome dimensionality
reduction methods such as {P}rincipal {C}omponent {A}nalysis ({PCA})
are used to roughly visualize the distribution of high dimensional
gene expression data. {H}owever, in the case of binary classification
of gene expression data, {PCA} does not utilize class information
when choosing axes. {T}hus clearly separable data in the original
space may not be so in the reduced space used in {PCA}.{R}esults:
{F}or visualization and class prediction of gene expression data,
we have developed a new {SVM}-based method called multidimensional
{SVM}s, that generate multiple orthogonal axes. {T}his method projects
high dimensional data into lower dimensional space to exhibit properties
of the data clearly and to visualize a distribution of the data roughly.
{F}urthermore, the multiple axes can be used for class prediction.
{T}he basic properties of conventional {SVM}s are retained in our
method: solutions of mathematical programming are sparse, and nonlinear
classification is implemented implicitly through the use of kernel
functions. {T}he application of our method to the experimentally
obtained gene expression datasets for patients' samples indicates
that our algorithm is efficient and useful for visualization and
class prediction.},
doi = {10.1093/bioinformatics/bti188},
pdf = {../local/Komura2005Multidimensional.pdf},
file = {Komura2005Multidimensional.pdf:local/Komura2005Multidimensional.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/bti188v1}
}
@incollection{Kondor2004Diffusion,
author = {Kondor, R. and Vert, J.-P.},
title = {Diffusion kernels},
booktitle = {Kernel {M}ethods in {C}omputational {B}iology},
publisher = {MIT Press},
year = {2004},
editor = {Sch{\"o}lkopf, B. and Tsuda, K. and Vert, J.P.},
pages = {171-192},
pdf = {../local/saigo.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/saigo.pdf:PDF;saigo.pdf:http\},
file = {saigo.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/saigo.pdf:PDF;saigo.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/saigo.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@inproceedings{Kondor2002Diffusion,
author = {R. I. Kondor and J. Lafferty},
title = {Diffusion kernels on graphs and other discrete input},
booktitle = {Proceedings of the Nineteenth International Conference on Machine
Learning},
year = {2002},
pages = {315--322},
address = {San Francisco, CA, USA},
publisher = {Morgan Kaufmann Publishers Inc.},
pdf = {../local/Kondor2002Diffusion.pdf},
file = {Kondor2002Diffusion.pdf:Kondor2002Diffusion.pdf:PDF},
keywords = {biosvm},
subject = {kernelnet}
}
@article{Kote-Jarai2004Gene,
author = {Zsofia Kote-Jarai and Richard D Williams and Nicola Cattini and Maria
Copeland and Ian Giddings and Richard Wooster and Robert H tePoele
and Paul Workman and Barry Gusterson and John Peacock and Gerald
Gui and Colin Campbell and Ros Eeles},
title = {Gene expression profiling after radiation-induced {DNA} damage is
strongly predictive of {BRCA}1 mutation carrier status.},
journal = {Clin. {C}ancer {R}es.},
year = {2004},
volume = {10},
pages = {958-63},
number = {3},
month = {Feb},
abstract = {P{URPOSE}: {T}he impact of the presence of a germ-line {BRCA}1 mutation
on gene expression in normal breast fibroblasts after radiation-induced
{DNA} damage has been investigated. {EXPERIMENTAL} {DESIGN}: {H}igh-density
c{DNA} microarray technology was used to identify differential responses
to {DNA} damage in fibroblasts from nine heterozygous {BRCA}1 mutation
carriers compared with five control samples without personal or family
history of any cancer. {F}ibroblast cultures were irradiated, and
their expression profile was compared using intensity ratios of the
c{DNA} microarrays representing 5603 {IMAGE} clones. {RESULTS}: {C}lass
comparison and class prediction analysis has shown that {BRCA}1 mutation
carriers can be distinguished from controls with high probability
(approximately 85\%). {S}ignificance analysis of microarrays and
the support vector machine classifier identified gene sets that discriminate
the samples according to their mutation status. {T}hese include genes
already known to interact with {BRCA}1 such as {CDKN}1{B}, {ATR},
and {RAD}51. {CONCLUSIONS}: {T}he results of this initial study suggest
that normal cells from heterozygous {BRCA}1 mutation carriers display
a different gene expression profile from controls in response to
{DNA} damage. {A}daptations of this pilot result to other cell types
could result in the development of a functional assay for {BRCA}1
mutation status.},
pdf = {../local/Kote-Jarai2004Gene.pdf},
file = {Kote-Jarai2004Gene.pdf:local/Kote-Jarai2004Gene.pdf:PDF},
keywords = {biosvm , breastcancer},
url = {http://clincancerres.aacrjournals.org/cgi/content/abstract/10/3/958}
}
@article{Kramer2002Fragment,
author = {S. Kramer and E. Frank and C. Helma},
title = {Fragment generation and support vector machines for inducing {SAR}s.},
journal = {S{AR} {QSAR} {E}nviron {R}es},
year = {2002},
volume = {13},
pages = {509-23},
number = {5},
month = {Jul},
abstract = {We present a new approach to the induction of {SAR}s based on the
generation of structural fragments and support vector machines ({SVM}s).
{I}t is tailored for bio-chemical databases, where the examples are
two-dimensional descriptions of chemical compounds. {T}he fragment
generator finds all fragments (i.e. linearly connected atoms) that
satisfy user-specified constraints regarding their frequency and
generality. {I}n this paper, we are querying for fragments within
a minimum and a maximum frequency in the dataset. {A}fter fragment
generation, we propose to apply {SVM}s to the problem of inducing
{SAR}s from these fragments. {W}e conjecture that the {SVM}s are
particularly useful in this context, as they can deal with a large
number of features. {E}xperiments in the domains of carcinogenicity
and mutagenicity prediction show that the minimum and the maximum
frequency queries for fragments can be answered within a reasonable
time, and that the predictive accuracy obtained using these fragments
is satisfactory. {H}owever, further experiments will have to confirm
that this is a viable approach to inducing {SAR}s.},
doi = {10.1080/10629360290023340},
keywords = {biosvm},
url = {http://dx.doi.org/10.1080/10629360290023340}
}
@article{Krishnan2003comparative,
author = {Krishnan, V. G. and Westhead, D. R.},
title = {A comparative study of machine-learning methods to predict the effects
of single nucleotide polymorphisms on protein function},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {2199-2209},
number = {17},
abstract = {Motivation: {T}he large volume of single nucleotide polymorphism data
now available motivates the development of methods for distinguishing
neutral changes from those which have real biological effects. {H}ere,
two different machine-learning methods, decision trees and support
vector machines ({SVM}s), are applied for the first time to this
problem. {I}n common with most other methods, only non-synonymous
changes in protein coding regions of the genome are considered. {R}esults:
{I}n detailed cross-validation analysis, both learning methods are
shown to compete well with existing methods, and to out-perform them
in some key tests. {SVM}s show better generalization performance,
but decision trees have the advantage of generating interpretable
rules with robust estimates of prediction confidence. {I}t is shown
that the inclusion of protein structure information produces more
accurate methods, in agreement with other recent studies, and the
effect of using predicted rather than actual structure is evaluated.
{A}vailability: {S}oftware is available on request from the authors.},
pdf = {../local/Krishnan2003comparative.pdf},
file = {Krishnan2003comparative.pdf:local/Krishnan2003comparative.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/17/2199}
}
@incollection{Krishnapuram2004Gene,
author = {Krishnapuram, B. and Carin, L. and Hartemink, A.},
title = {Gene expression analysis: joint feature selection and classifier
design},
booktitle = {Kernel {M}ethods in {C}omputational {B}iology},
publisher = {MIT Press},
year = {2004},
editor = {Schölkopf, B. and Tsuda, K. and Vert, J.P.},
pages = {299-317},
pdf = {../local/heterogeneous.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/heterogeneous.pdf:PDF;heterogeneous.pdf:http\},
file = {heterogeneous.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/heterogeneous.pdf:PDF;heterogeneous.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/heterogeneous.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@article{Krishnapuram2004Joint,
author = {Krishnapuram, B. and Carin, L. and Hartemink, A.},
title = {Joint {C}lassifier and {F}eature {O}ptimization for {C}omprehensive
{C}ancer {D}iagnosis {U}sing {G}ene {E}xpression {D}ata},
journal = {J. {C}omput. {B}iol.},
year = {2004},
volume = {11},
pages = {227-242},
number = {2-3},
abstract = {ecent research has demonstrated quite convincingly that accurate cancer
diagnosis can be achieved by constructing classifiers that are designed
to compare the gene expression profile of a tissue of unknown cancer
status to a database of stored expression profiles from tissues of
known cancer status. {T}his paper introduces the {JCFO}, a novel
algorithm that uses a sparse {B}ayesian approach to jointly identify
both the optimal nonlinear classifier for diagnosis and the optimal
set of genes on which to base that diagnosis. {W}e show that the
diagnostic classification accuracy of the proposed algorithm is superior
to a number of current state-of-the-art methods in a full leave-one-out
cross-validation study of five widely used benchmark datasets. {I}n
addition to its superior classification accuracy, the algorithm is
designed to automatically identify a small subset of genes (typically
around twenty in our experiments) that are capable of providing complete
discriminatory information for diagnosis. {F}ocusing attention on
a small subset of genes is useful not only because it produces a
classifier with good generalization capacity, but also because this
set of genes may provide insights into the mechanisms responsible
for the disease itself. {A} number of the genes identified by the
{JCFO} in our experiments are already in use as clinical markers
for cancer diagnosis; some of the remaining genes may be excellent
candidates for further clinical investigation. {I}f it is possible
to identify a small set of genes that is indeed capable of providing
complete discrimination, inexpensive diagnostic assays might be widely
deployable in clinical settings.},
doi = {10.1089/1066527041410463},
pdf = {../local/Krishnapuram2004Joint.pdf},
file = {Krishnapuram2004Joint.pdf:local/Krishnapuram2004Joint.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1089/1066527041410463}
}
@article{Krishnapuram2004bayesian,
author = {Krishnapuram, B. and Hartemink, A. J. and Carin, L. and Figueiredo,
M. A. T.},
title = {A bayesian approach to joint feature selection and classifier design},
journal = {IEEE T. Pattern. Anal.},
year = {2004},
volume = {26},
pages = {1105-11},
number = {9},
month = {Sep},
abstract = {This paper adopts a {B}ayesian approach to simultaneously learn both
an optimal nonlinear classifier and a subset of predictor variables
(or features) that are most relevant to the classification task.
{T}he approach uses heavy-tailed priors to promote sparsity in the
utilization of both basis functions and features; these priors act
as regularizers for the likelihood function that rewards good classification
on the training data. {W}e derive an expectation-maximization ({EM})
algorithm to efficiently compute a maximum a posteriori ({MAP}) point
estimate of the various parameters. {T}he algorithm is an extension
of recent state-of-the-art sparse {B}ayesian classifiers, which in
turn can be seen as {B}ayesian counterparts of support vector machines.
{E}xperimental comparisons using kernel classifiers demonstrate both
parsimonious feature selection and excellent classification accuracy
on a range of synthetic and benchmark data sets.},
doi = {10.1109/TPAMI.2004.55},
pdf = {../local/Krishnapuram2004bayesian.pdf},
file = {Krishnapuram2004bayesian.pdf:local/Krishnapuram2004bayesian.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1109/TPAMI.2004.55}
}
@article{Kuang2005Profile-based,
author = {Kuang, R. and Ie, E. and Wang, K. and Wang, K. and Siddiqi, M. and
Freund, Y. and Leslie, C.},
title = {Profile-based string kernels for remote homology detection and motif
extraction.},
journal = {J. Bioinform. Comput. Biol.},
year = {2005},
volume = {3},
pages = {527--550},
number = {3},
month = {Jun},
abstract = {We introduce novel profile-based string kernels for use with support
vector machines (SVMs) for the problems of protein classification
and remote homology detection. These kernels use probabilistic profiles,
such as those produced by the PSI-BLAST algorithm, to define position-dependent
mutation neighborhoods along protein sequences for inexact matching
of k-length subsequences ("k-mers") in the data. By use of an efficient
data structure, the kernels are fast to compute once the profiles
have been obtained. For example, the time needed to run PSI-BLAST
in order to build the profiles is significantly longer than both
the kernel computation time and the SVM training time. We present
remote homology detection experiments based on the SCOP database
where we show that profile-based string kernels used with SVM classifiers
strongly outperform all recently presented supervised SVM methods.
We further examine how to incorporate predicted secondary structure
information into the profile kernel to obtain a small but significant
performance improvement. We also show how we can use the learned
SVM classifier to extract "discriminative sequence motifs"--short
regions of the original profile that contribute almost all the weight
of the SVM classification score--and show that these discriminative
motifs correspond to meaningful structural features in the protein
data. The use of PSI-BLAST profiles can be seen as a semi-supervised
learning technique, since PSI-BLAST leverages unlabeled data from
a large sequence database to build more informative profiles. Recently
presented "cluster kernels" give general semi-supervised methods
for improving SVM protein classification performance. We show that
our profile kernel results also outperform cluster kernels while
providing much better scalability to large datasets.},
keywords = {biosvm},
owner = {vert},
pii = {S021972000500120X},
pmid = {16108083},
timestamp = {2007.08.01}
}
@article{Kuang2004Profile-based,
author = {Kuang, R. and Ie, E. and Wang, K. and Wang, K. and Siddiqi, M. and
Freund, Y. and Leslie, C.},
title = {Profile-based string kernels for remote homology detection and motif
extraction.},
journal = {Proc IEEE Comput Syst Bioinform Conf},
year = {2004},
pages = {152--160},
abstract = {We introduce novel profile-based string kernels for use with support
vector machines (SVMs) for the problems of protein classification
and remote homology detection. These kernels use probabilistic profiles,
such as those produced by the PSI-BLAST algorithm, to define position-dependent
mutation neighborhoods along protein sequences for inexact matching
of k-length subsequences ("k-mers") in the data. By use of an efficient
data structure, the kernels are fast to compute once the profiles
have been obtained. For example, the time needed to run PSI-BLAST
in order to build the pro- files is significantly longer than both
the kernel computation time and the SVM training time. We present
remote homology detection experiments based on the SCOP database
where we show that profile-based string kernels used with SVM classifiers
strongly outperform all recently presented supervised SVM methods.
We also show how we can use the learned SVM classifier to extract
"discriminative sequence motifs" -- short regions of the original
profile that contribute almost all the weight of the SVM classification
score -- and show that these discriminative motifs correspond to
meaningful structural features in the protein data. The use of PSI-BLAST
profiles can be seen as a semi-supervised learning technique, since
PSI-BLAST leverages unlabeled data from a large sequence database
to build more informative profiles. Recently presented "cluster kernels"
give general semi-supervised methods for improving SVM protein classification
performance. We show that our profile kernel results are comparable
to cluster kernels while providing much better scalability to large
datasets.},
keywords = {biosvm},
owner = {vert},
pmid = {16448009},
timestamp = {2007.08.01}
}
@article{Kuang2004Protein,
author = {Kuang, R. and Leslie, C. S. and Yang, A.-S.},
title = {Protein backbone angle prediction with machine learning approaches},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {1612-1621},
number = {10},
abstract = {Motivation: {P}rotein backbone torsion angle prediction provides useful
local structural information that goes beyond conventional three-state
({alpha}, {beta} and coil) secondary structure predictions. {A}ccurate
prediction of protein backbone torsion angles will substantially
improve modeling procedures for local structures of protein sequence
segments, especially in modeling loop conformations that do not form
regular structures as in {alpha}-helices or {beta}-strands. {R}esults:
{W}e have devised two novel automated methods in protein backbone
conformational state prediction: one method is based on support vector
machines ({SVM}s); the other method combines a standard feed-forward
back-propagation artificial neural network ({NN}) with a local structure-based
sequence profile database ({LSBSP}1). {E}xtensive benchmark experiments
demonstrate that both methods have improved the prediction accuracy
rate over the previously published methods for conformation state
prediction when using an alphabet of three or four states. {A}vailability:
{LSBSP}1 and the {NN} algorithm have been implemented in {P}r{ISM}.1,
which is available from www.columbia.edu/~ay1/. {S}upplementary information:
{S}upplementary data for the {SVM} method can be downloaded from
the {W}ebsite www.cs.columbia.edu/compbio/backbone.},
pdf = {../local/Kuang2004Protein.pdf},
file = {Kuang2004Protein.pdf:local/Kuang2004Protein.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/10/1612}
}
@article{Kumar2005BhairPred,
author = {Kumar, M. and Bhasin, M. and Natt, N. K. and Raghava, G. P. S.},
title = {Bhair{P}red: prediction of beta-hairpins in a protein from multiple
alignment information using {ANN} and {SVM} techniques.},
journal = {Nucleic {A}cids {R}es},
year = {2005},
volume = {33},
pages = {W154-9},
number = {Web Server issue},
month = {Jul},
abstract = {This paper describes a method for predicting a supersecondary structural
motif, beta-hairpins, in a protein sequence. {T}he method was trained
and tested on a set of 5102 hairpins and 5131 non-hairpins, obtained
from a non-redundant dataset of 2880 proteins using the {DSSP} and
{PROMOTIF} programs. {T}wo machine-learning techniques, an artificial
neural network ({ANN}) and a support vector machine ({SVM}), were
used to predict beta-hairpins. {A}n accuracy of 65.5\% was achieved
using {ANN} when an amino acid sequence was used as the input. {T}he
accuracy improved from 65.5 to 69.1\% when evolutionary information
({PSI}-{BLAST} profile), observed secondary structure and surface
accessibility were used as the inputs. {T}he accuracy of the method
further improved from 69.1 to 79.2\% when the {SVM} was used for
classification instead of the {ANN}. {T}he performances of the methods
developed were assessed in a test case, where predicted secondary
structure and surface accessibility were used instead of the observed
structure. {T}he highest accuracy achieved by the {SVM} based method
in the test case was 77.9\%. {A} maximum accuracy of 71.1\% with
{M}atthew's correlation coefficient of 0.41 in the test case was
obtained on a dataset previously used by {X}. {C}ruz, {E}. {G}. {H}utchinson,
{A}. {S}hephard and {J}. {M}. {T}hornton (2002) {P}roc. {N}atl {A}cad.
{S}ci. {USA}, 99, 11157-11162. {T}he performance of the method was
also evaluated on proteins used in the '6th community-wide experiment
on the critical assessment of techniques for protein structure prediction
({CASP}6)'. {B}ased on the algorithm described, a web server, {B}hair{P}red
(http://www.imtech.res.in/raghava/bhairpred/), has been developed,
which can be used to predict beta-hairpins in a protein using the
{SVM} approach.},
doi = {doi:10.1093/nar/gki588},
pdf = {../local/Kumar2005BhairPred.pdf},
file = {Kumar2005BhairPred.pdf:local/Kumar2005BhairPred.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/doi:10.1093/nar/gki588}
}
@incollection{Lanckriet2004Kernel-based,
author = {Lanckriet, G.R.G. and Cristianini, N. and Jordan, M.I. and Noble,
W.S.},
title = {Kernel-based integration of genomic data using semidefinite programming},
booktitle = {Kernel {M}ethods in {C}omputational {B}iology},
publisher = {MIT Press},
year = {2004},
editor = {Schölkopf, B. and Tsuda, K. and Vert, J.P.},
pages = {231-259},
keywords = {biosvm},
owner = {vert}
}
@inproceedings{Lanckriet2004Kernel-baseda,
author = {Lanckriet, G.R. and Deng, M. and Cristianini, N. and Jordan, M.I.
and Noble, W.S.},
title = {Kernel-based data fusion and its application to protein function
prediction in yeast.},
booktitle = {Proceedings of the {P}acific {S}ymposium on {B}iocomputing},
year = {2004},
pages = {300-311},
abstract = {Kernel methods provide a principled framework in which to represent
many types of data, including vectors, strings, trees and graphs.
{A}s such, these methods are useful for drawing inferences about
biological phenomena. {W}e describe a method for combining multiple
kernel representations in an optimal fashion, by formulating the
problem as a convex optimization problem that can be solved using
semidefinite programming techniques. {T}he method is applied to the
problem of predicting yeast protein functional classifications using
a support vector machine ({SVM}) trained on five types of data. {F}or
this problem, the new method performs better than a previously-described
{M}arkov random field method, and better than the {SVM} trained on
any single type of data.},
pdf = {../local/Lanckriet2004Kernel-baseda.pdf},
file = {Lanckriet2004Kernel-baseda.pdf:local/Lanckriet2004Kernel-baseda.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Lanckriet2004statistical,
author = {Lanckriet, G. R. G. and De Bie, T. and Cristianini, N. and Jordan,
M. I. and Noble, W. S.},
title = {A statistical framework for genomic data fusion},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {2626-2635},
number = {16},
abstract = {Motivation: {D}uring the past decade, the new focus on genomics has
highlighted a particular challenge: to integrate the different views
of the genome that are provided by various types of experimental
data. {R}esults: {T}his paper describes a computational framework
for integrating and drawing inferences from a collection of genome-wide
measurements. {E}ach dataset is represented via a kernel function,
which defines generalized similarity relationships between pairs
of entities, such as genes or proteins. {T}he kernel representation
is both flexible and efficient, and can be applied to many different
types of data. {F}urthermore, kernel functions derived from different
types of data can be combined in a straightforward fashion. {R}ecent
advances in the theory of kernel methods have provided efficient
algorithms to perform such combinations in a way that minimizes a
statistical loss function. {T}hese methods exploit semidefinite programming
techniques to reduce the problem of finding optimizing kernel combinations
to a convex optimization problem. {C}omputational experiments performed
using yeast genome-wide datasets, including amino acid sequences,
hydropathy profiles, gene expression data and known protein-protein
interactions, demonstrate the utility of this approach. {A} statistical
learning algorithm trained from all of these data to recognize particular
classes of proteins--membrane proteins and ribosomal proteins--performs
significantly better than the same algorithm trained on any single
type of data. {A}vailability: {S}upplementary data at http://noble.gs.washington.edu/proj/sdp-svm},
doi = {10.1093/bioinformatics/bth294},
pdf = {../local/Lanckriet2004statistical.pdf},
file = {Lanckriet2004statistical.pdf:local/Lanckriet2004statistical.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/16/2626}
}
@article{Lee2003Discovery,
author = {Dongkwon Lee and Sang Wook Choi and Myengsoo Kim and Jin Hyun Park
and Moonkyu Kim and Jungchul Kim and In-Beum Lee},
title = {Discovery of differentially expressed genes related to histological
subtype of hepatocellular carcinoma.},
journal = {Biotechnol {P}rog.},
year = {2003},
volume = {19},
pages = {1011-5},
number = {3},
abstract = {Hepatocellular carcinoma ({HCC}) is one of the most common human malignancies
in the world. {T}o identify the histological subtype-specific genes
of {HCC}, we analyzed the gene expression profile of 10 {HCC} patients
by means of c{DNA} microarray. {W}e proposed a systematic approach
for determining the discriminatory genes and revealing the biological
phenomena of {HCC} with c{DNA} microarray data. {F}irst, normalization
of c{DNA} microarray data was performed to reduce or minimize systematic
variations. {O}n the basis of the suitably normalized data, we identified
specific genes involved in histological subtype of {HCC}. {T}wo classification
methods, {F}isher's discriminant analysis ({FDA}) and support vector
machine ({SVM}), were used to evaluate the reliability of the selected
genes and discriminate the histological subtypes of {HCC}. {T}his
study may provide a clue for the needs of different chemotherapy
and the reason for heterogeneity of the clinical responses according
to histological subtypes.},
doi = {10.1021/bp025746a},
pdf = {../local/Lee2003Discovery.pdf},
file = {Lee2003Discovery.pdf:local/Lee2003Discovery.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/bp025746a}
}
@article{Lee2003Classification,
author = {Lee, Y. and Lee, C.-K.},
title = {Classification of multiple cancer types by multicategory support
vector machines using gene expression data},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {1132-1139},
number = {9},
abstract = {Motivation: {H}igh-density {DNA} microarray measures the activities
of several thousand genes simultaneously and the gene expression
profiles have been used for the cancer classification recently. {T}his
new approach promises to give better therapeutic measurements to
cancer patients by diagnosing cancer types with improved accuracy.
{T}he {S}upport {V}ector {M}achine ({SVM}) is one of the classification
methods successfully applied to the cancer diagnosis problems. {H}owever,
its optimal extension to more than two classes was not obvious, which
might impose limitations in its application to multiple tumor types.
{W}e briefly introduce the {M}ulticategory {SVM}, which is a recently
proposed extension of the binary {SVM}, and apply it to multiclass
cancer diagnosis problems {R}esults: {I}ts applicability is demonstrated
on the leukemia data ({G}olub et al., 1999) and the small round blue
cell tumors of childhood data ({K}han et al., 2001). {C}omparable
classification accuracy shown in the applications and its flexibility
render the {MSVM} a viable alternative to other classification methods
{S}upplementary {I}nformation: http://www.stat.ohio-state.edu/~yklee/msvm.html
{C}ontact: yklee@stat.ohio-state.edu},
pdf = {../local/Lee2003Classification.pdf},
file = {Lee2003Classification.pdf:local/Lee2003Classification.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/9/1132}
}
@inproceedings{Leslie2002spectrum,
author = {Leslie, C. and Eskin, E. and Noble, W.S.},
title = {The spectrum kernel: a string kernel for {SVM} protein classification},
booktitle = {Proceedings of the {P}acific {S}ymposium on {B}iocomputing 2002},
year = {2002},
editor = {Russ B. Altman and A. Keith Dunker and Lawrence Hunter and Kevin
Lauerdale and Teri E. Klein},
pages = {564--575},
address = {Singapore},
publisher = {World Scientific},
pdf = {../local/lesl02.pdf},
file = {lesl02.pdf:local/lesl02.pdf:PDF},
keywords = {biosvm},
subject = {biokernel}
}
@inproceedings{Leslie2003Mismatch,
author = {Leslie, C. and Eskin, E. and Weston, J. and Noble, W.S.},
title = {Mismatch {S}tring {K}ernels for {SVM} {P}rotein {C}lassification},
booktitle = {Advances in {N}eural {I}nformation {P}rocessing {S}ystems 15},
year = {2003},
editor = {Suzanna Becker and Sebastian Thrun and Klaus Obermayer},
publisher = {MIT Press},
pdf = {../local/lesl02b.pdf},
file = {lesl02b.pdf:local/lesl02b.pdf:PDF},
keywords = {biosvm},
subject = {biokernel},
url = {http://www.cs.columbia.edu/~cleslie/papers/mismatch-short.pdf}
}
@article{Leslie2004Mismatch,
author = {Leslie, C. S. and Eskin, E. and Cohen, A. and Weston, J. and Noble,
W. S.},
title = {Mismatch string kernels for discriminative protein classification},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {467-476},
number = {4},
abstract = {Motivation: {C}lassification of proteins sequences into functional
and structural families based on sequence homology is a central problem
in computational biology. {D}iscriminative supervised machine learning
approaches provide good performance, but simplicity and computational
efficiency of training and prediction are also important concerns.
{R}esults: {W}e introduce a class of string kernels, called mismatch
kernels, for use with support vector machines ({SVM}s) in a discriminative
approach to the problem of protein classification and remote homology
detection. {T}hese kernels measure sequence similarity based on shared
occurrences of fixed-length patterns in the data, allowing for mutations
between patterns. {T}hus, the kernels provide a biologically well-motivated
way to compare protein sequences without relying on family-based
generative models such as hidden {M}arkov models. {W}e compute the
kernels efficiently using a mismatch tree data structure, allowing
us to calculate the contributions of all patterns occurring in the
data in one pass while traversing the tree. {W}hen used with an {SVM},
the kernels enable fast prediction on test sequences. {W}e report
experiments on two benchmark {SCOP} datasets, where we show that
the mismatch kernel used with an {SVM} classifier performs competitively
with state-of-the-art methods for homology detection, particularly
when very few training examples are available. {E}xamination of the
highest-weighted patterns learned by the {SVM} classifier recovers
biologically important motifs in protein families and superfamilies.
{A}vailability: {SVM} software is publicly available at http://microarray.cpmc.columbia.edu/gist.
{M}ismatch kernel software is available upon request.},
pdf = {../local/Leslie2004Mismatch.pdf},
file = {Leslie2004Mismatch.pdf:local/Leslie2004Mismatch.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/4/467}
}
@article{Lett2004Interaction,
author = {Lett, D. and Hsing, M. and Pio, F.},
title = {Interaction profile-based protein classification of death domain},
journal = {B{MC} {B}ioinformatics},
year = {2004},
volume = {5},
number = {75},
abstract = {Background {T}he increasing number of protein sequences and 3{D} structure
obtained from genomic initiatives is leading many of us to focus
on proteomics, and to dedicate our experimental and computational
efforts on the creation and analysis of information derived from
3{D} structure. {I}n particular, the high-throughput generation of
protein-protein interaction data from a few organisms makes such
an approach very important towards understanding the molecular recognition
that make-up the entire protein-protein interaction network. {S}ince
the generation of sequences, and experimental protein-protein interactions
increases faster than the 3{D} structure determination of protein
complexes, there is tremendous interest in developing in silico methods
that generate such structure for prediction and classification purposes.
{I}n this study we focused on classifying protein family members
based on their protein-protein interaction distinctiveness. {S}tructure-based
classification of protein-protein interfaces has been described initially
by {P}onstingl et al. [1] and more recently by {V}aldar et al. [2]
and {M}intseris et al. [3], from complex structures that have been
solved experimentally. {H}owever, little has been done on protein
classification based on the prediction of protein-protein complexes
obtained from homology modeling and docking simulation. {R}esults
{W}e have developed an in silico classification system entitled {HODOCO}
({H}omology modeling, {D}ocking and {C}lassification {O}racle), in
which protein {R}esidue {P}otential {I}nteraction {P}rofiles ({RPIPS})
are used to summarize protein-protein interaction characteristics.
{T}his system applied to a dataset of 64 proteins of the death domain
superfamily was used to classify each member into its proper subfamily.
{T}wo classification methods were attempted, heuristic and support
vector machine learning. {B}oth methods were tested with a 5-fold
cross-validation. {T}he heuristic approach yielded a 61% average
accuracy, while the machine learning approach yielded an 89% average
accuracy. {C}onclusion {W}e have confirmed the reliability and potential
value of classifying proteins via their predicted interactions. {O}ur
results are in the same range of accuracy as other studies that classify
protein-protein interactions from 3{D} complex structure obtained
experimentally. {W}hile our classification scheme does not take directly
into account sequence information our results are in agreement with
functional and sequence based classification of death domain family
members.},
doi = {10.1186/1471-2105-5-75},
pdf = {../local/Lett2004Interaction.pdf},
file = {Lett2004Interaction.pdf:local/Lett2004Interaction.pdf:PDF},
keywords = {biosvm},
owner = {vert},
url = {http://www.biomedcentral.com/1471-2105/5/75}
}
@article{Li2005Prediction,
author = {H. Li and C. Ung and C. Yap and Y. Xue and Z. Li and Z. Cao and Y.
Chen},
title = {Prediction of genotoxicity of chemical compounds by statistical learning
methods.},
journal = {Chem. {R}es. {T}oxicol.},
year = {2005},
volume = {18},
pages = {1071-1080},
number = {6},
month = {Jun},
abstract = {Various toxicological profiles, such as genotoxic potential, need
to be studied in drug discovery processes and submitted to the drug
regulatory authorities for drug safety evaluation. {A}s part of the
effort for developing low cost and efficient adverse drug reaction
testing tools, several statistical learning methods have been used
for developing genotoxicity prediction systems with an accuracy of
up to 73.8\% for genotoxic ({GT}+) and 92.8\% for nongenotoxic ({GT}-)
agents. {T}hese systems have been developed and tested by using less
than 400 known {GT}+ and {GT}- agents, which is significantly less
in number and diversity than the 860 {GT}+ and {GT}- agents known
at present. {T}here is a need to examine if a similar level of accuracy
can be achieved for the more diverse set of molecules and to evaluate
other statistical learning methods not yet applied to genotoxicity
prediction. {T}his work is intended for testing several statistical
learning methods by using 860 {GT}+ and {GT}- agents, which include
support vector machines ({SVM}), probabilistic neural network ({PNN}),
k-nearest neighbor (k-{NN}), and {C}4.5 decision tree ({DT}). {A}
feature selection method, recursive feature elimination, is used
for selecting molecular descriptors relevant to genotoxicity study.
{T}he overall accuracies of {SVM}, k-{NN}, and {PNN} are comparable
to and those of {DT} lower than the results from earlier studies,
with {SVM} giving the highest accuracies of 77.8\% for {GT}+ and
92.7\% for {GT}- agents. {O}ur study suggests that statistical learning
methods, particularly {SVM}, k-{NN}, and {PNN}, are useful for facilitating
the prediction of genotoxic potential of a diverse set of molecules.},
doi = {10.1021/tx049652h},
pdf = {../local/Li2005Prediction.pdf},
file = {Li2005Prediction.pdf:local/Li2005Prediction.pdf:PDF},
keywords = {biosvm chemoinformatics},
url = {http://dx.doi.org/10.1021/tx049652h}
}
@article{Li2005robust,
author = {Li, L. and Jiang, W. and Li, X. and Moser, K.L. and Guo, Z. and Du,
L. and Wang, Q. and Topol, E.J. and Wang, Q. and Rao, S.},
title = {A robust hybrid between genetic algorithm and support vector machine
for extracting an optimal feature gene subset},
journal = {Genomics},
year = {2005},
volume = {85},
pages = {16-23},
number = {1},
abstract = {Development of a robust and efficient approach for extracting useful
information from microarray data continues to be a significant and
challenging task. {M}icroarray data are characterized by a high dimension,
high signal-to-noise ratio, and high correlations between genes,
but with a relatively small sample size. {C}urrent methods for dimensional
reduction can further be improved for the scenario of the presence
of a single (or a few) high influential gene(s) in which its effect
in the feature subset would prohibit inclusion of other important
genes. {W}e have formalized a robust gene selection approach based
on a hybrid between genetic algorithm and support vector machine.
{T}he major goal of this hybridization was to exploit fully their
respective merits (e.g., robustness to the size of solution space
and capability of handling a very large dimension of feature genes)
for identification of key feature genes (or molecular signatures)
for a complex biological phenotype. {W}e have applied the approach
to the microarray data of diffuse large {B} cell lymphoma to demonstrate
its behaviors and properties for mining the high-dimension data of
genome-wide gene expression profiles. {T}he resulting classifier(s)
(the optimal gene subset(s)) has achieved the highest accuracy (99%)
for prediction of independent microarray samples in comparisons with
marginal filters and a hybrid between genetic algorithm and {K} nearest
neighbors.},
doi = {10.1016/j.ygeno.2004.09.007},
pdf = {../local/Li2005robust.pdf},
file = {Li2005robust.pdf:local/Li2005robust.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/j.ygeno.2004.09.007}
}
@article{Li2004Data,
author = {Li, L. and Tang, H. and Wu, Z. and Gong, J. and Gruidl, M. and Zou,
J. and Tockman, M. and Clark, R.A.},
title = {Data mining techniques for cancer detection using serum proteomic
profiling.},
journal = {Artif. {I}ntell. {M}ed.},
year = {2004},
volume = {32},
pages = {71-83},
number = {2},
abstract = {O{BJECTIVE}: {P}athological changes in an organ or tissue may be reflected
in proteomic patterns in serum. {I}t is possible that unique serum
proteomic patterns could be used to discriminate cancer samples from
non-cancer ones. {D}ue to the complexity of proteomic profiling,
a higher order analysis such as data mining is needed to uncover
the differences in complex proteomic patterns. {T}he objectives of
this paper are (1) to briefly review the application of data mining
techniques in proteomics for cancer detection/diagnosis; (2) to explore
a novel analytic method with different feature selection methods;
(3) to compare the results obtained on different datasets and that
reported by {P}etricoin et al. in terms of detection performance
and selected proteomic patterns. {METHODS} {AND} {MATERIAL}: {T}hree
serum {SELDI} {MS} data sets were used in this research to identify
serum proteomic patterns that distinguish the serum of ovarian cancer
cases from non-cancer controls. {A} support vector machine-based
method is applied in this study, in which statistical testing and
genetic algorithm-based methods are used for feature selection respectively.
{L}eave-one-out cross validation with receiver operating characteristic
({ROC}) curve is used for evaluation and comparison of cancer detection
performance. {RESULTS} {AND} {CONCLUSIONS}: {T}he results showed
that (1) data mining techniques can be successfully applied to ovarian
cancer detection with a reasonably high performance; (2) the classification
using features selected by the genetic algorithm consistently outperformed
those selected by statistical testing in terms of accuracy and robustness;
(3) the discriminatory features (proteomic patterns) can be very
different from one selection method to another. {I}n other words,
the pattern selection and its classification efficiency are highly
classifier dependent. {T}herefore, when using data mining techniques,
the discrimination of cancer from normal does not depend solely upon
the identity and origination of cancer-related proteins.},
doi = {10.1016/j.artmed.2004.03.006},
pdf = {../local/Li2004Data.pdf},
file = {Li2004Data.pdf:local/Li2004Data.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/j.artmed.2004.03.006}
}
@article{Li2004comparative,
author = {Li, T. and Zhang, C. and Ogihara, M.},
title = {A comparative study of feature selection and multiclass classification
methods for tissue classification based on gene expression},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {2429-2437},
number = {15},
abstract = {Summary: {T}his paper studies the problem of building multiclass classifiers
for tissue classification based on gene expression. {T}he recent
development of microarray technologies has enabled biologists to
quantify gene expression of tens of thousands of genes in a single
experiment. {B}iologists have begun collecting gene expression for
a large number of samples. {O}ne of the urgent issues in the use
of microarray data is to develop methods for characterizing samples
based on their gene expression. {T}he most basic step in the research
direction is binary sample classification, which has been studied
extensively over the past few years. {T}his paper investigates the
next step--multiclass classification of samples based on gene expression.
{T}he characteristics of expression data (e.g. large number of genes
with small sample size) makes the classification problem more challenging.
{T}he process of building multiclass classifiers is divided into
two components: (i) selection of the features (i.e. genes) to be
used for training and testing and (ii) selection of the classification
method. {T}his paper compares various feature selection methods as
well as various state-of-the-art classification methods on various
multiclass gene expression datasets. {O}ur study indicates that multiclass
classification problem is much more difficult than the binary one
for the gene expression datasets. {T}he difficulty lies in the fact
that the data are of high dimensionality and that the sample size
is small. {T}he classification accuracy appears to degrade very rapidly
as the number of classes increases. {I}n particular, the accuracy
was very low regardless of the choices of the methods for large-class
datasets (e.g. {NCI}60 and {GCM}). {W}hile increasing the number
of samples is a plausible solution to the problem of accuracy degradation,
it is important to develop algorithms that are able to analyze effectively
multiple-class expression data for these special datasets.},
pdf = {../local/Li2004comparative.pdf},
file = {Li2004comparative.pdf:local/Li2004comparative.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/15/2429}
}
@article{Liao2003Combining,
author = {Liao, L. and Noble, W.S.},
title = {Combining {P}airwise {S}equence {S}imilarity and {S}upport {V}ector
{M}achines for {D}etecting {R}emote {P}rotein {E}volutionary and
{S}tructural {R}elationships},
journal = {J. {C}omput. {B}iol.},
year = {2003},
volume = {10},
pages = {857-868},
number = {6},
abstract = {One key element in understanding the molecular machinery of the cell
is to understand the structure and function of each protein encoded
in the genome. {A} very successful means of inferring the structure
or function of a previously unannotated protein is via sequence similarity
with one or more proteins whose structure or function is already
known. {T}oward this end, we propose a means of representing proteins
using pairwise sequence similarity scores. {T}his representation,
combined with a discriminative classification algorithm known as
the support vector machine ({SVM}), provides a powerful means of
detecting subtle structural and evolutionary relationships among
proteins. {T}he algorithm, called {SVM}-pairwise, when tested on
its ability to recognize previously unseen families from the {SCOP}
database, yields significantly better performance than {SVM}-{F}isher,
profile {HMM}s, and {PSI}-{BLAST}.},
pdf = {../local/Liao2003Combining.pdf},
file = {Liao2003Combining.pdf:local/Liao2003Combining.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.liebertonline.com/doi/abs/10.1089/106652703322756113}
}
@inproceedings{Liao2002Combining,
author = {Liao, L. and Noble, W. S.},
title = {Combining pairwise sequence similarity and support vector machines
for remote protein homology detection},
booktitle = {Proceedings of the {S}ixth {I}nternational {C}onference on {C}omputational
{M}olecular {B}iology},
year = {2002},
pdf = {../local/liao02.pdf},
file = {liao02.pdf:local/liao02.pdf:PDF},
keywords = {biosvm},
subject = {biokernelcasp},
url = {http://www.cs.columbia.edu/~bgrundy/papers/fps-svm.html}
}
@article{Lin2002Conserved,
author = {Lin, K. and Kuang, Y. and Joseph, J. S. and Kolatkar, P. R.},
title = {Conserved codon composition of ribosomal protein coding genes in
{E}scherichia coli, {M}ycobacterium tuberculosis and {S}accharomyces
cerevisiae: lessons from supervised machine learning in functional
genomics},
journal = {Nucl. {A}cids {R}es.},
year = {2002},
volume = {30},
pages = {2599-2607},
number = {11},
abstract = {Genomics projects have resulted in a flood of sequence data. {F}unctional
annotation currently relies almost exclusively on inter-species sequence
comparison and is restricted in cases of limited data from related
species and widely divergent sequences with no known homologs. {H}ere,
we demonstrate that codon composition, a fusion of codon usage bias
and amino acid composition signals, can accurately discriminate,
in the absence of sequence homology information, cytoplasmic ribosomal
protein genes from all other genes of known function in {S}accharomyces
cerevisiae, {E}scherichia coli and {M}ycobacterium tuberculosis using
an implementation of support vector machines, {SVM}light. {A}nalysis
of these codon composition signals is instructive in determining
features that confer individuality to ribosomal protein genes. {E}ach
of the sets of positively charged, negatively charged and small hydrophobic
residues, as well as codon bias, contribute to their distinctive
codon composition profile. {T}he representation of all these signals
is sensitively detected, combined and augmented by the {SVM}s to
perform an accurate classification. {O}f special mention is an obvious
outlier, yeast gene {RPL}22{B}, highly homologous to {RPL}22{A} but
employing very different codon usage, perhaps indicating a non-ribosomal
function. {F}inally, we propose that codon composition be used in
combination with other attributes in gene/protein classification
by supervised machine learning algorithms.},
pdf = {../local/Lin2002Conserved.pdf},
file = {Lin2002Conserved.pdf:local/Lin2002Conserved.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://nar.oupjournals.org/cgi/content/abstract/30/11/2599}
}
@article{Lind2003Support,
author = {P. Lind and T. Maltseva},
title = {Support vector machines for the estimation of aqueous solubility.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2003},
volume = {43},
pages = {1855-9},
number = {6},
abstract = {Support {V}ector {M}achines ({SVM}s) are used to estimate aqueous
solubility of organic compounds. {A} {SVM} equipped with a {T}animoto
similarity kernel estimates solubility with accuracy comparable to
results from other reported methods where the same data sets have
been studied. {C}omplete cross-validation on a diverse data set resulted
in a root-mean-squared error = 0.62 and {R}(2) = 0.88. {T}he data
input to the machine is in the form of molecular fingerprints. {N}o
physical parameters are explicitly involved in calculations.},
doi = {10.1021/ci034107s},
pdf = {../local/Lind2003Support.pdf},
file = {Lind2003Support.pdf:local/Lind2003Support.pdf:PDF},
keywords = {biosvm chemoinformatics},
url = {http://dx.doi.org/10.1021/ci034107s}
}
@article{Listgarten2004Predictive,
author = {Listgarten, J. and Damaraju, S. and Poulin, B. and Cook, L. and Dufour,
J. and Driga, A. and Mackey, J. and Wishart, D. and Greiner, R. and
Zanke, B.},
title = {Predictive {M}odels for {B}reast {C}ancer {S}usceptibility from {M}ultiple
{S}ingle {N}ucleotide {P}olymorphisms},
journal = {Clin. {C}ancer {R}es.},
year = {2004},
volume = {10},
pages = {2725-2737},
number = {8},
abstract = {Hereditary predisposition and causative environmental exposures have
long been recognized in human malignancies. {I}n most instances,
cancer cases occur sporadically, suggesting that environmental influences
are critical in determining cancer risk. {T}o test the influence
of genetic polymorphisms on breast cancer risk, we have measured
98 single nucleotide polymorphisms ({SNP}s) distributed over 45 genes
of potential relevance to breast cancer etiology in 174 patients
and have compared these with matched normal controls. {U}sing machine
learning techniques such as support vector machines ({SVM}s), decision
trees, and naive {B}ayes, we identified a subset of three {SNP}s
as key discriminators between breast cancer and controls. {T}he {SVM}s
performed maximally among predictive models, achieving 69% predictive
power in distinguishing between the two groups, compared with a 50%
baseline predictive power obtained from the data after repeated random
permutation of class labels (individuals with cancer or controls).
{H}owever, the simpler naive {B}ayes model as well as the decision
tree model performed quite similarly to the {SVM}. {T}he three {SNP}
sites most useful in this model were (a) the +4536{T}/{C} site of
the aldosterone synthase gene {CYP}11{B}2 at amino acid residue 386
{V}al/{A}la ({T}/{C}) (rs4541); (b) the +4328{C}/{G} site of the
aryl hydrocarbon hydroxylase {CYP}1{B}1 at amino acid residue 293
{L}eu/{V}al ({C}/{G}) (rs5292); and (c) the +4449{C}/{T} site of
the transcription factor {BCL}6 at amino acid 387 {A}sp/{A}sp (rs1056932).
{N}o single {SNP} site on its own could achieve more than 60% in
predictive accuracy. {W}e have shown that multiple {SNP} sites from
different genes over distant parts of the genome are better at identifying
breast cancer patients than any one {SNP} alone. {A}s high-throughput
technology for {SNP}s improves and as more {SNP}s are identified,
it is likely that much higher predictive accuracy will be achieved
and a useful clinical tool developed.},
eprint = {http://clincancerres.aacrjournals.org/cgi/reprint/10/8/2725.pdf},
pdf = {../local/Listgarten2004Predictive.pdf},
file = {Listgarten2004Predictive.pdf:local/Listgarten2004Predictive.pdf:PDF},
keywords = {biosvm, breastcancer},
owner = {jeanphilippevert},
url = {http://clincancerres.aacrjournals.org/cgi/content/abstract/10/8/2725}
}
@article{Liu2004Using,
author = {Huiqing Liu and Hao Han and Jinyan Li and Limsoon Wong},
title = {Using amino acid patterns to accurately predict translation initiation
sites.},
journal = {In {S}ilico {B}iol.},
year = {2004},
volume = {4},
pages = {255-69},
number = {3},
abstract = {The translation initiation site ({TIS}) prediction problem is about
how to correctly identify {TIS} in m{RNA}, c{DNA}, or other types
of genomic sequences. {H}igh prediction accuracy can be helpful in
a better understanding of protein coding from nucleotide sequences.
{T}his is an important step in genomic analysis to determine protein
coding from nucleotide sequences. {I}n this paper, we present an
in silico method to predict translation initiation sites in vertebrate
c{DNA} or m{RNA} sequences. {T}his method consists of three sequential
steps as follows. {I}n the first step, candidate features are generated
using k-gram amino acid patterns. {I}n the second step, a small number
of top-ranked features are selected by an entropy-based algorithm.
{I}n the third step, a classification model is built to recognize
true {TIS}s by applying support vector machines or ensembles of decision
trees to the selected features. {W}e have tested our method on several
independent data sets, including two public ones and our own extracted
sequences. {T}he experimental results achieved are better than those
reported previously using the same data sets. {O}ur high accuracy
not only demonstrates the feasibility of our method, but also indicates
that there might be "amino acid" patterns around {TIS} in c{DNA}
and m{RNA} sequences.},
keywords = {biosvm},
pii = {2004040022},
url = {http://www.bioinfo.de/isb/2004/04/0022/}
}
@article{Liu2003in-silico,
author = {Huiqing Liu and Hao Han and Jinyan Li and Limsoon Wong},
title = {An in-silico method for prediction of polyadenylation signals in
human sequences.},
journal = {Genome {I}nform {S}er {W}orkshop {G}enome {I}nform},
year = {2003},
volume = {14},
pages = {84-93},
abstract = {This paper presents a machine learning method to predict polyadenylation
signals ({PAS}es) in human {DNA} and m{RNA} sequences by analysing
features around them. {T}his method consists of three sequential
steps of feature manipulation: generation, selection and integration
of features. {I}n the first step, new features are generated using
k-gram nucleotide acid or amino acid patterns. {I}n the second step,
a number of important features are selected by an entropy-based algorithm.
{I}n the third step, support vector machines are employed to recognize
true {PAS}es from a large number of candidates. {O}ur study shows
that true {PAS}es in {DNA} and m{RNA} sequences can be characterized
by different features, and also shows that both upstream and downstream
sequence elements are important for recognizing {PAS}es from {DNA}
sequences. {W}e tested our method on several public data sets as
well as our own extracted data sets. {I}n most cases, we achieved
better validation results than those reported previously on the same
data sets. {T}he important motifs observed are highly consistent
with those reported in literature.},
keywords = {biosvm}
}
@article{Liu2005Use,
author = {Huiqing Liu and Jinyan Li and Limsoon Wong},
title = {Use of extreme patient samples for outcome prediction from gene expression
data.},
journal = {Bioinformatics},
year = {2005},
month = {Jun},
abstract = {M{OTIVATION}: {P}atient outcome prediction using microarray technologies
is an important application in bioinformatics. {B}ased on patients'
genotypic microarray data, predictions are made to estimate patients'
survival time and their risk of tumor metastasis or recurrence. {S}o,
accurate prediction can potentially help to provide better treatment
for patients. {RESULTS}: {W}e present a new computational method
for patient outcome prediction. {I}n the training phase of this method,
we make use of two types of extreme patient samples: short-term survivors
who got an unfavorable outcome within a short period and long-term
survivors who were maintaining a favorable outcome after a long follow-up
time. {T}hese extreme training samples yield a clear platform for
us to identify relevant genes whose expression is closely related
to the outcome. {T}he selected extreme samples and the relevant genes
are then integrated by a support vector machine to build a prediction
model, by which each validation sample is assigned a risk score that
falls into one of special pre-defined risk groups. {W}e apply this
method to several public data sets. {I}n most cases, patients in
high and low risk groups stratified by our method have clearly distinguishable
outcome status as seen in their {K}aplan-{M}eier curves. {W}e also
show that the idea of selecting only extreme patient samples for
training is effective for improving the prediction accuracy when
different gene selection methods are used. {SUPPLEMENTARY} {INFORMATION}:
http://research.i2r.a-star.edu.sg/huiqing/supplementaldata/survival/survival.html.},
doi = {10.1093/bioinformatics/bti544},
pdf = {../local/Liu2005Use.pdf},
file = {Liu2005Use.pdf:local/Liu2005Use.pdf:PDF},
keywords = {biosvm},
pii = {bti544},
url = {http://dx.doi.org/10.1093/bioinformatics/bti544}
}
@article{Liu2004Quantitative,
author = {H. X. Liu and C. X. Xue and R. S. Zhang and X. J. Yao and M. C. Liu
and Z. D. Hu and B. T. Fan},
title = {Quantitative prediction of logk of peptides in high-performance liquid
chromatography based on molecular descriptors by using the heuristic
method and support vector machine.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2004},
volume = {44},
pages = {1979-86},
number = {6},
abstract = {A new method support vector machine ({SVM}) and the heuristic method
({HM}) were used to develop the nonlinear and linear models between
the capacity factor (logk) and seven molecular descriptors of 75
peptides for the first time. {T}he molecular descriptors representing
the structural features of the compounds only included the constitutional
and topological descriptors, which can be obtained easily without
optimizing the structure of the molecule. {T}he seven molecular descriptors
selected by the heuristic method in {CODESSA} were used as inputs
for {SVM}. {T}he results obtained by {SVM} were compared with those
obtained by the heuristic method. {T}he prediction result of the
{SVM} model is better than that of heuristic method. {F}or the test
set, a predictive correlation coefficient {R} = 0.9801 and root-mean-square
error of 0.1523 were obtained. {T}he prediction results are in very
good agreement with the experimental values. {B}ut the linear model
of the heuristic method is easier to understand and ready to use
for a chemist. {T}his paper provided a new and effective method for
predicting the chromatography retention of peptides and some insight
into the structural features which are related to the capacity factor
of peptides.},
doi = {10.1021/ci049891a},
pdf = {../local/Liu2004Quantitative.pdf},
file = {Liu2004Quantitative.pdf:local/Liu2004Quantitative.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci049891a}
}
@article{Liu2004Prediction,
author = {H. X. Liu and R. S. Zhang and X. J. Yao and M. C. Liu and Z. D. Hu
and B. T. Fan},
title = {Prediction of the isoelectric point of an amino acid based on {GA}-{PLS}
and {SVM}s.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2004},
volume = {44},
pages = {161-7},
number = {1},
abstract = {The support vector machine ({SVM}), as a novel type of a learning
machine, for the first time, was used to develop a {QSPR} model that
relates the structures of 35 amino acids to their isoelectric point.
{M}olecular descriptors calculated from the structure alone were
used to represent molecular structures. {T}he seven descriptors selected
using {GA}-{PLS}, which is a sophisticated hybrid approach that combines
{GA} as a powerful optimization method with {PLS} as a robust statistical
method for variable selection, were used as inputs of {RBFNN}s and
{SVM} to predict the isoelectric point of an amino acid. {T}he optimal
{QSPR} model developed was based on support vector machines, which
showed the following results: the root-mean-square error of 0.2383
and the prediction correlation coefficient {R}=0.9702 were obtained
for the whole data set. {S}atisfactory results indicated that the
{GA}-{PLS} approach is a very effective method for variable selection,
and the support vector machine is a very promising tool for the nonlinear
approximation.},
doi = {10.1021/ci034173u},
pdf = {../local/Liu2004Prediction.pdf},
file = {Liu2004Prediction.pdf:local/Liu2004Prediction.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci034173u}
}
@article{Liu2004QSAR,
author = {H. X. Liu and R. S. Zhang and X. J. Yao and M. C. Liu and Z. D. Hu
and B. T. Fan},
title = {Q{SAR} and classification models of a novel series of {COX}-2 selective
inhibitors: 1,5-diarylimidazoles based on support vector machines.},
journal = {J {C}omput {A}ided {M}ol {D}es},
year = {2004},
volume = {18},
pages = {389-99},
number = {6},
month = {Jun},
abstract = {The support vector machine, which is a novel algorithm from the machine
learning community, was used to develop quantitation and classification
models which can be used as a potential screening mechanism for a
novel series of {COX}-2 selective inhibitors. {E}ach compound was
represented by calculated structural descriptors that encode constitutional,
topological, geometrical, electrostatic, and quantum-chemical features.
{T}he heuristic method was then used to search the descriptor space
and select the descriptors responsible for activity. {Q}uantitative
modelling results in a nonlinear, seven-descriptor model based on
{SVM}s with root mean-square errors of 0.107 and 0.136 for training
and prediction sets, respectively. {T}he best classification results
are found using {SVM}s: the accuracy for training and test sets is
91.2\% and 88.2\%, respectively. {T}his paper proposes a new and
effective method for drug design and screening.},
keywords = {biosvm chemoinformatics}
}
@article{Liu2003QSAR,
author = {H. X. Liu and R. S. Zhang and X. J. Yao and M. C. Liu and Z. D. Hu
and B. T. Fan},
title = {Q{SAR} study of ethyl 2-[(3-methyl-2,5-dioxo(3-pyrrolinyl))amino]-4-(trifluoromethyl)
pyrimidine-5-carboxylate: an inhibitor of {AP}-1 and {NF}-kappa {B}
mediated gene expression based on support vector machines.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2003},
volume = {43},
pages = {1288-96},
number = {4},
abstract = {The support vector machine, as a novel type of learning machine, for
the first time, was used to develop a {QSAR} model of 57 analogues
of ethyl 2-[(3-methyl-2,5-dioxo(3-pyrrolinyl))amino]-4-(trifluoromethyl)pyrimidine-5-carboxylate
({EPC}), an inhibitor of {AP}-1 and {NF}-kappa {B} mediated gene
expression, based on calculated quantum chemical parameters. {T}he
quantum chemical parameters involved in the model are {K}ier and
{H}all index (order3) ({KHI}3), {I}nformation content (order 0) ({IC}0),
{YZ} {S}hadow ({YZS}) and {M}ax partial charge for an {N} atom ({M}ax{PCN}),
{M}in partial charge for an {N} atom ({M}in{PCN}). {T}he mean relative
error of the training set, the validation set, and the testing set
is 1.35\%, 1.52\%, and 2.23\%, respectively, and the maximum relative
error is less than 5.00\%.},
doi = {10.1021/ci0340355},
pdf = {../local/Liu2003QSAR.pdf},
file = {Liu2003QSAR.pdf:local/Liu2003QSAR.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci0340355}
}
@article{Liu2005Multiclass,
author = {Jane Jijun Liu and Gene Cutler and Wuxiong Li and Zheng Pan and Sihua
Peng and Tim Hoey and Liangbiao Chen and Xuefeng Bruce Ling},
title = {Multiclass cancer classification and biomarker discovery using {GA}-based
algorithms.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {2691-7},
number = {11},
month = {Jun},
abstract = {M{OTIVATION}: {T}he development of microarray-based high-throughput
gene profiling has led to the hope that this technology could provide
an efficient and accurate means of diagnosing and classifying tumors,
as well as predicting prognoses and effective treatments. {H}owever,
the large amount of data generated by microarrays requires effective
reduction of discriminant gene features into reliable sets of tumor
biomarkers for such multiclass tumor discrimination. {T}he availability
of reliable sets of biomarkers, especially serum biomarkers, should
have a major impact on our understanding and treatment of cancer.
{RESULTS}: {W}e have combined genetic algorithm ({GA}) and all paired
({AP}) support vector machine ({SVM}) methods for multiclass cancer
categorization. {P}redictive features can be automatically determined
through iterative {GA}/{SVM}, leading to very compact sets of non-redundant
cancer-relevant genes with the best classification performance reported
to date. {I}nterestingly, these different classifier sets harbor
only modest overlapping gene features but have similar levels of
accuracy in leave-one-out cross-validations ({LOOCV}). {F}urther
characterization of these optimal tumor discriminant features, including
the use of nearest shrunken centroids ({NSC}), analysis of annotations
and literature text mining, reveals previously unappreciated tumor
subclasses and a series of genes that could be used as cancer biomarkers.
{W}ith this approach, we believe that microarray-based multiclass
molecular analysis can be an effective tool for cancer biomarker
discovery and subsequent molecular cancer diagnosis.},
doi = {10.1093/bioinformatics/bti419},
pdf = {../local/Liu2005Multiclass.pdf},
file = {Liu2005Multiclass.pdf:local/Liu2005Multiclass.pdf:PDF},
keywords = {biosvm},
pii = {bti419},
url = {http://dx.doi.org/10.1093/bioinformatics/bti419}
}
@article{Liu2004Active,
author = {Liu, Y.},
title = {Active learning with support vector machine applied to gene expression
data for cancer classification},
journal = {J. {C}hem. {I}nf. {C}omput. {S}ci.},
year = {2004},
volume = {44},
pages = {1936-1941},
number = {6},
abstract = {There is growing interest in the application of machine learning techniques
in bioinformatics. {T}he supervised machine learning approach has
been widely applied to bioinformatics and gained a lot of success
in this research area. {W}ith this learning approach researchers
first develop a large training set, which is a time-consuming and
costly process. {M}oreover, the proportion of the positive examples
and negative examples in the training set may not represent the real-world
data distribution, which causes concept drift. {A}ctive learning
avoids these problems. {U}nlike most conventional learning methods
where the training set used to derive the model remains static, the
classifier can actively choose the training data and the size of
training set increases. {W}e introduced an algorithm for performing
active learning with support vector machine and applied the algorithm
to gene expression profiles of colon cancer, lung cancer, and prostate
cancer samples. {W}e compared the classification performance of active
learning with that of passive learning. {T}he results showed that
employing the active learning method can achieve high accuracy and
significantly reduce the need for labeled training instances. {F}or
lung cancer classification, to achieve 96% of the total positives,
only 31 labeled examples were needed in active learning whereas in
passive learning 174 labeled examples were required. {T}hat meant
over 82% reduction was realized by active learning. {I}n active learning
the areas under the receiver operating characteristic ({ROC}) curves
were over 0.81, while in passive learning the areas under the {ROC}
curves were below 0.50.},
doi = {10.1021/ci049810a},
pdf = {../local/Liu2004Active.pdf},
file = {Liu2004Active.pdf:local/Liu2004Active.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1021/ci049810a}
}
@article{Liu2004comparative,
author = {Y. Liu},
title = {A comparative study on feature selection methods for drug discovery.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2004},
volume = {44},
pages = {1823-8},
number = {5},
abstract = {Feature selection is frequently used as a preprocessing step to machine
learning. {T}he removal of irrelevant and redundant information often
improves the performance of learning algorithms. {T}his paper is
a comparative study of feature selection in drug discovery. {T}he
focus is on aggressive dimensionality reduction. {F}ive methods were
evaluated, including information gain, mutual information, a chi2-test,
odds ratio, and {GSS} coefficient. {T}wo well-known classification
algorithms, {N}aïve {B}ayesian and {S}upport {V}ector {M}achine
({SVM}), were used to classify the chemical compounds. {T}he results
showed that {N}aïve {B}ayesian benefited significantly from the
feature selection, while {SVM} performed better when all features
were used. {I}n this experiment, information gain and chi2-test were
most effective feature selection methods. {U}sing information gain
with a {N}aïve {B}ayesian classifier, removal of up to 96\% of the
features yielded an improved classification accuracy measured by
sensitivity. {W}hen information gain was used to select the features,
{SVM} was much less sensitive to the reduction of feature space.
{T}he feature set size was reduced by 99\%, while losing only a few
percent in terms of sensitivity (from 58.7\% to 52.5\%) and specificity
(from 98.4\% to 97.2\%). {I}n contrast to information gain and chi2-test,
mutual information had relatively poor performance due to its bias
toward favoring rare features and its sensitivity to probability
estimation errors.},
doi = {10.1021/ci049875d},
pdf = {../local/Liu2004comparative.pdf},
file = {Liu2004comparative.pdf:local/Liu2004comparative.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci049875d}
}
@article{Liu2005Gene,
author = {Zhenqiu Liu and Dechang Chen and Halima Bensmail},
title = {Gene expression data classification with kernel principal component
analysis.},
journal = {J {B}iomed {B}iotechnol},
year = {2005},
volume = {2005},
pages = {155-9},
number = {2},
abstract = {One important feature of the gene expression data is that the number
of genes ${M}$ far exceeds the number of samples ${N}$ . {S}tandard
statistical methods do not work well when ${N} < {M}$ . {D}evelopment
of new methodologies or modification of existing methodologies is
needed for the analysis of the microarray data. {I}n this paper,
we propose a novel analysis procedure for classifying the gene expression
data. {T}his procedure involves dimension reduction using kernel
principal component analysis ({KPCA}) and classification with logistic
regression (discrimination). {KPCA} is a generalization and nonlinear
version of principal component analysis. {T}he proposed algorithm
was applied to five different gene expression datasets involving
human tumor samples. {C}omparison with other popular classification
methods such as support vector machines and neural networks shows
that our algorithm is very promising in classifying gene expression
data.},
doi = {10.1155/JBB.2005.155},
pdf = {../local/Liu2005Gene.pdf},
file = {Liu2005Gene.pdf:local/Liu2005Gene.pdf:PDF},
keywords = {biosvm},
pii = {S1110724304406032_THIS_PII_IS_INCORRECT_},
url = {http://dx.doi.org/10.1155/JBB.2005.155}
}
@article{Lo2005Effect,
author = {Siaw Ling Lo and Cong Zhong Cai and Yu Zong Chen and Maxey C M Chung},
title = {Effect of training datasets on support vector machine prediction
of protein-protein interactions.},
journal = {Proteomics},
year = {2005},
volume = {5},
pages = {876-84},
number = {4},
month = {Mar},
abstract = {Knowledge of protein-protein interaction is useful for elucidating
protein function via the concept of 'guilt-by-association'. {A} statistical
learning method, {S}upport {V}ector {M}achine ({SVM}), has recently
been explored for the prediction of protein-protein interactions
using artificial shuffled sequences as hypothetical noninteracting
proteins and it has shown promising results ({B}ock, {J}. {R}., {G}ough,
{D}. {A}., {B}ioinformatics 2001, 17, 455-460). {I}t remains unclear
however, how the prediction accuracy is affected if real protein
sequences are used to represent noninteracting proteins. {I}n this
work, this effect is assessed by comparison of the results derived
from the use of real protein sequences with that derived from the
use of shuffled sequences. {T}he real protein sequences of hypothetical
noninteracting proteins are generated from an exclusion analysis
in combination with subcellular localization information of interacting
proteins found in the {D}atabase of {I}nteracting {P}roteins. {P}rediction
accuracy using real protein sequences is 76.9\% compared to 94.1\%
using artificial shuffled sequences. {T}he discrepancy likely arises
from the expected higher level of difficulty for separating two sets
of real protein sequences than that for separating a set of real
protein sequences from a set of artificial sequences. {T}he use of
real protein sequences for training a {SVM} classification system
is expected to give better prediction results in practical cases.
{T}his is tested by using both {SVM} systems for predicting putative
protein partners of a set of thioredoxin related proteins. {T}he
prediction results are consistent with observations, suggesting that
real sequence is more practically useful in development of {SVM}
classification system for facilitating protein-protein interaction
prediction.},
doi = {10.1002/pmic.200401118},
pdf = {../local/Lo2005Effect.pdf},
file = {Lo2005Effect.pdf:local/Lo2005Effect.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1002/pmic.200401118}
}
@article{Lodhi2002Text,
author = {Lodhi, H. and Saunders, C. and Shawe-Taylor, J. and Cristianini,
N. and Watkins, C.je n'ai pas vraiment d'éléments de réponse.},
title = {Text classification using string kernels},
journal = {J. {M}ach. {L}earn. {R}es.},
year = {2002},
volume = {2},
pages = {419--444},
pdf = {../local/lodh02.pdf},
file = {lodh02.pdf:local/lodh02.pdf:PDF},
keywords = {biosvm},
subject = {kernel},
url = {http://www.ai.mit.edu/projects/jmlr/papers/volume2/lodhi02a/abstract.html}
}
@inproceedings{Lodhi2000Text,
author = {Lodhi, H. and Shawe-Taylor, J. and Cristianini, N. and Watkins, C.
J. C. H.},
title = {Text {C}lassification using {S}tring {K}ernels},
booktitle = {Adv. {N}eural {I}nform. {P}rocess. {S}yst.},
year = {2000},
pages = {563-569},
pdf = {../local/lodh00.pdf},
file = {lodh00.pdf:local/lodh00.pdf:PDF},
keywords = {biosvm},
subject = {kernel},
url = {http://www.neurocolt.com/tech_reps/2000/00079.ps.gz}
}
@techreport{Logan2001Study,
author = {Logan, B. and Moreno, P. and Suzek, B. and Weng, Z. and Kasif, S.},
title = {A {S}tudy of {R}emote {H}omology {D}etection},
institution = {Compaq Cambridge Research laboratory},
year = {2001},
number = {CRL 2001/05},
month = {June},
abstract = {Functional annotation of newly sequenced genomes is an important challenge
for computational biology systems. {W}hile much progress has been
made towards scalingup experimental methods for functional assignment
to putative genes, most current genomic annotation systems rely on
computational solutions for homology modeling via sequence or structural
similarity. {W}e present a new method for remote homology detection
that relies on combining probabilistic modeling and supervised learning
in high-dimensional features spaces. {O}ur system uses a transformation
that converts protein domains to fixed-dimension representative feature
vectors, where each feature records the sensitivity of each protein
domain to a previously learned set of ?protein motifs? or ?blocks?.
{S}ubsequently, the system utilizes {S}upport {V}ector {M}achine
({SVM}) classifiers to learn the boundaries between structural protein
classes. {O}ur experiments suggest that this technique performs well
relative to several other remote homology methods for the majority
of protein domains in {SCOP} 1.37 {PDB}90.},
pdf = {../local/Logan2001Study.pdf},
file = {Logan2001Study.pdf:local/Logan2001Study.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Lu2003Expression,
author = {Lu, Y.J. and Williamson, D. and Wang, R. and Summersgill, B. and
Rodriguez, S. and Rogers, S. and Pritchard-Jones, K. and Campbell,
C. and Shipley, J.},
title = {Expression profiling targeting chromosomes for tumor classification
and prediction of clinical behavior.},
journal = {Genes {C}hromosomes {C}ancer},
year = {2003},
volume = {38},
pages = {207-214},
number = {3},
abstract = {Tumors are associated with altered or deregulated gene products that
affect critical cellular functions. {H}ere we assess the use of a
global expression profiling technique that identifies chromosome
regions corresponding to differential gene expression, termed comparative
expressed sequence hybridization ({CESH}). {CESH} analysis was performed
on a total of 104 tumors with a diagnosis of rhabdomyosarcoma, leiomyosarcoma,
prostate cancer, and favorable-histology {W}ilms tumors. {T}hrough
the use of the chromosome regions identified as variables, support
vector machine analysis was applied to assess classification potential,
and feature selection (recursive feature elimination) was used to
identify the best discriminatory regions. {W}e demonstrate that the
{CESH} profiles have characteristic patterns in tumor groups and
were also able to distinguish subgroups of rhabdomyosarcoma. {T}he
overall {CESH} profiles in favorable-histology {W}ilms tumors were
found to correlate with subsequent clinical behavior. {C}lassification
by use of {CESH} profiles was shown to be similar in performance
to previous microarray expression studies and highlighted regions
for further investigation. {W}e conclude that analysis of chromosomal
expression profiles can group, subgroup, and even predict clinical
behavior of tumors to a level of performance similar to that of microarray
analysis. {CESH} is independent of selecting sequences for interrogation
and is a simple, rapid, and widely accessible approach to identify
clinically useful differential expression.},
doi = {10.1002/gcc.10276},
pdf = {../local/Lu2003Expression.pdf},
file = {Lu2003Expression.pdf:local/Lu2003Expression.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Luan2005Classification,
author = {Feng Luan and Ruisheng Zhang and Chunyan Zhao and Xiaojun Yao and
Mancang Liu and Zhide Hu and Botao Fan},
title = {Classification of the carcinogenicity of {N}-nitroso compounds based
on support vector machines and linear discriminant analysis.},
journal = {Chem {R}es {T}oxicol},
year = {2005},
volume = {18},
pages = {198-203},
number = {2},
month = {Feb},
abstract = {The support vector machine ({SVM}), as a novel type of learning machine,
was used to develop a classification model of carcinogenic properties
of 148 {N}-nitroso compounds. {T}he seven descriptors calculated
solely from the molecular structures of compounds selected by forward
stepwise linear discriminant analysis ({LDA}) were used as inputs
of the {SVM} model. {T}he obtained results confirmed the discriminative
capacity of the calculated descriptors. {T}he result of {SVM} (total
accuracy of 95.2\%) is better than that of {LDA} (total accuracy
of 89.8\%).},
doi = {10.1021/tx049782q},
pdf = {../local/Luan2005Classification.pdf},
file = {Luan2005Classification.pdf:local/Luan2005Classification.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/tx049782q}
}
@inproceedings{Mahe2004Extensions,
author = {Mah{\'e}, P. and Ueda, N. and Akutsu, T. and Perret, J.-L. and Vert,
J.-P.},
title = {Extensions of marginalized graph kernels},
booktitle = {Proceedings of the {T}wenty-{F}irst {I}nternational {C}onference
on {M}achine {L}earning ({ICML} 2004)},
year = {2004},
editor = {Greiner, R. and Schuurmans, D.},
pages = {552-559},
publisher = {ACM Press},
abstract = {Positive definite kernels between labeled graphs have recently been
proposed.{T}hey enable the application of kernel methods, such as
support vectormachines, to the analysis and classification of graphs,
for example, chemicalcompounds. {T}hese graph kernels are obtained
by marginalizing a kernel betweenpaths with respect to a random walk
model on the graph vertices along theedges. {W}e propose two extensions
of these graph kernels, with the double goal toreduce their computation
time and increase their relevance as measure ofsimilarity between
graphs. {F}irst, we propose to modify the label of eachvertex by
automatically adding information about its environment with the useof
the {M}organ algorithm. {S}econd, we suggest a modification of the
random walkmodel to prevent the walk from coming back to a vertex
that was just visited.{T}hese extensions are then tested on benchmark
experiments of chemicalcompounds classification, with promising results.},
pdf = {../local/icmlMod.pdf:http\://cg.ensmp.fr/~vert/publi/04icml/icmlMod.pdf:PDF;icmlMod.pdf:http\},
file = {icmlMod.pdf:http\://cg.ensmp.fr/~vert/publi/04icml/icmlMod.pdf:PDF;icmlMod.pdf:http\://cg.ensmp.fr/~vert/publi/04icml/icmlMod.pdf:PDF},
keywords = {biosvm chemoinformatics},
owner = {vert}
}
@article{Mahe2005Graph,
author = {Mah{\'e}, P. and Ueda, N. and Akutsu, T. and Perret, J.-L. and Vert,
J.-P.},
title = {Graph kernels for molecular structure-activity relationship analysis
with support vector machines},
journal = {J. Chem. Inf. Model.},
year = {2005},
volume = {45},
pages = {939-51},
number = {4},
abstract = {The support vector machine algorithm together with graph kernel functions
has recently been introduced to model structure-activity relationships
({SAR}) of molecules from their 2{D} structure, without the need
for explicit molecular descriptor computation. {W}e propose two extensions
to this approach with the double goal to reduce the computational
burden associated with the model and to enhance its predictive accuracy:
description of the molecules by a {M}organ index process and definition
of a second-order {M}arkov model for random walks on 2{D} structures.
{E}xperiments on two mutagenicity data sets validate the proposed
extensions, making this approach a possible complementary alternative
to other modeling strategies.},
doi = {10.1021/ci050039t},
pdf = {../local/Mahe2005Graph.pdf},
file = {Mahe2005Graph.pdf:local/Mahe2005Graph.pdf:PDF},
keywords = {biosvm chemoinformatics},
url = {http://dx.doi.org/10.1021/ci050039t}
}
@article{Man2004Evaluating,
author = {Man, M.Z. and Dyson, G. and Johnson, K. and Liao, B.},
title = {Evaluating methods for classifying expression data.},
journal = {J. {B}iopharm. {S}tat.},
year = {2004},
volume = {14},
pages = {1065-1084},
number = {4},
abstract = {An attractive application of expression technologies is to predict
drug efficacy or safety using expression data of biomarkers. {T}o
evaluate the performance of various classification methods for building
predictive models, we applied these methods on six expression datasets.
{T}hese datasets were from studies using microarray technologies
and had either two or more classes. {F}rom each of the original datasets,
two subsets were generated to simulate two scenarios in biomarker
applications. {F}irst, a 50-gene subset was used to simulate a candidate
gene approach when it might not be practical to measure a large number
of genes/biomarkers. {N}ext, a 2000-gene subset was used to simulate
a whole genome approach. {W}e evaluated the relative performance
of several classification methods by using leave-one-out cross-validation
and bootstrap cross-validation. {A}lthough all methods perform well
in both subsets for a relative easy dataset with two classes, differences
in performance do exist among methods for other datasets. {O}verall,
partial least squares discriminant analysis ({PLS}-{DA}) and support
vector machines ({SVM}) outperform all other methods. {W}e suggest
a practical approach to take advantage of multiple methods in biomarker
applications.},
doi = {10.1081/BIP-200035491},
pdf = {../local/Man2004Evaluating.pdf},
file = {Man2004Evaluating.pdf:local/Man2004Evaluating.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Mao2005Multiclass,
author = {Yong Mao and Xiaobo Zhou and Daoying Pi and Youxian Sun and Stephen
T C Wong},
title = {Multiclass cancer classification by using fuzzy support vector machine
and binary decision tree with gene selection.},
journal = {J {B}iomed {B}iotechnol},
year = {2005},
volume = {2005},
pages = {160-71},
number = {2},
abstract = {We investigate the problems of multiclass cancer classification with
gene selection from gene expression data. {T}wo different constructed
multiclass classifiers with gene selection are proposed, which are
fuzzy support vector machine ({FSVM}) with gene selection and binary
classification tree based on {SVM} with gene selection. {U}sing {F}
test and recursive feature elimination based on {SVM} as gene selection
methods, binary classification tree based on {SVM} with {F} test,
binary classification tree based on {SVM} with recursive feature
elimination based on {SVM}, and {FSVM} with recursive feature elimination
based on {SVM} are tested in our experiments. {T}o accelerate computation,
preselecting the strongest genes is also used. {T}he proposed techniques
are applied to analyze breast cancer data, small round blue-cell
tumors, and acute leukemia data. {C}ompared to existing multiclass
cancer classifiers and binary classification tree based on {SVM}
with {F} test or binary classification tree based on {SVM} with recursive
feature elimination based on {SVM} mentioned in this paper, {FSVM}
based on recursive feature elimination based on {SVM} can find most
important genes that affect certain types of cancer with high recognition
accuracy.},
doi = {10.1155/JBB.2005.160},
pdf = {../local/Mao2005Multiclass.pdf},
file = {Mao2005Multiclass.pdf:local/Mao2005Multiclass.pdf:PDF},
keywords = {biosvm},
pii = {S1110724304406044_THIS_PII_IS_INCORRECT_},
url = {http://dx.doi.org/10.1155/JBB.2005.160}
}
@article{Markowetz2003Support,
author = {F. Markowetz and L. Edler and M. Vingron},
title = {Support {V}ector {M}achines for {P}rotein {F}old {C}lass {P}rediction},
journal = {Biometrical {J}ournal},
year = {2003},
volume = {45},
pages = {377-389},
number = {3},
abstract = {Knowledge of the three-dimensional structure of a protein is essential
for describing and understanding its function. {T}oday, a large number
of known protein sequences faces a small number of identified structures.
{T}hus, the need arises to predict structure from sequence without
using time-consuming experimental identification. {I}n this paper
the performance of {S}upport {V}ector {M}achines ({SVM}s) is compared
to {N}eural {N}etworks and to standard statistical classification
methods as {D}iscriminant {A}nalysis and {N}earest {N}eighbor {C}lassification.
{W}e show that {SVM}s can beat the competing methods on a dataset
of 268 protein sequences to be classified into a set of 42 fold classes.
{W}e discuss misclassification with respect to biological function
and similarity. {I}n a second step we examine the performance of
{SVM}s if the embedding is varied from frequencies of single amino
acids to frequencies of tripletts of amino acids. {T}his work shows
that {SVM} provide a promising alternative to standard statistical
classification and prediction methods in functional genomics.},
doi = {10.1002/bimj.200390019},
pdf = {../local/Markowetz2003Support.pdf},
file = {Markowetz2003Support.pdf:local/Markowetz2003Support.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www3.interscience.wiley.com/cgi-bin/abstract/104525729/START}
}
@article{Martin2005Predicting,
author = {Martin, S. and Roe, D. and Faulon, J.-L.},
title = {Predicting protein-protein interactions using signature products},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {218-226},
number = {2},
month = {Jan},
abstract = {Motivation: {P}roteome-wide prediction of protein-protein interaction
is a difficult and important problem in biology. {A}lthough there
have been recent advances in both experimental and computational
methods for predicting protein-protein interactions, we are only
beginning to see a confluence of these techniques. {I}n this paper,
we describe a very general, high-throughput method for predicting
protein-protein interactions. {O}ur method combines a sequence-based
description of proteins with experimental information that can be
gathered from any type of protein-protein interaction screen. {T}he
method uses a novel description of interacting proteins by extending
the signature descriptor, which has demonstrated success in predicting
peptide/protein binding interactions for individual proteins. {T}his
descriptor is extended to protein pairs by taking signature products.
{T}he signature product is implemented within a support vector machine
classifier as a kernel function. {R}esults: {W}e have applied our
method to publicly available yeast, {H}elicobacter pylori, human
and mouse datasets. {W}e used the yeast and {H}.pylori datasets to
verify the predictive ability of our method, achieving from 70 to
80% accuracy rates using 10-fold cross-validation. {W}e used the
human and mouse datasets to demonstrate that our method is capable
of cross-species prediction. {F}inally, we reused the yeast dataset
to explore the ability of our algorithm to predict domains. {C}ontact:
smartin@sandia.gov.},
doi = {10.1093/bioinformatics/bth483},
pdf = {../local/Martin2005Predicting.pdf},
file = {Martin2005Predicting.pdf:local/Martin2005Predicting.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/21/2/218}
}
@article{Matsuda2005novel,
author = {Matsuda, A. and Vert, J.-P. and Saigo, H. and Ueda, N. and Toh, H.
and Akutsu, T.},
title = {A novel representation of protein sequences for prediction of subcellular
location using support vector machines},
journal = {Protein {S}ci.},
year = {2005},
volume = {14},
pages = {2804-2813},
number = {11},
abstract = {As the number of complete genomes rapidly increases, accurate methods
to automatically predict the subcellular location of proteins are
increasingly useful to help their functional annotation. {I}n order
to improve the predictive accuracy of the many prediction methods
developed to date, a novel representation of protein sequences is
proposed. {T}his representation involves local compositions of amino
acids and twin amino acids, and local frequencies of distance between
successive (basic, hydrophobic, and other) amino acids. {F}or calculating
the local features, each sequence is split into three parts: {N}-terminal,
middle, and {C}-terminal. {T}he {N}-terminal part is further divided
into four regions to consider ambiguity in the length and position
of signal sequences. {W}e tested this representation with support
vector machines on two data sets extracted from the {SWISS}-{PROT}
database. {T}hrough fivefold cross-validation tests, overall accuracies
of more than 87% and 91% were obtained for eukaryotic and prokaryotic
proteins, respectively. {I}t is concluded that considering the respective
features in the {N}-terminal, middle, and {C}-terminal parts is helpful
to predict the subcellular location.},
doi = {10.1110/ps.051597405},
keywords = {biosvm},
url = {http://dx.doi.org/10.1110/ps.051597405}
}
@article{Mattfeldt2003Classification,
author = {Mattfeldt, T. and Gottfried, H.W. and Wolter, H. and Schmidt, V.
and Kestler, H.A. and Mayer, J.},
title = {Classification of prostatic carcinoma with artificial neural networks
using comparative genomic hybridization and quantitative stereological
data},
journal = {Pathol. {R}es. {P}ract.},
year = {2003},
volume = {199},
pages = {773-784},
number = {12},
abstract = {Staging of prostate cancer is a mainstay of treatment decisions and
prognostication. {I}n the present study, 50 p{T}2{N}0 and 28 p{T}3{N}0
prostatic adenocarcinomas were characterized by {G}leason grading,
comparative genomic hybridization ({CGH}), and histological texture
analysis based on principles of stereology and stochastic geometry.
{T}he cases were classified by learning vector quantization and support
vector machines. {T}he quality of classification was tested by cross-validation.
{C}orrect prediction of stage from primary tumor data was possible
with an accuracy of 74-80% from different data sets. {T}he accuracy
of prediction was similar when the {G}leason score was used as input
variable, when stereological data were used, or when a combination
of {CGH} data and stereological data was used. {T}he results of classification
by learning vector quantization were slightly better than those by
support vector machines. {A} method is briefly sketched by which
training of neural networks can be adapted to unequal sample sizes
per class. {P}rogression from p{T}2 to p{T}3 prostate cancer is correlated
with complex changes of the epithelial cells in terms of volume fraction,
of surface area, and of second-order stereological properties. {G}enetically,
this progression is accompanied by a significant global increase
in losses and gains of {DNA}, and specifically by increased numerical
aberrations on chromosome arms 1q, 7p, and 8p.},
doi = {10.1078/0344-0338-00496},
keywords = {biosvm, cgh},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1078/0344-0338-00496}
}
@article{McKnight2003Categorization,
author = {Larry McKnight and Padmini Srinivasan},
title = {Categorization of sentence types in medical abstracts.},
journal = {A{MIA} {A}nnu {S}ymp {P}roc},
year = {2003},
pages = {440-4},
abstract = {This study evaluated the use of machine learning techniques in the
classification of sentence type. 7253 structured abstracts and 204
unstructured abstracts of {R}andomized {C}ontrolled {T}rials from
{M}ed{LINE} were parsed into sentences and each sentence was labeled
as one of four types ({I}ntroduction, {M}ethod, {R}esult, or {C}onclusion).
{S}upport {V}ector {M}achine ({SVM}) and {L}inear {C}lassifier models
were generated and evaluated on cross-validated data. {T}reating
sentences as a simple "bag of words", the {SVM} model had an average
{ROC} area of 0.92. {A}dding a feature of relative sentence location
improved performance markedly for some models and overall increasing
the average {ROC} to 0.95. {L}inear classifier performance was significantly
worse than the {SVM} in all datasets. {U}sing the {SVM} model trained
on structured abstracts to predict unstructured abstracts yielded
performance similar to that of models trained with unstructured abstracts
in 3 of the 4 types. {W}e conclude that classification of sentence
type seems feasible within the domain of {RCT}'s. {I}dentification
of sentence types may be helpful for providing context to end users
or other text summarization techniques.},
keywords = {biosvm},
pii = {D030003164}
}
@article{Meinicke2004Oligo,
author = {Meinicke, P. and Tech, M. and Morgenstern, B. and Merkl, R.},
title = {Oligo kernels for datamining on biological sequences: a case study
on prokaryotic translation initiation sites.},
journal = {B{MC} {B}ioinformatics},
year = {2004},
volume = {5},
number = {169},
abstract = {Background {K}ernel-based learning algorithms are among the most advanced
machine learning methods and have been successfully applied to a
variety of sequence classification tasks within the field of bioinformatics.
{C}onventional kernels utilized so far do not provide an easy interpretation
of the learnt representations in terms of positional and compositional
variability of the underlying biological signals. {R}esults {W}e
propose a kernel-based approach to datamining on biological sequences.
{W}ith our method it is possible to model and analyze positional
variability of oligomers of any length in a natural way. {O}n one
hand this is achieved by mapping the sequences to an intuitive but
high-dimensional feature space, well-suited for interpretation of
the learnt models. {O}n the other hand, by means of the kernel trick
we can provide a general learning algorithm for that high-dimensional
representation because all required statistics can be computed without
performing an explicit feature space mapping of the sequences. {B}y
introducing a kernel parameter that controls the degree of position-dependency,
our feature space representation can be tailored to the characteristics
of the biological problem at hand. {A} regularized learning scheme
enables application even to biological problems for which only small
sets of example sequences are available. {O}ur approach includes
a visualization method for transparent representation of characteristic
sequence features. {T}hereby importance of features can be measured
in terms of discriminative strength with respect to classification
of the underlying sequences. {T}o demonstrate and validate our concept
on a biochemically well-defined case, we analyze {E}. coli translation
initiation sites in order to show that we can find biologically relevant
signals. {F}or that case, our results clearly show that the {S}hine-{D}algarno
sequence is the most important signal upstream a start codon. {T}he
variability in position and composition we found for that signal
is in accordance with previous biological knowledge. {W}e also find
evidence for signals downstream of the start codon, previously introduced
as transcriptional enhancers. {T}hese signals are mainly characterized
by occurrences of adenine in a region of about 4 nucleotides next
to the start codon. {C}onclusions {W}e showed that the oligo kernel
can provide a valuable tool for the analysis of relevant signals
in biological sequences. {I}n the case of translation initiation
sites we could clearly deduce the most discriminative motifs and
their positional variation from example sequences. {A}ttractive features
of our approach are its flexibility with respect to oligomer length
and position conservation. {B}y means of these two parameters oligo
kernels can easily be adapted to different biological problems.},
doi = {10.1186/1471-2105-5-169},
pdf = {../local/Meinicke2004Oligo.pdf},
file = {Meinicke2004Oligo.pdf:local/Meinicke2004Oligo.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.biomedcentral.com/1471-2105/5/169}
}
@article{Meireles2003Differentially,
author = {Meireles, S.I. and Carvalho, A.F. and Hirata, R. and Montagnini,
A.L. and Martins, W.K. and Runza, F.B. and Stolf, B.S. and Termini,
L. and Neto, C.E. and Silva, R.L. and Soares, F.A. and Neves, E.J.
and Reis, L.F.},
title = {Differentially expressed genes in gastric tumors identified by c{DNA}
array.},
journal = {Cancer {L}ett.},
year = {2003},
volume = {190},
pages = {199-211},
number = {2},
month = {Feb},
abstract = {Using c{DNA} fragments from the {FAPESP}/l{ICR} {C}ancer {G}enome
{P}roject, we constructed a c{DNA} array having 4512 elements and
determined gene expression in six normal and six tumor gastric tissues.
{U}sing t-statistics, we identified 80 c{DNA}s whose expression in
normal and tumor samples differed more than 3.5 sample standard deviations.
{U}sing {S}elf-{O}rganizing {M}ap, the expression profile of these
c{DNA}s allowed perfect separation of malignant and non-malignant
samples. {U}sing the supervised learning procedure {S}upport {V}ector
{M}achine, we identified trios of c{DNA}s that could be used to classify
samples as normal or tumor, based on single-array analysis. {F}inally,
we identified genes with altered linear correlation when their expression
in normal and tumor samples were compared. {F}urther investigation
concerning the function of these genes could contribute to the understanding
of gastric carcinogenesis and may prove useful in molecular diagnostics.},
doi = {10.1016/S0304-3835(02)00587},
pdf = {../local/Meireles2003Differentially.pdf},
file = {Meireles2003Differentially.pdf:local/Meireles2003Differentially.pdf:PDF},
keywords = {biosvm microarray},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/S0304-3835(02)00587-6}
}
@article{Middendorf2004Discriminative,
author = {Middendorf, M. and Ziv, E. and Adams, C. and Hom, J. and Koytcheff,
R. and Levovitz, C. and Woods, G. and Chen, L. and Wiggins, C.},
title = {Discriminative topological features reveal biological network mechanisms.},
journal = {B{MC} {B}ioinformatics},
year = {2004},
volume = {5},
number = {181},
abstract = {B{ACKGROUND}: {R}ecent genomic and bioinformatic advances have motivated
the development of numerous network models intending to describe
graphs of biological, technological, and sociological origin. {I}n
most cases the success of a model has been evaluated by how well
it reproduces a few key features of the real-world data, such as
degree distributions, mean geodesic lengths, and clustering coefficients.
{O}ften pairs of models can reproduce these features with indistinguishable
fidelity despite being generated by vastly different mechanisms.
{I}n such cases, these few target features are insufficient to distinguish
which of the different models best describes real world networks
of interest; moreover, it is not clear a priori that any of the presently-existing
algorithms for network generation offers a predictive description
of the networks inspiring them. {RESULTS}: {W}e present a method
to assess systematically which of a set of proposed network generation
algorithms gives the most accurate description of a given biological
network. {T}o derive discriminative classifiers, we construct a mapping
from the set of all graphs to a high-dimensional (in principle infinite-dimensional)
"word space". {T}his map defines an input space for classification
schemes which allow us to state unambiguously which models are most
descriptive of a given network of interest. {O}ur training sets include
networks generated from 17 models either drawn from the literature
or introduced in this work. {W}e show that different duplication-mutation
schemes best describe the {E}. coli genetic network, the {S}. cerevisiae
protein interaction network, and the {C}. elegans neuronal network,
out of a set of network models including a linear preferential attachment
model and a small-world model. {CONCLUSIONS}: {O}ur method is a first
step towards systematizing network models and assessing their predictability,
and we anticipate its usefulness for a number of communities.},
doi = {10.1186/1471-2105-5-181},
pdf = {../local/Middendorf2004Discriminative.pdf},
file = {Middendorf2004Discriminative.pdf:local/Middendorf2004Discriminative.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.biomedcentral.com/1471-2105/5/181}
}
@article{Mika2004NLProt,
author = {Sven Mika and Burkhard Rost},
title = {N{LP}rot: extracting protein names and sequences from papers.},
journal = {Nucleic {A}cids {R}es},
year = {2004},
volume = {32},
pages = {W634-7},
number = {Web Server issue},
month = {Jul},
abstract = {Automatically extracting protein names from the literature and linking
these names to the associated entries in sequence databases is becoming
increasingly important for annotating biological databases. {NLP}rot
is a novel system that combines dictionary- and rule-based filtering
with several support vector machines ({SVM}s) to tag protein names
in {P}ub{M}ed abstracts. {W}hen considering partially tagged names
as errors, {NLP}rot still reached a precision of 75\% at a recall
of 76\%. {B}y many criteria our system outperformed other tagging
methods significantly; in particular, it proved very reliable even
for novel names. {N}ames encountered particularly frequently in {D}rosophila,
such as white, wing and bizarre, constitute an obvious limitation
of {NLP}rot. {O}ur method is available both as an {I}nternet server
and as a program for download (http://cubic.bioc.columbia.edu/services/{NLP}rot/).
{I}nput can be {P}ub{M}ed/{MEDLINE} identifiers, authors, titles
and journals, as well as collections of abstracts, or entire papers.},
doi = {10.1093/nar/gkh427},
keywords = {biosvm nlp},
pii = {32/suppl_2/W634},
url = {http://dx.doi.org/10.1093/nar/gkh427}
}
@article{Mika2004Protein,
author = {Mika, Sven and Rost, Burkhard},
title = {Protein names precisely peeled off free text},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {i241-i247},
number = {Suppl. 1},
abstract = {Motivation: {A}utomatically identifying protein names from the scientific
literature is a pre-requisite for the increasing demand in data-mining
this wealth of information. {E}xisting approaches are based on dictionaries,
rules and machine-learning. {H}ere, we introduced a novel system
that combines a pre-processing dictionary- and rule-based filtering
step with several separately trained support vector machines ({SVM}s)
to identify protein names in the {MEDLINE} abstracts. {R}esults:
{O}ur new tagging-system {NLP}rot is capable of extracting protein
names with a precision (accuracy) of 75% at a recall (coverage) of
76% after training on a corpus, which was used before by other groups
and contains 200 annotated abstracts. {F}or our estimate of sustained
performance, we considered partially identified names as false positives.
{O}ne important issue frequently ignored in the literature is the
redundancy in evaluation sets. {W}e suggested some guidelines for
removing overly inadequate overlaps between training and testing
sets. {A}pplying these new guidelines, our program appeared to significantly
out-perform other methods tagging protein names. {NLP}rot was so
successful due to the {SVM}-building blocks that succeeded in utilizing
the local context of protein names in the scientific literature.
{W}e challenge that our system may constitute the most general and
precise method for tagging protein names. {A}vailability: http://cubic.bioc.columbia.edu/services/nlprot/},
pdf = {../local/Mika2004Protein.pdf},
file = {Mika2004Protein.pdf:Mika2004Protein.pdf:PDF},
keywords = {biosvm nlp},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/suppl_1/i241}
}
@article{Mitsumori2005Gene,
author = {Tomohiro Mitsumori and Sevrani Fation and Masaki Murata and Kouichi
Doi and Hirohumi Doi},
title = {Gene/protein name recognition based on support vector machine using
dictionary as features.},
journal = {B{MC} {B}ioinformatics},
year = {2005},
volume = {6 Suppl 1},
pages = {S8},
abstract = {B{ACKGROUND}: {A}utomated information extraction from biomedical literature
is important because a vast amount of biomedical literature has been
published. {R}ecognition of the biomedical named entities is the
first step in information extraction. {W}e developed an automated
recognition system based on the {SVM} algorithm and evaluated it
in {T}ask 1.{A} of {B}io{C}re{A}t{I}v{E}, a competition for automated
gene/protein name recognition. {RESULTS}: {I}n the work presented
here, our recognition system uses the feature set of the word, the
part-of-speech ({POS}), the orthography, the prefix, the suffix,
and the preceding class. {W}e call these features "internal resource
features", i.e., features that can be found in the training data.
{A}dditionally, we consider the features of matching against dictionaries
to be external resource features. {W}e investigated and evaluated
the effect of these features as well as the effect of tuning the
parameters of the {SVM} algorithm. {W}e found that the dictionary
matching features contributed slightly to the improvement in the
performance of the f-score. {W}e attribute this to the possibility
that the dictionary matching features might overlap with other features
in the current multiple feature setting. {CONCLUSION}: {D}uring {SVM}
learning, each feature alone had a marginally positive effect on
system performance. {T}his supports the fact that the {SVM} algorithm
is robust on the high dimensionality of the feature vector space
and means that feature selection is not required.},
doi = {10.1186/1471-2105-6-S1-S8},
pdf = {../local/Mitsumori2005Gene.pdf},
file = {Mitsumori2005Gene.pdf:local/Mitsumori2005Gene.pdf:PDF},
keywords = {biosvm nlp},
pii = {1471-2105-6-S1-S8},
url = {http://dx.doi.org/10.1186/1471-2105-6-S1-S8}
}
@article{Model2001Feature,
author = {Model, F. and Adorjan, P. and Olek, A. and Piepenbrock, C.},
title = {Feature selection for {DNA} methylation based cancer classification},
journal = {Bioinformatics},
year = {2001},
volume = {17},
pages = {S157-S164},
number = {Supp. 1},
abstract = {Molecular portraits, such as m{RNA} expression or {DNA} methylation
patterns, have been shown to be strongly correlated with phenotypical
parameters. {T}hese molecular patterns can be revealed routinely
on a genomic scale. {H}owever, class prediction based on these patterns
is an under-determined problem, due to the extreme high dimensionality
of the data compared to the usually small number of available samples.
{T}his makes a reduction of the data dimensionality necessary. {H}ere
we demonstrate how phenotypic classes can be predicted by combining
feature selection and discriminant analysis. {B}y comparing several
feature selection methods we show that the right dimension reduction
strategy is of crucial importance for the classification performance.
{T}he techniques are demonstrated by methylation pattern based discrimination
between acute lymphoblastic leukemia and acute myeloid leukemia.
{C}ontact: {F}abian.{M}odel@epigenomics.com},
pdf = {../local/Model2001Feature.pdf},
file = {Model2001Feature.pdf:local/Model2001Feature.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/17/suppl_1/S157}
}
@article{Moler2000Analysis,
author = {Moler, E. J. and Chow, M. L. and Mian, I. S.},
title = {Analysis of molecular profile data using generative and discriminative
methods},
journal = {Physiol. {G}enomics},
year = {2000},
volume = {4},
pages = {109-126},
number = {2},
month = {Dec},
abstract = {A modular framework is proposed for modeling and understanding the
relationships between molecular profile data and other domain knowledge
using a combination of generative (here, graphical models) and discriminative
[{S}upport {V}ector {M}achines ({SVM}s)] methods. {A}s illustration,
naive {B}ayes models, simple graphical models, and {SVM}s were applied
to published transcription profile data for 1,988 genes in 62 colon
adenocarcinoma tissue specimens labeled as tumor or nontumor. {T}hese
unsupervised and supervised learning methods identified three classes
or subtypes of specimens, assigned tumor or nontumor labels to new
specimens and detected six potentially mislabeled specimens. {T}he
probability parameters of the three classes were utilized to develop
a novel gene relevance, ranking, and selection method. {SVM}s trained
to discriminate nontumor from tumor specimens using only the 50-200
top-ranked genes had the same or better generalization performance
than the full repertoire of 1,988 genes. {A}pproximately 90 marker
genes were pinpointed for use in understanding the basic biology
of colon adenocarcinoma, defining targets for therapeutic intervention
and developing diagnostic tools. {T}hese potential markers highlight
the importance of tissue biology in the etiology of cancer. {C}omparative
analysis of molecular profile data is proposed as a mechanism for
predicting the physiological function of genes in instances when
comparative sequence analysis proves uninformative, such as with
human and yeast translationally controlled tumour protein. {G}raphical
models and {SVM}s hold promise as the foundations for developing
decision support systems for diagnosis, prognosis, and monitoring
as well as inferring biological networks.},
pdf = {../local/Moler2000Analysis.pdf},
file = {Moler2000Analysis.pdf:local/Moler2000Analysis.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://physiolgenomics.physiology.org/cgi/content/abstract/4/2/109}
}
@techreport{Mukherjee1998Support,
author = {S. Mukherjee and P. Tamayo and J. P. Mesirov and D. Slonim and A.
Verri and T. Poggio},
title = {Support vector machine classification of microarray data},
institution = {C.B.L.C.},
year = {1998},
number = {182},
note = {A.I. Memo 1677},
pdf = {../local/Mukherjee1998Support.pdf},
file = {Mukherjee1998Support.pdf:local/Mukherjee1998Support.pdf:PDF},
keywords = {biosvm microarray},
subject = {biokernel},
url = {http://citeseer.nj.nec.com/437379.html}
}
@article{Myasnikova2002Support,
author = {Myasnikova, E. and Samsonova, A. and Samsonova, M. and Reinitz, J.},
title = {Support vector regression applied to the determination of the developmental
age of a {D}rosophila embryo from its segmentation gene expression
patterns},
journal = {Bioinformatics},
year = {2002},
volume = {18},
pages = {S87-S95},
number = {Suppl. 1},
abstract = {Motivation: {I}n this paper we address the problem of the determination
of developmental age of an embryo from its segmentation gene expression
patterns in {D}rosophila. {R}esults: {B}y applying support vector
regression we have developed a fast method for automated staging
of an embryo on the basis of its gene expression pattern. {S}upport
vector regression is a statistical method for creating regression
functions of arbitrary type from a set of training data. {T}he training
set is composed of embryos for which the precise developmental age
was determined by measuring the degree of membrane invagination.
{T}esting the quality of regression on the training set showed good
prediction accuracy. {T}he optimal regression function was then used
for the prediction of the gene expression based age of embryos in
which the precise age has not been measured by membrane morphology.
{M}oreover, we show that the same accuracy of prediction can be achieved
when the dimensionality of the feature vector was reduced by applying
factor analysis. {T}he data reduction allowed us to avoid over-fitting
and to increase the efficiency of the algorithm. {A}vailability:
{T}his software may be obtained from the authors. {C}ontact: samson@fn.csa.ru
{K}eywords: gene expression patterns; development; embryo staging;
support vector regression; segmentation genes; {D}rosophila.},
pdf = {../local/Myasnikova2002Support.pdf},
file = {Myasnikova2002Support.pdf:local/Myasnikova2002Support.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/18/suppl_1/S87}
}
@article{Mueller2005Classifying,
author = {K.-R. M{\"u}ller and G. R{\"a}tsch and S. Sonnenburg and S. Mika
and M. Grimm and N. Heinrich},
title = {Classifying 'drug-likeness' with {K}ernel-based learning methods.},
journal = {J {C}hem {I}nf {M}odel},
year = {2005},
volume = {45},
pages = {249-53},
number = {2},
abstract = {In this article we report about a successful application of modern
machine learning technology, namely {S}upport {V}ector {M}achines,
to the problem of assessing the 'drug-likeness' of a chemical from
a given set of descriptors of the substance. {W}e were able to drastically
improve the recent result by {B}yvatov et al. (2003) on this task
and achieved an error rate of about 7\% on unseen compounds using
{S}upport {V}ector {M}achines. {W}e see a very high potential of
such machine learning techniques for a variety of computational chemistry
problems that occur in the drug discovery and drug design process.},
doi = {10.1021/ci049737o},
pdf = {../local/Mueller2005Classifying.pdf},
file = {Mueller2005Classifying.pdf:local/Mueller2005Classifying.pdf:PDF},
keywords = {biosvm chemoinformatics},
url = {http://dx.doi.org/10.1021/ci049737o}
}
@article{Nair2005Mimicking,
author = {Rajesh Nair and Burkhard Rost},
title = {Mimicking cellular sorting improves prediction of subcellular localization.},
journal = {J {M}ol {B}iol},
year = {2005},
volume = {348},
pages = {85-100},
number = {1},
month = {Apr},
abstract = {Predicting the native subcellular compartment of a protein is an important
step toward elucidating its function. {H}ere we introduce {LOC}tree,
a hierarchical system combining support vector machines ({SVM}s)
and other prediction methods. {LOC}tree predicts the subcellular
compartment of a protein by mimicking the mechanism of cellular sorting
and exploiting a variety of sequence and predicted structural features
in its input. {C}urrently {LOC}tree does not predict localization
for membrane proteins, since the compositional properties of membrane
proteins significantly differ from those of non-membrane proteins.
{W}hile any information about function can be used by the system,
we present estimates of performance that are valid when only the
amino acid sequence of a protein is known. {W}hen evaluated on a
non-redundant test set, {LOC}tree achieved sustained levels of 74\%
accuracy for non-plant eukaryotes, 70\% for plants, and 84\% for
prokaryotes. {W}e rigorously benchmarked {LOC}tree in comparison
to the best alternative methods for localization prediction. {LOC}tree
outperformed all other methods in nearly all benchmarks. {L}ocalization
assignments using {LOC}tree agreed quite well with data from recent
large-scale experiments. {O}ur preliminary analysis of a few entirely
sequenced organisms, namely human ({H}omo sapiens), yeast ({S}accharomyces
cerevisiae), and weed ({A}rabidopsis thaliana) suggested that over
35\% of all non-membrane proteins are nuclear, about 20\% are retained
in the cytosol, and that every fifth protein in the weed resides
in the chloroplast.},
doi = {10.1016/j.jmb.2005.02.025},
pdf = {../local/Nair2005Mimicking.pdf},
file = {Nair2005Mimicking.pdf:local/Nair2005Mimicking.pdf:PDF},
keywords = {biosvm},
pii = {S0022-2836(05)00177-4},
url = {http://dx.doi.org/10.1016/j.jmb.2005.02.025}
}
@article{Natt2004Prediction,
author = {Natt, N.K. and Kaur, H. and Raghava, G.P.},
title = {Prediction of transmembrane regions of beta-barrel proteins using
{ANN}- and {SVM}-based methods.},
journal = {Proteins},
year = {2004},
volume = {56},
pages = {11-18},
number = {1},
abstract = {This article describes a method developed for predicting transmembrane
beta-barrel regions in membrane proteins using machine learning techniques:
artificial neural network ({ANN}) and support vector machine ({SVM}).
{T}he {ANN} used in this study is a feed-forward neural network with
a standard back-propagation training algorithm. {T}he accuracy of
the {ANN}-based method improved significantly, from 70.4% to 80.5%,
when evolutionary information was added to a single sequence as a
multiple sequence alignment obtained from {PSI}-{BLAST}. {W}e have
also developed an {SVM}-based method using a primary sequence as
input and achieved an accuracy of 77.4%. {T}he {SVM} model was modified
by adding 36 physicochemical parameters to the amino acid sequence
information. {F}inally, {ANN}- and {SVM}-based methods were combined
to utilize the full potential of both techniques. {T}he accuracy
and {M}atthews correlation coefficient ({MCC}) value of {SVM}, {ANN},
and combined method are 78.5%, 80.5%, and 81.8%, and 0.55, 0.63,
and 0.64, respectively. {T}hese methods were trained and tested on
a nonredundant data set of 16 proteins, and performance was evaluated
using "leave one out cross-validation" ({LOOCV}). {B}ased on this
study, we have developed a {W}eb server, {TBBP}red, for predicting
transmembrane beta-barrel regions in proteins (available at http://www.imtech.res.in/raghava/tbbpred).},
doi = {10.1002/prot.20092},
pdf = {../local/Natt2004Prediction.pdf},
file = {Natt2004Prediction.pdf:local/Natt2004Prediction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/prot.20092}
}
@article{Nguyen2005Prediction,
author = {Minh N Nguyen and Jagath C Rajapakse},
title = {Prediction of protein relative solvent accessibility with a two-stage
{SVM} approach.},
journal = {Proteins},
year = {2005},
volume = {59},
pages = {30-7},
number = {1},
month = {Apr},
abstract = {Information on relative solvent accessibility ({RSA}) of amino acid
residues in proteins provides valuable clues to the prediction of
protein structure and function. {A} two-stage approach with support
vector machines ({SVM}s) is proposed, where an {SVM} predictor is
introduced to the output of the single-stage {SVM} approach to take
into account the contextual relationships among solvent accessibilities
for the prediction. {B}y using the position-specific scoring matrices
({PSSM}s) generated by {PSI}-{BLAST}, the two-stage {SVM} approach
achieves accuracies up to 90.4\% and 90.2\% on the {M}anesh data
set of 215 protein structures and the {RS}126 data set of 126 nonhomologous
globular proteins, respectively, which are better than the highest
published scores on both data sets to date. {A} {W}eb server for
protein {RSA} prediction using a two-stage {SVM} method has been
developed and is available (http://birc.ntu.edu.sg/~pas0186457/rsa.html).},
doi = {10.1002/prot.20404},
pdf = {../local/Nguyen2005Prediction.pdf},
file = {Nguyen2005Prediction.pdf:local/Nguyen2005Prediction.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1002/prot.20404}
}
@article{Nguyen2005Two-stage,
author = {M. N. Nguyen and J. C. Rajapakse},
title = {Two-stage multi-class support vector machines to protein secondary
structure prediction.},
journal = {Pac {S}ymp {B}iocomput},
year = {2005},
pages = {346-57},
abstract = {Bioinformatics techniques to protein secondary structure ({PSS}) prediction
are mostly single-stage approaches in the sense that they predict
secondary structures of proteins by taking into account only the
contextual information in amino acid sequences. {I}n this paper,
we propose two-stage {M}ulti-class {S}upport {V}ector {M}achine ({MSVM})
approach where a {MSVM} predictor is introduced to the output of
the first stage {MSVM} to capture the sequential relationship among
secondary structure elements for the prediction. {B}y using position
specific scoring matrices, generated by {PSI}-{BLAST}, the two-stage
{MSVM} approach achieves {Q}3 accuracies of 78.0\% and 76.3\% on
the {RS}126 dataset of 126 nonhomologous globular proteins and the
{CB}396 dataset of 396 nonhomologous proteins, respectively, which
are better than the highest scores published on both datasets to
date.},
keywords = {biosvm}
}
@article{Nguyen2003Multi-class,
author = {Minh N Nguyen and Jagath C Rajapakse},
title = {Multi-class support vector machines for protein secondary structure
prediction.},
journal = {Genome {I}nform {S}er {W}orkshop {G}enome {I}nform},
year = {2003},
volume = {14},
pages = {218-27},
abstract = {The solution of binary classification problems using the {S}upport
{V}ector {M}achine ({SVM}) method has been well developed. {T}hough
multi-class classification is typically solved by combining several
binary classifiers, recently, several multi-class methods that consider
all classes at once have been proposed. {H}owever, these methods
require resolving a much larger optimization problem and are applicable
to small datasets. {T}hree methods based on binary classifications:
one-against-all ({OAA}), one-against-one ({OAO}), and directed acyclic
graph ({DAG}), and two approaches for multi-class problem by solving
one single optimization problem, are implemented to predict protein
secondary structure. {O}ur experiments indicate that multi-class
{SVM} methods are more suitable for protein secondary structure ({PSS})
prediction than the other methods, including binary {SVM}s, because
their capacity to solve an optimization problem in one step. {F}urthermore,
in this paper, we argue that it is feasible to extend the prediction
accuracy by adding a second-stage multi-class {SVM} to capture the
contextual information among secondary structural elements and thereby
further improving the accuracies. {W}e demonstrate that two-stage
{SVM}s perform better than single-stage {SVM} techniques for {PSS}
prediction using two datasets and report a maximum accuracy of 79.5\%.},
keywords = {biosvm}
}
@incollection{Noble2004Support,
author = {Noble, W. S.},
title = {Support vector machine applications in computational biology},
booktitle = {Kernel {M}ethods in {C}omputational {B}iology},
publisher = {MIT Press},
year = {2004},
editor = {Schölkopf, B. and Tsuda, K. and Vert, J.P.},
pages = {71-92},
abstract = {During the past three years, the support vector machine learning algorithm
has been extensively applied within the field of computational biology.
{T}he algorithm has been used to detect patterns within and among
biological sequences, to classify genes and patients based upon gene
expression profiles, and has recently been applied to several new
biological problems. {T}his chapter reviews the state of the art
with respect to {SVM} applications in computational biology.},
pdf = {../local/Noble2004Support.pdf},
file = {Noble2004Support.pdf:local/Noble2004Support.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@article{ODonnell2005Gene,
author = {Rebekah K O'Donnell and Michael Kupferman and S. Jack Wei and Sunil
Singhal and Randal Weber and Bert O'Malley and Yi Cheng and Mary
Putt and Michael Feldman and Barry Ziober and Ruth J Muschel},
title = {Gene expression signature predicts lymphatic metastasis in squamous
cell carcinoma of the oral cavity.},
journal = {Oncogene},
year = {2005},
volume = {24},
pages = {1244-51},
number = {7},
month = {Feb},
abstract = {Metastasis via the lymphatics is a major risk factor in squamous cell
carcinoma of the oral cavity ({OSCC}). {W}e sought to determine whether
the presence of metastasis in the regional lymph node could be predicted
by a gene expression signature of the primary tumor. {A} total of
18 {OSCC}s were characterized for gene expression by hybridizing
{RNA} to {A}ffymetrix {U}133{A} gene chips. {G}enes with differential
expression were identified using a permutation technique and verified
by quantitative {RT}-{PCR} and immunohistochemistry. {A} predictive
rule was built using a support vector machine, and the accuracy of
the rule was evaluated using crossvalidation on the original data
set and prediction of an independent set of four patients. {M}etastatic
primary tumors could be differentiated from nonmetastatic primary
tumors by a signature gene set of 116 genes. {T}his signature gene
set correctly predicted the four independent patients as well as
associating five lymph node metastases from the original patient
set with the metastatic primary tumor group. {W}e concluded that
lymph node metastasis could be predicted by gene expression profiles
of primary oral cavity squamous cell carcinomas. {T}he presence of
a gene expression signature for lymph node metastasis indicates that
clinical testing to assess risk for lymph node metastasis should
be possible.},
doi = {10.1038/sj.onc.1208285},
pdf = {../local/O'Donnell2005Gene.pdf},
file = {O'Donnell2005Gene.pdf:local/O'Donnell2005Gene.pdf:PDF},
keywords = {biosvm microarray},
pii = {1208285},
url = {http://dx.doi.org/10.1038/sj.onc.1208285}
}
@article{OFlanagan2005Non,
author = {R. A. O'Flanagan and G. Paillard and R. Lavery and A. M. Sengupta},
title = {Non-additivity in protein-{DNA} binding.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {2254-63},
number = {10},
month = {May},
abstract = {M{OTIVATION}: {L}ocalizing protein binding sites within genomic {DNA}
is of considerable importance, but remains difficult for protein
families, such as transcription factors, which have loosely defined
target sequences. {I}t is generally assumed that protein affinity
for {DNA} involves additive contributions from successive nucleotide
pairs within the target sequence. {T}his is not necessarily true,
and non-additive effects have already been experimentally demonstrated
in a small number of cases. {T}he principal origin of non-additivity
involves the so-called indirect component of protein-{DNA} recognition
which is related to the sequence dependence of {DNA} deformation
induced during complex formation. {N}on-additive effects are difficult
to study because they require the identification of many more binding
sequences than are normally necessary for describing additive specificity
(typically via the construction of weight matrices). {RESULTS}: {I}n
the present work we will use theoretically estimated binding energies
as a basis for overcoming this problem. {O}ur approach enables us
to study the full combinatorial set of sequences for a variety of
{DNA}-binding proteins, make a detailed analysis of non-additive
effects and exploit this information to improve binding site predictions
using either weight matrices or support vector machines. {T}he results
underline the fact that, even in the presence of significant deformation,
non-additive effects may involve only a limited number of dinucleotide
steps. {T}his information helps to reduce the number of binding sites
which need to be identified for successful predictions and to avoid
problems of over-fitting. {AVAILABILITY}: {T}he {SVM} software is
available upon request from the authors.},
doi = {10.1093/bioinformatics/bti361},
pdf = {../local/OFlanagan2005Non.pdf},
file = {OFlanagan2005Non.pdf:local/OFlanagan2005Non.pdf:PDF},
keywords = {biosvm},
pii = {bti361},
url = {http://dx.doi.org/10.1093/bioinformatics/bti361}
}
@article{Pahikkala2005Contextual,
author = {Tapio Pahikkala and Filip Ginter and Jorma Boberg and Jouni Jarvinen
and Tapio Salakoski},
title = {Contextual weighting for {S}upport {V}ector {M}achines in literature
mining: an application to gene versus protein name disambiguation.},
journal = {B{MC} {B}ioinformatics},
year = {2005},
volume = {6},
pages = {157},
number = {1},
month = {Jun},
abstract = {B{ACKGROUND}: {T}he ability to distinguish between genes and proteins
is essential for understanding biological text. {S}upport {V}ector
{M}achines ({SVM}s) have been proven to be very efficient in general
data mining tasks. {W}e explore their capability for the gene versus
protein name disambiguation task. {RESULTS}: {W}e incorporated into
the conventional {SVM} a weighting scheme based on distances of context
words from the word to be disambiguated. {T}his weighting scheme
increased the performance of {SVM}s by five percentage points giving
performance better than 85\% as measured by the area under {ROC}
curve and outperformed the {W}eighted {A}dditive {C}lassifier, which
also incorporates the weighting, and the {N}aive {B}ayes classifier.
{CONCLUSIONS}: {W}e show that the performance of {SVM}s can be improved
by the proposed weighting scheme. {F}urthermore, our results suggest
that in this study the increase of the classification performance
due to the weighting is greater than that obtained by selecting the
underlying classifier or the kernel part of the {SVM}.},
doi = {10.1186/1471-2105-6-157},
pdf = {../local/Pahikkala2005Contextual.pdf},
file = {Pahikkala2005Contextual.pdf:local/Pahikkala2005Contextual.pdf:PDF},
keywords = {biosvm},
pii = {1471-2105-6-157},
url = {http://dx.doi.org/10.1186/1471-2105-6-157}
}
@article{Pan2004Comprehensive,
author = {Fei Pan and Baoying Wang and Xin Hu and William Perrizo},
title = {Comprehensive vertical sample-based {KNN}/{LSVM} classification for
gene expression analysis.},
journal = {J {B}iomed {I}nform},
year = {2004},
volume = {37},
pages = {240-8},
number = {4},
month = {Aug},
abstract = {Classification analysis of microarray gene expression data has been
widely used to uncover biological features and to distinguish closely
related cell types that often appear in the diagnosis of cancer.
{H}owever, the number of dimensions of gene expression data is often
very high, e.g., in the hundreds or thousands. {A}ccurate and efficient
classification of such high-dimensional data remains a contemporary
challenge. {I}n this paper, we propose a comprehensive vertical sample-based
{KNN}/{LSVM} classification approach with weights optimized by genetic
algorithms for high-dimensional data. {E}xperiments on common gene
expression datasets demonstrated that our approach can achieve high
accuracy and efficiency at the same time. {T}he improvement of speed
is mainly related to the vertical data representation, {P}-tree,{P}atents
are pending on the {P}-tree technology. {T}his work is partially
supported by {GSA} {G}rant {ACT}#:{K}96130308. and its optimized
logical algebra. {T}he high accuracy is due to the combination of
a {KNN} majority voting approach and a local support vector machine
approach that makes optimal decisions at the local level. {A}s a
result, our approach could be a powerful tool for high-dimensional
gene expression data analysis.},
doi = {10.1016/j.jbi.2004.07.003},
pdf = {../local/Pan2004Comprehensive.pdf},
file = {Pan2004Comprehensive.pdf:local/Pan2004Comprehensive.pdf:PDF},
keywords = {biosvm},
pii = {S1532-0464(04)00070-X},
url = {http://dx.doi.org/10.1016/j.jbi.2004.07.003}
}
@article{Park2003Prediction,
author = {Park, K.-J. and Kanehisa, M.},
title = {Prediction of protein subcellular locations by support vector machines
using compositions of amino acids and amino acid pairs},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {1656-1663},
number = {13},
abstract = {Motivation: {T}he subcellular location of a protein is closely correlated
to its function. {T}hus, computational prediction of subcellular
locations from the amino acid sequence information would help annotation
and functional prediction of protein coding genes in complete genomes.
{W}e have developed a method based on support vector machines ({SVM}s).
{R}esults: {W}e considered 12 subcellular locations in eukaryotic
cells: chloroplast, cytoplasm, cytoskeleton, endoplasmic reticulum,
extracellular medium, {G}olgi apparatus, lysosome, mitochondrion,
nucleus, peroxisome, plasma membrane, and vacuole. {W}e constructed
a data set of proteins with known locations from the {SWISS}-{PROT}
database. {A} set of {SVM}s was trained to predict the subcellular
location of a given protein based on its amino acid, amino acid pair,
and gapped amino acid pair compositions. {T}he predictors based on
these different compositions were then combined using a voting scheme.
{R}esults obtained through 5-fold cross-validation tests showed an
improvement in prediction accuracy over the algorithm based on the
amino acid composition only. {T}his prediction method is available
via the {I}nternet. {A}vailability: http://www.genome.ad.jp/{SIT}/ploc.html
{S}upplementary information: http://web.kuicr.kyoto-u.ac.jp/~park/{S}eqdata/},
pdf = {../local/Park2003Prediction.pdf},
file = {Park2003Prediction.pdf:local/Park2003Prediction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/13/1656}
}
@article{Passerini2004Learning,
author = {Passerini, A. and Frasconi, P.},
title = {Learning to discriminate between ligand-bound and disulfide-bound
cysteines},
journal = {Protein {E}ng. {D}es. {S}el.},
year = {2004},
volume = {17},
pages = {367-373},
number = {4},
abstract = {We present a machine learning method to discriminate between cysteines
involved in ligand binding and cysteines forming disulfide bridges.
{O}ur method uses a window of multiple alignment profiles to represent
each instance and support vector machines with a polynomial kernel
as the learning algorithm. {W}e also report results obtained with
two new kernel functions based on similarity matrices. {E}xperimental
results indicate that binding type can be predicted at significantly
higher accuracy than using {PROSITE} patterns.},
doi = {10.1093/protein/gzh042},
pdf = {../local/Passerini2004Learning.pdf},
file = {Passerini2004Learning.pdf:local/Passerini2004Learning.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1093/protein/gzh042}
}
@inproceedings{Patterson2002Pre-mRNA,
author = {Patterson, D.J. and Yasuhara, K. and Ruzzo, W.L.},
title = {Pre-{m{RNA}} secondary structure prediction aids splice site prediction.},
booktitle = {Proceedings of the {P}acific {S}ymposium on {B}iocomputing 2002},
year = {2002},
editor = {Russ B. Altman and A. Keith Dunker and Lawrence Hunter and Kevin
Lauerdale and Teri E. Klein},
pages = {223-234},
publisher = {World Scientific},
abstract = {Accurate splice site prediction is a critical component of any computational
approach to gene prediction in higher organisms. {E}xisting approaches
generally use sequence-based models that capture local dependencies
among nucleotides in a small window around the splice site. {W}e
present evidence that computationally predicted secondary structure
of moderate length pre-m{RNA} subsequencies contains information
that can be exploited to improve acceptor splice site prediction
beyond that possible with conventional sequence-based approaches.
{B}oth decision tree and support vector machine classifiers, using
folding energy and structure metrics characterizing helix formation
near the splice site, achieve a 5-10% reduction in error rate with
a human data set. {B}ased on our data, we hypothesize that acceptors
preferentially exhibit short helices at the splice site.},
pdf = {../local/Patterson2002Pre-mRNA.pdf},
file = {Patterson2002Pre-mRNA.pdf:local/Patterson2002Pre-mRNA.pdf:PDF},
keywords = {biosvm},
subject = {biokernel},
url = {http://www.smi.stanford.edu/projects/helix/psb02/patterson.pdf}
}
@article{Pavey2004Microarray,
author = {Pavey, S. and Johansson, P. and Packer, L. and Taylor, J. and Stark,
M. and Pollock, P.M. and Walker, G.J. and Boyle, G.M. and Harper,
U. and Cozzi, S.J. and Hansen, K. and Yudt, L. and Schmidt, C. and
Hersey, P. and Ellem, K.A. and O'Rourke, M.G. and Parsons, P.G. and
Meltzer, P. and Ringner, M. and Hayward, N.K.},
title = {Microarray expression profiling in melanoma reveals a {BRAF} mutation
signature},
journal = {Oncogene},
year = {2004},
volume = {23},
pages = {4060-4067},
number = {23},
month = {May},
abstract = {We have used microarray gene expression profiling and machine learning
to predict the presence of {BRAF} mutations in a panel of 61 melanoma
cell lines. {T}he {BRAF} gene was found to be mutated in 42 samples
(69%) and intragenic mutations of the {NRAS} gene were detected in
seven samples (11%). {N}o cell line carried mutations of both genes.
{U}sing support vector machines, we have built a classifier that
differentiates between melanoma cell lines based on {BRAF} mutation
status. {A}s few as 83 genes are able to discriminate between {BRAF}
mutant and {BRAF} wild-type samples with clear separation observed
using hierarchical clustering. {M}ultidimensional scaling was used
to visualize the relationship between a {BRAF} mutation signature
and that of a generalized mitogen-activated protein kinase ({MAPK})
activation (either {BRAF} or {NRAS} mutation) in the context of the
discriminating gene list. {W}e observed that samples carrying {NRAS}
mutations lie somewhere between those with or without {BRAF} mutations.
{T}hese observations suggest that there are gene-specific mutation
signals in addition to a common {MAPK} activation that result from
the pleiotropic effects of either {BRAF} or {NRAS} on other signaling
pathways, leading to measurably different transcriptional changes.},
doi = {10.1038/sj.onc.1207563},
pdf = {../local/Pavey2004Microarray.pdf},
file = {Pavey2004Microarray.pdf:local/Pavey2004Microarray.pdf:PDF},
keywords = {biosvm microarray},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1038/sj.onc.1207563}
}
@inproceedings{Pavlidis2001Promoter,
author = {P. Pavlidis and T. S. Furey and M. Liberto and D. Haussler and W.
N. Grundy},
title = {Promoter {R}egion-{B}ased {C}lassification of {G}enes},
booktitle = {Pacific {S}ymposium on {B}iocomputing},
year = {2001},
pages = {139--150},
pdf = {../local/pavl01b.pdf},
file = {pavl01b.pdf:local/pavl01b.pdf:PDF},
keywords = {biosvm},
subject = {biokernel},
url = {http://www.smi.stanford.edu/projects/helix/psb01/pavlidis.pdf}
}
@inproceedings{Pavlidis2001Gene,
author = {Pavlidis, P. and Weston, J. and Cai, J. and Grundy, W.N.},
title = {Gene functional classification from heterogeneous data},
booktitle = {Proceedings of the {F}ifth {A}nnual {I}nternational {C}onference
on {C}omputational {B}iology},
year = {2001},
pages = {249--255},
pdf = {../local/pavl01.pdf},
file = {pavl01.pdf:local/pavl01.pdf:PDF},
keywords = {biosvm},
subject = {biokernel},
url = {http://www.cs.columbia.edu/compbio/papers/exp-phylo.pdf}
}
@article{Pavlidis2002Learning,
author = {Pavlidis, P. and Weston, J. and Cai, J. and Noble, W.S.},
title = {Learning Gene Functional Classifications from Multiple Data Types},
journal = {J. Comput. Biol.},
year = {2002},
volume = {9},
pages = {401--411},
number = {2},
abstract = {In our attempts to understand cellular function at the molecular level,
we must be able to synthesize information from disparate types of
genomic data. {W}e consider the problem of inferring gene functional
classifications from a heterogeneous data set consisting of {DNA}
microarray expression measurements and phylogenetic profiles from
whole-genome sequence comparisons. {W}e demonstrate the application
of the support vector machine ({SVM}) learning algorithm to this
functional inference task. {O}ur results suggest the importance of
exploiting prior information about the heterogeneity of the data.
{I}n particular, we propose an {SVM} kernel function that is explicitly
heterogeneous. {I}n addition, we describe feature scaling methods
for further exploiting prior knowledge of heterogeneity by giving
each data type different weights.},
doi = {10.1089/10665270252935539},
pdf = {../local/Pavlidis2002Learning.pdf},
file = {Pavlidis2002Learning.pdf:local/Pavlidis2002Learning.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@article{Peng2003Molecular,
author = {Peng, S. and Xu, Q. and Ling, X.B. and Peng, X. and Du, W. and Chen,
L.},
title = {Molecular classification of cancer types from microarray data using
the combination of genetic algorithms and support vector machines.},
journal = {F{EBS} {L}ett.},
year = {2003},
volume = {555},
pages = {358-362},
number = {2},
abstract = {Simultaneous multiclass classification of tumor types is essential
for future clinical implementations of microarray-based cancer diagnosis.
{I}n this study, we have combined genetic algorithms ({GA}s) and
all paired support vector machines ({SVM}s) for multiclass cancer
identification. {T}he predictive features have been selected through
iterative {SVM}s/{GA}s, and recursive feature elimination post-processing
steps, leading to a very compact cancer-related predictive gene set.
{L}eave-one-out cross-validations yielded accuracies of 87.93% for
the eight-class and 85.19% for the fourteen-class cancer classifications,
outperforming the results derived from previously published methods.},
doi = {10.1016/S0014-5793(03)01275-4},
pdf = {../local/Peng2003Molecular.pdf},
file = {Peng2003Molecular.pdf:local/Peng2003Molecular.pdf:PDF},
keywords = {biosvm microarray},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/S0014-5793(03)01275-4}
}
@article{Pham2005Support,
author = {Tho Hoan Pham and Kenji Satou and Tu Bao Ho},
title = {Support vector machines for prediction and analysis of beta and gamma-turns
in proteins.},
journal = {J. {B}ioinform. {C}omput. {B}iol.},
year = {2005},
volume = {3},
pages = {343-58},
number = {2},
month = {Apr},
abstract = {Tight turns have long been recognized as one of the three important
features of proteins, together with alpha-helix and beta-sheet. {T}ight
turns play an important role in globular proteins from both the structural
and functional points of view. {M}ore than 90\% tight turns are beta-turns
and most of the rest are gamma-turns. {A}nalysis and prediction of
beta-turns and gamma-turns is very useful for design of new molecules
such as drugs, pesticides, and antigens. {I}n this paper we investigated
two aspects of applying support vector machine ({SVM}), a promising
machine learning method for bioinformatics, to prediction and analysis
of beta-turns and gamma-turns. {F}irst, we developed two {SVM}-based
methods, called {BTSVM} and {GTSVM}, which predict beta-turns and
gamma-turns in a protein from its sequence. {W}hen compared with
other methods, {BTSVM} has a superior performance and {GTSVM} is
competitive. {S}econd, we used {SVM}s with a linear kernel to estimate
the support of amino acids for the formation of beta-turns and gamma-turns
depending on their position in a protein. {O}ur analysis results
are more comprehensive and easier to use than the previous results
in designing turns in proteins.},
keywords = {biosvm},
pii = {S0219720005001089}
}
@article{Pham2003Prediction,
author = {Tho Hoan Pham and Kenji Satou and Tu Bao Ho},
title = {Prediction and analysis of beta-turns in proteins by support vector
machine.},
journal = {Genome {I}nform {S}er {W}orkshop {G}enome {I}nform},
year = {2003},
volume = {14},
pages = {196-205},
abstract = {Tight turn has long been recognized as one of the three important
features of proteins after the alpha-helix and beta-sheet. {T}ight
turns play an important role in globular proteins from both the structural
and functional points of view. {M}ore than 90\% tight turns are beta-turns.
{A}nalysis and prediction of beta-turns in particular and tight turns
in general are very useful for the design of new molecules such as
drugs, pesticides, and antigens. {I}n this paper, we introduce a
support vector machine ({SVM}) approach to prediction and analysis
of beta-turns. {W}e have investigated two aspects of applying {SVM}
to the prediction and analysis of beta-turns. {F}irst, we developed
a new {SVM} method, called {BTSVM}, which predicts beta-turns of
a protein from its sequence. {T}he prediction results on the dataset
of 426 non-homologous protein chains by sevenfold cross-validation
technique showed that our method is superior to the other previous
methods. {S}econd, we analyzed how amino acid positions support (or
prevent) the formation of beta-turns based on the "multivariable"
classification model of a linear {SVM}. {T}his model is more general
than the other ones of previous statistical methods. {O}ur analysis
results are more comprehensive and easier to use than previously
published analysis results.},
keywords = {biosvm}
}
@article{Plewczyski2005support,
author = {Dariusz Plewczynski and Adrian Tkacz and Adam Godzik and Leszek Rychlewski},
title = {A support vector machine approach to the identification of phosphorylation
sites.},
journal = {Cell {M}ol {B}iol {L}ett},
year = {2005},
volume = {10},
pages = {73-89},
number = {1},
abstract = {We describe a bioinformatics tool that can be used to predict the
position of phosphorylation sites in proteins based only on sequence
information. {T}he method uses the support vector machine ({SVM})
statistical learning theory. {T}he statistical models for phosphorylation
by various types of kinases are built using a dataset of short (9-amino
acid long) sequence fragments. {T}he sequence segments are dissected
around post-translationally modified sites of proteins that are on
the current release of the {S}wiss-{P}rot database, and that were
experimentally confirmed to be phosphorylated by any kinase. {W}e
represent them as vectors in a multidimensional abstract space of
short sequence fragments. {T}he prediction method is as follows.
{F}irst, a given query protein sequence is dissected into overlapping
short segments. {A}ll the fragments are then projected into the multidimensional
space of sequence fragments via a collection of different representations.
{T}hose points are classified with pre-built statistical models (the
{SVM} method with linear, polynomial and radial kernel functions)
either as phosphorylated or inactive ones. {T}he resulting list of
plausible sites for phosphorylation by various types of kinases in
the query protein is returned to the user. {T}he efficiency of the
method for each type of phosphorylation is estimated using leave-one-out
tests and presented here. {T}he sensitivities of the models can reach
over 70\%, depending on the type of kinase. {T}he additional information
from profile representations of short sequence fragments helps in
gaining a higher degree of accuracy in some phosphorylation types.
{T}he further development of an automatic phosphorylation site annotation
predictor based on our algorithm should yield a significant improvement
when using statistical algorithms in order to quantify the results.},
pdf = {../local/Plewczyski2005support.pdf},
file = {Plewczyski2005support.pdf:local/Plewczyski2005support.pdf:PDF},
keywords = {biosvm}
}
@article{Plewczynski2005AutoMotif,
author = {Dariusz Plewczynski and Adrian Tkacz and Lucjan Stanislaw Wyrwicz
and Leszek Rychlewski},
title = {Auto{M}otif server: prediction of single residue post-translational
modifications in proteins.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {2525-7},
number = {10},
month = {May},
abstract = {The {A}uto{M}otif {S}erver allows for identification of post-translational
modification ({PTM}) sites in proteins based only on local sequence
information. {T}he local sequence preferences of short segments around
{PTM} residues are described here as linear functional motifs ({LFM}s).
{S}equence models for all types of {PTM}s are trained by support
vector machine on short-sequence fragments of proteins in the current
release of {S}wiss-{P}rot database (phosphorylation by various protein
kinases, sulfation, acetylation, methylation, amidation, etc.). {T}he
accuracy of the identification is estimated using the standard leave-one-out
procedure. {T}he sensitivities for all types of short {LFM}s are
in the range of 70\%. {AVAILABILITY}: {T}he {A}uto{M}otif {S}erver
is available free for academic use at http://automotif.bioinfo.pl/},
doi = {10.1093/bioinformatics/bti333},
pdf = {../local/Plewczynski2005AutoMotif.pdf},
file = {Plewczynski2005AutoMotif.pdf:local/Plewczynski2005AutoMotif.pdf:PDF},
keywords = {biosvm},
pii = {bti333},
url = {http://dx.doi.org/10.1093/bioinformatics/bti333}
}
@article{Pochet2004Systematic,
author = {Pochet, N. and De Smet, F. and Suykens, J. A. K. and De Moor, B.
L. R.},
title = {Systematic benchmarking of microarray data classification: assessing
the role of non-linearity and dimensionality reduction},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {3185-3195},
number = {17},
month = {Nov},
abstract = {Motivation: {M}icroarrays are capable of determining the expression
levels of thousands of genes simultaneously. {I}n combination with
classification methods, this technology can be useful to support
clinical management decisions for individual patients, e.g. in oncology.
{T}he aim of this paper is to systematically benchmark the role of
non-linear versus linear techniques and dimensionality reduction
methods. {R}esults: {A} systematic benchmarking study is performed
by comparing linear versions of standard classification and dimensionality
reduction techniques with their non-linear versions based on non-linear
kernel functions with a radial basis function ({RBF}) kernel. {A}
total of 9 binary cancer classification problems, derived from 7
publicly available microarray datasets, and 20 randomizations of
each problem are examined. {C}onclusions: {T}hree main conclusions
can be formulated based on the performances on independent test sets.
(1) {W}hen performing classification with least squares support vector
machines ({LS}-{SVM}s) (without dimensionality reduction), {RBF}
kernels can be used without risking too much overfitting. {T}he results
obtained with well-tuned {RBF} kernels are never worse and sometimes
even statistically significantly better compared to results obtained
with a linear kernel in terms of test set receiver operating characteristic
and test set accuracy performances. (2) {E}ven for classification
with linear classifiers like {LS}-{SVM} with linear kernel, using
regularization is very important. (3) {W}hen performing kernel principal
component analysis (kernel {PCA}) before classification, using an
{RBF} kernel for kernel {PCA} tends to result in overfitting, especially
when using supervised feature selection. {I}t has been observed that
an optimal selection of a large number of features is often an indication
for overfitting. {K}ernel {PCA} with linear kernel gives better results.
{A}vailability: {M}atlab scripts are available on request. {S}upplementary
information: http://www.esat.kuleuven.ac.be/~npochet/{B}ioinformatics/},
doi = {10.1093/bioinformatics/bth383},
pdf = {../local/Pochet2004Systematic.pdf},
file = {Pochet2004Systematic.pdf:local/Pochet2004Systematic.pdf:PDF},
keywords = {biosvm microarray},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1093/bioinformatics/bth383}
}
@article{Prados2004Mining,
author = {Prados, J. and Kalousis, A. and Sanchez, J.C. and Allard, L. and
Carrette, O. and Hilario, M.},
title = {Mining mass spectra for diagnosis and biomarker discovery of cerebral
accidents.},
journal = {Proteomics},
year = {2004},
volume = {4},
pages = {2320-2332},
number = {8},
abstract = {In this paper we try to identify potential biomarkers for early stroke
diagnosis using surface-enhanced laser desorption/ionization mass
spectrometry coupled with analysis tools from machine learning and
data mining. {D}ata consist of 42 specimen samples, i.e., mass spectra
divided in two big categories, stroke and control specimens. {A}mong
the stroke specimens two further categories exist that correspond
to ischemic and hemorrhagic stroke; in this paper we limit our data
analysis to discriminating between control and stroke specimens.
{W}e performed two suites of experiments. {I}n the first one we simply
applied a number of different machine learning algorithms; in the
second one we have chosen the best performing algorithm as it was
determined from the first phase and coupled it with a number of different
feature selection methods. {T}he reason for this was 2-fold, first
to establish whether feature selection can indeed improve performance,
which in our case it did not seem to confirm, but more importantly
to acquire a small list of potentially interesting biomarkers. {O}f
the different methods explored the most promising one was support
vector machines which gave us high levels of sensitivity and specificity.
{F}inally, by analyzing the models constructed by support vector
machines we produced a small set of 13 features that could be used
as potential biomarkers, and which exhibited good performance both
in terms of sensitivity, specificity and model stability.},
doi = {10.1002/pmic.200400857},
pdf = {../local/Prados2004Mining.pdf},
file = {Prados2004Mining.pdf:local/Prados2004Mining.pdf:PDF},
keywords = {biosvm proteomics},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/pmic.200400857}
}
@article{Qian2003Prediction,
author = {Qian, J. and Lin, J. and Luscombe, N. M. and Yu, H. and Gerstein,
M.},
title = {Prediction of regulatory networks: genome-wide identification of
transcription factor targets from gene expression data},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {1917-1926},
number = {15},
abstract = {Motivation: {D}efining regulatory networks, linking transcription
factors ({TF}s) to their targets, is a central problem in post-genomic
biology. {O}ne might imagine one could readily determine these networks
through inspection of gene expression data. {H}owever, the relationship
between the expression timecourse of a transcription factor and its
target is not obvious (e.g. simple correlation over the timecourse),
and current analysis methods, such as hierarchical clustering, have
not been very successful in deciphering them. {R}esults: {H}ere we
introduce an approach based on support vector machines ({SVM}s) to
predict the targets of a transcription factor by identifying subtle
relationships between their expression profiles. {I}n particular,
we used {SVM}s to predict the regulatory targets for 36 transcription
factors in the {S}accharomyces cerevisiae genome based on the microarray
expression data from many different physiological conditions. {W}e
trained and tested our {SVM} on a data set constructed to include
a significant number of both positive and negative examples, directly
addressing data imbalance issues. {T}his was non-trivial given that
most of the known experimental information is only for positives.
{O}verall, we found that 63% of our {TF}-target relationships were
confirmed through cross-validation. {W}e further assessed the performance
of our regulatory network identifications by comparing them with
the results from two recent genome-wide {C}h{IP}-chip experiments.
{O}verall, we find the agreement between our results and these experiments
is comparable to the agreement (albeit low) between the two experiments.
{W}e find that this network has a delocalized structure with respect
to chromosomal positioning, with a given transcription factor having
targets spread fairly uniformly across the genome. {A}vailability:
{T}he overall network of the relationships is available on the web
at http://bioinfo.mbb.yale.edu/expression/echipchip},
pdf = {../local/Qian2003Prediction.pdf},
file = {Qian2003Prediction.pdf:local/Qian2003Prediction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/15/1917}
}
@article{Qin2003Kernel,
author = {Qin, J. and Lewis, D. P. and Noble, W. S.},
title = {Kernel hierarchical gene clustering from microarray expression data},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {2097-2104},
number = {16},
abstract = {Motivation: {U}nsupervised analysis of microarray gene expression
data attempts to find biologically significant patterns within a
given collection of expression measurements. {F}or example, hierarchical
clustering can be applied to expression profiles of genes across
multiple experiments, identifying groups of genes that share similiar
expression profiles. {P}revious work using the support vector machine
supervised learning algorithm with microarray data suggests that
higher-order features, such as pairwise and tertiary correlations
across multiple experiments, may provide significant benefit in learning
to recognize classes of co-expressed genes. {R}esults: {W}e describe
a generalization of the hierarchical clustering algorithm that efficiently
incorporates these higher-order features by using a kernel function
to map the data into a high-dimensional feature space. {W}e then
evaluate the utility of the kernel hierarchical clustering algorithm
using both internal and external validation. {T}he experiments demonstrate
that the kernel representation itself is insufficient to provide
improved clustering performance. {W}e conclude that mapping gene
expression data into a high-dimensional feature space is only a good
idea when combined with a learning algorithm, such as the support
vector machine that does not suffer from the curse of dimensionality.
{A}vailability: {S}upplementary data at www.cs.columbia.edu/compbio/hiclust.
{S}oftware source code available by request.},
pdf = {../local/Qin2003Kernel.pdf},
file = {Qin2003Kernel.pdf:local/Qin2003Kernel.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/16/2097}
}
@article{Raghava2005Correlation,
author = {Gajendra P S Raghava and Joon H Han},
title = {Correlation and prediction of gene expression level from amino acid
and dipeptide composition of its protein.},
journal = {B{MC} {B}ioinformatics},
year = {2005},
volume = {6},
pages = {59},
number = {1},
month = {Mar},
abstract = {B{ACKGROUND}: {A} large number of papers have been published on analysis
of microarray data with particular emphasis on normalization of data,
detection of differentially expressed genes, clustering of genes
and regulatory network. {O}n other hand there are only few studies
on relation between expression level and composition of nucleotide/protein
sequence, using expression data. {T}here is a need to understand
why particular genes/proteins express more in particular conditions.
{I}n this study, we analyze 3468 genes of {S}accharomyces cerevisiae
obtained from {H}olstege et al., (1998) to understand the relationship
between expression level and amino acid composition. {RESULTS}: {W}e
compute the correlation between expression of a gene and amino acid
composition of its protein. {I}t was observed that some residues
(like {A}la, {G}ly, {A}rg and {V}al) have significant positive correlation
(r > 0.20) and some other residues ({L}ike {A}sp, {L}eu, {A}sn and
{S}er) have negative correlation (r < -0.15) with the expression
of genes. {A} significant negative correlation (r = -0.18) was also
found between length and gene expression. {T}hese observations indicate
the relationship between percent composition and gene expression
level. {T}hus, attempts have been made to develop a {S}upport {V}ector
{M}achine ({SVM}) based method for predicting the expression level
of genes from its protein sequence. {I}n this method the {SVM} is
trained with proteins whose gene expression data is known in a given
condition. {T}hen trained {SVM} is used to predict the gene expression
of other proteins of the same organism in the same condition. {A}
correlation coefficient r = 0.70 was obtained between predicted and
experimentally determined expression of genes, which improves from
r = 0.70 to 0.72 when dipeptide composition was used instead of residue
composition. {T}he method was evaluated using 5-fold cross validation
test. {W}e also demonstrate that amino acid composition information
along with gene expression data can be used for improving the function
classification of proteins. {CONCLUSION}: {T}here is a correlation
between gene expression and amino acid composition that can be used
to predict the expression level of genes up to a certain extent.
{A} web server based on the above strategy has been developed for
calculating the correlation between amino acid composition and gene
expression and prediction of expression level http://kiwi.postech.ac.kr/raghava/lgepred/.
{T}his server will allow users to study the evolution from expression
data.},
doi = {10.1186/1471-2105-6-59},
keywords = {biosvm},
pii = {1471-2105-6-59},
url = {http://dx.doi.org/10.1186/1471-2105-6-59}
}
@article{Ramaswamy2001Multiclass,
author = {Ramaswamy, S. and Tamayo, P. and Rifkin, R. and Mukherjee, S. and
Yeang, C.H. and Angelo, M. and Ladd, C. and Reich, M. and Latulippe,
E. and Mesirov, J.P. and Poggio, T. and Gerald, W. and Loda, M. and
Lander, E.S. and Golub, T.R.},
title = {Multiclass cancer diagnosis using tumor gene expression signatures},
journal = {Proc. {N}atl. {A}cad. {S}ci. {USA}},
year = {2001},
volume = {98},
pages = {15149-15154},
number = {26},
month = {Dec},
abstract = {The optimal treatment of patients with cancer depends on establishing
accurate diagnoses by using a complex combination of clinical and
histopathological data. {I}n some instances, this task is difficult
or impossible because of atypical clinical presentation or histopathology.
{T}o determine whether the diagnosis of multiple common adult malignancies
could be achieved purely by molecular classification, we subjected
218 tumor samples, spanning 14 common tumor types, and 90 normal
tissue samples to oligonucleotide microarray gene expression analysis.
{T}he expression levels of 16,063 genes and expressed sequence tags
were used to evaluate the accuracy of a multiclass classifier based
on a support vector machine algorithm. {O}verall classification accuracy
was 78%, far exceeding the accuracy of random classification (9%).
{P}oorly differentiated cancers resulted in low-confidence predictions
and could not be accurately classified according to their tissue
of origin, indicating that they are molecularly distinct entities
with dramatically different gene expression patterns compared with
their well differentiated counterparts. {T}aken together, these results
demonstrate the feasibility of accurate, multiclass molecular cancer
classification and suggest a strategy for future clinical implementation
of molecular cancer diagnostics.},
doi = {10.1073/pnas.211566398},
pdf = {../local/Ramaswamy2001Multiclass.pdf},
file = {Ramaswamy2001Multiclass.pdf:local/Ramaswamy2001Multiclass.pdf:PDF},
keywords = {biosvm microarray},
owner = {vert},
url = {http://dx.doi.org/10.1073/pnas.211566398}
}
@article{Rangwala2005Profile-based,
author = {Rangwala, H. and Karypis, G.},
title = {Profile-based direct kernels for remote homology detection and fold
recognition.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {4239--4247},
number = {23},
month = {Dec},
abstract = {MOTIVATION: Protein remote homology detection is a central problem
in computational biology. Supervised learning algorithms based on
support vector machines are currently one of the most effective methods
for remote homology detection. The performance of these methods depends
on how the protein sequences are modeled and on the method used to
compute the kernel function between them. RESULTS: We introduce two
classes of kernel functions that are constructed by combining sequence
profiles with new and existing approaches for determining the similarity
between pairs of protein sequences. These kernels are constructed
directly from these explicit protein similarity measures and employ
effective profile-to-profile scoring schemes for measuring the similarity
between pairs of proteins. Experiments with remote homology detection
and fold recognition problems show that these kernels are capable
of producing results that are substantially better than those produced
by all of the existing state-of-the-art SVM-based methods. In addition,
the experiments show that these kernels, even when used in the absence
of profiles, produce results that are better than those produced
by existing non-profile-based schemes. AVAILABILITY: The programs
for computing the various kernel functions are available on request
from the authors.},
doi = {10.1093/bioinformatics/bti687},
keywords = {biosvm},
owner = {vert},
pii = {bti687},
pmid = {16188929},
timestamp = {2007.08.01},
url = {http://dx.doi.org/10.1093/bioinformatics/bti687}
}
@article{Rensing2005Protein,
author = {Stefan A Rensing and Dana Fritzowsky and Daniel Lang and Ralf Reski},
title = {Protein encoding genes in an ancient plant: analysis of codon usage,
retained genes and splice sites in a moss, {P}hyscomitrella patens.},
journal = {B{MC} {G}enomics},
year = {2005},
volume = {6},
pages = {43},
number = {1},
month = {Mar},
abstract = {B{ACKGROUND}: {T}he moss {P}hyscomitrella patens is an emerging plant
model system due to its high rate of homologous recombination, haploidy,
simple body plan, physiological properties as well as phylogenetic
position. {A}vailable {EST} data was clustered and assembled, and
provided the basis for a genome-wide analysis of protein encoding
genes. {RESULTS}: {W}e have clustered and assembled {P}hyscomitrella
patens {EST} and {CDS} data in order to represent the transcriptome
of this non-seed plant. {C}lustering of the publicly available data
and subsequent prediction resulted in a total of 19,081 non-redundant
{ORF}. {O}f these putative transcripts, approximately 30\% have a
homolog in both rice and {A}rabidopsis transcriptome. {M}ore than
130 transcripts are not present in seed plants but can be found in
other kingdoms. {T}hese potential "retained genes" might have been
lost during seed plant evolution. {F}unctional annotation of these
genes reveals unequal distribution among taxonomic groups and intriguing
putative functions such as cytotoxicity and nucleic acid repair.
{W}hereas introns in the moss are larger on average than in the seed
plant {A}rabidopsis thaliana, position and amount of introns are
approximately the same. {C}ontrary to {A}rabidopsis, where {CDS}
contain on average 44\% {G}/{C}, in {P}hyscomitrella the average
{G}/{C} content is 50\%. {I}nterestingly, moss orthologs of {A}rabidopsis
genes show a significant drift of codon fraction usage, towards the
seed plant. {W}hile averaged codon bias is the same in {P}hyscomitrella
and {A}rabidopsis, the distribution pattern is different, with 15\%
of moss genes being unbiased. {S}pecies-specific, sensitive and selective
splice site prediction for {P}hyscomitrella has been developed using
a dataset of 368 donor and acceptor sites, utilizing a support vector
machine. {T}he prediction accuracy is better than those achieved
with tools trained on {A}rabidopsis data. {CONCLUSION}: {A}nalysis
of the moss transcriptome displays differences in gene structure,
codon and splice site usage in comparison with the seed plant {A}rabidopsis.
{P}utative retained genes exhibit possible functions that might explain
the peculiar physiological properties of mosses. {B}oth the transcriptome
representation (including a {BLAST} and retrieval service) and splice
site prediction have been made available on http://www.cosmoss.org,
setting the basis for assembly and annotation of the {P}hyscomitrella
genome, of which draft shotgun sequences will become available in
2005.},
doi = {10.1186/1471-2164-6-43},
pdf = {../local/Rensing2005Protein.pdf},
file = {Rensing2005Protein.pdf:local/Rensing2005Protein.pdf:PDF},
keywords = {biosvm},
pii = {1471-2164-6-43},
url = {http://dx.doi.org/10.1186/1471-2164-6-43}
}
@article{Res2005evolution,
author = {I. Res and I. Mihalek and O. Lichtarge},
title = {An evolution based classifier for prediction of protein interfaces
without using protein structures.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {2496-501},
number = {10},
month = {May},
abstract = {M{OTIVATION}: {T}he number of available protein structures still lags
far behind the number of known protein sequences. {T}his makes it
important to predict which residues participate in protein-protein
interactions using only sequence information. {F}ew studies have
tackled this problem until now. {RESULTS}: {W}e applied support vector
machines to sequences in order to generate a classification of all
protein residues into those that are part of a protein interface
and those that are not. {F}or the first time evolutionary information
was used as one of the attributes and this inclusion of evolutionary
importance rankings improves the classification. {L}eave-one-out
cross-validation experiments show that prediction accuracy reaches
64\%.},
doi = {10.1093/bioinformatics/bti340},
pdf = {../local/Res2005evolution.pdf},
file = {Res2005evolution.pdf:local/Res2005evolution.pdf:PDF},
keywords = {biosvm},
pii = {bti340},
url = {http://dx.doi.org/10.1093/bioinformatics/bti340}
}
@article{Rice2005Mining,
author = {Simon B Rice and Goran Nenadic and Benjamin J Stapley},
title = {Mining protein function from text using term-based support vector
machines.},
journal = {B{MC} {B}ioinformatics},
year = {2005},
volume = {6 Suppl 1},
pages = {S22},
abstract = {B{ACKGROUND}: {T}ext mining has spurred huge interest in the domain
of biology. {T}he goal of the {B}io{C}re{A}t{I}v{E} exercise was
to evaluate the performance of current text mining systems. {W}e
participated in {T}ask 2, which addressed assigning {G}ene {O}ntology
terms to human proteins and selecting relevant evidence from full-text
documents. {W}e approached it as a modified form of the document
classification task. {W}e used a supervised machine-learning approach
(based on support vector machines) to assign protein function and
select passages that support the assignments. {A}s classification
features, we used a protein's co-occurring terms that were automatically
extracted from documents. {RESULTS}: {T}he results evaluated by curators
were modest, and quite variable for different problems: in many cases
we have relatively good assignment of {GO} terms to proteins, but
the selected supporting text was typically non-relevant (precision
spanning from 3\% to 50\%). {T}he method appears to work best when
a substantial set of relevant documents is obtained, while it works
poorly on single documents and/or short passages. {T}he initial results
suggest that our approach can also mine annotations from text even
when an explicit statement relating a protein to a {GO} term is absent.
{CONCLUSION}: {A} machine learning approach to mining protein function
predictions from text can yield good performance only if sufficient
training data is available, and significant amount of supporting
data is used for prediction. {T}he most promising results are for
combined document retrieval and {GO} term assignment, which calls
for the integration of methods developed in {B}io{C}re{A}t{I}v{E}
{T}ask 1 and {T}ask 2.},
doi = {10.1186/1471-2105-6-S1-S22},
pdf = {../local/Rice2005Mining.pdf},
file = {Rice2005Mining.pdf:local/Rice2005Mining.pdf:PDF},
keywords = {biosvm},
pii = {1471-2105-6-S1-S22},
url = {http://dx.doi.org/10.1186/1471-2105-6-S1-S22}
}
@article{Riedesel2004Peptide,
author = {Henning Riedesel and Björn Kolbeck and Oliver Schmetzer and Ernst-Walter
Knapp},
title = {Peptide binding at class {I} major histocompatibility complex scored
with linear functions and support vector machines.},
journal = {Genome {I}nform {S}er {W}orkshop {G}enome {I}nform},
year = {2004},
volume = {15},
pages = {198-212},
number = {1},
abstract = {We explore two different methods to predict the binding ability of
nonapeptides at the class {I} major histocompatibility complex using
a general linear scoring function that defines a separating hyperplane
in the feature space of sequences. {I}n absence of suitable data
on non-binding nonapeptides we generated sequences randomly from
a selected set of proteins from the protein data bank. {T}he parameters
of the scoring function were determined by a generalized least square
optimization ({LSM}) and alternatively by the support vector machine
({SVM}). {W}ith the generalized {LSM} impaired data for learning
with a small set of binding peptides and a large set of non-binding
peptides can be treated in a balanced way rendering {LSM} more successful
than {SVM}, while for symmetric data sets {SVM} has a slight advantage
compared to {LSM}.},
pdf = {../local/Riedesel2004Peptide.pdf},
file = {Riedesel2004Peptide.pdf:local/Riedesel2004Peptide.pdf:PDF},
keywords = {biosvm},
url = {http://www.jsbi.org/journal/IBSB04/IBSB04F004.html}
}
@article{Rose2005Correlation,
author = {Rose, J. R. and Turkett, W. H., Jr. and Oroian, I. C. and Laegreid,
W. W. and Keele, J.},
title = {Correlation of amino acid preference and mammalian viral genome type},
journal = {Bioinformatics},
year = {2005},
abstract = {Motivation: {I}n the event of an outbreak of a disease caused by an
initially unknown pathogen, the ability to characterize anonymous
sequences prior to isolation and culturing of the pathogen will be
helpful. {W}e show that it is possible to classify viral sequences
by genome type (ds{DNA}, ss{DNA}, ss{RNA} positive strand, ss{RNA}
negative strand, retroid) using amino acid distribution.{R}esults:
{I}n this paper we describe the results of analysis of amino acid
preference in mammalian viruses. {T}he study was carried out at the
genome level as well as two shorter sequence levels: short (300 amino
acids) and medium length (660 amino acids). {T}he analysis indicates
a correlation between the viral genome types ds{DNA}, ss{DNA}, ss{RNA}
positive strand, ss{RNA} negative strand, and retroid and amino acid
preference. {W}e investigated three different models of amino acid
preference. {T}he simplest amino acid preference model, 1-{AAP},
is a normalized description of the frequency of amino acids in genomes
of a viral genome type. {A} slightly more complex model is the ordered
pair amino acid preference model (2-{AAP}), which characterizes genomes
of different viral genome types by the frequency of ordered pairs
of amino acids. {T}he most complex and accurate model is the ordered
triple amino acid preference model (3-{AAP}), which is based on ordered
triples of amino acids. {T}he results demonstrate that mammalian
viral genome types differ in their amino acid preference.{A}vailability:
{T}he tools used to format and analyze data and supplementary material
are available at http://www.cse.sc.edu/~rose/amino{P}reference/index.html.},
doi = {10.1093/bioinformatics/bti174.},
pdf = {../local/Rose2005Correlation.pdf},
file = {Rose2005Correlation.pdf:local/Rose2005Correlation.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/bti174v1}
}
@article{Rudd2005Eclair,
author = {Rudd, S. and Tetko, I. V.},
title = {Eclair--a web service for unravelling species origin of sequences
sampled from mixed host interfaces.},
journal = {Nucleic {A}cids {R}es},
year = {2005},
volume = {33},
pages = {W724-7},
number = {Web Server issue},
month = {Jul},
abstract = {The identification of the genes that participate at the biological
interface of two species remains critical to our understanding of
the mechanisms of disease resistance, disease susceptibility and
symbiosis. {T}he sequencing of complementary {DNA} (c{DNA}) libraries
prepared from the biological interface between two organisms provides
an inexpensive way to identify the novel genes that may be expressed
as a cause or consequence of compatible or incompatible interactions.
{S}equence classification and annotation of species origin typically
use an orthology-based approach and require access to large portions
of either genome, or a close relative. {N}ovel species- or clade-specific
sequences may have no counterpart within existing databases and remain
ambiguous features. {H}ere we present a web-service, {E}clair, which
utilizes support vector machines for the classification of the origin
of expressed sequence tags stemming from mixed host c{DNA} libraries.
{I}n addition to providing an interface for the classification of
sequences, users are presented with the opportunity to train a model
to suit their preferred species pair. {E}clair is freely available
at http://eclair.btk.fi.},
doi = {10.1093/nar/gki434},
pdf = {../local/Rudd2005Eclair.pdf},
file = {Rudd2005Eclair.pdf:local/Rudd2005Eclair.pdf:PDF},
keywords = {biosvm},
pii = {33/suppl_2/W724},
url = {http://dx.doi.org/10.1093/nar/gki434}
}
@article{Ruepp2005Assessment,
author = {Ruepp, S. and Boess, F. and Suter, L. and de Vera, M. C. and Steiner,
G. and Steele, T. and Weiser, T. and Albertini, S.},
title = {Assessment of hepatotoxic liabilities by transcript profiling.},
journal = {Toxicol {A}ppl {P}harmacol},
year = {2005},
month = {Jun},
abstract = {Male {W}istar rats were treated with various model compounds or the
appropriate vehicle controls in order to create a reference database
for toxicogenomics assessment of novel compounds. {H}epatotoxic compounds
in the database were either known hepatotoxicants or showed hepatotoxicity
during preclinical testing. {H}istopathology and clinical chemistry
data were used to anchor the transcript profiles to an established
endpoint (steatosis, cholestasis, direct acting, peroxisomal proliferation
or nontoxic/control). {T}hese reference data were analyzed using
a supervised learning method (support vector machines, {SVM}) to
generate classification rules. {T}his predictive model was subsequently
used to assess compounds with regard to a potential hepatotoxic liability.
{A} steatotic and a non-hepatotoxic 5{HT}(6) receptor antagonist
compound from the same series were successfully discriminated by
this toxicogenomics model. {A}dditionally, an example is shown where
a hepatotoxic liability was correctly recognized in the absence of
pathological findings. {I}n vitro experiments and a dog study confirmed
the correctness of the toxicogenomics alert. {A}nother interesting
observation was that transcript profiles indicate toxicologically
relevant changes at an earlier timepoint than routinely used methods.
{T}ogether, these results support the useful application of toxicogenomics
in raising alerts for adverse effects and generating mechanistic
hypotheses that can be followed up by confirmatory experiments.},
doi = {10.1016/j.taap.2005.05.008},
pdf = {../local/Ruepp2005Assessment.pdf},
file = {Ruepp2005Assessment.pdf:local/Ruepp2005Assessment.pdf:PDF},
keywords = {biosvm},
pii = {S0041-008X(05)00295-4},
url = {http://dx.doi.org/10.1016/j.taap.2005.05.008}
}
@incollection{Ratsch2004Accurate,
author = {R{\"a}tsch, G. and Sonnenburg, S.},
title = {Accurate splice site detection for {C}aenorhabditis elegans},
booktitle = {Kernel {M}ethods in {C}omputational {B}iology},
publisher = {MIT Press},
year = {2004},
editor = {Sch{\"o}lkopf, B. and Tsuda, K. and Vert, J.P.},
pages = {277-298},
abstract = {During the past three years, the support vector machine learning algorithm
has been extensively applied within the field of computational biology.
{T}he algorithm has been used to detect patterns within and among
biological sequences, to classify genes and patients based upon gene
expression profiles, and has recently been applied to several new
biological problems. {T}his chapter reviews the state of the art
with respect to {SVM} applications in computational biology.},
keywords = {biosvm},
owner = {vert}
}
@article{Raetsch2005RASE,
author = {G. R{\"a}tsch and S. Sonnenburg and B. Sch{\"o}lkopf},
title = {R{ASE}: recognition of alternatively spliced exons in {C}.elegans.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {i369-i377},
number = {Suppl. 1},
month = {Jun},
abstract = {M{OTIVATION}: {E}ukaryotic pre-m{RNA}s are spliced to form mature
m{RNA}. {P}re-m{RNA} alternative splicing greatly increases the complexity
of gene expression. {E}stimates show that more than half of the human
genes and at least one-third of the genes of less complex organisms,
such as nematodes or flies, are alternatively spliced. {I}n this
work, we consider one major form of alternative splicing, namely
the exclusion of exons from the transcript. {I}t has been shown that
alternatively spliced exons have certain properties that distinguish
them from constitutively spliced exons. {A}lthough most recent computational
studies on alternative splicing apply only to exons which are conserved
among two species, our method only uses information that is available
to the splicing machinery, i.e. the {DNA} sequence itself. {W}e employ
advanced machine learning techniques in order to answer the following
two questions: (1) {I}s a certain exon alternatively spliced? (2)
{H}ow can we identify yet unidentified exons within known introns?
{RESULTS}: {W}e designed a support vector machine ({SVM}) kernel
well suited for the task of classifying sequences with motifs having
positional preferences. {I}n order to solve the task (1), we combine
the kernel with additional local sequence information, such as lengths
of the exon and the flanking introns. {T}he resulting {SVM}-based
classifier achieves a true positive rate of 48.5\% at a false positive
rate of 1\%. {B}y scanning over single {EST} confirmed exons we identified
215 potential alternatively spliced exons. {F}or 10 randomly selected
such exons we successfully performed biological verification experiments
and confirmed three novel alternatively spliced exons. {T}o answer
question (2), we additionally used {SVM}-based predictions to recognize
acceptor and donor splice sites. {C}ombined with the above mentioned
features we were able to identify 85.2\% of skipped exons within
known introns at a false positive rate of 1\%. {AVAILABILITY}: {D}atasets,
model selection results, our predictions and additional experimental
results are available at http://www.fml.tuebingen.mpg.de/~raetsch/{RASE}
{CONTACT}: {G}unnar.{R}aetsch@tuebingen.mpg.de {SUPPLEMENTARY} {INFORMATION}:
http://www.fml.tuebingen.mpg.de/raetsch/{RASE}.},
doi = {10.1093/bioinformatics/bti1053},
pdf = {../local/Raetsch2005RASE.pdf},
file = {Raetsch2005RASE.pdf:local/Raetsch2005RASE.pdf:PDF},
keywords = {biosvm},
pii = {21/suppl_1/i369},
url = {http://dx.doi.org/10.1093/bioinformatics/bti1053}
}
@article{Roegnvaldsson2004Why,
author = {Thorsteinn R{\"o}gnvaldsson and Liwen You},
title = {Why neural networks should not be used for {HIV}-1 protease cleavage
site prediction.},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {1702-9},
number = {11},
month = {Jul},
abstract = {S{UMMARY}: {S}everal papers have been published where nonlinear machine
learning algorithms, e.g. artificial neural networks, support vector
machines and decision trees, have been used to model the specificity
of the {HIV}-1 protease and extract specificity rules. {W}e show
that the dataset used in these studies is linearly separable and
that it is a misuse of nonlinear classifiers to apply them to this
problem. {T}he best solution on this dataset is achieved using a
linear classifier like the simple perceptron or the linear support
vector machine, and it is straightforward to extract rules from these
linear models. {W}e identify key residues in peptides that are efficiently
cleaved by the {HIV}-1 protease and list the most prominent rules,
relating them to experimental results for the {HIV}-1 protease. {MOTIVATION}:
{U}nderstanding {HIV}-1 protease specificity is important when designing
{HIV} inhibitors and several different machine learning algorithms
have been applied to the problem. {H}owever, little progress has
been made in understanding the specificity because nonlinear and
overly complex models have been used. {RESULTS}: {W}e show that the
problem is much easier than what has previously been reported and
that linear classifiers like the simple perceptron or linear support
vector machines are at least as good predictors as nonlinear algorithms.
{W}e also show how sets of specificity rules can be generated from
the resulting linear classifiers. {AVAILABILITY}: {T}he datasets
used are available at http://www.hh.se/staff/bioinf/},
doi = {10.1093/bioinformatics/bth144},
pdf = {../local/Roegnvaldsson2004Why.pdf},
file = {Roegnvaldsson2004Why.pdf:local/Roegnvaldsson2004Why.pdf:PDF},
keywords = {biosvm},
pii = {bth144},
url = {http://dx.doi.org/10.1093/bioinformatics/bth144}
}
@article{Saeh2005Lead,
author = {Saeh, J. and Lyne, P. and Takasaki, B. and Cosgrove, D.},
title = {Lead hopping using {SVM} and 3{D} pharmacophore fingerprints.},
journal = {J {C}hem {I}nf {M}odel},
year = {2005},
volume = {45},
pages = {1122-1133},
number = {4},
month = {Jul},
abstract = {The combination of 3{D} pharmacophore fingerprints and the support
vector machine classification algorithm has been used to generate
robust models that are able to classify compounds as active or inactive
in a number of {G}-protein-coupled receptor assays. {T}he models
have been tested against progressively more challenging validation
sets where steps are taken to ensure that compounds in the validation
set are chemically and structurally distinct from the training set.
{I}n the most challenging example, we simulate a lead-hopping experiment
by excluding an entire class of compounds (defined by a core substructure)
from the training set. {T}he left-out active compounds comprised
approximately 40\% of the actives. {T}he model trained on the remaining
compounds is able to recall 75\% of the actives from the "new" lead
series while correctly classifying >99\% of the 5000 inactives included
in the validation set.},
doi = {10.1021/ci049732r},
pdf = {../local/Saeh2005Lead.pdf},
file = {Saeh2005Lead.pdf:local/Saeh2005Lead.pdf:PDF},
keywords = {biosvm chemoinformatics},
url = {http://dx.doi.org/10.1021/ci049732r}
}
@article{Saetrom2004Predicting,
author = {Saetrom, P.},
title = {Predicting the efficacy of short oligonucleotides in antisense and
{RNA}i experiments with boosted genetic programming},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {3055-3063},
number = {17},
abstract = {Motivation: {B}oth small interfering {RNA}s (si{RNA}s) and antisense
oligonucleotides can selectively block gene expression. {A}lthough
the two methods rely on different cellular mechanisms, these methods
share the common property that not all oligonucleotides (oligos)
are equally effective. {T}hat is, if m{RNA} target sites are picked
at random, many of the antisense or si{RNA} oligos will not be effective.
{A}lgorithms that can reliably predict the efficacy of candidate
oligos can greatly reduce the cost of knockdown experiments, but
previous attempts to predict the efficacy of antisense oligos have
had limited success. {M}achine learning has not previously been used
to predict si{RNA} efficacy. {R}esults: {W}e develop a genetic programming
based prediction system that shows promising results on both antisense
and si{RNA} efficacy prediction. {W}e train and evaluate our system
on a previously published database of antisense efficacies and our
own database of si{RNA} efficacies collected from the literature.
{T}he best models gave an overall correlation between predicted and
observed efficacy of 0.46 on both antisense and si{RNA} data. {A}s
a comparison, the best correlations of support vector machine classifiers
trained on the same data were 0.40 and 0.30, respectively. {A}vailability:
{T}he prediction system uses proprietary hardware and is available
for both commercial and strategic academic collaborations. {T}he
si{RNA} database is available upon request.},
doi = {10.1093/bioinformatics/bth364},
pdf = {../local/Saetrom2004Predicting.pdf},
file = {Saetrom2004Predicting.pdf:local/Saetrom2004Predicting.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/17/3055}
}
@article{Saeys2004Feature,
author = {Saeys, Y. and Degroeve, S. and Aeyels, D. and Rouzé, P. and Van
de Peer, Y.},
title = {Feature selection for splice site prediction: {A} new method using
{EDA}-based feature ranking},
journal = {B{MC} {B}ioinformatics},
year = {2004},
volume = {5},
number = {64},
abstract = {Background {T}he identification of relevant biological features in
large and complex datasets is an important step towards gaining insight
in the processes underlying the data. {O}ther advantages of feature
selection include the ability of the classification system to attain
good or even better solutions using a restricted subset of features,
and a faster classification. {T}hus, robust methods for fast feature
selection are of key importance in extracting knowledge from complex
biological data. {R}esults {I}n this paper we present a novel method
for feature subset selection applied to splice site prediction, based
on estimation of distribution algorithms, a more general framework
of genetic algorithms. {F}rom the estimated distribution of the algorithm,
a feature ranking is derived. {A}fterwards this ranking is used to
iteratively discard features. {W}e apply this technique to the problem
of splice site prediction, and show how it can be used to gain insight
into the underlying biological process of splicing. {C}onclusion
{W}e show that this technique proves to be more robust than the traditional
use of estimation of distribution algorithms for feature selection:
instead of returning a single best subset of features (as they normally
do) this method provides a dynamical view of the feature selection
process, like the traditional sequential wrapper methods. {H}owever,
the method is faster than the traditional techniques, and scales
better to datasets described by a large number of features.},
doi = {10.1186/1471-2105-5-64},
pdf = {../local/Saeys2004Feature.pdf},
file = {Saeys2004Feature.pdf:local/Saeys2004Feature.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@article{Saeys2003Fast,
author = {Saeys, Y. and Degroeve, S. and Aeyels, D. and Van de Peer, Y. and
Rouze, P.},
title = {Fast feature selection using a simple estimation of distribution
algorithm: a case study on splice site prediction},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {ii179-ii188},
number = {Suppl. 1},
abstract = {Motivation: {F}eature subset selection is an important preprocessing
step for classification. {I}n biology, where structures or processes
are described by a large number of features, the elimination of irrelevant
and redundant information in a reasonable amount of time has a number
of advantages. {I}t enables the classification system to achieve
good or even better solutions with a restricted subset of features,
allows for a faster classification, and it helps the human expert
focus on a relevant subset of features, hence providing useful biological
knowledge. {R}esults: {W}e present a heuristic method based on {E}stimation
of {D}istribution {A}lgorithms to select relevant subsets of features
for splice site prediction in {A}rabidopsis thaliana. {W}e show that
this method performs a fast detection of relevant feature subsets
using the technique of constrained feature subsets. {C}ompared to
the traditional greedy methods the gain in speed can be up to one
order of magnitude, with results being comparable or even better
than the greedy methods. {T}his makes it a very practical solution
for classification tasks that can be solved using a relatively small
amount of discriminative features (or feature dependencies), but
where the initial set of potential discriminative features is rather
large. {K}eywords: {M}achine {L}earning, {F}eature {S}ubset {S}election,
{E}stimation of {D}istribution {A}lgorithms, {S}plice {S}ite {P}rediction.
{C}ontact: yvsae@gengenp.rug.ac.be},
pdf = {../local/Saeys2003Fast.pdf},
file = {Saeys2003Fast.pdf:local/Saeys2003Fast.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/suppl_2/ii179}
}
@article{Saigo2004Protein,
author = {Saigo, H. and Vert, J.-P. and Ueda, N. and Akutsu, T.},
title = {Protein homology detection using string alignment kernels},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {1682-1689},
number = {11},
abstract = {Motivation: {R}emote homology detection between protein sequences
is a central problem in computational biology. {D}iscriminative methods
involving support vector machines ({SVM}s) are currently the most
effective methods for the problem of superfamily recognition in the
{S}tructural {C}lassification {O}f {P}roteins ({SCOP}) database.
{T}he performance of {SVM}s depends critically on the kernel function
used to quantify the similarity between sequences. {R}esults: {W}e
propose new kernels for strings adapted to biological sequences,
which we call local alignment kernels. {T}hese kernels measure the
similarity between two sequences by summing up scores obtained from
local alignments with gaps of the sequences. {W}hen tested in combination
with {SVM} on their ability to recognize {SCOP} superfamilies on
a benchmark dataset, the new kernels outperform state-of-the-art
methods for remote homology detection. {A}vailability: {S}oftware
and data available upon request.},
pdf = {../local/Saigo2004Protein.pdf},
file = {Saigo2004Protein.pdf:local/Saigo2004Protein.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/11/1682}
}
@article{Sanchez-Carbayo2003Gene,
author = {Marta Sanchez-Carbayo and Nicholas D Socci and Juan Jose Lozano and
Wentian Li and Elizabeth Charytonowicz and Thomas J Belbin and Michael
B Prystowsky and Angel R Ortiz and Geoffrey Childs and Carlos Cordon-Cardo},
title = {Gene discovery in bladder cancer progression using c{DNA} microarrays.},
journal = {Am. {J}. {P}athol.},
year = {2003},
volume = {163},
pages = {505-16},
number = {2},
month = {Aug},
abstract = {To identify gene expression changes along progression of bladder cancer,
we compared the expression profiles of early-stage and advanced bladder
tumors using c{DNA} microarrays containing 17,842 known genes and
expressed sequence tags. {T}he application of bootstrapping techniques
to hierarchical clustering segregated early-stage and invasive transitional
carcinomas into two main clusters. {M}ultidimensional analysis confirmed
these clusters and more importantly, it separated carcinoma in situ
from papillary superficial lesions and subgroups within early-stage
and invasive tumors displaying different overall survival. {A}dditionally,
it recognized early-stage tumors showing gene profiles similar to
invasive disease. {D}ifferent techniques including standard t-test,
single-gene logistic regression, and support vector machine algorithms
were applied to identify relevant genes involved in bladder cancer
progression. {C}ytokeratin 20, neuropilin-2, p21, and p33{ING}1 were
selected among the top ranked molecular targets differentially expressed
and validated by immunohistochemistry using tissue microarrays (n
= 173). {T}heir expression patterns were significantly associated
with pathological stage, tumor grade, and altered retinoblastoma
({RB}) expression. {M}oreover, p33{ING}1 expression levels were significantly
associated with overall survival. {A}nalysis of the annotation of
the most significant genes revealed the relevance of critical genes
and pathways during bladder cancer progression, including the overexpression
of oncogenic genes such as {DEK} in superficial tumors or immune
response genes such as {C}d86 antigen in invasive disease. {G}ene
profiling successfully classified bladder tumors based on their progression
and clinical outcome. {T}he present study has identified molecular
biomarkers of potential clinical significance and critical molecular
targets associated with bladder cancer progression.},
pdf = {../local/Sanchez-Carbayo2003Gene.pdf},
file = {Sanchez-Carbayo2003Gene.pdf:local/Sanchez-Carbayo2003Gene.pdf:PDF},
keywords = {biosvm},
url = {http://ajp.amjpathol.org/cgi/content/abstract/163/2/505}
}
@article{Sarda2005pSLIP,
author = {Deepak Sarda and Gek Huey Chua and Kuo-Bin Li and Arun Krishnan},
title = {p{SLIP}: {SVM} based protein subcellular localization prediction
using multiple physicochemical properties.},
journal = {B{MC} {B}ioinformatics},
year = {2005},
volume = {6},
pages = {152},
number = {1},
month = {Jun},
abstract = {B{ACKGROUND}: {P}rotein subcellular localization is an important determinant
of protein function and hence, reliable methods for prediction of
localization are needed. {A} number of prediction algorithms have
been developed based on amino acid compositions or on the {N}-terminal
characteristics (signal peptides) of proteins. {H}owever, such approaches
lead to a loss of contextual information. {M}oreover, where information
about the physicochemical properties of amino acids has been used,
the methods employed to exploit that information are less than optimal
and could use the information more effectively. {RESULTS}: {I}n this
paper, we propose a new algorithm called p{SLIP} which uses {S}upport
{V}ector {M}achines ({SVM}s) in conjunction with multiple physicochemical
properties of amino acids to predict protein subcellular localization
in eukaryotes across six different locations, namely, chloroplast,
cytoplasmic, extracellular, mitochondrial, nuclear and plasma membrane.
{T}he algorithm was applied to the dataset provided by {P}ark and
{K}anehisa and we obtained prediction accuracies for the different
classes ranging from 87.7\%-97.0\% with an overall accuracy of 93.1\%.
{CONCLUSIONS}: {T}his study presents a physicochemical property based
protein localization prediction algorithm. {U}nlike other algorithms,
contextual information is preserved by dividing the protein sequences
into clusters. {T}he prediction accuracy shows an improvement over
other algorithms based on various types of amino acid composition
(single, pair and gapped pair). {W}e have also implemented a web
server to predict protein localization across the six classes (available
at http://pslip.bii.a-star.edu.sg).},
doi = {10.1186/1471-2105-6-152},
pdf = {../local/Sarda2005pSLIP.pdf},
file = {Sarda2005pSLIP.pdf:local/Sarda2005pSLIP.pdf:PDF},
keywords = {biosvm},
pii = {1471-2105-6-152},
url = {http://dx.doi.org/10.1186/1471-2105-6-152}
}
@article{Schwender2004pilot,
author = {Holger Schwender and Manuela Zucknick and Katja Ickstadt and Hermann
M Bolt and G. E. N. I. C. A. network},
title = {A pilot study on the application of statistical classification procedures
to molecular epidemiological data.},
journal = {Toxicol {L}ett},
year = {2004},
volume = {151},
pages = {291-9},
number = {1},
month = {Jun},
abstract = {The development of new statistical methods for use in molecular epidemiology
comprises the building and application of appropriate classification
rules. {T}he aim of this study was to assess various classification
methods that can potentially handle genetic interactions. {A} data
set comprising genotypes at 25 single nucleotide polymorphic ({SNP})
loci from 518 breast cancer cases and 586 age-matched population-based
controls from the {GENICA} study was used to built a classification
rule with the discrimination methods {SVM} (support vector machine),
{CART} (classification and regression tree), {B}agging, {R}andom
{F}orest, {L}ogit{B}oost and k nearest neighbours (k{NN}). {A} blind
pilot analysis of the genotypic data set was a first approach to
obtain an impression of the statistical structure of the data. {F}urthermore,
this analysis was performed to explore classification methods that
may be applied to molecular-epidemiological evaluation. {T}he results
showed that all blindly applied classification methods had a slightly
smaller misclassification rate than a random classification. {T}he
findings, nevertheless, suggest that {SNP} data might be useful for
the classification of individuals into categories of high or low
risk of diseases.},
keywords = {biosvm}
}
@book{Schoelkopf2004Kernel,
title = {Kernel {M}ethods in {C}omputational {B}iology},
publisher = {MIT Press},
year = {2004},
author = {Sch{\"o}lkopf, B. and Tsuda, K. and Vert, J.-P.},
address = {The MIT Press, Cambridge, Massachussetts},
keywords = {biosvm},
owner = {vert}
}
@inproceedings{Seeger2002Covariance,
author = {Seeger, M.},
title = {Covariance {K}ernels from {B}ayesian {G}enerative {M}odels},
booktitle = {Adv. {N}eural {I}nform. {P}rocess. {S}yst.},
year = {2002},
volume = {14},
pages = {905-912},
pdf = {../local/nips2001.pdf:http\://www.cs.berkeley.edu/~mseeger/papers/nips2001.pdf:PDF;nips2001.pdf:http\},
file = {nips2001.pdf:http\://www.cs.berkeley.edu/~mseeger/papers/nips2001.pdf:PDF;nips2001.pdf:http\://www.cs.berkeley.edu/~mseeger/papers/nips2001.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@article{Segal2003Regression,
author = {Segal, M. R. and Dahlquist, K. D. and Conklin, B. R.},
title = {Regression approaches for microarray data analysis.},
journal = {J. {C}omput. {B}iol.},
year = {2003},
volume = {10},
pages = {961-980},
number = {6},
abstract = {A variety of new procedures have been devised to handle the two-sample
comparison (e.g., tumor versus normal tissue) of gene expression
values as measured with microarrays. {S}uch new methods are required
in part because of some defining characteristics of microarray-based
studies: (i) the very large number of genes contributing expression
measures which far exceeds the number of samples (observations) available
and (ii) the fact that by virtue of pathway/network relationships,
the gene expression measures tend to be highly correlated. {T}hese
concerns are exacerbated in the regression setting, where the objective
is to relate gene expression, simultaneously for multiple genes,
to some external outcome or phenotype. {C}orrespondingly, several
methods have been recently proposed for addressing these issues.
{W}e briefly critique some of these methods prior to a detailed evaluation
of gene harvesting. {T}his reveals that gene harvesting, without
additional constraints, can yield artifactual solutions. {R}esults
obtained employing such constraints motivate the use of regularized
regression procedures such as the lasso, least angle regression,
and support vector machines. {M}odel selection and solution multiplicity
issues are also discussed. {T}he methods are evaluated using a microarray-based
study of cardiomyopathy in transgenic mice.},
doi = {10.1089/106652703322756177},
pdf = {../local/Segal2003Regression.pdf},
file = {Segal2003Regression.pdf:local/Segal2003Regression.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Segal2003Classificationa,
author = {Segal, N. H. and Pavlidis, P. and Antonescu, C. R. and Maki, R. G.
and Noble, W. S. and DeSantis, D. and Woodruff, J. M. and Lewis,
J. J. and Brennan, M. F. and Houghton, A. N. and Cordon-Cardo, C.},
title = {Classification and {S}ubtype {P}rediction of {A}dult {S}oft {T}issue
{S}arcoma by {F}unctional {G}enomics},
journal = {Am. {J}. {P}athol.},
year = {2003},
volume = {163},
pages = {691-700},
number = {2},
month = {Aug},
abstract = {Adult soft tissue sarcomas are a heterogeneous group of tumors, including
well-described subtypes by histological and genotypic criteria, and
pleomorphic tumors typically characterized by non-recurrent genetic
aberrations and karyotypic heterogeneity. {T}he latter pose a diagnostic
challenge, even to experienced pathologists. {W}e proposed that gene
expression profiling in soft tissue sarcoma would identify a genomic-based
classification scheme that is useful in diagnosis. {RNA} samples
from 51 pathologically confirmed cases, representing nine different
histological subtypes of adult soft tissue sarcoma, were examined
using the {A}ffymetrix {U}95{A} {G}ene{C}hip. {S}tatistical tests
were performed on experimental groups identified by cluster analysis,
to find discriminating genes that could subsequently be applied in
a support vector machine algorithm. {S}ynovial sarcomas, round-cell/myxoid
liposarcomas, clear-cell sarcomas and gastrointestinal stromal tumors
displayed remarkably distinct and homogenous gene expression profiles.
{P}leomorphic tumors were heterogeneous. {N}otably, a subset of malignant
fibrous histiocytomas, a controversialhistological subtype, was identified
as a distinct genomic group. {T}he support vector machine algorithm
supported a genomic basis for diagnosis, with both high sensitivity
and specificity. {I}n conclusion, we showed gene expression profiling
to be useful in classification and diagnosis, providing insights
into pathogenesis and pointing to potential new therapeutic targets
of soft tissue sarcoma.},
pdf = {../local/Segal2003Classificationa.pdf},
file = {Segal2003Classificationa.pdf:local/Segal2003Classificationa.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://ajp.amjpathol.org/cgi/content/abstract/163/2/691}
}
@article{Segal2003Classification,
author = {Segal, N. H. and Pavlidis, P. and Noble, W. S. and Antonescu, C.
R. and Viale, A. and Wesley, U. V. and Busam, K. and Gallardo, H.
and DeSantis, D. and Brennan, M. F. and Cordon-Cardo, C. and Wolchok,
J. D. and Houghton, A. N.},
title = {Classification of {C}lear-{C}ell {S}arcoma as a {S}ubtype of {M}elanoma
by {G}enomic {P}rofiling},
journal = {J. {C}lin. {O}ncol.},
year = {2003},
volume = {21},
pages = {1775-1781},
number = {9},
month = {May},
abstract = {Purpose: {T}o develop a genome-based classification scheme for clear-cell
sarcoma ({CCS}), also known as melanoma of soft parts ({MSP}), which
would have implications for diagnosis and treatment. {T}his tumor
displays characteristic features of soft tissue sarcoma ({STS}),
including deep soft tissue primary location and a characteristic
translocation, t(12;22)(q13;q12), involving {EWS} and {ATF}1 genes.
{CCS}/{MSP} also has typical melanoma features, including immunoreactivity
for {S}100 and {HMB}45, pigmentation, {MITF}-{M} expression, and
a propensity for regional lymph node metastases. {M}aterials and
{M}ethods: {RNA} samples from 21 cell lines and 60 pathologically
confirmed cases of {STS}, melanoma, and {CCS}/{MSP} were examined
using the {U}95{A} {G}ene{C}hip ({A}ffymetrix, {S}anta {C}lara, {CA}).
{H}ierarchical cluster analysis, principal component analysis, and
support vector machine ({SVM}) analysis exploited genomic correlations
within the data to classify {CCS}/{MSP}. {R}esults: {U}nsupervised
analyses demonstrated a clear distinction between {STS} and melanoma
and, furthermore, showed that {CCS}/{MSP} cluster with the melanomas
as a distinct group. {A} supervised {SVM} learning approach further
validated this finding and provided a user-independent approach to
diagnosis. {G}enes of interest that discriminate {CCS}/{MSP} included
those encoding melanocyte differentiation antigens, {MITF}, {SOX}10,
{ERBB}3, and {FGFR}1. {C}onclusion: {G}ene expression profiles support
the classification of {CCS}/{MSP} as a distinct genomic subtype of
melanoma. {A}nalysis of these gene profiles using the {SVM} may be
an important diagnostic tool. {G}enomic analysis identified potential
targets for the development of therapeutic strategies in the treatment
of this disease.},
doi = {10.1200/JCO.2003.10.108},
pdf = {../local/Segal2003Classification.pdf},
file = {Segal2003Classification.pdf:local/Segal2003Classification.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1200/JCO.2003.10.108}
}
@article{Seike2005Proteomic,
author = {Seike, M. and Kondo, T. and Fujii, K. and Okano, T. and Yamada, T.
and Matsuno, Y. and Gemma, A. and Kudoh, S. and Hirohashi, S.},
title = {Proteomic signatures for histological types of lung cancer.},
journal = {Proteomics},
year = {2005},
month = {Jul},
abstract = {We performed proteomic studies on lung cancer cells to elucidate the
mechanisms that determine histological phenotype. {T}hirty lung cancer
cell lines with three different histological backgrounds (squamous
cell carcinoma, small cell lung carcinoma and adenocarcinoma) were
subjected to two-dimensional difference gel electrophoresis (2-{D}
{DIGE}) and grouped by multivariate analyses on the basis of their
protein expression profiles. 2-{D} {DIGE} achieves more accurate
quantification of protein expression by using highly sensitive fluorescence
dyes to label the cysteine residues of proteins prior to two-dimensional
polyacrylamide gel electrophoresis. {W}e found that hierarchical
clustering analysis and principal component analysis divided the
cell lines according to their original histology. {S}pot ranking
analysis using a support vector machine algorithm and unsupervised
classification methods identified 32 protein spots essential for
the classification. {T}he proteins corresponding to the spots were
identified by mass spectrometry. {N}ext, lung cancer cells isolated
from tumor tissue by laser microdissection were classified on the
basis of the expression pattern of these 32 protein spots. {B}ased
on the expression profile of the 32 spots, the isolated cancer cells
were categorized into three histological groups: the squamous cell
carcinoma group, the adenocarcinoma group, and a group of carcinomas
with other histological types. {I}n conclusion, our results demonstrate
the utility of quantitative proteomic analysis for molecular diagnosis
and classification of lung cancer cells.},
doi = {10.1002/pmic.200401166},
pdf = {../local/Seike2005Proteomic.pdf},
file = {Seike2005Proteomic.pdf:local/Seike2005Proteomic.pdf:PDF},
keywords = {biosvm proteomics},
url = {http://dx.doi.org/10.1002/pmic.200401166}
}
@article{Sen2004Predicting,
author = {Sen, T.Z. and Kloczkowski, A. and Jernigan, R.L. and Yan, C. and
Honavar, V. and Ho, K.M. and Wang, C.Z. and Ihm, Y. and Cao, H. and
Gu, X. and Dobbs, D.},
title = {Predicting binding sites of hydrolase-inhibitor complexes by combining
several methods.},
journal = {B{MC} {B}ioinformatics},
year = {2004},
volume = {5},
number = {205},
abstract = {Background {P}rotein-protein interactions play a critical role in
protein function. {C}ompletion of many genomes is being followed
rapidly by major efforts to identify interacting protein pairs experimentally
in order to decipher the networks of interacting, coordinated-in-action
proteins. {I}dentification of protein-protein interaction sites and
detection of specific amino acids that contribute to the specificity
and the strength of protein interactions is an important problem
with broad applications ranging from rational drug design to the
analysis of metabolic and signal transduction networks. {R}esults
{I}n order to increase the power of predictive methods for protein-protein
interaction sites, we have developed a consensus methodology for
combining four different methods. {T}hese approaches include: data
mining using {S}upport {V}ector {M}achines, threading through protein
structures, prediction of conserved residues on the protein surface
by analysis of phylogenetic trees, and the {C}onservatism of {C}onservatism
method of {M}irny and {S}hakhnovich. {R}esults obtained on a dataset
of hydrolase-inhibitor complexes demonstrate that the combination
of all four methods yield improved predictions over the individual
methods. {C}onclusions {W}e developed a consensus method for predicting
protein-protein interface residues by combining sequence and structure-based
methods. {T}he success of our consensus approach suggests that similar
methodologies can be developed to improve prediction accuracies for
other bioinformatic problems.},
doi = {10.1186/1471-2105-5-205},
pdf = {../local/Sen2004Predicting.pdf},
file = {Sen2004Predicting.pdf:local/Sen2004Predicting.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Senawongse2005Predicting,
author = {Pasak Senawongse and Andrew R Dalby and Zheng Rong Yang},
title = {Predicting the phosphorylation sites using hidden markov models and
machine learning methods.},
journal = {J {C}hem {I}nf {M}odel},
year = {2005},
volume = {45},
pages = {1147-52},
number = {4},
abstract = {Accurately predicting phosphorylation sites in proteins is an important
issue in postgenomics, for which how to efficiently extract the most
predictive features from amino acid sequences for modeling is still
challenging. {A}lthough both the distributed encoding method and
the bio-basis function method work well, they still have some limits
in use. {T}he distributed encoding method is unable to code the biological
content in sequences efficiently, whereas the bio-basis function
method is a nonparametric method, which is often computationally
expensive. {A}s hidden {M}arkov models ({HMM}s) can be used to generate
one model for one cluster of aligned protein sequences, the aim in
this study is to use {HMM}s to extract features from amino acid sequences,
where sequence clusters are determined using available biological
knowledge. {I}n this novel method, {HMM}s are first constructed using
functional sequences only. {B}oth functional and nonfunctional training
sequences are then inputted into the trained {HMM}s to generate functional
and nonfunctional feature vectors. {F}rom this, a machine learning
algorithm is used to construct a classifier based on these feature
vectors. {I}t is found in this work that (1) this method provides
much better prediction accuracy than the use of {HMM}s only for prediction,
and (2) the support vector machines ({SVM}s) algorithm outperforms
decision trees and neural network algorithms when they are constructed
on the features extracted using the trained {HMM}s.},
doi = {10.1021/ci050047+},
pdf = {../local/Senawongse2005Predicting.pdf},
file = {Senawongse2005Predicting.pdf:local/Senawongse2005Predicting.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci050047+}
}
@article{Serra2003Development,
author = {Serra, J.R. and Thompson, E.D. and Jurs, P.C.},
title = {Development of binary classification of structural chromosome aberrations
for a diverse set of organic compounds from molecular structure},
journal = {Chem. {R}es. {T}oxicol.},
year = {2003},
volume = {16},
pages = {153-163},
number = {2},
abstract = {Classification models are generated to predict in vitro cytogenetic
results for a diverse set of 383 organic compounds. {B}oth k-nearest
neighbor and support vector machine models are developed. {T}hey
are based on calculated molecular structure descriptors. {E}ndpoints
used are the labels clastogenic or nonclastogenic according to an
in vitro chromosomal aberration assay with {C}hinese hamster lung
cells. {C}ompounds that were tested with both a 24 and 48 h exposure
are included. {E}ach compound is represented by calculated molecular
structure descriptors encoding the topological, electronic, geometrical,
or polar surface area aspects of the structure. {S}ubsets of informative
descriptors are identified with genetic algorithm feature selection
coupled to the appropriate classification algorithm. {T}he overall
classification success rate for a k-nearest neighbor classifier built
with just six topological descriptors is 81.2% for the training set
and 86.5% for an external prediction set. {T}he overall classification
success rate for a three-descriptor support vector machine model
is 99.7% for the training set, 92.1% for the cross-validation set,
and 83.8% for an external prediction set.},
doi = {10.1021/tx020077w},
pdf = {../local/Serra2003Development.pdf},
file = {Serra2003Development.pdf:local/Serra2003Development.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1021/tx020077w}
}
@article{Sharan2005motif-based,
author = {R. Sharan and E. W Myers},
title = {A motif-based framework for recognizing sequence families.},
journal = {Bioinformatics},
year = {2005},
volume = {21 Suppl 1},
pages = {i387-i393},
month = {Jun},
abstract = {M{OTIVATION}: {M}any signals in biological sequences are based on
the presence or absence of base signals and their spatial combinations.
{O}ne of the best known examples of this is the signal identifying
a core promoter-the site at which the basal transcription machinery
starts the transcription of a gene. {O}ur goal is a fully automatic
pattern recognition system for a family of sequences, which simultaneously
discovers the base signals, their spatial relationships and a classifier
based upon them. {RESULTS}: {I}n this paper we present a general
method for characterizing a set of sequences by their recurrent motifs.
{O}ur approach relies on novel probabilistic models for {DNA} binding
sites and modules of binding sites, on algorithms to study them from
the data and on a support vector machine that uses the models studied
to classify a set of sequences. {W}e demonstrate the applicability
of our approach to diverse instances, ranging from families of promoter
sequences to a dataset of intronic sequences flanking alternatively
spliced exons. {O}n a core promoter dataset our results are comparable
with the state-of-the-art {M}c{P}romoter. {O}n a dataset of alternatively
spliced exons we outperform a previous approach. {W}e also achieve
high success rates in recognizing cell cycle regulated genes. {T}hese
results demonstrate that a fully automatic pattern recognition algorithm
can meet or exceed the performance of hand-crafted approaches. {AVAILABILITY}:
{T}he software and datasets are available from the authors upon request.
{CONTACT}: roded@tau.ac.il.},
doi = {10.1093/bioinformatics/bti1002},
pdf = {../local/Sharan2005motif-based.pdf},
file = {Sharan2005motif-based.pdf:local/Sharan2005motif-based.pdf:PDF},
keywords = {biosvm},
pii = {21/suppl_1/i387},
url = {http://dx.doi.org/10.1093/bioinformatics/bti1002}
}
@inproceedings{She2003Frequent-subsequence-based,
author = {She, R. and Chen, F. and Wang, K. and Ester, M. and Gardy, J.L. and
Brinkman, F.S.L.},
title = {Frequent-subsequence-based prediction of outer membrane proteins},
booktitle = {K{DD} '03: {P}roceedings of the ninth {ACM} {SIGKDD} international
conference on {K}nowledge discovery and data mining},
year = {2003},
pages = {436-445},
publisher = {ACM Press},
abstract = {A number of medically important disease-causing bacteria (collectively
called {G}ram-negative bacteria) are noted for the extra "outer"
membrane that surrounds their cell. {P}roteins resident in this membrane
(outer membrane proteins, or {OMP}s) are of primary research interest
for antibiotic and vaccine drug design as they are on the surface
of the bacteria and so are the most accessible targets to develop
new drugs against. {W}ith the development of genome sequencing technology
and bioinformatics, biologists can now deduce all the proteins that
are likely produced in a given bacteria and have attempted to classify
where proteins are located in a bacterial cell. {H}owever such protein
localization programs are currently least accurate when predicting
{OMP}s, and so there is a current need for the development of a better
{OMP} classifier. {D}ata mining research suggests that the use of
frequent patterns has good performance in aiding the development
of accurate and efficient classification algorithms. {I}n this paper,
we present two methods to identify {OMP}s based on frequent subsequences
and test them on all {G}ram-negative bacterial proteins whose localizations
have been determined by biological experiments. {O}ne classifier
follows an association rule approach, while the other is based on
support vector machines ({SVM}s). {W}e compare the proposed methods
with the state-of-the-art methods in the biological domain. {T}he
results demonstrate that our methods are better both in terms of
accurately identifying {OMP}s and providing biological insights that
increase our understanding of the structures and functions of these
important proteins.},
doi = {10.1145/956750.956800},
pdf = {../local/She2003Frequent-subsequence-based.pdf},
file = {She2003Frequent-subsequence-based.pdf:local/She2003Frequent-subsequence-based.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Shi2005Building,
author = {Lei Shi and Fabien Campagne},
title = {Building a protein name dictionary from full text: a machine learning
term extraction approach.},
journal = {B{MC} {B}ioinformatics},
year = {2005},
volume = {6},
pages = {88},
number = {1},
month = {Apr},
abstract = {B{ACKGROUND}: {T}he majority of information in the biological literature
resides in full text articles, instead of abstracts. {Y}et, abstracts
remain the focus of many publicly available literature data mining
tools. {M}ost literature mining tools rely on pre-existing lexicons
of biological names, often extracted from curated gene or protein
databases. {T}his is a limitation, because such databases have low
coverage of the many name variants which are used to refer to biological
entities in the literature. {RESULTS}: {W}e present an approach to
recognize named entities in full text. {T}he approach collects high
frequency terms in an article, and uses support vector machines ({SVM})
to identify biological entity names. {I}t is also computationally
efficient and robust to noise commonly found in full text material.
{W}e use the method to create a protein name dictionary from a set
of 80,528 full text articles. {O}nly 8.3\% of the names in this dictionary
match {S}wiss{P}rot description lines. {W}e assess the quality of
the dictionary by studying its protein name recognition performance
in full text. {CONCLUSION}: {T}his dictionary term lookup method
compares favourably to other published methods, supporting the significance
of our direct extraction approach. {T}he method is strong in recognizing
name variants not found in {S}wiss{P}rot.},
doi = {10.1186/1471-2105-6-88},
pdf = {../local/Shi2005Building.pdf},
file = {Shi2005Building.pdf:local/Shi2005Building.pdf:PDF},
keywords = {biosvm},
pii = {1471-2105-6-88},
url = {http://dx.doi.org/10.1186/1471-2105-6-88}
}
@article{Shipp2002Diffuse,
author = {Shipp, M. A. and Ross, K. N. and Tamayo, P. and Weng, A. P. and Kutok,
J. L. and Aguiar, R. C. T. and Gaasenbeek, M. and Angelo, M. and
Reich, M. and Pinkus, G. A. and Ray, T. S. and Koval, M. A. and Last,
K. W. and Norton, A. and Lister, T. A. and Mesirov, J. and Neuberg,
D. S. and Lander, E. S. and Aster, J. C. and Golub, T. R.},
title = {Diffuse large {B}-cell lymphoma outcome prediction by gene-expression
profiling and supervised machine learning},
journal = {Nat. {M}ed.},
year = {2002},
volume = {8},
pages = {68-74},
number = {1},
abstract = {Diffuse large {B}-cell lymphoma ({DLBCL}), the most common lymphoid
malignancy in adults, is curable in less than 50% of patients. {P}rognostic
models based on pre-treatment characteristics, such as the {I}nternational
{P}rognostic {I}ndex ({IPI}), are currently used to predict outcome
in {DLBCL}. {H}owever, clinical outcome models identify neither the
molecular basis of clinical heterogeneity, nor specific therapeutic
targets. {W}e analyzed the expression of 6,817 genes in diagnostic
tumor specimens from {DLBCL} patients who received cyclophosphamide,
adriamycin, vincristine and prednisone ({CHOP})-based chemotherapy,
and applied a supervised learning prediction method to identify cured
versus fatal or refractory disease. {T}he algorithm classified two
categories of patients with very different five-year overall survival
rates (70% versus 12%). {T}he model also effectively delineated patients
within specific {IPI} risk categories who were likely to be cured
or to die of their disease. {G}enes implicated in {DLBCL} outcome
included some that regulate responses to {B}-cell?receptor signaling,
critical serine/threonine phosphorylation pathways and apoptosis.
{O}ur data indicate that supervised learning classification techniques
can predict outcome in {DLBCL} and identify rational targets for
intervention.},
doi = {10.1038/nm0102-68},
pdf = {../local/Shipp2002Diffuse.pdf},
file = {Shipp2002Diffuse.pdf:local/Shipp2002Diffuse.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@article{Siepen2003Beta,
author = {Siepen, J. A. and Radford, S. E. and Westhead, D. R.},
title = {Beta {E}dge strands in protein structure prediction and aggregation},
journal = {Protein {S}ci.},
year = {2003},
volume = {12},
pages = {2348-2359},
number = {10},
abstract = {It is well established that recognition between exposed edges of {beta}-sheets
is an important mode of protein-protein interaction and can have
pathological consequences; for instance, it has been linked to the
aggregation of proteins into a fibrillar structure, which is associated
with a number of predominantly neurodegenerative disorders. {A} number
of protective mechanisms have evolved in the edge strands of {beta}-sheets,
preventing the aggregation and insolubility of most natural {beta}-sheet
proteins. {S}uch mechanisms are unfavorable in the interior of a
{beta}-sheet. {T}he problem of distinguishing edge strands from central
strands based on sequence information alone is important in predicting
residues and mutations likely to be involved in aggregation, and
is also a first step in predicting folding topology. {H}ere we report
support vector machine ({SVM}) and decision tree methods developed
to classify edge strands from central strands in a representative
set of protein domains. {I}nterestingly, rules generated by the decision
tree method are in close agreement with our knowledge of protein
structure and are potentially useful in a number of different biological
applications. {W}hen trained on strands from proteins of known structure,
using structure-based ({D}ictionary of {S}econdary {S}tructure in
{P}roteins) strand assignments, both methods achieved mean cross-validated,
prediction accuracies of ~78%. {T}hese accuracies were reduced when
strand assignments from secondary structure prediction were used.
{F}urther investigation of this effect revealed that it could be
explained by a significant reduction in the accuracy of standard
secondary structure prediction methods for edge strands, in comparison
with central strands.},
doi = {10.1110/ps.03234503},
pdf = {../local/Siepen2003beta.pdf},
file = {Siepen2003beta.pdf:local/Siepen2003beta.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.proteinscience.org/cgi/content/abstract/12/10/2348}
}
@inproceedings{Sonnenburg2002New,
author = {Sonnenburg, S. and R{\"a}tsch, G. and Jagota, A. and M{\"u}ller,
K.-R.},
title = {New methods for splice-site recognition},
booktitle = {Proc. {I}nternational conference on artificial {N}eural {N}etworks
? {ICANN}?02},
year = {2002},
editor = {JR. Dorronsoro},
number = {2415},
series = {LNCS},
pages = {329-336},
publisher = {Springer Berlin},
pdf = {../local/Sonnenburg2002New.pdf},
file = {Sonnenburg2002New.pdf:local/Sonnenburg2002New.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Sorich2004Rapid,
author = {Michael J Sorich and Ross A McKinnon and John O Miners and David
A Winkler and Paul A Smith},
title = {Rapid prediction of chemical metabolism by human {UDP}-glucuronosyltransferase
isoforms using quantum chemical descriptors derived with the electronegativity
equalization method.},
journal = {J {M}ed {C}hem},
year = {2004},
volume = {47},
pages = {5311-7},
number = {21},
month = {Oct},
abstract = {This study aimed to evaluate in silico models based on quantum chemical
({QC}) descriptors derived using the electronegativity equalization
method ({EEM}) and to assess the use of {QC} properties to predict
chemical metabolism by human {UDP}-glucuronosyltransferase ({UGT})
isoforms. {V}arious {EEM}-derived {QC} molecular descriptors were
calculated for known {UGT} substrates and nonsubstrates. {C}lassification
models were developed using support vector machine and partial least
squares discriminant analysis. {I}n general, the most predictive
models were generated with the support vector machine. {C}ombining
{QC} and 2{D} descriptors (from previous work) using a consensus
approach resulted in a statistically significant improvement in predictivity
(to 84\%) over both the {QC} and 2{D} models and the other methods
of combining the descriptors. {EEM}-derived {QC} descriptors were
shown to be both highly predictive and computationally efficient.
{I}t is likely that {EEM}-derived {QC} properties will be generally
useful for predicting {ADMET} and physicochemical properties during
drug discovery.},
doi = {10.1021/jm0495529},
pdf = {../local/Sorich2004Rapid.pdf},
file = {Sorich2004Rapid.pdf:local/Sorich2004Rapid.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/jm0495529}
}
@article{Sorich2003Comparison,
author = {M. J. Sorich and J. O. Miners and R. A. McKinnon and D. A. Winkler
and F. R. Burden and P. A. Smith},
title = {Comparison of linear and nonlinear classification algorithms for
the prediction of drug and chemical metabolism by human {UDP}-glucuronosyltransferase
isoforms.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2003},
volume = {43},
pages = {2019-24},
number = {6},
abstract = {Partial least squares discriminant analysis ({PLSDA}), {B}ayesian
regularized artificial neural network ({BRANN}), and support vector
machine ({SVM}) methodologies were compared by their ability to classify
substrates and nonsubstrates of 12 isoforms of human {UDP}-glucuronosyltransferase
({UGT}), an enzyme "superfamily" involved in the metabolism of drugs,
nondrug xenobiotics, and endogenous compounds. {S}imple two-dimensional
descriptors were used to capture chemical information. {F}or each
data set, 70\% of the data were used for training, and the remainder
were used to assess the generalization performance. {I}n general,
the {SVM} methodology was able to produce models with the best predictive
performance, followed by {BRANN} and then {PLSDA}. {H}owever, a small
number of data sets showed either equivalent or better predictability
using {PLSDA}, which may indicate relatively linear relationships
in these data sets. {A}ll {SVM} models showed predictive ability
(>60\% of test set predicted correctly) and five out of the 12 test
sets showed excellent prediction (>80\% prediction accuracy). {T}hese
models represent the first use of pattern recognition methods to
discriminate between substrates and nonsubstrates of human drug metabolizing
enzymes and the first thorough assessment of three classification
algorithms using multiple metabolic data sets.},
doi = {10.1021/ci034108k},
pdf = {../local/Sorich2003Comparison.pdf},
file = {Sorich2003Comparison.pdf:local/Sorich2003Comparison.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci034108k}
}
@inproceedings{Stapley2002Predicting,
author = {Stapley, B.J. and Kelley, L.A. and Sternberg, M.J.},
title = {Predicting the sub-cellular location of proteins from text using
support vector machines.},
booktitle = {Proceedings of the {P}acific {S}ymposium on {B}iocomputing 2002},
year = {2002},
editor = {Russ B. Altman and A. Keith Dunker and Lawrence Hunter and Kevin
Lauerdale and Teri E. Klein},
pages = {374-385},
publisher = {World Scientific},
abstract = {We present an automatic method to classify the sub-cellular location
of proteins based on the text of relevant medline abstracts. {F}or
each protein, a vector of terms is generated from medline abstracts
in which the protein/gene's name or synonym occurs. {A} {S}upport
{V}ector {M}achine ({SVM}) is used to automatically partition the
term space and to thus discriminate the textual features that define
sub-cellular location. {T}he method is benchmarked on a set of proteins
of known sub-cellular location from {S}. cerevisiae. {N}o prior knowledge
of the problem domain nor any natural language processing is used
at any stage. {T}he method out-performs support vector machines trained
on amino acid composition and has comparable performance to rule-based
text classifiers. {C}ombining text with protein amino-acid composition
improves recall for some sub-cellular locations. {W}e discuss the
generality of the method and its potential application to a variety
of biological classification problems.},
pdf = {../local/Stapley2002Predicting.pdf},
file = {Stapley2002Predicting.pdf:local/Stapley2002Predicting.pdf:PDF},
keywords = {biosvm},
subject = {biokernel},
url = {http://www.smi.stanford.edu/projects/helix/psb02/stapley.pdf}
}
@article{Statnikov2004Methods,
author = {Alexander Statnikov and Constantin F Aliferis and Ioannis Tsamardinos},
title = {Methods for multi-category cancer diagnosis from gene expression
data: a comprehensive evaluation to inform decision support system
development.},
journal = {Medinfo},
year = {2004},
volume = {11},
pages = {813-7},
number = {Pt 2},
abstract = {Cancer diagnosis is a major clinical applications area of gene expression
microarray technology. {W}e are seeking to develop a system for cancer
diagnostic model creation based on microarray data. {I}n order to
equip the system with the optimal combination of data modeling methods,
we performed a comprehensive evaluation of several major classification
algorithms, gene selection methods, and cross-validation designs
using 11 datasets spanning 74 diagnostic categories (41 cancer types
and 12 normal tissue types). {T}he {M}ulti-{C}ategory {S}upport {V}ector
{M}achine techniques by {C}rammer and {S}inger, {W}eston and {W}atkins,
and one-versus-rest were found to be the best methods and they outperform
other learning algorithms such as {K}-{N}earest {N}eighbors and {N}eural
{N}etworks often to a remarkable degree. {G}ene selection techniques
are shown to significantly improve classification performance. {T}hese
results guided the development of a software system that fully automates
cancer diagnostic model construction with quality on par with or
better than previously published results derived by expert human
analysts.},
keywords = {biosvm},
pii = {D040004907}
}
@article{Statnikov2005comprehensive,
author = {Statnikov, A. and Aliferis, C. F. and Tsamardinos, I. and Hardin,
D. and Levy, S.},
title = {A comprehensive evaluation of multicategory classification methods
for microarray gene expression cancer diagnosis},
journal = {Bioinformatics},
year = {2005},
note = {To appear},
abstract = {Motivation: {C}ancer diagnosis is one of the most important emerging
clinical applications of gene expression microarray technology. {W}e
are seeking to develop a computer system for powerful and reliable
cancer diagnostic model creation based on microarray data. {T}o keep
a realistic perspective on clinical applications we focus on multicategory
diagnosis. {I}n order to equip the system with the optimum combination
of classifier, gene selection and cross-validation methods, we performed
a systematic and comprehensive evaluation of several major algorithms
for multicategory classification, several gene selection methods,
multiple ensemble classifier methods, and two cross validation designs
using 11 datasets spanning 74 diagnostic categories and 41 cancer
types and 12 normal tissue types.{R}esults: {M}ulticategory {S}upport
{V}ector {M}achines ({MC}-{SVM}s) are the most effective classifiers
in performing accurate cancer diagnosis from gene expression data.
{T}he {MC}-{SVM} techniques by {C}rammer and {S}inger, {W}eston and
{W}atkins, and one-versus-rest were found to be the best methods
in this domain. {MC}-{SVM}s outperform other popular machine learning
algorithms such as {K}-{N}earest {N}eighbors, {B}ackpropagation and
{P}robabilistic {N}eural {N}etworks, often to a remarkable degree.
{G}ene selection techniques can significantly improve classification
performance of both {MC}-{SVM}s and other non-{SVM} learning algorithms.
{E}nsemble classifiers do not generally improve performance of the
best non-ensemble models. {T}hese results guided the construction
of a software system {GEMS} ({G}ene {E}xpression {M}odel {S}elector)
that automates high-quality model construction and enforces sound
optimization and performance estimation procedures. {T}his is the
first such system to be informed by a rigorous comparative analysis
of the available algorithms and datasets.{A}vailability: {T}he software
system {GEMS} is available for download from http://www.gems-system.org
for non-commercial use.},
pdf = {../local/Statnikov2005comprehensive.pdf},
file = {Statnikov2005comprehensive.pdf:local/Statnikov2005comprehensive.pdf:PDF},
keywords = {biosvm microarray},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/bti033v1}
}
@article{Steiner2004Discriminating,
author = {Guido Steiner and Laura Suter and Franziska Boess and Rodolfo Gasser
and Maria Cristina de Vera and Silvio Albertini and Stefan Ruepp},
title = {Discriminating different classes of toxicants by transcript profiling.},
journal = {Environ. {H}ealth {P}erspect.},
year = {2004},
volume = {112},
pages = {1236-48},
number = {12},
month = {Aug},
abstract = {Male rats were treated with various model compounds or the appropriate
vehicle controls. {M}ost substances were either well-known hepatotoxicants
or showed hepatotoxicity during preclinical testing. {T}he aim of
the present study was to determine if biological samples from rats
treated with various compounds can be classified based on gene expression
profiles. {I}n addition to gene expression analysis using microarrays,
a complete serum chemistry profile and liver and kidney histopathology
were performed. {W}e analyzed hepatic gene expression profiles using
a supervised learning method (support vector machines; {SVM}s) to
generate classification rules and combined this with recursive feature
elimination to improve classification performance and to identify
a compact subset of probe sets with potential use as biomarkers.
{T}wo different {SVM} algorithms were tested, and the models obtained
were validated with a compound-based external cross-validation approach.
{O}ur predictive models were able to discriminate between hepatotoxic
and nonhepatotoxic compounds. {F}urthermore, they predicted the correct
class of hepatotoxicant in most cases. {W}e provide an example showing
that a predictive model built on transcript profiles from one rat
strain can successfully classify profiles from another rat strain.
{I}n addition, we demonstrate that the predictive models identify
nonresponders and are able to discriminate between gene changes related
to pharmacology and toxicity. {T}his work confirms the hypothesis
that compound classification based on gene expression data is feasible.},
pdf = {../local/Steiner2004Discriminating.pdf},
file = {Steiner2004Discriminating.pdf:local/Steiner2004Discriminating.pdf:PDF},
keywords = {biosvm},
url = {http://ehp.niehs.nih.gov/txg/docs/2004/7036/abstract.html}
}
@article{Su2001Molecular,
author = {Su, A. I. and Welsh, J. B. and Sapinoso, L. M. and Kern, S. G. and
Dimitrov, P. and Lapp, H. and Schultz, P. G. and Powell, S. M. and
Moskaluk, C. A. and Frierson, H. F.Jr. and Hampton, G. M.},
title = {Molecular {C}lassification of {H}uman {C}arcinomas by {U}se of {G}ene
{E}xpression {S}ignatures},
journal = {Cancer {R}es.},
year = {2001},
volume = {61},
pages = {7388-7393},
number = {20},
abstract = {Classification of human tumors according to their primary anatomical
site of origin is fundamental for the optimal treatment of patients
with cancer. {H}ere we describe the use of large-scale {RNA} profiling
and supervised machine learning algorithms to construct a first-generation
molecular classification scheme for carcinomas of the prostate, breast,
lung, ovary, colorectum, kidney, liver, pancreas, bladder/ureter,
and gastroesophagus, which collectively account for [~]70% of all
cancer-related deaths in the {U}nited {S}tates. {T}he classification
scheme was based on identifying gene subsets whose expression typifies
each cancer class, and we quantified the extent to which these genes
are characteristic of a specific tumor type by accurately and confidently
predicting the anatomical site of tumor origin for 90% of 175 carcinomas,
including 9 of 12 metastatic lesions. {T}he predictor gene subsets
include those whose expression is typical of specific types of normal
epithelial differentiation, as well as other genes whose expression
is elevated in cancer. {T}his study demonstrates the feasibility
of predicting the tissue origin of a carcinoma in the context of
multiple cancer classes.},
pdf = {../local/Su2001Molecular.pdf.html},
file = {Su2001Molecular.pdf.html:local/Su2001Molecular.pdf.html:PDF},
keywords = {biosvm, breastcancer},
owner = {jeanphilippevert},
url = {http://cancerres.aacrjournals.org/cgi/content/abstract/61/20/7388}
}
@article{Su2003RankGene,
author = {Su, Yang and Murali, T.M. and Pavlovic, Vladimir and Schaffer, Michael
and Kasif, Simon},
title = {{{R}ank{G}ene}: identification of diagnostic genes based on expression
data},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {1578-1579},
number = {12},
abstract = {Summary: {R}ank{G}ene is a program for analyzing gene expression data
and computing diagnostic genes based on their predictive power in
distinguishing between different types of samples. {T}he program
integrates into one system a variety of popular ranking criteria,
ranging from the traditional t-statistic to one-dimensional support
vector machines. {T}his flexibility makes {R}ank{G}ene a useful tool
in gene expression analysis and feature selection. {A}vailability:
http://genomics10.bu.edu/yangsu/rankgene {C}ontact: murali@bu.edu},
pdf = {../local/Su2003RankGene.pdf},
file = {Su2003RankGene.pdf:local/Su2003RankGene.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/12/1578}
}
@article{Sun2003Identifying,
author = {Sun, Y.F. and Fan, X.D. and Li, Y.D.},
title = {Identifying splicing sites in eukaryotic {RNA}: support vector machine
approach.},
journal = {Comput. {B}iol. {M}ed.},
year = {2003},
volume = {33},
pages = {17-29},
number = {1},
abstract = {We introduce a new method for splicing sites prediction based on the
theory of support vector machines ({SVM}). {T}he {SVM} represents
a new approach to supervised pattern classification and has been
successfully applied to a wide range of pattern recognition problems.
{I}n the process of splicing sites prediction, the statistical information
of {RNA} secondary structure in the vicinity of splice sites, e.g.
donor and acceptor sites, is introduced in order to compare recognition
ratio of true positive and true negative. {F}rom the results of comparison,
addition of structural information has brought no significant benefit
for the recognition of splice sites and had even lowered the rate
of recognition. {O}ur results suggest that, through three cross validation,
the {SVM} method can achieve a good performance for splice sites
identification.},
doi = {10.1016/S0010-4825(02)00057-4},
pdf = {../local/Sun2003Identifying.pdf},
file = {Sun2003Identifying.pdf:local/Sun2003Identifying.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/S0010-4825(02)00057-4}
}
@article{Swamidass2005Kernels,
author = {Swamidass, S. J. and Chen, J. and Bruand, J. and Phung, P. and Ralaivola,
L. and Baldi, P.},
title = {Kernels for small molecules and the prediction of mutagenicity, toxicity
and anti-cancer activity.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {i359-i368},
number = {Suppl. 1},
month = {Jun},
abstract = {M{OTIVATION}: {S}mall molecules play a fundamental role in organic
chemistry and biology. {T}hey can be used to probe biological systems
and to discover new drugs and other useful compounds. {A}s increasing
numbers of large datasets of small molecules become available, it
is necessary to develop computational methods that can deal with
molecules of variable size and structure and predict their physical,
chemical and biological properties. {RESULTS}: {H}ere we develop
several new classes of kernels for small molecules using their 1{D},
2{D} and 3{D} representations. {I}n 1{D}, we consider string kernels
based on {SMILES} strings. {I}n 2{D}, we introduce several similarity
kernels based on conventional or generalized fingerprints. {G}eneralized
fingerprints are derived by counting in different ways subpaths contained
in the graph of bonds, using depth-first searches. {I}n 3{D}, we
consider similarity measures between histograms of pairwise distances
between atom classes. {T}hese kernels can be computed efficiently
and are applied to problems of classification and prediction of mutagenicity,
toxicity and anti-cancer activity on three publicly available datasets.
{T}he results derived using cross-validation methods are state-of-the-art.
{T}radeoffs between various kernels are briefly discussed. {AVAILABILITY}:
{D}atasets available from http://www.igb.uci.edu/servers/servers.html
{CONTACT}: pfbaldi@ics.uci.edu.},
doi = {10.1093/bioinformatics/bti1055},
pdf = {../local/Swamidass2005Kernels.pdf},
file = {Swamidass2005Kernels.pdf:Swamidass2005Kernels.pdf:PDF},
keywords = {biosvm},
pii = {21/suppl_1/i359},
url = {http://dx.doi.org/10.1093/bioinformatics/bti1055}
}
@article{Takaoka2003Development,
author = {Y. Takaoka and Y. Endo and S. Yamanobe and H. Kakinuma and T. Okubo
and Y. Shimazaki and T. Ota and S. Sumiya and K. Yoshikawa},
title = {Development of a method for evaluating drug-likeness and ease of
synthesis using a data set in which compounds are assigned scores
based on chemists' intuition.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2003},
volume = {43},
pages = {1269-75},
number = {4},
abstract = {The concept of drug-likeness, an important characteristic for any
compound in a screening library, is nevertheless difficult to pin
down. {B}ased on our belief that this concept is implicit within
the collective experience of working chemists, we devised a data
set to capture an intuitive human understanding of both this characteristic
and ease of synthesis, a second key characteristic. {F}ive chemists
assigned a pair of scores to each of 3980 diverse compounds, with
the component scores of each pair corresponding to drug-likeness
and ease of synthesis, respectively. {U}sing this data set, we devised
binary classifiers with an artificial neural network and a support
vector machine. {T}hese models were found to efficiently eliminate
compounds that are not drug-like and/or hard-to-synthesize derivatives,
demonstrating the suitability of these models for use as compound
acquisition filters.},
doi = {10.1021/ci034043l},
pdf = {../local/Takaoka2003Development.pdf},
file = {Takaoka2003Development.pdf:local/Takaoka2003Development.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci034043l}
}
@article{Takeuchi2005Bio-medical,
author = {Koichi Takeuchi and Nigel Collier},
title = {Bio-medical entity extraction using support vector machines.},
journal = {Artif. {I}ntell. {M}ed.},
year = {2005},
volume = {33},
pages = {125-37},
number = {2},
month = {Feb},
abstract = {O{BJECTIVE}: {S}upport vector machines ({SVM}s) have achieved state-of-the-art
performance in several classification tasks. {I}n this article we
apply them to the identification and semantic annotation of scientific
and technical terminology in the domain of molecular biology. {T}his
illustrates the extensibility of the traditional named entity task
to special domains with large-scale terminologies such as those in
medicine and related disciplines. {METHODS} {AND} {MATERIALS}: {T}he
foundation for the model is a sample of text annotated by a domain
expert according to an ontology of concepts, properties and relations.
{T}he model then learns to annotate unseen terms in new texts and
contexts. {T}he results can be used for a variety of intelligent
language processing applications. {W}e illustrate {SVM}s capabilities
using a sample of 100 journal abstracts texts taken from the {human,
blood cell, transcription factor} domain of {MEDLINE}. {RESULTS}:
{A}pproximately 3400 terms are annotated and the model performs at
about 74\% {F}-score on cross-validation tests. {A} detailed analysis
based on empirical evidence shows the contribution of various feature
sets to performance. {CONCLUSION}: {O}ur experiments indicate a relationship
between feature window size and the amount of training data and that
a combination of surface words, orthographic features and head noun
features achieve the best performance among the feature sets tested.},
doi = {10.1016/j.artmed.2004.07.019},
pdf = {../local/Takeuchi2005Bio-medical.pdf},
file = {Takeuchi2005Bio-medical.pdf:local/Takeuchi2005Bio-medical.pdf:PDF},
keywords = {biosvm},
pii = {S0933-3657(04)00130-7},
url = {http://dx.doi.org/10.1016/j.artmed.2004.07.019}
}
@article{Tang2005Discovering,
author = {Thomas Tang and Jinbo Xu and Ming Li},
title = {Discovering sequence-structure motifs from protein segments and two
applications.},
journal = {Pac {S}ymp {B}iocomput},
year = {2005},
pages = {370-81},
abstract = {We present a novel method for clustering short protein segments having
strong sequence-structure correlations, and demonstrate that these
clusters contain useful structural information via two applications.
{W}hen applied to local tertiary structure prediction, we achieve
approximately 60\% accuracy with a novel dynamic programming algorithm.
{W}hen applied to secondary structure prediction based on {S}upport
{V}ector {M}achines, we obtain a approximately 2\% gain in {Q}3 performance
by incorporating cluster-derived data into training and classification.
{T}hese encouraging results illustrate the great potential of using
conserved local motifs to tackle protein structure predictions and
possibly other important problems in biology.},
keywords = {biosvm}
}
@article{Teramoto2005Prediction,
author = {Reiji Teramoto and Mikio Aoki and Toru Kimura and Masaharu Kanaoka},
title = {Prediction of si{RNA} functionality using generalized string kernel
and support vector machine.},
journal = {F{EBS} {L}ett.},
year = {2005},
volume = {579},
pages = {2878-82},
number = {13},
month = {May},
abstract = {Small interfering {RNA}s (si{RNA}s) are becoming widely used for sequence-specific
gene silencing in mammalian cells, but designing an effective si{RNA}
is still a challenging task. {I}n this study, we developed an algorithm
for predicting si{RNA} functionality by using generalized string
kernel ({GSK}) combined with support vector machine ({SVM}). {W}ith
{GSK}, si{RNA} sequences were represented as vectors in a multi-dimensional
feature space according to the numbers of subsequences in each si{RNA},
and subsequently classified with {SVM} into effective or ineffective
si{RNA}s. {W}e applied this algorithm to published si{RNA}s, and
could classify effective and ineffective si{RNA}s with 90.6\%, 86.2\%
accuracy, respectively.},
doi = {10.1016/j.febslet.2005.04.045},
pdf = {../local/Teramoto2005Prediction.pdf},
file = {Teramoto2005Prediction.pdf:local/Teramoto2005Prediction.pdf:PDF},
keywords = {sirna biosvm},
pii = {S0014-5793(05)00520-X},
url = {http://dx.doi.org/10.1016/j.febslet.2005.04.045}
}
@article{Tobita2005discriminant,
author = {Tobita, M. and Nishikawa, T. and Nagashima, R.},
title = {A discriminant model constructed by the support vector machine method
for {HERG} potassium channel inhibitors.},
journal = {Bioorg. {M}ed. {C}hem. {L}ett.},
year = {2005},
volume = {15},
pages = {2886-90},
number = {11},
month = {Jun},
abstract = {H{ERG} attracts attention as a risk factor for arrhythmia, which might
trigger torsade de pointes. {A} highly accurate classifier of chemical
compounds for inhibition of the {HERG} potassium channel is constructed
using support vector machine. {F}or two test sets, our discriminant
models achieved 90\% and 95\% accuracy, respectively. {T}he classifier
is even applied for the prediction of cardio vascular adverse effects
to achieve about 70\% accuracy. {W}hile modest inhibitors are partly
characterized by properties linked to global structure of a molecule
including hydrophobicity and diameter, strong inhibitors are exclusively
characterized by properties linked to substructures of a molecule.},
doi = {10.1016/j.bmcl.2005.03.080},
pdf = {../local/Tobita2005discriminant.pdf},
file = {Tobita2005discriminant.pdf:local/Tobita2005discriminant.pdf:PDF},
keywords = {biosvm chemoinformatics herg},
pii = {S0960-894X(05)00403-8},
url = {http://dx.doi.org/10.1016/j.bmcl.2005.03.080}
}
@article{Tothill2005expression-based,
author = {Richard W Tothill and Adam Kowalczyk and Danny Rischin and Alex Bousioutas
and Izhak Haviv and Ryan K van Laar and Paul M Waring and John Zalcberg
and Robyn Ward and Andrew V Biankin and Robert L Sutherland and Susan
M Henshall and Kwun Fong and Jonathan R Pollack and David D L Bowtell
and Andrew J Holloway},
title = {An expression-based site of origin diagnostic method designed for
clinical application to cancer of unknown origin.},
journal = {Cancer {R}es.},
year = {2005},
volume = {65},
pages = {4031-40},
number = {10},
month = {May},
abstract = {Gene expression profiling offers a promising new technique for the
diagnosis and prognosis of cancer. {W}e have applied this technology
to build a clinically robust site of origin classifier with the ultimate
aim of applying it to determine the origin of cancer of unknown primary
({CUP}). {A} single c{DNA} microarray platform was used to profile
229 primary and metastatic tumors representing 14 tumor types and
multiple histologic subtypes. {T}his data set was subsequently used
for training and validation of a support vector machine ({SVM}) classifier,
demonstrating 89\% accuracy using a 13-class model. {F}urther, we
show the translation of a five-class classifier to a quantitative
{PCR}-based platform. {S}electing 79 optimal gene markers, we generated
a quantitative-{PCR} low-density array, allowing the assay of both
fresh-frozen and formalin-fixed paraffin-embedded ({FFPE}) tissue.
{D}ata generated using both quantitative {PCR} and microarray were
subsequently used to train and validate a cross-platform {SVM} model
with high prediction accuracy. {F}inally, we applied our {SVM} classifiers
to 13 cases of {CUP}. {W}e show that the microarray {SVM} classifier
was capable of making high confidence predictions in 11 of 13 cases.
{T}hese predictions were supported by comprehensive review of the
patients' clinical histories.},
doi = {10.1158/0008-5472.CAN-04-3617},
pdf = {../local/Tothill2005expression-based.pdf},
file = {Tothill2005expression-based.pdf:Tothill2005expression-based.pdf:PDF},
keywords = {biosvm microarray},
pii = {65/10/4031},
url = {http://dx.doi.org/10.1158/0008-5472.CAN-04-3617}
}
@article{Tsai2004Gene,
author = {Tsai, C.A. and Chen, C.H. and Lee, T.C. and Ho, I.C. and Yang, U.C.
and Chen, J.J.},
title = {Gene selection for sample classifications in microarray experiments.},
journal = {D{NA} {C}ell {B}iol.},
year = {2004},
volume = {23},
pages = {607-614},
number = {10},
abstract = {D{NA} microarray technology provides useful tools for profiling global
gene expression patterns in different cell/tissue samples. {O}ne
major challenge is the large number of genes relative to the number
of samples. {T}he use of all genes can suppress or reduce the performance
of a classification rule due to the noise of nondiscriminatory genes.
{S}election of an optimal subset from the original gene set becomes
an important prestep in sample classification. {I}n this study, we
propose a family-wise error ({FWE}) rate approach to selection of
discriminatory genes for two-sample or multiple-sample classification.
{T}he {FWE} approach controls the probability of the number of one
or more false positives at a prespecified level. {A} public colon
cancer data set is used to evaluate the performance of the proposed
approach for the two classification methods: k nearest neighbors
(k-{NN}) and support vector machine ({SVM}). {T}he selected gene
sets from the proposed procedure appears to perform better than or
comparable to several results reported in the literature using the
univariate analysis without performing multivariate search. {I}n
addition, we apply the {FWE} approach to a toxicogenomic data set
with nine treatments (a control and eight metals, {A}s, {C}d, {N}i,
{C}r, {S}b, {P}b, {C}u, and {A}s{V}) for a total of 55 samples for
a multisample classification. {T}wo gene sets are considered: the
gene set omega{F} formed by the {ANOVA} {F}-test, and a gene set
omega{T} formed by the union of one-versus-all t-tests. {T}he predicted
accuracies are evaluated using the internal and external crossvalidation.
{U}sing the {SVM} classification, the overall accuracies to predict
55 samples into one of the nine treatments are above 80% for internal
crossvalidation. {O}mega{F} has slightly higher accuracy rates than
omega{T}. {T}he overall predicted accuracies are above 70% for the
external crossvalidation; the two gene sets omega{T} and omega{F}
performed equally well.},
doi = {10.1089/1044549042476947},
pdf = {../local/Tsai2004Gene.pdf},
file = {Tsai2004Gene.pdf:local/Tsai2004Gene.pdf:PDF},
keywords = {biosvm microarray},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1089/1044549042476947}
}
@article{Tsirigos2005sensitive,
author = {Tsirigos, A. and Rigoutsos, I.},
title = {A sensitive, support-vector-machine method for the detection of horizontal
gene transfers in viral, archaeal and bacterial genomes.},
journal = {Nucleic {A}cids {R}es.},
year = {2005},
volume = {33},
pages = {3699-707},
number = {12},
abstract = {In earlier work, we introduced and discussed a generalized computational
framework for identifying horizontal transfers. {T}his framework
relied on a gene's nucleotide composition, obviated the need for
knowledge of codon boundaries and database searches, and was shown
to perform very well across a wide range of archaeal and bacterial
genomes when compared with previously published approaches, such
as {C}odon {A}daptation {I}ndex and {C} + {G} content. {N}onetheless,
two considerations remained outstanding: we wanted to further increase
the sensitivity of detecting horizontal transfers and also to be
able to apply the method to increasingly smaller genomes. {I}n the
discussion that follows, we present such a method, {W}n-{SVM}, and
show that it exhibits a very significant improvement in sensitivity
compared with earlier approaches. {W}n-{SVM} uses a one-class support-vector
machine and can learn using rather small training sets. {T}his property
makes {W}n-{SVM} particularly suitable for studying small-size genomes,
similar to those of viruses, as well as the typically larger archaeal
and bacterial genomes. {W}e show experimentally that the new method
results in a superior performance across a wide range of organisms
and that it improves even upon our own earlier method by an average
of 10\% across all examined genomes. {A}s a small-genome case study,
we analyze the genome of the human cytomegalovirus and demonstrate
that {W}n-{SVM} correctly identifies regions that are known to be
conserved and prototypical of all beta-herpesvirinae, regions that
are known to have been acquired horizontally from the human host
and, finally, regions that had not up to now been suspected to be
horizontally transferred. {A}typical region predictions for many
eukaryotic viruses, including the alpha-, beta- and gamma-herpesvirinae,
and 123 archaeal and bacterial genomes, have been made available
online at http://cbcsrv.watson.ibm.com/{HGT}_{SVM}/.},
doi = {10.1093/nar/gki660},
pdf = {../local/Tsirigos2005sensitive.pdf},
file = {Tsirigos2005sensitive.pdf:local/Tsirigos2005sensitive.pdf:PDF},
keywords = {biosvm},
pii = {33/12/3699},
url = {http://dx.doi.org/10.1093/nar/gki660}
}
@article{Tsuda2003em,
author = {Tsuda, K. and Akaho, S. and Asai, K.},
title = {The em {A}lgorithm for {K}ernel {M}atrix {C}ompletion with {A}uxiliary
{D}ata},
journal = {J. {M}ach. {L}earn. {R}es.},
year = {2003},
volume = {4},
pages = {67-81},
abstract = {In biological data, it is often the case that observed data are available
only for a subset of samples. {W}hen a kernel matrix is derived from
such data, we have to leave the entries for unavailable samples as
missing. {I}n this paper, the missing entries are completed by exploiting
an auxiliary kernel matrix derived from another information source.
{T}he parametric model of kernel matrices is created as a set of
spectral variants of the auxiliary kernel matrix, and the missing
entries are estimated by fitting this model to the existing entries.
{F}or model fitting, we adopt the em algorithm (distinguished from
the {EM} algorithm of {D}empster et al., 1977) based on the information
geometry of positive definite matrices. {W}e will report promising
results on bacteria clustering experiments using two marker sequences:
16{S} and gyr{B}.},
pdf = {../local/Tsuda2003em.pdf},
file = {Tsuda2003em.pdf:local/Tsuda2003em.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.jmlr.org/papers/v4/tsuda03a.html}
}
@article{Tsuda2002new,
author = {K. Tsuda and M. Kawanabe and G. R{\"a}tsch and S. Sonnenburg and
K.-R. M{\"u}ller},
title = {A new discriminative kernel from probabilistic models},
journal = {Neural {C}omputation},
year = {2002},
volume = {14},
pages = {2397--2414},
number = {10},
doi = {10.1162/08997660260293274},
pdf = {../local/Tsuda2002new.pdf},
file = {Tsuda2002new.pdf:local/Tsuda2002new.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1162/08997660260293274}
}
@article{Tsuda2002Marginalized,
author = {K. Tsuda and T. Kin and K. Asai},
title = {Marginalized {K}ernels for {B}iological {S}equences},
journal = {Bioinformatics},
year = {2002},
volume = {18},
pages = {S268--S275},
abstract = {Motivation: {K}ernel methods such as support vector machines require
a kernel function between objects to be defined a priori. {S}everal
works have been done to derive kernels from probability distributions,
e.g., the {F}isher kernel. {H}owever, a general methodology to design
a kernel is not fully developed. {R}esults: {W}e propose a reasonable
way of designing a kernel when objects are generated from latent
variable models (e.g., {HMM}). {F}irst of all, a joint kernel is
designed for complete data which include both visible and hidden
variables. {T}hen a marginalized kernel for visible data is obtained
by taking the expectation with respect to hidden variables. {W}e
will show that the {F}isher kernel is a special case of marginalized
kernels, which gives another viewpoint to the {F}isher kernel theory.
{A}lthough our approach can be applied to any object, we particularly
derive several marginalized kernels useful for biological sequences
(e.g., {DNA} and proteins). {T}he effectiveness of marginalized kernels
is illustrated in the task of classifying bacterial gyrase subunit
{B} (gyr{B}) amino acid sequences.},
comment = {Introduces the idea of marginalized kernel. Show that the Fisher kernel
is a particular case of it, and modify it. Application to bacterial
gyrB classification.},
pdf = {../local/Tsuda2002Marginalized.pdf},
file = {Tsuda2002Marginalized.pdf:local/Tsuda2002Marginalized.pdf:PDF},
keywords = {biosvm}
}
@article{Tsuda2004Learning,
author = {Tsuda, K. and Noble, W.S.},
title = {Learning kernels from biological networks by maximizing entropy},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {i326--i333},
abstract = {Motivation: {T}he diffusion kernel is a general method for computing
pairwise distances among all nodes in a graph, based on the sum of
weighted paths between each pair of nodes. {T}his technique has been
used successfully, in conjunction with kernel-based learning methods,
to draw inferences from several types of biological networks. {R}esults:
{W}e show that computing the diffusion kernel is equivalent to maximizing
the von {N}eumann entropy, subject to a global constraint on the
sum of the {E}uclidean distances between nodes. {T}his global constraint
allows for high variance in the pairwise distances. {A}ccordingly,
we propose an alternative, locally constrained diffusion kernel,
and we demonstrate that the resulting kernel allows for more accurate
support vector machine prediction of protein functional classifications
from metabolic and protein?protein interaction networks. {A}vailability:
{S}upplementary results and data are available at noble.gs.washington.edu/proj/maxent},
comment = {Problem = multiclass classification of tumor cells from gene expression.
Show that the one-versus-all approach of combining SVM yields the
minimum number of classification errors on their Affymetrix data
with 14 tumor types. In addition to not taking variability estimates
of repeated measurements into account, this approach selects different
relevant features (genes) for each binary classifier.},
doi = {10.1093/bioinformatics/bth906},
pdf = {../local/Tsuda2004Learning.pdf},
file = {Tsuda2004Learning.pdf:local/Tsuda2004Learning.pdf:PDF},
keywords = {learning-kernel graph-kernel biosvm},
owner = {vert},
url = {http://dx.doi.org/10.1093/bioinformatics/bth906}
}
@article{Valentini2002Gene,
author = {Valentini, G.},
title = {Gene expression data analysis of human lymphoma using support vector
machines and output coding ensembles.},
journal = {Artif. {I}ntell. {M}ed.},
year = {2002},
volume = {26},
pages = {281-304},
number = {3},
month = {Nov},
abstract = {The large amount of data generated by {DNA} microarrays was originally
analysed using unsupervised methods, such as clustering or self-organizing
maps. {R}ecently supervised methods such as decision trees, dot-product
support vector machines ({SVM}) and multi-layer perceptrons ({MLP})
have been applied in order to classify normal and tumoural tissues.
{W}e propose methods based on non-linear {SVM} with polynomial and
{G}aussian kernels, and output coding ({OC}) ensembles of learning
machines to separate normal from malignant tissues, to classify different
types of lymphoma and to analyse the role of sets of coordinately
expressed genes in carcinogenic processes of lymphoid tissues. {U}sing
gene expression data from "{L}ymphochip", a specialised {DNA} microarray
developed at {S}tanford {U}niversity {S}chool of {M}edicine, we show
that {SVM} can correctly separate normal from tumoural tissues, and
{OC} ensembles can be successfully used to classify different types
of lymphoma. {M}oreover, we identify a group of coordinately expressed
genes related to the separation of two distinct subgroups inside
diffuse large {B}-cell lymphoma ({DLBCL}), validating a previous
{A}lizadeh's hypothesis about the existence of two distinct diseases
inside {DLBCL}.},
doi = {10.1016/S0933-3657(02)00077},
pdf = {../local/Valentini2002Gene.pdf},
file = {Valentini2002Gene.pdf:local/Valentini2002Gene.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@inproceedings{Vert2002Support,
author = {Vert, J.-P.},
title = {Support vector machine prediction of signal peptide cleavage site
using a new class of kernels for strings},
booktitle = {Proceedings of the {P}acific {S}ymposium on {B}iocomputing 2002},
year = {2002},
editor = {R. B. Altman and A. K. Dunker and L. Hunter and K. Lauerdale and
T. E. Klein},
pages = {649--660},
publisher = {World Scientific},
pdf = {../local/vert02.pdf},
file = {vert02.pdf:local/vert02.pdf:PDF},
keywords = {biosvm},
subject = {biokernel},
url = {http://www.smi.stanford.edu/projects/helix/psb02/vert.pdf}
}
@techreport{Vert2005Kernel,
author = {Vert, J.-P.},
title = {Kernel methods in computational biology},
institution = {CNRS-HAL},
year = {2005},
number = {ccsd-00012124},
month = {Oct},
abstract = {Support vector machines and kernel methods are increasingly popular
in genomics and computational biology, due to their good performance
in real-world applications and strong modularity that makes them
suitable to a wide range of problems, from the classification of
tumors to the automatic annotation of proteins. {T}heir ability to
work in high dimension, to process non-vectorial data, and the natural
framework they provide to integrate heterogeneous data are particularly
relevant to various problems arising in computational biology. {I}n
this chapter we survey some of the most prominent applications published
so far, highlighting the particular developments in kernel methods
triggered by problems in biology, and mention a few promising research
directions likely to expand in the future.},
pdf = {../local/Vert2005Kernel.pdf},
file = {Vert2005Kernel.pdf:local/Vert2005Kernel.pdf:PDF},
keywords = {biosvm},
url = {http://hal.ccsd.cnrs.fr/ccsd-00012124}
}
@article{Vert2002tree,
author = {Vert, J.-P.},
title = {A tree kernel to analyze phylogenetic profiles},
journal = {Bioinformatics},
year = {2002},
volume = {18},
pages = {S276--S284},
pdf = {../local/vert02b.pdf},
file = {vert02b.pdf:local/vert02b.pdf:PDF},
keywords = {biosvm},
subject = {biokernel},
url = {http://cbio.ensmp.fr/~jvert/publi/ismb02/index.html}
}
@inproceedings{Vert2003Graph-driven,
author = {Vert, J.-P. and Kanehisa, M.},
title = {Graph-driven features extraction from microarray data using diffusion
kernels and kernel {CCA}},
booktitle = {Adv. {N}eural {I}nform. {P}rocess. {S}yst.},
year = {2003},
editor = {S. Becker and S. Thrun and K. Obermayer},
pages = {1449--1456},
publisher = {MIT Press},
pdf = {../local/Vert2003Graph-driven.pdf},
file = {Vert2003Graph-driven.pdf:local/Vert2003Graph-driven.pdf:PDF},
keywords = {biosvm}
}
@article{Vert2003Extracting,
author = {Vert, J.-P. and Kanehisa, M. },
title = {Extracting active pathways from gene expression data},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {238ii-234ii},
abstract = {Motivation: {A} promising way to make sense out of gene expression
profiles is to relate them to the activity of metabolic and signalling
pathways. {E}ach pathway usually involves many genes, such as enzymes,
which can themselves participate in many pathways. {T}he set of all
known pathways can therefore be represented by a complex network
of genes. {S}earching for regularities in the set of gene expression
profiles with respect to the topology of this gene network is a way
to automatically extract active pathways and their associated patterns
of activity. {M}ethod: {W}e present a method to perform this task,
which consists in encoding both the gene network and the set of profiles
into two kernel functions, and performing a regularized form of canonical
correlation analysis between the two kernels. {R}esults: {W}hen applied
to publicly available expression data the method is able to extract
biologically relevant expression patterns, as well as pathways with
related activity.},
pdf = {../local/Vert2003Extracting.pdf},
file = {Vert2003Extracting.pdf:local/Vert2003Extracting.pdf:PDF},
keywords = {biosvm},
owner = {vert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/suppl_2/ii238}
}
@techreport{Vert2002Graph-driven,
author = {Vert, J.-P. and Kanehisa, M.},
title = {Graph-driven features extraction from microarray data},
institution = {Arxiv physics},
year = {2002},
number = {0206055},
keywords = {biosvm}
}
@incollection{Vert2004Local,
author = {Vert, J.-P. and Saigo, H. and Akutsu, T.},
title = {Local alignment kernels for biological sequences},
booktitle = {Kernel {M}ethods in {C}omputational {B}iology},
publisher = {MIT Press},
year = {2004},
editor = {Sch{\"o}lkopf, B. and Tsuda, K. and Vert, J.P.},
pages = {131-154},
address = {The MIT Press, Cambridge, Massachussetts},
pdf = {../local/saigo.pdf:http\},
file = {saigo.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/saigo.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@inproceedings{Vert2006Kernels,
author = {Vert, J.-P. and Thurman, R. and Noble, W. S.},
title = {Kernels for gene regulatory regions},
booktitle = {Adv. {N}eural. {I}nform. {P}rocess {S}yst.},
year = {2006},
editor = {Y. Weiss and B. Sch\"{o}lkopf and J. Platt},
volume = {18},
pages = {1401-1408},
address = {Cambridge, MA},
publisher = {MIT Press},
keywords = {biosvm}
}
@incollection{Vert2004primer,
author = {Vert, J.-P. and Tsuda, K. and Sch{\"o}lkopf, B.},
title = {A primer on kernel methods},
booktitle = {Kernel {M}ethods in {C}omputational {B}iology},
publisher = {MIT Press},
year = {2004},
editor = {Schölkopf, B. and Tsuda, K. and Vert, J.P.},
pages = {35-70},
keywords = {biosvm},
owner = {vert}
}
@inproceedings{Vert2005Supervised,
author = {Vert, J.-P. and Yamanishi, Y.},
title = {Supervised graph inference},
booktitle = {Adv. {N}eural {I}nform. {P}rocess. {S}yst.},
year = {2005},
editor = {Saul, L. K. and Weiss, Y. and Bottou, L.},
volume = {17},
pages = {1433-1440},
publisher = {MIT Press, Cambridge, MA},
pdf = {../local/nips2004.pdf:http\://cg.ensmp.fr/~vert/publi/04nips_yamanishi/nips2004.pdf:PDF;nips2004.pdf:http\},
file = {nips2004.pdf:http\://cg.ensmp.fr/~vert/publi/04nips_yamanishi/nips2004.pdf:PDF;nips2004.pdf:http\://cg.ensmp.fr/~vert/publi/04nips_yamanishi/nips2004.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@article{Vinayagam2004Applying,
author = {Vinayagam, A. and König, R. and Moormann, J. and Schubert, F. and
Eils, R. and Glatting, K.-H. and Suhai, S.},
title = {Applying {S}upport {V}ector {M}achines for {G}ene {O}ntology based
gene function prediction.},
journal = {B{MC} {B}ioinformatics},
year = {2004},
volume = {5},
pages = {116},
number = {1},
month = {Aug},
abstract = {B{ACKGROUND}: {T}he current progress in sequencing projects calls
for rapid, reliable and accurate function assignments of gene products.
{A} variety of methods has been designed to annotate sequences on
a large scale. {H}owever, these methods can either only be applied
for specific subsets, or their results are not formalised, or they
do not provide precise confidence estimates for their predictions.
{RESULTS}: {W}e have developed a large-scale annotation system that
tackles all of these shortcomings. {I}n our approach, annotation
was provided through {G}ene {O}ntology terms by applying multiple
{S}upport {V}ector {M}achines ({SVM}) for the classification of correct
and false predictions. {T}he general performance of the system was
benchmarked with a large dataset. {A}n organism-wise cross-validation
was performed to define confidence estimates, resulting in an average
precision of 80\% for 74\% of all test sequences. {T}he validation
results show that the prediction performance was organism-independent
and could reproduce the annotation of other automated systems as
well as high-quality manual annotations. {W}e applied our trained
classification system to {X}enopus laevis sequences, yielding functional
annotation for more than half of the known expressed genome. {C}ompared
to the currently available annotation, we provided more than twice
the number of contigs with good quality annotation, and additionally
we assigned a confidence value to each predicted {GO} term. {CONCLUSIONS}:
{W}e present a complete automated annotation system that overcomes
many of the usual problems by applying a controlled vocabulary of
{G}ene {O}ntology and an established classification method on large
and well-described sequence data sets. {I}n a case study, the function
for {X}enopus laevis contig sequences was predicted and the results
are publicly available at ftp://genome.dkfz-heidelberg.de/pub/agd/gene_association.agd_{X}enopus.},
doi = {10.1186/1471-2105-5-116},
pdf = {../local/Vinayagam2004Applying.pdf},
file = {Vinayagam2004Applying.pdf:local/Vinayagam2004Applying.pdf:PDF},
keywords = {biosvm},
pii = {1471-2105-5-116},
url = {http://dx.doi.org/10.1186/1471-2105-5-116}
}
@article{Vlahovicek2005SBASE,
author = {Kristian Vlahovicek and László Kaján and Vilmos Agoston and Sándor
Pongor},
title = {The {SBASE} domain sequence resource, release 12: prediction of protein
domain-architecture using support vector machines.},
journal = {Nucleic {A}cids {R}es},
year = {2005},
volume = {33},
pages = {D223-5},
number = {Database issue},
month = {Jan},
abstract = {S{BASE} (http://www.icgeb.trieste.it/sbase) is an online resource
designed to facilitate the detection of domain homologies based on
sequence database search. {T}he present release of the {SBASE} {A}
library of protein domain sequences contains 972,397 protein sequence
segments annotated by structure, function, ligand-binding or cellular
topology, clustered into 8547 domain groups. {SBASE} {B} contains
169,916 domain sequences clustered into 2526 less well-characterized
groups. {D}omain prediction is based on an evaluation of database
search results in comparison with a 'similarity network' of inter-sequence
similarity scores, using support vector machines trained on similarity
search results of known domains.},
doi = {10.1093/nar/gki112},
pdf = {../local/Vlahovicek2005SBASE.pdf},
file = {Vlahovicek2005SBASE.pdf:local/Vlahovicek2005SBASE.pdf:PDF},
keywords = {biosvm},
pii = {33/suppl_1/D223},
url = {http://dx.doi.org/10.1093/nar/gki112}
}
@article{Wagner2003Protocols,
author = {Wagner, M. and Naik, D. and Pothen, A.},
title = {Protocols for disease classification from mass spectrometry data.},
journal = {Proteomics},
year = {2003},
volume = {3},
pages = {1692-1698},
number = {9},
abstract = {We report our results in classifying protein matrix-assisted laser
desorption/ionization-time of flight mass spectra obtained from serum
samples into diseased and healthy groups. {W}e discuss in detail
five of the steps in preprocessing the mass spectral data for biomarker
discovery, as well as our criterion for choosing a small set of peaks
for classifying the samples. {C}ross-validation studies with four
selected proteins yielded misclassification rates in the 10-15% range
for all the classification methods. {T}hree of these proteins or
protein fragments are down-regulated and one up-regulated in lung
cancer, the disease under consideration in this data set. {W}hen
cross-validation studies are performed, care must be taken to ensure
that the test set does not influence the choice of the peaks used
in the classification. {M}isclassification rates are lower when both
the training and test sets are used to select the peaks used in classification
versus when only the training set is used. {T}his expectation was
validated for various statistical discrimination methods when thirteen
peaks were used in cross-validation studies. {O}ne particular classification
method, a linear support vector machine, exhibited especially robust
performance when the number of peaks was varied from four to thirteen,
and when the peaks were selected from the training set alone. {E}xperiments
with the samples randomly assigned to the two classes confirmed that
misclassification rates were significantly higher in such cases than
those observed with the true data. {T}his indicates that our findings
are indeed significant. {W}e found closely matching masses in a database
for protein expression in lung cancer for three of the four proteins
we used to classify lung cancer. {D}ata from additional samples,
increased experience with the performance of various preprocessing
techniques, and affirmation of the biological roles of the proteins
that help in classification, will strengthen our conclusions in the
future.},
doi = {10.1002/pmic.200300519},
pdf = {../local/Wagner2003Protocols.pdf},
file = {Wagner2003Protocols.pdf:local/Wagner2003Protocols.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/pmic.200300519}
}
@article{Wagner2004Computational,
author = {Wagner, M. and Naik, D.N. and Pothen, A. and Kasukurti, S. and Devineni,
R.R. and Adam, B.L. and Semmes, O.J. and Wright Jr, G.L.},
title = {Computational protein biomarker prediction: a case study for prostate
cancer},
journal = {B{MC} {B}ioinformatics},
year = {2004},
volume = {5},
number = {26},
abstract = {Background {R}ecent technological advances in mass spectrometry pose
challenges in computational mathematics and statistics to process
the mass spectral data into predictive models with clinical and biological
significance. {W}e discuss several classification-based approaches
to finding protein biomarker candidates using protein profiles obtained
via mass spectrometry, and we assess their statistical significance.
{O}ur overall goal is to implicate peaks that have a high likelihood
of being biologically linked to a given disease state, and thus to
narrow the search for biomarker candidates. {R}esults {T}horough
cross-validation studies and randomization tests are performed on
a prostate cancer dataset with over 300 patients, obtained at the
{E}astern {V}irginia {M}edical {S}chool using {SELDI}-{TOF} mass
spectrometry. {W}e obtain average classification accuracies of 87%
on a four-group classification problem using a two-stage linear {SVM}-based
procedure and just 13 peaks, with other methods performing comparably.
{C}onclusions {M}odern feature selection and classification methods
are powerful techniques for both the identification of biomarker
candidates and the related problem of building predictive models
from protein mass spectrometric profiles. {C}ross-validation and
randomization are essential tools that must be performed carefully
in order not to bias the results unfairly. {H}owever, only a biological
validation and identification of the underlying proteins will ultimately
confirm the actual value and power of any computational predictions.},
doi = {10.1186/1471-2105-5-26},
pdf = {../local/Wagner2004Computational.pdf},
file = {Wagner2004Computational.pdf:local/Wagner2004Computational.pdf:PDF},
keywords = {biosvm},
owner = {vert},
url = {http://www.biomedcentral.com/1471-2105/5/26}
}
@article{Wang2005Protein,
author = {Wang, J. and Sung, W.-K. and Krishnan, A. and Li, K.-B.},
title = {Protein subcellular localization prediction for {G}ram-negative bacteria
using amino acid subalphabets and a combination of multiple support
vector machines.},
journal = {B{MC} {B}ioinformatics},
year = {2005},
volume = {6},
pages = {174},
number = {1},
month = {Jul},
abstract = {B{ACKGROUND}: {P}redicting the subcellular localization of proteins
is important for determining the function of proteins. {P}revious
works focused on predicting protein localization in {G}ram-negative
bacteria obtained good results. {H}owever, these methods had relatively
low accuracies for the localization of extracellular proteins. {T}his
paper studies ways to improve the accuracy for predicting extracellular
localization in {G}ram-negative bacteria. {RESULTS}: {W}e have developed
a system for predicting the subcellular localization of proteins
for {G}ram-negative bacteria based on amino acid subalphabets and
a combination of multiple support vector machines. {T}he recall of
the extracellular site and overall recall of our predictor reach
86.0\% and 89.8\%, respectively, in 5-fold cross-validation. {T}o
the best of our knowledge, these are the most accurate results for
predicting subcellular localization in {G}ram-negative bacteria.
{CONCLUSIONS}: {C}lustering 20 amino acids into a few groups by the
proposed greedy algorithm provides a new way to extract features
from protein sequences to cover more adjacent amino acids and hence
reduce the dimensionality of the input vector of protein features.
{I}t was observed that a good amino acid grouping leads to an increase
in prediction performance. {F}urthermore, a proper choice of a subset
of complementary support vector machines constructed by different
features of proteins maximizes the prediction accuracy.},
doi = {10.1186/1471-2105-6-174},
pdf = {../local/Wang2005Protein.pdf},
file = {Wang2005Protein.pdf:local/Wang2005Protein.pdf:PDF},
keywords = {biosvm},
pii = {1471-2105-6-174},
url = {http://dx.doi.org/10.1186/1471-2105-6-174}
}
@article{Wang2004Predicting,
author = {Long-Hui Wang and Juan Liu and Yan-Fu Li and Huai-Bei Zhou},
title = {Predicting protein secondary structure by a support vector machine
based on a new coding scheme.},
journal = {Genome {I}nform {S}er {W}orkshop {G}enome {I}nform},
year = {2004},
volume = {15},
pages = {181-90},
number = {2},
abstract = {Protein structure prediction is one of the most important problems
in modern computational biology. {P}rotein secondary structure prediction
is a key step in prediction of protein tertiary structure. {T}here
have emerged many methods based on machine learning techniques, such
as neural networks ({NN}) and support vector machine ({SVM}) etc.,
to focus on the prediction of the secondary structures. {I}n this
paper, a new method was proposed based on {SVM}. {D}ifferent from
the existing methods, this method takes into account of the physical-chemical
properties and structure properties of amino acids. {W}hen tested
on the most popular dataset {CB}513, it achieved a {Q}(3) accuracy
of 0.7844, which illustrates that it is one of the top range methods
for protein of secondary structure prediction.},
keywords = {biosvm},
url = {http://www.jsbi.org/journal/GIW04/GIW04F019.html}
}
@article{Wang2005Using,
author = {M. Wang and J. Yang and K-C. Chou},
title = {Using string kernel to predict signal peptide cleavage site based
on subsite coupling model.},
journal = {Amino {A}cids},
year = {2005},
volume = {28},
pages = {395-402},
number = {4},
month = {Jun},
abstract = {Owing to the importance of signal peptides for studying the molecular
mechanisms of genetic diseases, reprogramming cells for gene therapy,
and finding new drugs for healing a specific defect, it is in great
demand to develop a fast and accurate method to identify the signal
peptides. {I}ntroduction of the so-called {-3,-1, +1} coupling model
({C}hou, {K}. {C}.: {P}rotein {E}ngineering, 2001, 14-2, 75-79) has
made it possible to take into account the coupling effect among some
key subsites and hence can significantly enhance the prediction quality
of peptide cleavage site. {B}ased on the subsite coupling model,
a kind of string kernels for protein sequence is introduced. {I}ntegrating
the biologically relevant prior knowledge, the constructed string
kernels can thus be used by any kernel-based method. {A} {S}upport
vector machines ({SVM}) is thus built to predict the cleavage site
of signal peptides from the protein sequences. {T}he current approach
is compared with the classical weight matrix method. {A}t small false
positive ratios, our method outperforms the classical weight matrix
method, indicating the current approach may at least serve as a powerful
complemental tool to other existing methods for predicting the signal
peptide cleavage site.{T}he software that generated the results reported
in this paper is available upon requirement, and will appear at http://www.pami.sjtu.edu.cn/wm.},
doi = {10.1007/s00726-005-0189-6},
pdf = {../local/Wang2005Using.pdf},
file = {Wang2005Using.pdf:local/Wang2005Using.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1007/s00726-005-0189-6}
}
@article{Wang2004Weighted-support,
author = {Wang, M. and Yang, J. and Liu, G.-P. and Xu, Z.-J. and Chou, K.-C.},
title = {Weighted-support vector machines for predicting membrane protein
types based on pseudo-amino acid composition},
journal = {Protein {E}ng. {D}es. {S}el.},
year = {2004},
volume = {17},
pages = {509-516},
number = {6},
abstract = {Membrane proteins are generally classified into the following five
types: (1) type {I} membrane proteins, (2) type {II} membrane proteins,
(3) multipass transmembrane proteins, (4) lipid chain-anchored membrane
proteins and (5) {GPI}-anchored membrane proteins. {P}rediction of
membrane protein types has become one of the growing hot topics in
bioinformatics. {C}urrently, we are facing two critical challenges
in this area: first, how to take into account the extremely complicated
sequence-order effects, and second, how to deal with the highly uneven
sizes of the subsets in a training dataset. {I}n this paper, stimulated
by the concept of using the pseudo-amino acid composition to incorporate
the sequence-order effects, the spectral analysis technique is introduced
to represent the statistical sample of a protein. {B}ased on such
a framework, the weighted support vector machine ({SVM}) algorithm
is applied. {T}he new approach has remarkable power in dealing with
the bias caused by the situation when one subset in the training
dataset contains many more samples than the other. {T}he new method
is particularly useful when our focus is aimed at proteins belonging
to small subsets. {T}he results obtained by the self-consistency
test, jackknife test and independent dataset test are encouraging,
indicating that the current approach may serve as a powerful complementary
tool to other existing methods for predicting the types of membrane
proteins.},
doi = {10.1093/protein/gzh061},
eprint = {http://peds.oupjournals.org/cgi/reprint/17/6/509.pdf},
pdf = {../local/Wang2004Weighted-support.pdf},
file = {Wang2004Weighted-support.pdf:local/Wang2004Weighted-support.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1093/protein/gzh061}
}
@article{Wang2004Support,
author = {M-L. Wang and W-J. Li and M-L. Wang and W-B. Xu},
title = {Support vector machines for prediction of peptidyl prolyl cis/trans
isomerization.},
journal = {J {P}ept {R}es},
year = {2004},
volume = {63},
pages = {23-8},
number = {1},
month = {Jan},
abstract = {A new method for peptidyl prolyl cis/trans isomerization prediction
based on the theory of support vector machines ({SVM}) was introduced.
{T}he {SVM} represents a new approach to supervised pattern classification
and has been successfully applied to a wide range of pattern recognition
problems. {I}n this study, six training datasets consisting of different
length local sequence respectively were used. {T}he polynomial kernel
functions with different parameter d were chosen. {T}he test for
the independent testing dataset and the jackknife test were both
carried out. {W}hen the local sequence length was 20-residue and
the parameter d = 8, the {SVM} method archived the best performance
with the correct rate for the cis and trans forms reaching 70.4 and
69.7\% for the independent testing dataset, 76.7 and 76.6\% for the
jackknife test, respectively. {M}atthew's correlation coefficients
for the jackknife test could reach about 0.5. {T}he results obtained
through this study indicated that the {SVM} method would become a
powerful tool for predicting peptidyl prolyl cis/trans isomerization.},
keywords = {biosvm},
pii = {100}
}
@article{Wang2005Prediction,
author = {Ming-Lei Wang and Hui Yao and Wen-Bo Xu},
title = {Prediction by support vector machines and analysis by {Z}-score of
poly-{L}-proline type {II} conformation based on local sequence.},
journal = {Comput. {B}iol. {C}hem.},
year = {2005},
volume = {29},
pages = {95-100},
number = {2},
month = {Apr},
abstract = {In recent years, the poly-{L}-proline type {II} ({PPII}) conformation
has gained more and more importance. {T}his structure plays vital
roles in many biological processes. {B}ut few studies have been made
to predict {PPII} secondary structures computationally. {T}he support
vector machine ({SVM}) represents a new approach to supervised pattern
classification and has been successfully applied to a wide range
of pattern recognition problems. {I}n this paper, we present a {SVM}
prediction method of {PPII} conformation based on local sequence.
{T}he overall accuracy for both the independent testing set and estimate
of jackknife testing reached approximately 70\%. {M}atthew's correlation
coefficient ({MCC}) could reach 0.4. {B}y comparing the results of
training and testing datasets with different sequence identities,
we suggest that the performance of this method correlates with the
sequence identity of dataset. {T}he parameter of {SVM} kernel function
was an important factor to the performance of this method. {T}he
propensities of residues located at different positions were also
analyzed. {B}y computing {Z}-scores, we found that {P} and {G} were
the two most important residues to {PPII} structure conformation.},
doi = {10.1016/j.compbiolchem.2005.02.002},
pdf = {../local/Wang2005Prediction.pdf},
file = {Wang2005Prediction.pdf:local/Wang2005Prediction.pdf:PDF},
keywords = {biosvm},
pii = {S1476-9271(05)00017-4},
url = {http://dx.doi.org/10.1016/j.compbiolchem.2005.02.002}
}
@article{Wang2005Gene,
author = {Yu Wang and Igor V Tetko and Mark A Hall and Eibe Frank and Axel
Facius and Klaus F X Mayer and Hans W Mewes},
title = {Gene selection from microarray data for cancer classification--a
machine learning approach.},
journal = {Comput. {B}iol. {C}hem.},
year = {2005},
volume = {29},
pages = {37-46},
number = {1},
month = {Feb},
abstract = {A {DNA} microarray can track the expression levels of thousands of
genes simultaneously. {P}revious research has demonstrated that this
technology can be useful in the classification of cancers. {C}ancer
microarray data normally contains a small number of samples which
have a large number of gene expression levels as features. {T}o select
relevant genes involved in different types of cancer remains a challenge.
{I}n order to extract useful gene information from cancer microarray
data and reduce dimensionality, feature selection algorithms were
systematically investigated in this study. {U}sing a correlation-based
feature selector combined with machine learning algorithms such as
decision trees, naïve {B}ayes and support vector machines, we show
that classification performance at least as good as published results
can be obtained on acute leukemia and diffuse large {B}-cell lymphoma
microarray data sets. {W}e also demonstrate that a combined use of
different classification and feature selection approaches makes it
possible to select relevant genes with high confidence. {T}his is
also the first paper which discusses both computational and biological
evidence for the involvement of zyxin in leukaemogenesis.},
doi = {10.1016/j.compbiolchem.2004.11.001},
pdf = {../local/Wang2005Gene.pdf},
file = {Wang2005Gene.pdf:local/Wang2005Gene.pdf:PDF},
keywords = {biosvm microarray},
pii = {S1476-9271(04)00108-2},
url = {http://dx.doi.org/10.1016/j.compbiolchem.2004.11.001}
}
@article{Ward2003Secondary,
author = {Ward, J. J. and McGuffin, L. J. and Buxton, B. F. and Jones, D. T.},
title = {Secondary structure prediction with support vector machines},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {1650-1655},
number = {13},
abstract = {Motivation: {A} new method that uses support vector machines ({SVM}s)
to predict protein secondary structure is described and evaluated.
{T}he study is designed to develop a reliable prediction method using
an alternative technique and to investigate the applicability of
{SVM}s to this type of bioinformatics problem. {M}ethods: {B}inary
{SVM}s are trained to discriminate between two structural classes.
{T}he binary classifiers are combined in several ways to predict
multi-class secondary structure. {R}esults: {T}he average three-state
prediction accuracy per protein ({Q}3) is estimated by cross-validation
to be 77.07 {+/-} 0.26% with a segment overlap ({S}ov) score of 73.32
{+/-} 0.39%. {T}he {SVM} performs similarly to the 'state-of-the-art'
{PSIPRED} prediction method on a non-homologous test set of 121 proteins
despite being trained on substantially fewer examples. {A} simple
consensus of the {SVM}, {PSIPRED} and {PROF}sec achieves significantly
higher prediction accuracy than the individual methods. {A}vailability:
{T}he {SVM} classifier is available from the authors. {W}ork is in
progress to make the method available on-line and to integrate the
{SVM} predictions into the {PSIPRED} server.},
pdf = {../local/Ward2003Secondary.pdf},
file = {Ward2003Secondary.pdf:local/Ward2003Secondary.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/13/1650}
}
@article{Waring2004Interlaboratory,
author = {Jeffrey F Waring and Roger G Ulrich and Nick Flint and David Morfitt
and Arno Kalkuhl and Frank Staedtler and Michael Lawton and Johanna
M Beekman and Laura Suter},
title = {Interlaboratory evaluation of rat hepatic gene expression changes
induced by methapyrilene.},
journal = {Environ {H}ealth {P}erspect},
year = {2004},
volume = {112},
pages = {439-48},
number = {4},
month = {Mar},
abstract = {Several studies using microarrays have shown that changes in gene
expression provide information about the mechanism of toxicity induced
by xenobiotic agents. {N}evertheless, the issue of whether gene expression
profiles are reproducible across different laboratories remains to
be determined. {T}o address this question, several members of the
{H}epatotoxicity {W}orking {G}roup of the {I}nternational {L}ife
{S}ciences {I}nstitute {H}ealth and {E}nvironmental {S}ciences {I}nstitute
evaluated the liver gene expression profiles of rats treated with
methapyrilene ({MP}). {A}nimals were treated at one facility, and
{RNA} was distributed to five different sites for gene expression
analysis. {A} preliminary evaluation of the number of modulated genes
uncovered striking differences between the five different sites.
{H}owever, additional data analysis demonstrated that these differences
had an effect on the absolute gene expression results but not on
the outcome of the study. {F}or all users, unsupervised algorithms
showed that gene expression allows the distinction of the high dose
of {MP} from controls and low dose. {I}n addition, the use of a supervised
analysis method (support vector machines) made it possible to correctly
classify samples. {I}n conclusion, the results show that, despite
some variability, robust gene expression changes were consistent
between sites. {I}n addition, key expression changes related to the
mechanism of {MP}-induced hepatotoxicity were identified. {T}hese
results provide critical information regarding the consistency of
microarray results across different laboratories and shed light on
the strengths and limitations of expression profiling in drug safety
analysis.},
keywords = {biosvm}
}
@article{Warmuth2003Active,
author = {Warmuth, M. K. and Liao, J. and R{\"a}tsch, G. and Mathieson, M.
and Putta, S. and Lemmen, C.},
title = {Active learning with support vector machines in the drug discovery
process.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2003},
volume = {43},
pages = {667-673},
number = {2},
abstract = {We investigate the following data mining problem from computer-aided
drug design: {F}rom a large collection of compounds, find those that
bind to a target molecule in as few iterations of biochemical testing
as possible. {I}n each iteration a comparatively small batch of compounds
is screened for binding activity toward this target. {W}e employed
the so-called "active learning paradigm" from {M}achine {L}earning
for selecting the successive batches. {O}ur main selection strategy
is based on the maximum margin hyperplane-generated by "{S}upport
{V}ector {M}achines". {T}his hyperplane separates the current set
of active from the inactive compounds and has the largest possible
distance from any labeled compound. {W}e perform a thorough comparative
study of various other selection strategies on data sets provided
by {D}u{P}ont {P}harmaceuticals and show that the strategies based
on the maximum margin hyperplane clearly outperform the simpler ones.},
doi = {10.1021/ci025620t},
pdf = {../local/Warmuth2003Active.pdf},
file = {Warmuth2003Active.pdf:local/Warmuth2003Active.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1021/ci025620t}
}
@inproceedings{Warmuth2002Active,
author = {Warmuth, M. K. and R{\"a}tsch, G. and Mathieson, M. and Liao, L.
and Lemmen, C.},
title = {Active learning in the drug discovery process},
booktitle = {Adv. {N}eural {I}nform. {P}rocess. {S}yst.},
year = {2002},
editor = {T.G. Dietterich and S. Becker and Z. Ghahramani},
volume = {14},
pages = {1449--1456},
publisher = {MIT Press},
keywords = {biosvm},
subject = {qsar}
}
@incollection{Watkins2000Dynamic,
author = {C. Watkins},
title = {Dynamic alignment kernels},
booktitle = {Advances in {L}arge {M}argin {C}lassifiers},
publisher = {MIT Press},
year = {2000},
editor = {A.J. Smola and P.L. Bartlett and B. Sch{\"o}lkopf and D. Schuurmans},
pages = {39--50},
address = {Cambridge, MA},
pdf = {../local/Watkins2000Dynamic.pdf},
file = {Watkins2000Dynamic.pdf:local/Watkins2000Dynamic.pdf:PDF},
keywords = {biosvm},
subject = {kernel},
url = {http://www.cs.rhbnc.ac.uk/home/chrisw/dynk.ps.gz}
}
@article{Weathers2004Reduced,
author = {Weathers, E. A. and Paulaitis, M. E. and Woolf, T. B. and Hoh, J.
H.},
title = {Reduced amino acid alphabet is sufficient to accurately recognize
intrinsically disordered protein.},
journal = {F{EBS} {L}ett.},
year = {2004},
volume = {576},
pages = {348-352},
number = {3},
abstract = {Intrinsically disordered proteins are an important class of proteins
with unique functions and properties. {H}ere, we have applied a support
vector machine ({SVM}) trained on naturally occurring disordered
and ordered proteins to examine the contribution of various parameters
(vectors) to recognizing proteins that contain disordered regions.
{W}e find that a {SVM} that incorporates only amino acid composition
has a recognition accuracy of 87+/-2%. {T}his result suggests that
composition alone is sufficient to accurately recognize disorder.
{I}nterestingly, {SVM}s using reduced sets of amino acids based on
chemical similarity preserve high recognition accuracy. {A} set as
small as four retains an accuracy of 84+/-2%; this suggests that
general physicochemical properties rather than specific amino acids
are important factors contributing to protein disorder.},
doi = {10.1016/j.febslet.2004.09.036},
pdf = {../local/Weathers2004Reduced.pdf},
file = {Weathers2004Reduced.pdf:local/Weathers2004Reduced.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1016/j.febslet.2004.09.036}
}
@article{Weston2003Feature,
author = {Weston, J. and P{\'e}rez-Cruz, F. and Bousquet, O. and Chapelle,
O. and Elisseeff, A. and Sch{\"o}lkopf, B.},
title = {Feature selection and transduction for prediction of molecular bioactivity
for drug design},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {764-771},
number = {6},
abstract = {Motivation: {I}n drug discovery a key task is to identify characteristics
that separate active (binding) compounds from inactive (non-binding)
ones. {A}n automated prediction system can help reduce resources
necessary to carry out this task. {R}esults: {T}wo methods for prediction
of molecular bioactivity for drug design are introduced and shown
to perform well in a data set previously studied as part of the {KDD}
({K}nowledge {D}iscovery and {D}ata {M}ining) {C}up 2001. {T}he data
is characterized by very few positive examples, a very large number
of features (describing three-dimensional properties of the molecules)
and rather different distributions between training and test data.
{T}wo techniques are introduced specifically to tackle these problems:
a feature selection method for unbalanced data and a classifier which
adapts to the distribution of the the unlabeled test data (a so-called
transductive method). {W}e show both techniques improve identification
performance and in conjunction provide an improvement over using
only one of the techniques. {O}ur results suggest the importance
of taking into account the characteristics in this data which may
also be relevant in other problems of a similar type. {A}vailability:
{M}atlab source code is available at http://www.kyb.tuebingen.mpg.de/bs/people/weston/kdd/kdd.html
{C}ontact: jason.weston@tuebingen.mpg.de {S}upplementary information:
{S}upplementary material is available at http://www.kyb.tuebingen.mpg.de/bs/people/weston/kdd/kdd.html.},
pdf = {../local/Weston2003Feature.pdf},
file = {Weston2003Feature.pdf:local/Weston2003Feature.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/6/764}
}
@article{Williams2004Prognostic,
author = {Williams, R.D. and Hing, S.N. and Greer, B.T. and Whiteford, C.C.
and Wei, J.S. and Natrajan, R. and Kelsey, A. and Rogers, S. and
Campbell, C. and Pritchard-Jones, K. and Khan, J.},
title = {Prognostic classification of relapsing favorable histology {W}ilms
tumor using c{DNA} microarray expression profiling and support vector
machines.},
journal = {Genes {C}hromosomes {C}ancer},
year = {2004},
volume = {41},
pages = {65-79},
number = {1},
month = {Sep},
abstract = {Treatment of {W}ilms tumor has a high success rate, with some 85%
of patients achieving long-term survival. {H}owever, late effects
of treatment and management of relapse remain significant clinical
problems. {I}f accurate prognostic methods were available, effective
risk-adapted therapies could be tailored to individual patients at
diagnosis. {F}ew molecular prognostic markers for {W}ilms tumor are
currently defined, though previous studies have linked allele loss
on 1p or 16q, genomic gain of 1q, and overexpression from 1q with
an increased risk of relapse. {T}o identify specific patterns of
gene expression that are predictive of relapse, we used high-density
(30 k) c{DNA} microarrays to analyze {RNA} samples from 27 favorable
histology {W}ilms tumors taken from primary nephrectomies at the
time of initial diagnosis. {T}hirteen of these tumors relapsed within
2 years. {G}enes differentially expressed between the relapsing and
nonrelapsing tumor classes were identified by statistical scoring
(t test). {T}hese genes encode proteins with diverse molecular functions,
including transcription factors, developmental regulators, apoptotic
factors, and signaling molecules. {U}se of a support vector machine
classifier, feature selection, and test evaluation using cross-validation
led to identification of a generalizable expression signature, a
small subset of genes whose expression potentially can be used to
predict tumor outcome in new samples. {S}imilar methods were used
to identify genes that are differentially expressed between tumors
with and without genomic 1q gain. {T}his set of discriminators was
highly enriched in genes on 1q, indicating close agreement between
data obtained from expression profiling with data from genomic copy
number analyses.},
doi = {10.1002/gcc.20060Â },
pdf = {../local/Williams2004Prognostic.pdf},
file = {Williams2004Prognostic.pdf:local/Williams2004Prognostic.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/gcc.20060}
}
@article{Wilton2003Comparison,
author = {D. Wilton and P. Willett and K. Lawson and G. Mullier},
title = {Comparison of ranking methods for virtual screening in lead-discovery
programs.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2003},
volume = {43},
pages = {469-74},
number = {2},
abstract = {This paper discusses the use of several rank-based virtual screening
methods for prioritizing compounds in lead-discovery programs, given
a training set for which both structural and bioactivity data are
available. {S}tructures from the {NCI} {AIDS} data set and from the
{S}yngenta corporate database were represented by two types of fragment
bit-string and by sets of high-level molecular features. {T}hese
representations were processed using binary kernel discrimination,
similarity searching, substructural analysis, support vector machine,
and trend vector analysis, with the effectiveness of the methods
being judged by the extent to which active test set molecules were
clustered toward the top of the resultant rankings. {T}he binary
kernel discrimination approach yielded consistently superior rankings
and would appear to have considerable potential for chemical screening
applications.},
doi = {10.1021/ci025586i},
pdf = {../local/Wilton2003Comparison.pdf},
file = {Wilton2003Comparison.pdf:local/Wilton2003Comparison.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci025586i}
}
@article{Winters-Hilt2003Highly,
author = {Winters-Hilt, S. and Vercoutere, W. and DeGuzman, V.S. and Deamer,
D. and Akeson, M. and Haussler, D.},
title = {Highly accurate classification of {W}atson-{C}rick basepairs on termini
of single {DNA} molecules.},
journal = {Biophys. {J}.},
year = {2003},
volume = {84},
pages = {967-976},
number = {2},
abstract = {We introduce a computational method for classification of individual
{DNA} molecules measured by an{alpha} -hemolysin channel detector.
{W}e show classification with better than 99% accuracy for {DNA}
hairpin molecules that differ only in their terminal {W}atson-{C}rick
basepairs. {S}ignal classification was done in silico to establish
performance metrics (i.e., where train and test data were of known
type, via single-species data files). {I}t was then performed in
solution to assay real mixtures of {DNA} hairpins. {H}idden {M}arkov
{M}odels ({HMM}s) were used with {E}xpectation/{M}aximization for
denoising and for associating a feature vector with the ionic current
blockade of the {DNA} molecule. {S}upport {V}ector {M}achines ({SVM}s)
were used as discriminators, and were the focus of off-line training.
{A} multiclass {SVM} architecture was designed to place less discriminatory
load on weaker discriminators, and novel {SVM} kernels were used
to boost discrimination strength. {T}he tuning on {HMM}s and {SVM}s
enabled biophysical analysis of the captured molecule states and
state transitions; structure revealed in the biophysical analysis
was used for better feature selection.},
pdf = {../local/Winters-Hilt2003Highly.pdf},
file = {Winters-Hilt2003Highly.pdf:local/Winters-Hilt2003Highly.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.biophysj.org/cgi/content/abstract/84/2/967}
}
@article{Wu2003Comparison,
author = {Wu, B. and Abbott, T. and Fishman, D. and McMurray, W. and Mor, G.
and Stone, K. and Ward, D. and Williams, K. and Zhao, H.},
title = {Comparison of statistical methods for classification of ovarian cancer
using mass spectrometry data},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {1636-1643},
number = {13},
abstract = {Motivation: {N}ovel methods, both molecular and statistical, are urgently
needed to take advantage of recent advances in biotechnology and
the human genome project for disease diagnosis and prognosis. {M}ass
spectrometry ({MS}) holds great promise for biomarker identification
and genome-wide protein profiling. {I}t has been demonstrated in
the literature that biomarkers can be identified to distinguish normal
individuals from cancer patients using {MS} data. {S}uch progress
is especially exciting for the detection of early-stage ovarian cancer
patients. {A}lthough various statistical methods have been utilized
to identify biomarkers from {MS} data, there has been no systematic
comparison among these approaches in their relative ability to analyze
{MS} data. {R}esults: {W}e compare the performance of several classes
of statistical methods for the classification of cancer based on
{MS} spectra. {T}hese methods include: linear discriminant analysis,
quadratic discriminant analysis, k-nearest neighbor classifier, bagging
and boosting classification trees, support vector machine, and random
forest ({RF}). {T}he methods are applied to ovarian cancer and control
serum samples from the {N}ational {O}varian {C}ancer {E}arly {D}etection
{P}rogram clinic at {N}orthwestern {U}niversity {H}ospital. {W}e
found that {RF} outperforms other methods in the analysis of {MS}
data. {S}upplementary information: http://bioinformatics.med.yale.edu/proteomics/{B}io{S}upp1.html},
pdf = {../local/Wu2003Comparison.pdf},
file = {Wu2003Comparison.pdf:local/Wu2003Comparison.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/13/1636}
}
@article{Xie2005LOCSVMPSI,
author = {Dan Xie and Ao Li and Minghui Wang and Zhewen Fan and Huanqing Feng},
title = {L{OCSVMPSI}: a web server for subcellular localization of eukaryotic
proteins using {SVM} and profile of {PSI}-{BLAST}.},
journal = {Nucleic {A}cids {R}es.},
year = {2005},
volume = {33},
pages = {W105-10},
number = {Web Server issue},
month = {Jul},
abstract = {Subcellular location of a protein is one of the key functional characters
as proteins must be localized correctly at the subcellular level
to have normal biological function. {I}n this paper, a novel method
named {LOCSVMPSI} has been introduced, which is based on the support
vector machine ({SVM}) and the position-specific scoring matrix generated
from profiles of {PSI}-{BLAST}. {W}ith a jackknife test on the {RH}2427
data set, {LOCSVMPSI} achieved a high overall prediction accuracy
of 90.2\%, which is higher than the prediction results by {S}ub{L}oc
and {ESL}pred on this data set. {I}n addition, prediction performance
of {LOCSVMPSI} was evaluated with 5-fold cross validation test on
the {PK}7579 data set and the prediction results were consistently
better than the previous method based on several {SVM}s using composition
of both amino acids and amino acid pairs. {F}urther test on the {SWISSPROT}
new-unique data set showed that {LOCSVMPSI} also performed better
than some widely used prediction methods, such as {PSORTII}, {T}arget{P}
and {LOC}net. {A}ll these results indicate that {LOCSVMPSI} is a
powerful tool for the prediction of eukaryotic protein subcellular
localization. {A}n online web server (current version is 1.3) based
on this method has been developed and is freely available to both
academic and commercial users, which can be accessed by at http://{B}ioinformatics.ustc.edu.cn/{LOCSVMPSI}/{LOCSVMPSI}.php.},
doi = {10.1093/nar/gki359},
pdf = {../local/Xie2005LOCSVMPSI.pdf},
file = {Xie2005LOCSVMPSI.pdf:local/Xie2005LOCSVMPSI.pdf:PDF},
keywords = {biosvm},
pii = {33/suppl_2/W105},
url = {http://dx.doi.org/10.1093/nar/gki359}
}
@article{Xiong2001Biomarker,
author = {Xiong, M. and Fang, X. and Zhao, J.},
title = {Biomarker {I}dentification by {F}eature {W}rappers},
journal = {Genome {R}es.},
year = {2001},
volume = {11},
pages = {1878-1887},
number = {11},
abstract = {Gene expression studies bridge the gap between {DNA} information and
trait information by dissecting biochemical pathways into intermediate
components between genotype and phenotype. {T}hese studies open new
avenues for identifying complex disease genes and biomarkers for
disease diagnosis and for assessing drug efficacy and toxicity. {H}owever,
the majority of analytical methods applied to gene expression data
are not efficient for biomarker identification and disease diagnosis.
{I}n this paper, we propose a general framework to incorporate feature
(gene) selection into pattern recognition in the process to identify
biomarkers. {U}sing this framework, we develop three feature wrappers
that search through the space of feature subsets using the classification
error as measure of goodness for a particular feature subset being
"wrapped around": linear discriminant analysis, logistic regression,
and support vector machines. {T}o effectively carry out this computationally
intensive search process, we employ sequential forward search and
sequential forward floating search algorithms. {T}o evaluate the
performance of feature selection for biomarker identification we
have applied the proposed methods to three data sets. {T}he preliminary
results demonstrate that very high classification accuracy can be
attained by identified composite classifiers with several biomarkers.},
pdf = {../local/Xiong2001Biomarker.pdf},
file = {Xiong2001Biomarker.pdf:local/Xiong2001Biomarker.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.genome.org/cgi/content/abstract/11/11/1878}
}
@article{Xu2004Molecular,
author = {Xiu-Qin Xu and Chon K Leow and Xin Lu and Xuegong Zhang and Jun S
Liu and Wing-Hung Wong and Arndt Asperger and Sören Deininger and
Hon-Chiu Eastwood Leung},
title = {Molecular classification of liver cirrhosis in a rat model by proteomics
and bioinformatics.},
journal = {Proteomics},
year = {2004},
volume = {4},
pages = {3235-45},
number = {10},
month = {Oct},
abstract = {Liver cirrhosis is a worldwide health problem. {R}eliable, noninvasive
methods for early detection of liver cirrhosis are not available.
{U}sing a three-step approach, we classified sera from rats with
liver cirrhosis following different treatment insults. {T}he approach
consisted of: (i) protein profiling using surface-enhanced laser
desorption/ionization ({SELDI}) technology; (ii) selection of a statistically
significant serum biomarker set using machine learning algorithms;
and (iii) identification of selected serum biomarkers by peptide
sequencing. {W}e generated serum protein profiles from three groups
of rats: (i) normal (n=8), (ii) thioacetamide-induced liver cirrhosis
(n=22), and (iii) bile duct ligation-induced liver fibrosis (n=5)
using a weak cation exchanger surface. {P}rofiling data were further
analyzed by a recursive support vector machine algorithm to select
a panel of statistically significant biomarkers for class prediction.
{S}ensitivity and specificity of classification using the selected
protein marker set were higher than 92\%. {A} consistently down-regulated
3495 {D}a protein in cirrhosis samples was one of the selected significant
biomarkers. {T}his 3495 {D}a protein was purified on-chip and trypsin
digested. {F}urther structural characterization of this biomarkers
candidate was done by using cross-platform matrix-assisted laser
desorption/ionization mass spectrometry ({MALDI}-{MS}) peptide mass
fingerprinting ({PMF}) and matrix-assisted laser desorption/ionization
time of flight/time of flight ({MALDI}-{TOF}/{TOF}) tandem mass spectrometry
({MS}/{MS}). {C}ombined data from {PMF} and {MS}/{MS} spectra of
two tryptic peptides suggested that this 3495 {D}a protein shared
homology to a histidine-rich glycoprotein. {T}hese results demonstrated
a novel approach to discovery of new biomarkers for early detection
of liver cirrhosis and classification of liver diseases.},
doi = {10.1002/pmic.200400839},
pdf = {../local/Xu2004Molecular.pdf},
file = {Xu2004Molecular.pdf:Xu2004Molecular.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1002/pmic.200400839}
}
@article{Xue2004Support,
author = {C. X. Xue and R. S. Zhang and H. X. Liu and M. C. Liu and Z. D. Hu
and B. T. Fan},
title = {Support vector machines-based quantitative structure-property relationship
for the prediction of heat capacity.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2004},
volume = {44},
pages = {1267-74},
number = {4},
abstract = {The support vector machine ({SVM}), as a novel type of learning machine,
for the first time, was used to develop a {Q}uantitative {S}tructure-{P}roperty
{R}elationship ({QSPR}) model of the heat capacity of a diverse set
of 182 compounds based on the molecular descriptors calculated from
the structure alone. {M}ultiple linear regression ({MLR}) and radial
basis function networks ({RBFNN}s) were also utilized to construct
quantitative linear and nonlinear models to compare with the results
obtained by {SVM}. {T}he root-mean-square (rms) errors in heat capacity
predictions for the whole data set given by {MLR}, {RBFNN}s, and
{SVM} were 4.648, 4.337, and 2.931 heat capacity units, respectively.
{T}he prediction results are in good agreement with the experimental
value of heat capacity; also, the results reveal the superiority
of the {SVM} over {MLR} and {RBFNN}s models.},
doi = {10.1021/ci049934n},
pdf = {../local/Xue2004Support.pdf},
file = {Xue2004Support.pdf:local/Xue2004Support.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci049934n}
}
@article{Xue2004accurate,
author = {C. X. Xue and R. S. Zhang and H. X. Liu and X. J. Yao and M. C. Liu
and Z. D. Hu and B. T. Fan},
title = {An accurate {QSPR} study of {O}-{H} bond dissociation energy in substituted
phenols based on support vector machines.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2004},
volume = {44},
pages = {669-77},
number = {2},
abstract = {The support vector machine ({SVM}), as a novel type of learning machine,
was used to develop a {Q}uantitative {S}tructure-{P}roperty {R}elationship
({QSPR}) model of the {O}-{H} bond dissociation energy ({BDE}) of
78 substituted phenols. {T}he six descriptors calculated solely from
the molecular structures of compounds selected by forward stepwise
regression were used as inputs for the {SVM} model. {T}he root-mean-square
(rms) errors in {BDE} predictions for the training, test, and overall
data sets were 3.808, 3.320, and 3.713 {BDE} units (k{J} mol(-1)),
respectively. {T}he results obtained by {G}aussian-kernel {SVM} were
much better than those obtained by multiple linear regression, radial
basis function neural networks, linear-kernel {SVM}, and other {QSPR}
approaches.},
doi = {10.1021/ci034248u},
pdf = {../local/Xue2004accurate.pdf},
file = {Xue2004accurate.pdf:local/Xue2004accurate.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci034248u}
}
@article{Xue2004QSAR,
author = {C. X. Xue and R. S. Zhang and H. X. Liu and X. J. Yao and M. C. Liu
and Z. D. Hu and B. T. Fan},
title = {Q{SAR} models for the prediction of binding affinities to human serum
albumin using the heuristic method and a support vector machine.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2004},
volume = {44},
pages = {1693-700},
number = {5},
abstract = {The binding affinities to human serum albumin for 94 diverse drugs
and drug-like compounds were modeled with the descriptors calculated
from the molecular structure alone using a quantitative structure-activity
relationship ({QSAR}) technique. {T}he heuristic method ({HM}) and
support vector machine ({SVM}) were utilized to construct the linear
and nonlinear prediction models, leading to a good correlation coefficient
({R}2) of 0.86 and 0.94 and root-mean-square errors (rms) of 0.212
and 0.134 albumin drug binding affinity units, respectively. {F}urthermore,
the models were evaluated by a 10 compound external test set, yielding
{R}2 of 0.71 and 0.89 and rms error of 0.430 and 0.222. {T}he specific
information described by the heuristic linear model could give some
insights into the factors that are likely to govern the binding affinity
of the compounds and be used as an aid to the drug design process;
however, the prediction results of the nonlinear {SVM} model seem
to be better than that of the {HM}.},
doi = {10.1021/ci049820b},
pdf = {../local/Xue2004QSAR.pdf},
file = {Xue2004QSAR.pdf:local/Xue2004QSAR.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci049820b}
}
@article{Xue2004Study,
author = {C. X. Xue and R. S. Zhang and M. C. Liu and Z. D. Hu and B. T. Fan},
title = {Study of the quantitative structure-mobility relationship of carboxylic
acids in capillary electrophoresis based on support vector machines.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2004},
volume = {44},
pages = {950-7},
number = {3},
abstract = {The support vector machines ({SVM}), as a novel type of learning machine,
were used to develop a quantitative structure-mobility relationship
({QSMR}) model of 58 aliphatic and aromatic carboxylic acids based
on molecular descriptors calculated from the structure alone. {M}ultiple
linear regression ({MLR}) and radial basis function neural networks
({RBFNN}s) were also utilized to construct the linear and the nonlinear
model to compare with the results obtained by {SVM}. {T}he root-mean-square
errors in absolute mobility predictions for the whole data set given
by {MLR}, {RBFNN}s, and {SVM} were 1.530, 1.373, and 0.888 mobility
units (10(-5) cm(2) {S}(-1) {V}(-1)), respectively, which indicated
that the prediction result agrees well with the experimental values
of these compounds and also revealed the superiority of {SVM} over
{MLR} and {RBFNN}s models for the prediction of the absolute mobility
of carboxylic acids. {M}oreover, the models we proposed could also
provide some insight into what structural features are related to
the absolute mobility of aliphatic and aromatic carboxylic acids.},
doi = {10.1021/ci034280o},
pdf = {../local/Xue2004Study.pdf},
file = {Xue2004Study.pdf:local/Xue2004Study.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci034280o}
}
@article{Xue2004Effect,
author = {Y. Xue and Z. R. Li and C. W. Yap and L. Z. Sun and X. Chen and Y.
Z. Chen},
title = {Effect of molecular descriptor feature selection in support vector
machine classification of pharmacokinetic and toxicological properties
of chemical agents.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2004},
volume = {44},
pages = {1630-8},
number = {5},
abstract = {Statistical-learning methods have been developed for facilitating
the prediction of pharmacokinetic and toxicological properties of
chemical agents. {T}hese methods employ a variety of molecular descriptors
to characterize structural and physicochemical properties of molecules.
{S}ome of these descriptors are specifically designed for the study
of a particular type of properties or agents, and their use for other
properties or agents might generate noise and affect the prediction
accuracy of a statistical learning system. {T}his work examines to
what extent the reduction of this noise can improve the prediction
accuracy of a statistical learning system. {A} feature selection
method, recursive feature elimination ({RFE}), is used to automatically
select molecular descriptors for support vector machines ({SVM})
prediction of {P}-glycoprotein substrates ({P}-gp), human intestinal
absorption of molecules ({HIA}), and agents that cause torsades de
pointes ({T}d{P}), a rare but serious side effect. {RFE} significantly
reduces the number of descriptors for each of these properties thereby
increasing the computational speed for their classification. {T}he
{SVM} prediction accuracies of {P}-gp and {HIA} are substantially
increased and that of {T}d{P} remains unchanged by {RFE}. {T}hese
prediction accuracies are comparable to those of earlier studies
derived from a selective set of descriptors. {O}ur study suggests
that molecular feature selection is useful for improving the speed
and, in some cases, the accuracy of statistical learning methods
for the prediction of pharmacokinetic and toxicological properties
of chemical agents.},
doi = {10.1021/ci049869h},
pdf = {../local/Xue2004Effect.pdf},
file = {Xue2004Effect.pdf:local/Xue2004Effect.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci049869h}
}
@article{Xue2004Prediction,
author = {Y. Xue and C. W. Yap and L. Z. Sun and Z. W. Cao and J. F. Wang and
Y. Z. Chen},
title = {Prediction of {P}-glycoprotein substrates by a support vector machine
approach.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2004},
volume = {44},
pages = {1497-505},
number = {4},
abstract = {P-glycoproteins ({P}-gp) actively transport a wide variety of chemicals
out of cells and function as drug efflux pumps that mediate multidrug
resistance and limit the efficacy of many drugs. {M}ethods for facilitating
early elimination of potential {P}-gp substrates are useful for facilitating
new drug discovery. {A} computational ensemble pharmacophore model
has recently been used for the prediction of {P}-gp substrates with
a promising accuracy of 63\%. {I}t is desirable to extend the prediction
range beyond compounds covered by the known pharmacophore models.
{F}or such a purpose, a machine learning method, support vector machine
({SVM}), was explored for the prediction of {P}-gp substrates. {A}
set of 201 chemical compounds, including 116 substrates and 85 nonsubstrates
of {P}-gp, was used to train and test a {SVM} classification system.
{T}his {SVM} system gave a prediction accuracy of at least 81.2\%
for {P}-gp substrates based on two different evaluation methods,
which is substantially improved against that obtained from the multiple-pharmacophore
model. {T}he prediction accuracy for nonsubstrates of {P}-gp is 79.2\%
using 5-fold cross-validation. {T}hese accuracies are slightly better
than those obtained from other statistical classification methods,
including k-nearest neighbor (k-{NN}), probabilistic neural networks
({PNN}), and {C}4.5 decision tree, that use the same sets of data
and molecular descriptors. {O}ur study indicates the potential of
{SVM} in facilitating the prediction of {P}-gp substrates.},
doi = {10.1021/ci049971e},
pdf = {../local/Xue2004Prediction.pdf},
file = {Xue2004Prediction.pdf:local/Xue2004Prediction.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1021/ci049971e}
}
@article{Yabuki2005GRIFFIN,
author = {Yabuki, Y. and Muramatsu, T. and Hirokawa, T. and Mukai, H. and Suwa,
M.},
title = {G{RIFFIN}: a system for predicting {GPCR}-{G}-protein coupling selectivity
using a support vector machine and a hidden {M}arkov model.},
journal = {Nucleic {A}cids {R}es.},
year = {2005},
volume = {33},
pages = {W148-53},
number = {Web Server issue},
month = {Jul},
abstract = {We describe a novel system, {GRIFFIN} ({G}-protein and {R}eceptor
{I}nteraction {F}eature {F}inding {IN}strument), that predicts {G}-protein
coupled receptor ({GPCR}) and {G}-protein coupling selectivity based
on a support vector machine ({SVM}) and a hidden {M}arkov model ({HMM})
with high sensitivity and specificity. {B}ased on our assumption
that whole structural segments of ligands, {GPCR}s and {G}-proteins
are essential to determine {GPCR} and {G}-protein coupling, various
quantitative features were selected for ligands, {GPCR}s and {G}-protein
complex structures, and those parameters that are the most effective
in selecting {G}-protein type were used as feature vectors in the
{SVM}. {T}he main part of {GRIFFIN} includes a hierarchical {SVM}
classifier using the feature vectors, which is useful for {C}lass
{A} {GPCR}s, the major family. {F}or the opsins and olfactory subfamilies
of {C}lass {A} and other minor families ({C}lasses {B}, {C}, frizzled
and smoothened), the binding {G}-protein is predicted with high accuracy
using the {HMM}. {A}pplying this system to known {GPCR} sequences,
each binding {G}-protein is predicted with high sensitivity and specificity
(>85\% on average). {GRIFFIN} (http://griffin.cbrc.jp/) is freely
available and allows users to easily execute this reliable prediction
of {G}-proteins.},
doi = {10.1093/nar/gki495},
pdf = {../local/Yabuki2005GRIFFIN.pdf},
file = {Yabuki2005GRIFFIN.pdf:local/Yabuki2005GRIFFIN.pdf:PDF},
keywords = {biosvm},
pii = {33/suppl_2/W148},
url = {http://dx.doi.org/10.1093/nar/gki495}
}
@incollection{Yamanishi2004Heterogeneous,
author = {Yamanishi, Y. and Vert, J.-P. and Kanehisa, M.},
title = {Heterogeneous data comparison and gene selection with kernel canonical
correlation analysis},
booktitle = {Kernel {M}ethods in {C}omputational {B}iology},
publisher = {MIT Press},
year = {2004},
editor = {Schölkopf, B. and Tsuda, K. and Vert, J.P.},
pages = {209-230},
pdf = {../local/heterogeneous.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/heterogeneous.pdf:PDF;heterogeneous.pdf:http\},
file = {heterogeneous.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/heterogeneous.pdf:PDF;heterogeneous.pdf:http\://cg.ensmp.fr/~vert/publi/04kmcbbook/heterogeneous.pdf:PDF},
keywords = {biosvm},
owner = {vert}
}
@article{Yamanishi2005Supervised,
author = {Yamanishi, Y. and Vert, J.-P. and Kanehisa, M.},
title = {Supervised enzyme network inference from the integration of genomic
data and chemical information},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {i468-i477},
abstract = {Motivation: {T}he metabolic network is an important biological network
which relates enzyme proteins and chemical compounds. {A} large number
of metabolic pathways remain unknown nowadays, and many enzymes are
missing even in known metabolic pathways. {T}here is, therefore,
an incentive to develop methods to reconstruct the unknown parts
of the metabolic network and to identify genes coding for missing
enzymes. {R}esults: {T}his paper presents new methods to infer enzyme
networks from the integration of multiple genomic data and chemical
information, in the framework of supervised graph inference. {T}he
originality of the methods is the introduction of chemical compatibility
as a constraint for refining the network predicted by the network
inference engine. {T}he chemical compatibility between two enzymes
is obtained automatically from the information encoded by their {E}nzyme
{C}ommission ({EC}) numbers. {T}he proposed methods are tested and
compared on their ability to infer the enzyme network of the yeast
{S}accharomyces cerevisiae from four datasets for enzymes with assigned
{EC} numbers: gene expression data, protein localization data, phylogenetic
profiles and chemical compatibility information. {I}t is shown that
the prediction accuracy of the network reconstruction consistently
improves owing to the introduction of chemical constraints, the use
of a supervised approach and the weighted integration of multiple
datasets. {F}inally, we conduct a comprehensive prediction of a global
enzyme network consisting of all enzyme candidate proteins of the
yeast to obtain new biological findings.},
doi = {10.1093/bioinformatics/bti1012},
pdf = {../local/Yamanishi2005Supervised.pdf},
file = {Yamanishi2005Supervised.pdf:local/Yamanishi2005Supervised.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1093/bioinformatics/bti1012}
}
@article{Yamanishi2004Protein,
author = {Yamanishi, Y. and Vert, J.-P. and Kanehisa, M.},
title = {Protein network inference from multiple genomic data: a supervised
approach},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {i363-i370},
abstract = {Motivation: {A}n increasing number of observations support the hypothesis
that most biological functions involve the interactions between many
proteins, and that the complexity of living systems arises as a result
of such interactions. {I}n this context, the problem of inferring
a global protein network for a given organism, using all available
genomic data about the organism, is quickly becoming one of the main
challenges in current computational biology. {R}esults: {T}his paper
presents a new method to infer protein networks from multiple types
of genomic data. {B}ased on a variant of kernel canonical correlation
analysis, its originality is in the formalization of the protein
network inference problem as a supervised learning problem, and in
the integration of heterogeneous genomic data within this framework.
{W}e present promising results on the prediction of the protein network
for the yeast {S}accharomyces cerevisiae from four types of widely
available data: gene expressions, protein interactions measured by
yeast two-hybrid systems, protein localizations in the cell and protein
phylogenetic profiles. {T}he method is shown to outperform other
unsupervised protein network inference methods. {W}e finally conduct
a comprehensive prediction of the protein network for all proteins
of the yeast, which enables us to propose protein candidates for
missing enzymes in a biosynthesis pathway. {A}vailability: {S}oftwares
are available upon request.},
pdf = {../local/Yamanishi2004Protein.pdf},
file = {Yamanishi2004Protein.pdf:local/Yamanishi2004Protein.pdf:PDF},
keywords = {biosvm},
owner = {vert},
url = {http://bioinformatics.oupjournals.org/cgi/reprint/19/suppl\_1/i323}
}
@article{Yamanishi2003Extraction,
author = {Yamanishi, Y. and Vert, J.-P. and Nakaya, A. and Kanehisa, M.},
title = {Extraction of correlated gene clusters from multiple genomic data
by generalized kernel canonical correlation analysis},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {i323-i330},
number = {Suppl. 1},
abstract = {Motivation: {A} major issue in computational biology is the reconstruction
of pathways from several genomic datasets, such as expression data,
protein interaction data and phylogenetic profiles. {A}s a first
step toward this goal, it is important to investigate the amount
of correlation which exists between these data. {R}esults: {T}hese
methods are successfully tested on their ability to recognize operons
in the {E}scherichia coli genome, from the comparison of three datasets
corresponding to functional relationships between genes in metabolic
pathways, geometrical relationships along the chromosome, and co-expression
relationships as observed by gene expression data. {C}ontact: yoshi@kuicr.kyoto-u.ac.jp},
pdf = {../local/Yamanishi2003Extraction.pdf},
file = {Yamanishi2003Extraction.pdf:local/Yamanishi2003Extraction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/suppl_1/i323}
}
@article{Yan2004two-stage,
author = {Yan, C. and Dobbs, D. and Honavar, V.},
title = {A two-stage classifier for identification of protein-protein interface
residues},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {i371-i378},
number = {Suppl. 1},
abstract = {Motivation: {T}he ability to identify protein-protein interaction
sites and to detect specific amino acid residues that contribute
to the specificity and affinity of protein interactions has important
implications for problems ranging from rational drug design to analysis
of metabolic and signal transduction networks. {R}esults: {W}e have
developed a two-stage method consisting of a support vector machine
({SVM}) and a {B}ayesian classifier for predicting surface residues
of a protein that participate in protein-protein interactions. {T}his
approach exploits the fact that interface residues tend to form clusters
in the primary amino acid sequence. {O}ur results show that the proposed
two-stage classifier outperforms previously published sequence-based
methods for predicting interface residues. {W}e also present results
obtained using the two-stage classifier on an independent test set
of seven {CAPRI} ({C}ritical {A}ssessment of {PR}edicted {I}nteractions)
targets. {T}he success of the predictions is validated by examining
the predictions in the context of the three-dimensional structures
of protein complexes. {S}upplementary information: http://www.public.iastate.edu/~chhyan/{ISMB}2004/list.html},
pdf = {../local/Yan2004two-stage.pdf},
file = {Yan2004two-stage.pdf:local/Yan2004two-stage.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/suppl_1/i371}
}
@article{Yan2004Identification,
author = {Yan, C. and Honavar, V. and Dobbs, D.},
title = {Identification of interface residues in protease-inhibitor and antigen-antibody
complexes: a support vector machine},
journal = {Neural {C}omput. \& {A}pplic.},
year = {2004},
volume = {13},
pages = {123-129},
doi = {10.1007/s00521-004-0414-3},
pdf = {../local/Yan2004Identification.pdf},
file = {Yan2004Identification.pdf:local/Yan2004Identification.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Yang2004Bio-support,
author = {Yang, Z. R. and Chou, K.-C.},
title = {Bio-support vector machines for computational proteomics},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {735-741},
number = {5},
abstract = {Motivation: {O}ne of the most important issues in computational proteomics
is to produce a prediction model for the classification or annotation
of biological function of novel protein sequences. {I}n order to
improve the prediction accuracy, much attention has been paid to
the improvement of the performance of the algorithms used, few is
for solving the fundamental issue, namely, amino acid encoding as
most existing pattern recognition algorithms are unable to recognize
amino acids in protein sequences. {I}mportantly, the most commonly
used amino acid encoding method has the flaw that leads to large
computational cost and recognition bias. {R}esults: {B}y replacing
kernel functions of support vector machines ({SVM}s) with amino acid
similarity measurement matrices, we have modified {SVM}s, a new type
of pattern recognition algorithm for analysing protein sequences,
particularly for proteolytic cleavage site prediction. {W}e refer
to the modified {SVM}s as bio-support vector machine. {W}hen applied
to the prediction of {HIV} protease cleavage sites, the new method
has shown a remarkable advantage in reducing the model complexity
and enhancing the model robustness.},
pdf = {../local/Yang2004Bio-support.pdf},
file = {Yang2004Bio-support.pdf:local/Yang2004Bio-support.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/5/735}
}
@article{Yao2004Comparative,
author = {X. J. Yao and A. Panaye and J. P. Doucet and R. S. Zhang and H. F.
Chen and M. C. Liu and Z. D. Hu and B. T. Fan},
title = {Comparative study of {QSAR}/{QSPR} correlations using support vector
machines, radial basis function neural networks, and multiple linear
regression.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2004},
volume = {44},
pages = {1257-66},
number = {4},
abstract = {Support vector machines ({SVM}s) were used to develop {QSAR} models
that correlate molecular structures to their toxicity and bioactivities.
{T}he performance and predictive ability of {SVM} are investigated
and compared with other methods such as multiple linear regression
and radial basis function neural network methods. {I}n the present
study, two different data sets were evaluated. {T}he first one involves
an application of {SVM} to the development of a {QSAR} model for
the prediction of toxicities of 153 phenols, and the second investigation
deals with the {QSAR} model between the structures and the activities
of a set of 85 cyclooxygenase 2 ({COX}-2) inhibitors. {F}or each
application, the molecular structures were described using either
the physicochemical parameters or molecular descriptors. {I}n both
studied cases, the predictive ability of the {SVM} model is comparable
or superior to those obtained by {MLR} and {RBFNN}. {T}he results
indicate that {SVM} can be used as an alternative powerful modeling
tool for {QSAR} studies.},
doi = {10.1021/ci049965i},
pdf = {../local/Yao2004Comparative.pdf},
file = {Yao2004Comparative.pdf:local/Yao2004Comparative.pdf:PDF},
keywords = {biosvm chemoinformatics},
url = {http://dx.doi.org/10.1021/ci049965i}
}
@article{Yap2004Prediction,
author = {C. W. Yap and C. Z. Cai and Y. Xue and Y. Z. Chen},
title = {Prediction of torsade-causing potential of drugs by support vector
machine approach.},
journal = {Toxicol {S}ci},
year = {2004},
volume = {79},
pages = {170-7},
number = {1},
month = {May},
abstract = {In an effort to facilitate drug discovery, computational methods for
facilitating the prediction of various adverse drug reactions ({ADR}s)
have been developed. {S}o far, attention has not been sufficiently
paid to the development of methods for the prediction of serious
{ADR}s that occur less frequently. {S}ome of these {ADR}s, such as
torsade de pointes ({T}d{P}), are important issues in the approval
of drugs for certain diseases. {T}hus there is a need to develop
tools for facilitating the prediction of these {ADR}s. {T}his work
explores the use of a statistical learning method, support vector
machine ({SVM}), for {T}d{P} prediction. {T}d{P} involves multiple
mechanisms and {SVM} is a method suitable for such a problem. {O}ur
{SVM} classification system used a set of linear solvation energy
relationship ({LSER}) descriptors and was optimized by leave-one-out
cross validation procedure. {I}ts prediction accuracy was evaluated
by using an independent set of agents and by comparison with results
obtained from other commonly used classification methods using the
same dataset and optimization procedure. {T}he accuracies for the
{SVM} prediction of {T}d{P}-causing agents and non-{T}d{P}-causing
agents are 97.4 and 84.6\% respectively; one is substantially improved
against and the other is comparable to the results obtained by other
classification methods useful for multiple-mechanism prediction problems.
{T}his indicates the potential of {SVM} in facilitating the prediction
of {T}d{P}-causing risk of small molecules and perhaps other {ADR}s
that involve multiple mechanisms.},
doi = {10.1093/toxsci/kfh082},
pdf = {../local/Yap2004Prediction.pdf},
file = {Yap2004Prediction.pdf:local/Yap2004Prediction.pdf:PDF},
keywords = {biosvm chemoinformatics},
pii = {kfh082},
url = {http://dx.doi.org/10.1093/toxsci/kfh082}
}
@article{Yap2005Prediction,
author = {C. W. Yap and Y. Z. Chen},
title = {Prediction of {C}ytochrome {P}450 3{A}4, 2{D}6, and 2{C}9 {I}nhibitors
and {S}ubstrates by {U}sing {S}upport {V}ector {M}achines.},
journal = {J {C}hem {I}nf {M}odel},
year = {2005},
volume = {45},
pages = {982-92},
number = {4},
abstract = {Statistical learning methods have been used in developing filters
for predicting inhibitors of two {P}450 isoenzymes, {CYP}3{A}4 and
{CYP}2{D}6. {T}his work explores the use of different statistical
learning methods for predicting inhibitors of these enzymes and an
additional {P}450 enzyme, {CYP}2{C}9, and the substrates of the three
{P}450 isoenzymes. {T}wo consensus support vector machine ({CSVM})
methods, "positive majority" ({PM}-{CSVM}) and "positive probability"
({PP}-{CSVM}), were used in this work. {T}hese methods were first
tested for the prediction of inhibitors of {CYP}3{A}4 and {CYP}2{D}6
by using a significantly higher number of inhibitors and noninhibitors
than that used in earlier studies. {T}hey were then applied to the
prediction of inhibitors of {CYP}2{C}9 and substrates of the three
enzymes. {B}oth methods predict inhibitors of {CYP}3{A}4 and {CYP}2{D}6
at a similar level of accuracy as those of earlier studies. {F}or
classification of inhibitors of {CYP}2{C}9, the best {CSVM} method
gives an accuracy of 88.9\% for inhibitors and 96.3\% for noninhibitors.
{T}he accuracies for classification of substrates and nonsubstrates
of {CYP}3{A}4, {CYP}2{D}6, and {CYP}2{C}9 are 98.2 and 90.9\%, 96.6
and 94.4\%, and 85.7 and 98.8\%, respectively. {B}oth {CSVM} methods
are potentially useful as filters for predicting inhibitors and substrates
of {P}450 isoenzymes. {T}hese methods generally give better accuracies
than single {SVM} classification systems, and the performance of
the {PP}-{CSVM} method is slightly better than that of the {PM}-{CSVM}
method.},
doi = {10.1021/ci0500536},
pdf = {../local/Yap2005Prediction.pdf},
file = {Yap2005Prediction.pdf:local/Yap2005Prediction.pdf:PDF},
keywords = {biosvm chemoinformatics},
url = {http://dx.doi.org/10.1021/ci0500536}
}
@article{Yeang2001Molecular,
author = {Yeang, C.H. and Ramaswamy, S. and Tamayo, P. and Mukherjee, S. and
Rifkin, R.M. and Angelo, M. and Reich, M. and Lander, E. and Mesirov,
J. and Golub, T.},
title = {Molecular classification of multiple tumor types},
journal = {Bioinformatics},
year = {2001},
volume = {17},
pages = {S316--S322},
number = {Suppl. 1},
abstract = {Using gene expression data to classify tumor types is a very promising
tool in cancer diagnosis. {P}revious works show several pairs of
tumor types can be successfully distinguished by their gene expression
patterns ({G}olub et al. 1999, {B}en-{D}or et al. 2000, {A}lizadeh
et al. 2000). {H}owever, the simultaneous classification across a
heterogeneous set of tumor types has not been well studied yet. {W}e
obtained 190 samples from 14 tumor classes and generated a combined
expression dataset containing 16063 genes for each of those samples.
{W}e performed multi-class classification by combining the outputs
of binary classifiers. {T}hree binary classifiers (k-nearest neighbors,
weighted voting, and support vector machines) were applied in conjunction
with three combination scenarios (one-vs-all, all-pairs, hierarchical
partitioning). {W}e achieved the best cross validation error rate
of 18.75% and the best test error rate of 21.74% by using the one-vs-all
support vector machine algorithm. {T}he results demonstrate the feasibility
of performing clinically useful classification from samples of multiple
tumor types.},
pdf = {../local/Yeang2001Molecular.pdf},
file = {Yeang2001Molecular.pdf:local/Yeang2001Molecular.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/17/suppl_1/S316}
}
@article{Yiu2005Filtering,
author = {Yiu, S. M. and Wong, Prudence W. H. and Lam, T.W. and Mui, Y.C. and
Kung, H. F. and Lin, Marie and Cheung, Y. T.},
title = {Filtering of {I}neffective si{RNA}s and {I}mproved si{RNA} {D}esign
{T}ool},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {144-151},
number = {2},
month = {Jan},
note = {To appear},
abstract = {Motivation: {S}hort interfering {RNA}s (si{RNA}s) can be used to suppress
gene expression and possess many potential applications in therapy,
but how to design an effective si{RNA} is still not clear. {B}ased
on the {MPI} ({M}ax-{P}lanck-{I}nstitute) basic principles, a number
of si{RNA} design tools have been developed recently. {T}he set of
candidates reported by these tools is usually large and often contains
ineffective si{RNA}s. {I}n view of this, we initiate the study of
filtering ineffective si{RNA}s. {R}esults: {T}he contribution of
this paper is 2-fold. {F}irst, we propose a fair scheme to compare
existing design tools based on real data in the literature. {S}econd,
we attempt to improve the {MPI} principles and existing tools by
an algorithm that can filter ineffective si{RNA}s. {T}he algorithm
is based on some new observations on the secondary structure, which
we have verified by {AI} techniques (decision trees and support vector
machines). {W}e have tested our algorithm together with the {MPI}
principles and the existing tools. {T}he results show that our filtering
algorithm is effective. {A}vailability: {T}he si{RNA} design software
tool can be found in the website http://www.cs.hku.hk/~sirna/ {C}ontact:
smyiu@cs.hku.hk},
doi = {10.1093/bioinformatics/bth498},
pdf = {../local/Yiu2005Filtering.pdf},
file = {Yiu2005Filtering.pdf:local/Yiu2005Filtering.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/21/2/144}
}
@article{Yoon2003Analysis,
author = {Yoon, Y. and Song, J. and Hong, S.H. and Kim, J.Q.},
title = {Analysis of multiple single nucleotide polymorphisms of candidate
genes related to coronary heart disease susceptibility by using support
vector machines},
journal = {Clin. {C}hem. {L}ab. {M}ed.},
year = {2003},
volume = {41},
pages = {529-534},
number = {4},
abstract = {Coronary heart disease ({CHD}) is a complex genetic disease involving
gene-environment interaction. {M}any association studies between
single nucleotide polymorphisms ({SNP}s) of candidate genes and {CHD}
have been reported. {W}e have applied a new method to analyze such
relationships using support vector machines ({SVM}s), which is one
of the methods for artificial neuronal network. {W}e assumed that
common haplotype implicit in genotypes will differ between cases
and controls, and that this will allow {SVM}-derived patterns to
be classifiable according to subject genotypes. {F}ourteen {SNP}s
of ten candidate genes in 86 {CHD} patients and 119 controls were
investigated. {G}enotypes were transformed to a numerical vector
by giving scores based on difference between the genotypes of each
subject and the reference genotypes, which represent the healthy
normal population. {O}verall classification accuracy by {SVM}s was
64.4% with a receiver operating characteristic ({ROC}) area of 0.639.
{B}y conventional analysis using the chi2 test, the association between
{CHD} and the {SNP} of the scavenger receptor {B}1 gene was most
significant in terms of allele frequencies in cases vs. controls
(p = 0.0001). {I}n conclusion, we suggest that the application of
{SVM}s for association studies of {SNP}s in candidate genes shows
considerable promise and that further work could be usefully performed
upon the estimation of {CHD} susceptibility in individuals of high
risk.},
pdf = {../local/Yoon2003Analysis.pdf},
file = {Yoon2003Analysis.pdf:local/Yoon2003Analysis.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.degruyter.de/journals/cclm/abs/10592.html}
}
@article{Yu2003Fine-grained,
author = {Yu, C.S. and Wang, J.Y. and Yang, J.M. and Lyu, P.C. and Lin, C.J.
and Hwang, J.K.},
title = {Fine-grained protein fold assignment by support vector machines using
generalized npeptide coding schemes and jury voting from multiple-parameter
sets.},
journal = {Proteins},
year = {2003},
volume = {50},
pages = {531},
number = {4},
month = {6},
abstract = {In the coarse-grained fold assignment of major protein classes, such
as all-alpha, all-beta, alpha + beta, alpha/beta proteins, one can
easily achieve high prediction accuracy from primary amino acid sequences.
{H}owever, the fine-grained assignment of folds, such as those defined
in the {S}tructural {C}lassification of {P}roteins ({SCOP}) database,
presents a challenge due to the larger amount of folds available.
{R}ecent study yielded reasonable prediction accuracy of 56.0% on
an independent set of 27 most populated folds. {I}n this communication,
we apply the support vector machine ({SVM}) method, using a combination
of protein descriptors based on the properties derived from the composition
of n-peptide and jury voting, to the fine-grained fold prediction,
and are able to achieve an overall prediction accuracy of 69.6% on
the same independent set-significantly higher than the previous results.
{O}n 10-fold cross-validation, we obtained a prediction accuracy
of 65.3%. {O}ur results show that {SVM} coupled with suitable global
sequence-coding schemes can significantly improve the fine-grained
fold prediction. {O}ur approach should be useful in structure prediction
and modeling.},
doi = {10.1002/prot.10313},
pdf = {../local/Yu2003Fine-grained.pdf},
file = {Yu2003Fine-grained.pdf:local/Yu2003Fine-grained.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/prot.10313}
}
@article{Yu2005Classifying,
author = {Yu, C. and Zavaljevski, N. and Stevens, F. J. and Yackovich, K. and
Reifman, J.},
title = {Classifying noisy protein sequence data: a case study of immunoglobulin
light chains.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {i495-i501},
number = {Supp 1},
month = {Jun},
abstract = {S{UMMARY}: {T}he classification of protein sequences obtained from
patients with various immunoglobulin-related conformational diseases
may provide insight into structural correlates of pathogenicity.
{H}owever, clinical data are very sparse and, in the case of antibody-related
proteins, the collected sequences have large variability with only
a small subset of variations relevant to the protein pathogenicity
(function). {O}n this basis, these sequences represent a model system
for development of strategies to recognize the small subset of function-determining
variations among the much larger number of primary structure diversifications
introduced during evolution. {U}nder such conditions, most protein
classification algorithms have limited accuracy. {T}o address this
problem, we propose a support vector machine ({SVM})-based classifier
that combines sequence and 3{D} structural averaging information.
{E}ach amino acid in the sequence is represented by a set of six
physicochemical properties: hydrophobicity, hydrophilicity, volume,
surface area, bulkiness and refractivity. {E}ach position in the
sequence is described by the properties of the amino acid at that
position and the properties of its neighbors in 3{D} space or in
the sequence. {A} structure template is selected to determine neighbors
in 3{D} space and a window size is used to determine the neighbors
in the sequence. {T}he test data consist of 209 proteins of human
antibody immunoglobulin light chains, each represented by aligned
sequences of 120 amino acids. {T}he methodology is applied to the
classification of protein sequences collected from patients with
and without amyloidosis, and indicates that the proposed modified
classifiers are more robust to sequence variability than standard
{SVM} classifiers, improving classification error between 5 and 25\%
and sensitivity between 9 and 17\%. {T}he classification results
might also suggest possible mechanisms for the propensity of immunoglobulin
light chains to amyloid formation. {CONTACT}: cyu@bioanalysis.org.},
doi = {10.1093/bioinformatics/bti1024},
pdf = {../local/Yu2005Classifying.pdf},
file = {Yu2005Classifying.pdf:local/Yu2005Classifying.pdf:PDF},
keywords = {biosvm},
pii = {21/suppl_1/i495},
url = {http://dx.doi.org/10.1093/bioinformatics/bti1024}
}
@article{Yu2004Predicting,
author = {Yu, C.-S. and Lin, C.-J. and Hwang, J.-K.},
title = {Predicting subcellular localization of proteins for {G}ram-negative
bacteria by support vector machines based on n-peptide compositions},
journal = {Protein {S}ci.},
year = {2004},
volume = {13},
pages = {1402-1406},
number = {5},
abstract = {Gram-negative bacteria have five major subcellular localization sites:
the cytoplasm, the periplasm, the inner membrane, the outer membrane,
and the extracellular space. {T}he subcellular location of a protein
can provide valuable information about its function. {W}ith the rapid
increase of sequenced genomic data, the need for an automated and
accurate tool to predict subcellular localization becomes increasingly
important. {W}e present an approach to predict subcellular localization
for {G}ram-negative bacteria. {T}his method uses the support vector
machines trained by multiple feature vectors based on n-peptide compositions.
{F}or a standard data set comprising 1443 proteins, the overall prediction
accuracy reaches 89%, which, to the best of our knowledge, is the
highest prediction rate ever reported. {O}ur prediction is 14% higher
than that of the recently developed multimodular {PSORT}-{B}. {B}ecause
of its simplicity, this approach can be easily extended to other
organisms and should be a useful tool for the high-throughput and
large-scale analysis of proteomic and genomic data.},
doi = {10.1110/ps.03479604},
pdf = {../local/Yu2004Predicting.pdf},
file = {Yu2004Predicting.pdf:local/Yu2004Predicting.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.proteinscience.org/cgi/content/abstract/13/5/1402}
}
@article{Yu2004integrated,
author = {Yu, J.K. and Chen, Y.D. and Zheng, S.},
title = {An integrated approach to the detection of colorectal cancer utilizing
proteomics and bioinformatics},
journal = {World {J}. {G}astroenterol.},
year = {2004},
volume = {10},
pages = {3127-3131},
number = {21},
abstract = {A{IM}: {T}o find new potential biomarkers and to establish patterns
for early detection of colorectal cancer. {METHODS}: {O}ne hundred
and eighty-two serum samples including 55 from colorectal cancer
({CRC}) patients, 35 from colorectal adenoma ({CRA}) patients and
92 from healthy persons ({HP}) were detected by surface-enhanced
laser desorption/ionization mass spectrometry ({SELDI}-{MS}). {T}he
data of spectra were analyzed by bioinformatics tools like artificial
neural network ({ANN}) and support vector machine ({SVM}). {RESULTS}:
{T}he diagnostic pattern combined with 7 potential biomarkers could
differentiate {CRC} patients from {CRA} patients with a specificity
of 83%, sensitivity of 89% and positive predictive value of 89%.
{T}he diagnostic pattern combined with 4 potential biomarkers could
differentiate {CRC} patients from {HP} with a specificity of 92%,
sensitivity of 89% and positive predictive value of 86%. {CONCLUSION}:
{T}he combination of {SELDI} with bioinformatics tools could help
find new biomarkers and establish patterns with high sensitivity
and specificity for the detection of {CRC}.},
pdf = {../local/Yu2004integrated.pdf},
file = {Yu2004integrated.pdf:local/Yu2004integrated.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert}
}
@article{Yu2005Ovarian,
author = {J. S. Yu and S. Ongarello and R. Fiedler and X. W. Chen and G. Toffolo
and C. Cobelli and Z. Trajanoski},
title = {Ovarian cancer identification based on dimensionality reduction for
high-throughput mass spectrometry data.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {2200-9},
number = {10},
month = {May},
abstract = {M{OTIVATION}: {H}igh-throughput and high-resolution mass spectrometry
instruments are increasingly used for disease classification and
therapeutic guidance. {H}owever, the analysis of immense amount of
data poses considerable challenges. {W}e have therefore developed
a novel method for dimensionality reduction and tested on a published
ovarian high-resolution {SELDI}-{TOF} dataset. {RESULTS}: {W}e have
developed a four-step strategy for data preprocessing based on: (1)
binning, (2) {K}olmogorov-{S}mirnov test, (3) restriction of coefficient
of variation and (4) wavelet analysis. {S}ubsequently, support vector
machines were used for classification. {T}he developed method achieves
an average sensitivity of 97.38\% (sd = 0.0125) and an average specificity
of 93.30\% (sd = 0.0174) in 1000 independent k-fold cross-validations,
where k = 2, ..., 10. {AVAILABILITY}: {T}he software is available
for academic and non-commercial institutions.},
doi = {10.1093/bioinformatics/bti370},
pdf = {../local/Yu2005Ovarian.pdf},
file = {Yu2005Ovarian.pdf:local/Yu2005Ovarian.pdf:PDF},
keywords = {biosvm proteomics},
pii = {bti370},
url = {http://dx.doi.org/10.1093/bioinformatics/bti370}
}
@article{Yu2005integrated,
author = {Yu, J.-k. and Zheng, S. and Tang, Y. and Li, L.},
title = {An integrated approach utilizing proteomics and bioinformatics to
detect ovarian cancer.},
journal = {J {Z}hejiang {U}niv {S}ci {B}},
year = {2005},
volume = {6},
pages = {227-31},
number = {4},
month = {Apr},
abstract = {O{BJECTIVE}: {T}o find new potential biomarkers and establish the
patterns for the detection of ovarian cancer. {METHODS}: {S}ixty
one serum samples including 32 ovarian cancer patients and 29 healthy
people were detected by surface-enhanced laser desorption/ionization
mass spectrometry ({SELDI}-{MS}). {T}he protein fingerprint data
were analyzed by bioinformatics tools. {T}en folds cross-validation
support vector machine ({SVM}) was used to establish the diagnostic
pattern. {RESULTS}: {F}ive potential biomarkers were found (2085
{D}a, 5881 {D}a, 7564 {D}a, 9422 {D}a, 6044 {D}a), combined with
which the diagnostic pattern separated the ovarian cancer from the
healthy samples with a sensitivity of 96.7\%, a specificity of 96.7\%
and a positive predictive value of 96.7\%. {CONCLUSIONS}: {T}he combination
of {SELDI} with bioinformatics tools could find new biomarkers and
establish patterns with high sensitivity and specificity for the
detection of ovarian cancer.},
doi = {10.1631/jzus.2005.B0227},
pdf = {../local/Yu2005integrated.pdf},
file = {Yu2005integrated.pdf:local/Yu2005integrated.pdf:PDF},
keywords = {biosvm},
url = {http://dx.doi.org/10.1631/jzus.2005.B0227}
}
@article{Yuan2002Prediction,
author = {Yuan, Z. and Burrage, K. and Mattick, J.S.},
title = {Prediction of protein solvent accessibility using support vector
machines},
journal = {Proteins},
year = {2002},
volume = {48},
pages = {566-570},
number = {3},
abstract = {A {S}upport {V}ector {M}achine learning system has been trained to
predict protein solvent accessibility from the primary structure.
{D}ifferent kernel functions and sliding window sizes have been explored
to find how they affect the prediction performance. {U}sing a cut-off
threshold of 15% that splits the dataset evenly (an equal number
of exposed and buried residues), this method was able to achieve
a prediction accuracy of 70.1% for single sequence input and 73.9%
for multiple alignment sequence input, respectively. {T}he prediction
of three and more states of solvent accessibility was also studied
and compared with other methods. {T}he prediction accuracies are
better than, or comparable to, those obtained by other methods such
as neural networks, {B}ayesian classification, multiple linear regression,
and information theory. {I}n addition, our results further suggest
that this system may be combined with other prediction methods to
achieve more reliable results, and that the {S}upport {V}ector {M}achine
method is a very useful tool for biological sequence analysis.},
doi = {10.1002/prot.10176},
pdf = {../local/Yuan2002Prediction.pdf},
file = {Yuan2002Prediction.pdf:local/Yuan2002Prediction.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/prot.10176}
}
@article{Yuan2004SVMtm,
author = {Yuan, Z. and Mattick, J.S. and Teasdale, R.D.},
title = {{{SVM}tm}: support vector machines to predict transmembrane segments.},
journal = {J. {C}omput. {C}hem.},
year = {2004},
volume = {25},
pages = {632},
number = {5},
month = {6},
abstract = {A new method has been developed for prediction of transmembrane helices
using support vector machines. {D}ifferent coding schemes of protein
sequences were explored, and their performances were assessed by
crossvalidation tests. {T}he best performance method can predict
the transmembrane helices with sensitivity of 93.4% and precision
of 92.0%. {F}or each predicted transmembrane segment, a score is
given to show the strength of transmembrane signal and the prediction
reliability. {I}n particular, this method can distinguish transmembrane
proteins from soluble proteins with an accuracy of approximately
99%. {T}his method can be used to complement current transmembrane
helix prediction methods and can be used for consensus analysis of
entire proteomes. {T}he predictor is located at http://genet.imb.uq.edu.au/predictors/{SVM}tm.},
doi = {10.1002/jcc.10411},
pdf = {../local/Yuan2004SVMtm.pdf},
file = {Yuan2004SVMtm.pdf:local/Yuan2004SVMtm.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/jcc.10411}
}
@article{Zaki2005Application,
author = {Zaki, N. M. and Deris, S. and Illias, R.},
title = {Application of string kernels in protein sequence classification.},
journal = {Appl. {B}ioinformatics},
year = {2005},
volume = {4},
pages = {45-52},
number = {1},
abstract = {I{NTRODUCTION}: {T}he production of biological information has become
much greater than its consumption. {T}he key issue now is how to
organise and manage the huge amount of novel information to facilitate
access to this useful and important biological information. {O}ne
core problem in classifying biological information is the annotation
of new protein sequences with structural and functional features.
{METHOD}: {T}his article introduces the application of string kernels
in classifying protein sequences into homogeneous families. {A} string
kernel approach used in conjunction with support vector machines
has been shown to achieve good performance in text categorisation
tasks. {W}e evaluated and analysed the performance of this approach,
and we present experimental results on three selected families from
the {SCOP} ({S}tructural {C}lassification of {P}roteins) database.
{W}e then compared the overall performance of this method with the
existing protein classification methods on benchmark {SCOP} datasets.
{RESULTS}: {A}ccording to the {F}1 performance measure and the rate
of false positive ({RFP}) measure, the string kernel method performs
well in classifying protein sequences. {T}he method outperformed
all the generative-based methods and is comparable with the {SVM}-{F}isher
method. {DISCUSSION}: {A}lthough the string kernel approach makes
no use of prior biological knowledge, it still captures sufficient
biological information to enable it to outperform some of the state-of-the-art
methods.},
keywords = {biosvm},
pii = {415}
}
@article{Zavaljevski2002Support,
author = {Zavaljevski, N. and Stevens, F.J. and Reifman, J.},
title = {Support vector machines with selective kernel scaling for protein
classification and identification of key amino acid positions },
journal = {Bioinformatics},
year = {2002},
volume = {18},
pages = {689--696},
number = {5},
abstract = {Motivation: {D}ata that characterize primary and tertiary structures
of proteins are now accumulating at a rapid and accelerating rate
and require automated computational tools to extract critical information
relating amino acid changes with the spectrum of functionally attributes
exhibited by a protein. {W}e propose that immunoglobulin-type beta-domains,
which are found in approximate 400 functionally distinct forms in
humans alone, provide the immense genetic variation within limited
conformational changes that might facilitate the development of new
computational tools. {A}s an initial step, we describe here an approach
based on {S}upport {V}ector {M}achine ({SVM}) technology to identify
amino acid variations that contribute to the functional attribute
of pathological self-assembly by some human antibody light chains
produced during plasma cell diseases. {R}esults: {W}e demonstrate
that {SVM}s with selective kernel scaling are an effective tool in
discriminating between benign and pathologic human immunoglobulin
light chains. {I}nitial results compare favorably against manual
classification performed by experts and indicate the capability of
{SVM}s to capture the underlying structure of the data. {T}he data
set consists of 70 proteins of human antibody 1 light chains, each
represented by aligned sequences of 120 amino acids. {W}e perform
feature selection based on a first-order adaptive scaling algorithm,
which confirms the importance of changes in certain amino acid positions
and identifies other positions that are key in the characterization
of protein function.},
pdf = {../local/zava02.pdf},
file = {zava02.pdf:local/zava02.pdf:PDF},
keywords = {biosvm},
subject = {biokernel},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/18/5/689}
}
@article{Zernov2003Drug,
author = {V. V. Zernov and K. V. Balakin and A. A. Ivaschenko and N. P. Savchuk
and I. V. Pletnev},
title = {Drug discovery using support vector machines. {T}he case studies
of drug-likeness, agrochemical-likeness, and enzyme inhibition predictions.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2003},
volume = {43},
pages = {2048-56},
number = {6},
abstract = {Support {V}ector {M}achines ({SVM}) is a powerful classification and
regression tool that is becoming increasingly popular in various
machine learning applications. {W}e tested the ability of {SVM},
in comparison with well-known neural network techniques, to predict
drug-likeness and agrochemical-likeness for large compound collections.
{F}or both kinds of data, {SVM} outperforms various neural networks
using the same set of descriptors. {W}e also used {SVM} for estimating
the activity of {C}arbonic {A}nhydrase {II} ({CA} {II}) enzyme inhibitors
and found that the prediction quality of our {SVM} model is better
than that reported earlier for conventional {QSAR}. {M}odel characteristics
and data set features were studied in detail.},
doi = {10.1021/ci0340916},
pdf = {../local/Zernov2003Drug.pdf},
file = {Zernov2003Drug.pdf:local/Zernov2003Drug.pdf:PDF},
keywords = {biosvm chemoinformatics},
url = {http://dx.doi.org/10.1021/ci0340916}
}
@article{Zhang2005Improved,
author = {Qidong Zhang and Sukjoon Yoon and William J Welsh},
title = {Improved method for predicting beta-turn using support vector machine.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {2370-4},
number = {10},
month = {May},
abstract = {M{OTIVATION}: {N}umerous methods for predicting beta-turns in proteins
have been developed based on various computational schemes. {H}ere,
we introduce a new method of beta-turn prediction that uses the support
vector machine ({SVM}) algorithm together with predicted secondary
structure information. {V}arious parameters from the {SVM} have been
adjusted to achieve optimal prediction performance. {RESULTS}: {T}he
{SVM} method achieved excellent performance as measured by the {M}atthews
correlation coefficient ({MCC} = 0.45) using a 7-fold cross validation
on a database of 426 non-homologous protein chains. {T}o our best
knowledge, this {MCC} value is the highest achieved so far for predicting
beta-turn. {T}he overall prediction accuracy {Q}total was 77.3\%,
which is the best among the existing prediction methods. {A}mong
its unique attractive features, the present {SVM} method avoids overtraining
and compresses information and provides a predicted reliability index.},
doi = {10.1093/bioinformatics/bti358},
pdf = {../local/Zhang2005Improved.pdf},
file = {Zhang2005Improved.pdf:local/Zhang2005Improved.pdf:PDF},
keywords = {biosvm},
pii = {bti358},
url = {http://dx.doi.org/10.1093/bioinformatics/bti358}
}
@article{Zhang2003Classification,
author = {Zhang, S.-W. and Pan, Q. and Zhang, H.-C. and Zhang, Y-L. and Wang,
H.-Y.},
title = {Classification of protein quaternary structure with support vector
machine},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {2390-2396},
number = {18},
abstract = {Motivation: {S}ince the gap between sharply increasing known sequences
and slow accumulation of known structures is becoming large, an automatic
classification process based on the primary sequences and known three-dimensional
structure becomes indispensable. {T}he classification of protein
quaternary structure based on the primary sequences can provide some
useful information for the biologists. {S}o a fully automatic and
reliable classification system is needed. {T}his work tries to look
for the effective methods of extracting attribute and the algorithm
for classifying the quaternary structure from the primary sequences.
{R}esults: {B}oth of the support vector machine ({SVM}) and the covariant
discriminant algorithms have been first introduced to predict quaternary
structure properties from the protein primary sequences. {T}he amino
acid composition and the auto-correlation functions based on the
amino acid index profile of the primary sequence have been taken
into account in the algorithms. {W}e have analyzed 472 amino acid
indices and selected the four amino acid indices as the examples,
which have the best performance. {T}hus the five attribute parameter
data sets ({COMP}, {FASG}, {NISK}, {WOLS} and {KYTJ}) were established
from the protein primary sequences. {T}he {COMP} attribute data set
is composed of amino acid composition, and the {FASG}, {NISK}, {WOLS}
and {KYTJ} attribute data sets are composed of the amino acid composition
and the auto-correlation functions of the corresponding amino acid
residue index. {T}he overall accuracies of {SVM} are 78.5, 87.5,
83.2, 81.7 and 81.9%, respectively, for {COMP}, {FASG}, {NISK}, {WOLS}
and {KYTJ} data sets in jackknife test, which are 19.6, 7.8, 15.5,
13.1 and 15.8%, respectively, higher than that of the covariant discriminant
algorithm in the same test. {T}he results show that {SVM} may be
applied to discriminate between the primary sequences of homodimers
and non-homodimers and the two protein sequence descriptors can reflect
the quaternary structure information. {C}ompared with previous {R}obert
{G}arian's investigation, the performance of {SVM} is almost equal
to that of the {D}ecision tree models, and the methods of extracting
feature vector from the primary sequences are superior to {R}obert's
binning function method. {A}vailability: {P}rograms are available
on request from the authors.},
pdf = {../local/Zhang2003Classification.pdf},
file = {Zhang2003Classification.pdf:local/Zhang2003Classification.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/18/2390}
}
@article{Zhang2003Sequence,
author = {Zhang, X. H-F. and Heller, K. A. and Hefter, I. and Leslie, C. S.
and Chasin, L. A.},
title = {Sequence {I}nformation for the {S}plicing of {H}uman {P}re-m{RNA}
{I}dentified by {S}upport {V}ector {M}achine {C}lassification},
journal = {Genome {R}es.},
year = {2003},
volume = {13},
pages = {2637-2650},
number = {12},
abstract = {Vertebrate pre-m{RNA} transcripts contain many sequences that resemble
splice sites on the basis of agreement to the consensus, yet these
more numerous false splice sites are usually completely ignored by
the cellular splicing machinery. {E}ven at the level of exon definition,
pseudo exons defined by such false splices sites outnumber real exons
by an order of magnitude. {W}e used a support vector machine to discover
sequence information that could be used to distinguish real exons
from pseudo exons. {T}his machine learning tool led to the definition
of potential branch points, an extended polypyrimidine tract, and
{C}-rich and {TG}-rich motifs in a region limited to 50 nt upstream
of constitutively spliced exons. {C}-rich sequences were also found
in a region extending to 80 nt downstream of exons, along with {G}-triplet
motifs. {I}n addition, it was shown that combinations of three bases
within the splice donor consensus sequence were more effective than
consensus values in distinguishing real from pseudo splice sites;
two-way base combinations were optimal for distinguishing 3' splice
sites. {T}hese data also suggest that interactions between two or
more of these elements may contribute to exon recognition, and provide
candidate sequences for assessment as intronic splicing enhancers.},
doi = {10.1101/gr.1679003},
pdf = {../local/Zhang2003Sequence.pdf},
file = {Zhang2003Sequence.pdf:local/Zhang2003Sequence.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://www.genome.org/cgi/content/abstract/13/12/2637}
}
@article{Zhang2005Descriptor-based,
author = {Zhang, Z. and Kochhar, S. and Grigorov, M. G.},
title = {Descriptor-based protein remote homology identification.},
journal = {Protein {S}ci.},
year = {2005},
volume = {42},
pages = {431-444},
number = {2},
abstract = {Here, we report a novel protein sequence descriptor-based remote homology
identification method, able to infer fold relationships without the
explicit knowledge of structure. {I}n a first phase, we have individually
benchmarked 13 different descriptor types in fold identification
experiments in a highly diverse set of protein sequences. {T}he relevant
descriptors were related to the fold class membership by using simple
similarity measures in the descriptor spaces, such as the cosine
angle. {O}ur results revealed that the three best-performing sets
of descriptors were the sequence-alignment-based descriptor using
{PSI}-{BLAST} e-values, the descriptors based on the alignment of
secondary structural elements ({SSEA}), and the descriptors based
on the occurrence of {PROSITE} functional motifs. {I}n a second phase,
the three top-performing descriptors were combined to obtain a final
method with improved performance, which we named {D}esc{F}old. {C}lass
membership was predicted by {S}upport {V}ector {M}achine ({SVM})
learning. {I}n comparison with the individual {PSI}-{BLAST}-based
descriptor, the rate of remote homology identification increased
from 33.7% to 46.3%. {W}e found out that the composite set of descriptors
was able to identify the true remote homolog for nearly every sixth
sequence at the 95% confidence level, or some 10% more than a single
{PSI}-{BLAST} search. {W}e have benchmarked the {D}esc{F}old method
against several other state-of-the-art fold recognition algorithms
for the 172 {L}ive{B}ench-8 targets, and we concluded that it was
able to add value to the existing techniques by providing a confident
hit for at least 10% of the sequences not identifiable by the previously
known methods.},
doi = {10.1110/ps.041035505},
pdf = {../local/Zhang2005Descriptor-based.pdf},
file = {Zhang2005Descriptor-based.pdf:local/Zhang2005Descriptor-based.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1110/ps.041035505}
}
@article{Zhao2003Application,
author = {Zhao, Y. and Pinilla, C. and Valmori, D. and Martin, R. and Simon,
R.},
title = {Application of support vector machines for {T}-cell epitopes prediction},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {1978-1984},
number = {15},
abstract = {Motivation: {T}he {T}-cell receptor, a major histocompatibility complex
({MHC}) molecule, and a bound antigenic peptide, play major roles
in the process of antigen-specific {T}-cell activation. {T}-cell
recognition was long considered exquisitely specific. {R}ecent data
also indicate that it is highly flexible, and one receptor may recognize
thousands of different peptides. {D}eciphering the patterns of peptides
that elicit a {MHC} restricted {T}-cell response is critical for
vaccine development. {R}esults: {F}or the first time we develop a
support vector machine ({SVM}) for {T}-cell epitope prediction with
an {MHC} type {I} restricted {T}-cell clone. {U}sing cross-validation,
we demonstrate that {SVM}s can be trained on relatively small data
sets to provide prediction more accurate than those based on previously
published methods or on {MHC} binding. {S}upplementary information:
{D}ata for 203 synthesized peptides is available at http://linus.nci.nih.gov/{D}ata/{LAU}203_{P}eptide.pdf},
pdf = {../local/Zhao2003Application.pdf},
file = {Zhao2003Application.pdf:local/Zhao2003Application.pdf:PDF},
keywords = {biosvm immunoinformatics},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/19/15/1978}
}
@article{Zhou2005Recognition,
author = {GuoDong Zhou and Dan Shen and Jie Zhang and Jian Su and SoonHeng
Tan},
title = {Recognition of protein/gene names from text using an ensemble of
classifiers.},
journal = {B{MC} {B}ioinformatics},
year = {2005},
volume = {6 Suppl 1},
pages = {S7},
abstract = {This paper proposes an ensemble of classifiers for biomedical name
recognition in which three classifiers, one {S}upport {V}ector {M}achine
and two discriminative {H}idden {M}arkov {M}odels, are combined effectively
using a simple majority voting strategy. {I}n addition, we incorporate
three post-processing modules, including an abbreviation resolution
module, a protein/gene name refinement module and a simple dictionary
matching module, into the system to further improve the performance.
{E}valuation shows that our system achieves the best performance
from among 10 systems with a balanced {F}-measure of 82.58 on the
closed evaluation of the {B}io{C}reative protein/gene name recognition
task ({T}ask 1{A}).},
doi = {10.1186/1471-2105-6-S1-S7},
pdf = {../local/Zhou2005Recognition.pdf},
file = {Zhou2005Recognition.pdf:local/Zhou2005Recognition.pdf:PDF},
keywords = {biosvm nlp},
pii = {1471-2105-6-S1-S7},
url = {http://dx.doi.org/10.1186/1471-2105-6-S1-S7}
}
@article{Zhou2005LS,
author = {Xin Zhou and K. Z. Mao},
title = {L{S} {B}ound based gene selection for {DNA} microarray data.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {1559-64},
number = {8},
month = {Apr},
abstract = {M{OTIVATION}: {O}ne problem with discriminant analysis of {DNA} microarray
data is that each sample is represented by quite a large number of
genes, and many of them are irrelevant, insignificant or redundant
to the discriminant problem at hand. {M}ethods for selecting important
genes are, therefore, of much significance in microarray data analysis.
{I}n the present study, a new criterion, called {LS} {B}ound measure,
is proposed to address the gene selection problem. {T}he {LS} {B}ound
measure is derived from leave-one-out procedure of {LS}-{SVM}s (least
squares support vector machines), and as the upper bound for leave-one-out
classification results it reflects to some extent the generalization
performance of gene subsets. {RESULTS}: {W}e applied this {LS} {B}ound
measure for gene selection on two benchmark microarray datasets:
colon cancer and leukemia. {W}e also compared the {LS} {B}ound measure
with other evaluation criteria, including the well-known {F}isher's
ratio and {M}ahalanobis class separability measure, and other published
gene selection algorithms, including {W}eighting factor and {SVM}
{R}ecursive {F}eature {E}limination. {T}he strength of the {LS} {B}ound
measure is that it provides gene subsets leading to more accurate
classification results than the filter method while its computational
complexity is at the level of the filter method. {AVAILABILITY}:
{A} companion website can be accessed at http://www.ntu.edu.sg/home5/pg02776030/lsbound/.
{T}he website contains: (1) the source code of the gene selection
algorithm; (2) the complete set of tables and figures regarding the
experimental study; (3) proof of the inequality (9). {CONTACT}: ekzmao@ntu.edu.sg.},
doi = {10.1093/bioinformatics/bti216},
pdf = {../local/Zhou2005LS.pdf},
file = {Zhou2005LS.pdf:local/Zhou2005LS.pdf:PDF},
keywords = {biosvm featureselection microarray},
pii = {bti216},
url = {http://dx.doi.org/10.1093/bioinformatics/bti216}
}
@article{Zien2000Engineering,
author = {Zien, A. and R{\"a}tsch, G. and Mika, S. and Sch{\"o}lkopf, B. and
Lengauer, T. and M{\"u}ller, K.-R.},
title = {Engineering support vector machine kernels that recognize translation
initiation sites},
journal = {Bioinformatics},
year = {2000},
volume = {16},
pages = {799-807},
number = {9},
abstract = {Motivation: {I}n order to extract protein sequences from nucleotide
sequences, it is an important step to recognize points at which regions
start that code for proteins. {T}hese points are called translation
initiation sites ({TIS}). {R}esults: {T}he task of finding {TIS}
can be modeled as a classification problem. {W}e demonstrate the
applicability of support vector machines for this task, and show
how to incorporate prior biological knowledge by engineering an appropriate
kernel function. {W}ith the described techniques the recognition
performance can be improved by 26% over leading existing approaches.
{W}e provide evidence that existing related methods (e.g. {ESTS}can)
could profit from advanced {TIS} recognition.},
pdf = {../local/Zien2000Engineering.pdf},
file = {Zien2000Engineering.pdf:local/Zien2000Engineering.pdf:PDF},
keywords = {biosvm},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/16/9/799}
}
@comment{{jabref-meta: selector_author:}}
@comment{{jabref-meta: selector_journal:Adv. Drug Deliv. Rev.;Am. J. Hu
m. Genet.;Am. J. Pathol.;Ann. Appl. Stat.;Ann. Math. Statist.;Ann. N.
Y. Acad. Sci.;Ann. Probab.;Ann. Stat.;Artif. Intell. Med.;Bernoulli;Bi
ochim. Biophys. Acta;Bioinformatics;Biometrika;BMC Bioinformatics;Br.
J. Pharmacol.;Breast Cancer Res.;Cell;Cell. Signal.;Chem. Res. Toxicol
.;Clin. Cancer Res.;Combinator. Probab. Comput.;Comm. Pure Appl. Math.
;Comput. Chem.;Comput. Comm. Rev.;Comput. Stat. Data An.;Curr. Genom.;
Curr. Opin. Chem. Biol.;Curr. Opin. Drug Discov. Devel.;Data Min. Know
l. Discov.;Electron. J. Statist.;Eur. J. Hum. Genet.;FEBS Lett.;Found.
Comput. Math.;Genome Biol.;IEEE T. Neural Networ.;IEEE T. Pattern. An
al.;IEEE T. Signal. Proces.;IEEE Trans. Inform. Theory;IEEE Trans. Kno
wl. Data Eng.;IEEE/ACM Trans. Comput. Biol. Bioinf.;Int. J. Comput. Vi
sion;Int. J. Data Min. Bioinform.;Int. J. Qantum Chem.;J Biol Syst;J.
ACM;J. Am. Soc. Inf. Sci. Technol.;J. Am. Stat. Assoc.;J. Bioinform. C
omput. Biol.;J. Biol. Chem.;J. Biomed. Inform.;J. Cell. Biochem.;J. Ch
em. Inf. Comput. Sci.;J. Chem. Inf. Model.;J. Clin. Oncol.;J. Comput.
Biol.;J. Comput. Graph. Stat.;J. Eur. Math. Soc.;J. Intell. Inform. Sy
st.;J. Mach. Learn. Res.;J. Med. Chem.;J. Mol. BIol.;J. R. Stat. Soc.
Ser. B;Journal of Statistical Planning and Inference;Mach. Learn.;Math
. Program.;Meth. Enzymol.;Mol. Biol. Cell;Mol. Biol. Evol.;Mol. Cell.
Biol.;Mol. Syst. Biol.;N. Engl. J. Med.;Nat. Biotechnol.;Nat. Genet.;N
at. Med.;Nat. Methods;Nat. Rev. Cancer;Nat. Rev. Drug Discov.;Nat. Rev
. Genet.;Nature;Neural Comput.;Neural Network.;Neurocomputing;Nucleic
Acids Res.;Pattern Anal. Appl.;Pattern Recognit.;Phys. Rev. E;Phys. Re
v. Lett.;PLoS Biology;PLoS Comput. Biol.;Probab. Theory Relat. Fields;
Proc. IEEE;Proc. Natl. Acad. Sci. USA;Protein Eng.;Protein Eng. Des. S
el.;Protein Sci.;Protein. Struct. Funct. Genet.;Random Struct. Algorit
hm.;Rev. Mod. Phys.;Science;Stat. Probab. Lett.;Statistica Sinica;Theo
r. Comput. Sci.;Trans. Am. Math. Soc.;Trends Genet.;}}
@comment{{jabref-meta: selector_keywords:biogm;biosvm;breastcancer;cgh;
chemogenomics;chemoinformatics;csbcbook;csbcbook-ch1;csbcbook-ch2;csbc
book-ch3;csbcbook-ch4;csbcbook-ch5;csbcbook-ch6;csbcbook-ch7;csbcbook-
ch8;csbcbook-ch9;csbcbook-mustread;dimred;featureselection;glycans;her
g;hic;highcontentscreening;image;immunoinformatics;kernel-theory;kerne
lbook;lasso;microarray;ngs;nlp;plasmodium;proteomics;PUlearning;rnaseq
;segmentation;sirna;}}
@comment{{jabref-meta: selector_booktitle:Adv. Neural. Inform. Process
Syst.;}}
This file was generated by bibtex2html 1.97.