@comment{{This file has been generated by bib2bib 1.97}}
@comment{{Command line: bib2bib ../bibli.bib -c 'subject:"ngs" or keywords:"ngs"' -ob tmp.bib}}
@article{Alkan2009Personalized,
author = {Can Alkan and Jeffrey M Kidd and Tomas Marques-Bonet and Gozde Aksay
and Francesca Antonacci and Fereydoun Hormozdiari and Jacob O Kitzman
and Carl Baker and Maika Malig and Onur Mutlu and S. Cenk Sahinalp
and Richard A Gibbs and Evan E Eichler},
title = {Personalized copy number and segmental duplication maps using next-generation
sequencing.},
journal = {Nat. Genet.},
year = {2009},
volume = {41},
pages = {1061--1067},
number = {10},
month = {Oct},
abstract = {Despite their importance in gene innovation and phenotypic variation,
duplicated regions have remained largely intractable owing to difficulties
in accurately resolving their structure, copy number and sequence
content. We present an algorithm (mrFAST) to comprehensively map
next-generation sequence reads, which allows for the prediction of
absolute copy-number variation of duplicated segments and genes.
We examine three human genomes and experimentally validate genome-wide
copy number differences. We estimate that, on average, 73-87 genes
vary in copy number between any two individuals and find that these
genic differences overwhelmingly correspond to segmental duplications
(odds ratio = 135; P < 2.2 x 10(-16)). Our method can distinguish
between different copies of highly identical genes, providing a more
accurate assessment of gene content and insight into functional constraint
without the limitations of array-based technology.},
doi = {10.1038/ng.437},
pdf = {../local/Alkan2009Personalized.pdf},
file = {Alkan2009Personalized.pdf:Alkan2009Personalized.pdf:PDF},
institution = {Department of Genome Sciences, University of Washington School of
Medicine, Seattle, Washington, USA.},
keywords = {ngs},
owner = {jp},
pii = {ng.437},
pmid = {19718026},
timestamp = {2009.10.09},
url = {http://dx.doi.org/10.1038/ng.437}
}
@article{Bashir2008Evaluation,
author = {Ali Bashir and Stanislav Volik and Colin Collins and Vineet Bafna
and Benjamin J Raphael},
title = {Evaluation of paired-end sequencing strategies for detection of genome
rearrangements in cancer.},
journal = {PLoS Comput. Biol.},
year = {2008},
volume = {4},
pages = {e1000051},
number = {4},
month = {Apr},
abstract = {Paired-end sequencing is emerging as a key technique for assessing
genome rearrangements and structural variation on a genome-wide scale.
This technique is particularly useful for detecting copy-neutral
rearrangements, such as inversions and translocations, which are
common in cancer and can produce novel fusion genes. We address the
question of how much sequencing is required to detect rearrangement
breakpoints and to localize them precisely using both theoretical
models and simulation. We derive a formula for the probability that
a fusion gene exists in a cancer genome given a collection of paired-end
sequences from this genome. We use this formula to compute fusion
gene probabilities in several breast cancer samples, and we find
that we are able to accurately predict fusion genes in these samples
with a relatively small number of fragments of large size. We further
demonstrate how the ability to detect fusion genes depends on the
distribution of gene lengths, and we evaluate how different parameters
of a sequencing strategy impact breakpoint detection, breakpoint
localization, and fusion gene detection, even in the presence of
errors that suggest false rearrangements. These results will be useful
in calibrating future cancer sequencing efforts, particularly large-scale
studies of many cancer genomes that are enabled by next-generation
sequencing technologies.},
doi = {10.1371/journal.pcbi.1000051},
pdf = {../local/Bashir2008Evaluation.pdf},
file = {Bashir2008Evaluation.pdf:Bashir2008Evaluation.pdf:PDF},
institution = {Bioinformatics Graduate Program, University of California San Diego,
San Diego, California, United States of America. abashir@ucsd.edu},
keywords = {ngs},
owner = {jp},
pmid = {18404202},
timestamp = {2009.10.09},
url = {http://dx.doi.org/10.1371/journal.pcbi.1000051}
}
@article{Ben-Elazar2013Spatial,
author = {Ben-Elazar, S. and Yakhini, Z. and Yanai, I.},
title = {Spatial localization of co-regulated genes exceeds genomic gene clustering
in the Saccharomyces cerevisiae genome.},
journal = {Nucleic Acids Res},
year = {2013},
volume = {41},
pages = {2191--2201},
number = {4},
month = {Feb},
abstract = {While it has been long recognized that genes are not randomly positioned
along the genome, the degree to which its 3D structure influences
the arrangement of genes has remained elusive. In particular, several
lines of evidence suggest that actively transcribed genes are spatially
co-localized, forming transcription factories; however, a generalized
systematic test has hitherto not been described. Here we reveal transcription
factories using a rigorous definition of genomic structure based
on Saccharomyces cerevisiae chromosome conformation capture data,
coupled with an experimental design controlling for the primary gene
order. We develop a data-driven method for the interpolation and
the embedding of such datasets and introduce statistics that enable
the comparison of the spatial and genomic densities of genes. Combining
these, we report evidence that co-regulated genes are clustered in
space, beyond their observed clustering in the context of gene order
along the genome and show this phenomenon is significant for 64 out
of 117 transcription factors. Furthermore, we show that those transcription
factors with high spatially co-localized targets are expressed higher
than those whose targets are not spatially clustered. Collectively,
our results support the notion that, at a given time, the physical
density of genes is intimately related to regulatory activity.},
doi = {10.1093/nar/gks1360},
pdf = {../local/Ben-Elazar2013Spatial.pdf},
file = {Ben-Elazar2013Spatial.pdf:Ben-Elazar2013Spatial.pdf:PDF},
institution = {Department of Biology, Technion - Israel Institute of Technology,
Haifa, Israel, Department of Computer Science, Technion - Israel
Institute of Technology, Haifa, Israel and Agilent Laboratories,
Tel Aviv, Israel.},
keywords = {ngs, hic},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {gks1360},
pmid = {23303780},
timestamp = {2013.03.29},
url = {http://dx.doi.org/10.1093/nar/gks1360}
}
@article{Berkum2010HiC,
author = {van Berkum, N. L. and Lieberman-Aiden, E. and Williams, L. and Imakaev,
M. and Gnirke, A. and Mirny, L. A. and Dekker, J. and Lander, E.
S.},
title = {{Hi-C}: a method to study the three-dimensional architecture of genomes.},
journal = {J. Vis. Exp.},
year = {2010},
volume = {39},
pages = {e1869},
abstract = {The three-dimensional folding of chromosomes compartmentalizes the
genome and and can bring distant functional elements, such as promoters
and enhancers, into close spatial proximity (2-6). Deciphering the
relationship between chromosome organization and genome activity
will aid in understanding genomic processes, like transcription and
replication. However, little is known about how chromosomes fold.
Microscopy is unable to distinguish large numbers of loci simultaneously
or at high resolution. To date, the detection of chromosomal interactions
using chromosome conformation capture (3C) and its subsequent adaptations
required the choice of a set of target loci, making genome-wide studies
impossible (7-10). We developed Hi-C, an extension of 3C that is
capable of identifying long range interactions in an unbiased, genome-wide
fashion. In Hi-C, cells are fixed with formaldehyde, causing interacting
loci to be bound to one another by means of covalent DNA-protein
cross-links. When the DNA is subsequently fragmented with a restriction
enzyme, these loci remain linked. A biotinylated residue is incorporated
as the 5' overhangs are filled in. Next, blunt-end ligation is performed
under dilute conditions that favor ligation events between cross-linked
DNA fragments. This results in a genome-wide library of ligation
products, corresponding to pairs of fragments that were originally
in close proximity to each other in the nucleus. Each ligation product
is marked with biotin at the site of the junction. The library is
sheared, and the junctions are pulled-down with streptavidin beads.
The purified junctions can subsequently be analyzed using a high-throughput
sequencer, resulting in a catalog of interacting fragments. Direct
analysis of the resulting contact matrix reveals numerous features
of genomic organization, such as the presence of chromosome territories
and the preferential association of small gene-rich chromosomes.
Correlation analysis can be applied to the contact matrix, demonstrating
that the human genome is segregated into two compartments: a less
densely packed compartment containing open, accessible, and active
chromatin and a more dense compartment containing closed, inaccessible,
and inactive chromatin regions. Finally, ensemble analysis of the
contact matrix, coupled with theoretical derivations and computational
simulations, revealed that at the megabase scale Hi-C reveals features
consistent with a fractal globule conformation.},
doi = {10.3791/1869},
institution = {Program in Gene Function and Expression, Department of Biochemistry
and Molecular Pharmacology, University of Massachusetts Medical School.},
keywords = {ngs, hic},
language = {eng},
medline-pst = {epublish},
owner = {philippe},
pii = {1869},
pmid = {20461051},
timestamp = {2010.07.27},
url = {http://dx.doi.org/10.3791/1869}
}
@article{Boeva2011Control-free,
author = {Boeva, V. and Zinovyev, A. and Bleakley, K. and Vert, J.-P. and Janoueix-Lerosey,
I. and Delattre, O. and Barillot, E.},
title = {Control-free calling of copy number alterations in deep-sequencing
data using {GC}-content normalization.},
journal = {Bioinformatics},
year = {2011},
volume = {27},
pages = {268--269},
number = {2},
month = {Jan},
abstract = {We present a tool for control-free copy number alteration (CNA) detection
using deep-sequencing data, particularly useful for cancer studies.
The tool deals with two frequent problems in the analysis of cancer
deep-sequencing data: absence of control sample and possible polyploidy
of cancer cells. FREEC (control-FREE Copy number caller) automatically
normalizes and segments copy number profiles (CNPs) and calls CNAs.
If ploidy is known, FREEC assigns absolute copy number to each predicted
CNA. To normalize raw CNPs, the user can provide a control dataset
if available; otherwise GC content is used. We demonstrate that for
Illumina single-end, mate-pair or paired-end sequencing, GC-contentr
normalization provides smooth profiles that can be further segmented
and analyzed in order to predict CNAs.Source code and sample data
are available at http://bioinfo-out.curie.fr/projects/freec/.freec@curie.frSupplementary
data are available at Bioinformatics online.},
doi = {10.1093/bioinformatics/btq635},
pdf = {../local/Boeva2011Control-free.pdf},
file = {Boeva2011Control-free.pdf:Boeva2011Control-free.pdf:PDF},
institution = {Institut Curie, INSERM, U900, Paris, F-75248, Mines ParisTech, Fontainebleau,
F-77300 and INSERM, U830, Paris, F-75248 France.},
keywords = {ngs},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {btq635},
pmid = {21081509},
timestamp = {2011.01.25},
url = {http://dx.doi.org/10.1093/bioinformatics/btq635}
}
@article{Bohnert2009Transcript,
author = {Bohnert, R. and Behr, J. and R\"atsch, G.},
title = {Transcript quantification with {RNA-Seq} data},
journal = {BMC Bioinformatics},
year = {2009},
volume = {10 (Suppl 13)},
pages = {P5},
doi = {10.1186/1471-2105-10-S13-P5},
pdf = {../local/Bohnert2009Transcript.pdf},
file = {Bohnert2009Transcript.pdf:Bohnert2009Transcript.pdf:PDF},
keywords = {ngs, rnaseq},
owner = {jp},
timestamp = {2012.03.06},
url = {http://dx.doi.org/10.1186/1471-2105-10-S13-P5}
}
@article{Campbell2008Identification,
author = {Peter J Campbell and Philip J Stephens and Erin D Pleasance and Sarah
O'Meara and Heng Li and Thomas Santarius and Lucy A Stebbings and
Catherine Leroy and Sarah Edkins and Claire Hardy and Jon W Teague
and Andrew Menzies and Ian Goodhead and Daniel J Turner and Christopher
M Clee and Michael A Quail and Antony Cox and Clive Brown and Richard
Durbin and Matthew E Hurles and Paul A W Edwards and Graham R Bignell
and Michael R Stratton and P. Andrew Futreal},
title = {Identification of somatically acquired rearrangements in cancer using
genome-wide massively parallel paired-end sequencing.},
journal = {Nat. Genet.},
year = {2008},
volume = {40},
pages = {722--729},
number = {6},
month = {Jun},
abstract = {Human cancers often carry many somatically acquired genomic rearrangements,
some of which may be implicated in cancer development. However, conventional
strategies for characterizing rearrangements are laborious and low-throughput
and have low sensitivity or poor resolution. We used massively parallel
sequencing to generate sequence reads from both ends of short DNA
fragments derived from the genomes of two individuals with lung cancer.
By investigating read pairs that did not align correctly with respect
to each other on the reference human genome, we characterized 306
germline structural variants and 103 somatic rearrangements to the
base-pair level of resolution. The patterns of germline and somatic
rearrangement were markedly different. Many somatic rearrangements
were from amplicons, although rearrangements outside these regions,
notably including tandem duplications, were also observed. Some somatic
rearrangements led to abnormal transcripts, including two from internal
tandem duplications and two fusion transcripts created by interchromosomal
rearrangements. Germline variants were predominantly mediated by
retrotransposition, often involving AluY and LINE elements. The results
demonstrate the feasibility of systematic, genome-wide characterization
of rearrangements in complex human cancer genomes, raising the prospect
of a new harvest of genes associated with cancer using this strategy.},
doi = {10.1038/ng.128},
pdf = {../local/Campbell2008Identification.pdf},
file = {Campbell2008Identification.pdf:Campbell2008Identification.pdf:PDF},
institution = {Wellcome Trust Sanger Institute, Hinxton CB10 1SA, UK.},
keywords = {ngs},
owner = {jp},
pii = {ng.128},
pmid = {18438408},
timestamp = {2009.10.09},
url = {http://dx.doi.org/10.1038/ng.128}
}
@article{Chen2008Mapping,
author = {Wei Chen and Vera Kalscheuer and Andreas Tzschach and Corinna Menzel
and Reinhard Ullmann and Marcel Holger Schulz and Fikret Erdogan
and Na Li and Zofia Kijas and Ger Arkesteijn and Isidora Lopez Pajares
and Margret Goetz-Sothmann and Uwe Heinrich and Imma Rost and Andreas
Dufke and Ute Grasshoff and Birgitta Glaeser and Martin Vingron and
H. Hilger Ropers},
title = {Mapping translocation breakpoints by next-generation sequencing.},
journal = {Genome Res.},
year = {2008},
volume = {18},
pages = {1143--1149},
number = {7},
month = {Jul},
abstract = {Balanced chromosome rearrangements (BCRs) can cause genetic diseases
by disrupting or inactivating specific genes, and the characterization
of breakpoints in disease-associated BCRs has been instrumental in
the molecular elucidation of a wide variety of genetic disorders.
However, mapping chromosome breakpoints using traditional methods,
such as in situ hybridization with fluorescent dye-labeled bacterial
artificial chromosome clones (BAC-FISH), is rather laborious and
time-consuming. In addition, the resolution of BAC-FISH is often
insufficient to unequivocally identify the disrupted gene. To overcome
these limitations, we have performed shotgun sequencing of flow-sorted
derivative chromosomes using "next-generation" (Illumina/Solexa)
multiplex sequencing-by-synthesis technology. As shown here for three
different disease-associated BCRs, the coverage attained by this
platform is sufficient to bridge the breakpoints by PCR amplification,
and this procedure allows the determination of their exact nucleotide
positions within a few weeks. Its implementation will greatly facilitate
large-scale breakpoint mapping and gene finding in patients with
disease-associated balanced translocations.},
doi = {10.1101/gr.076166.108},
pdf = {../local/Chen2008Mapping.pdf},
file = {Chen2008Mapping.pdf:Chen2008Mapping.pdf:PDF},
institution = {Max Planck Institute for Molecular Genetics, 14195 Berlin, Germany.
wei@molgen.mpg.de},
keywords = {ngs, csbcbook, csbcbook-ch2},
owner = {jp},
pii = {gr.076166.108},
pmid = {18326688},
timestamp = {2009.10.09},
url = {http://dx.doi.org/10.1101/gr.076166.108}
}
@article{Chiang2009High-resolution,
author = {Derek Y Chiang and Gad Getz and David B Jaffe and Michael J T O'Kelly
and Xiaojun Zhao and Scott L Carter and Carsten Russ and Chad Nusbaum
and Matthew Meyerson and Eric S Lander},
title = {High-resolution mapping of copy-number alterations with massively
parallel sequencing.},
journal = {Nat. Methods},
year = {2009},
volume = {6},
pages = {99--103},
number = {1},
month = {Jan},
abstract = {Cancer results from somatic alterations in key genes, including point
mutations, copy-number alterations and structural rearrangements.
A powerful way to discover cancer-causing genes is to identify genomic
regions that show recurrent copy-number alterations (gains and losses)
in tumor genomes. Recent advances in sequencing technologies suggest
that massively parallel sequencing may provide a feasible alternative
to DNA microarrays for detecting copy-number alterations. Here we
present: (i) a statistical analysis of the power to detect copy-number
alterations of a given size; (ii) SegSeq, an algorithm to segment
equal copy numbers from massively parallel sequence data; and (iii)
analysis of experimental data from three matched pairs of tumor and
normal cell lines. We show that a collection of approximately 14
million aligned sequence reads from human cell lines has comparable
power to detect events as the current generation of DNA microarrays
and has over twofold better precision for localizing breakpoints
(typically, to within approximately 1 kilobase).},
doi = {10.1038/nmeth.1276},
pdf = {../local/Chiang2009High-resolution.pdf},
file = {Chiang2009High-resolution.pdf:Chiang2009High-resolution.pdf:PDF},
institution = {Broad Institute, Massachusetts Institute of Technology, 7 Cambridge
Center, Cambridge, MA 02142, USA.},
keywords = {ngs},
owner = {jp},
pii = {nmeth.1276},
pmid = {19043412},
timestamp = {2009.10.09},
url = {http://dx.doi.org/10.1038/nmeth.1276}
}
@article{Dixon2012Topological,
author = {Dixon, J. R. and Selvaraj, S. and Yue, F. and Kim, A. and Li, Y.
and Shen, Y. and Hu, M. and Liu, J. S. and Ren, B.},
title = {Topological domains in mammalian genomes identified by analysis of
chromatin interactions.},
journal = {Nature},
year = {2012},
volume = {485},
pages = {376-80},
number = {5},
doi = {10.1038/nature11082},
pdf = {../local/Dixon2012Topological.pdf},
file = {Dixon2012Topological.pdf:Dixon2012Topological.pdf:PDF},
keywords = {ngs, hic},
owner = {nelle},
timestamp = {2013.03.30},
url = {http://dx.doi.org/10.1038/nature11082}
}
@article{Girirajan2009Sequencing,
author = {Santhosh Girirajan and Lin Chen and Tina Graves and Tomas Marques-Bonet
and Mario Ventura and Catrina Fronick and Lucinda Fulton and Mariano
Rocchi and Robert S Fulton and Richard K Wilson and Elaine R Mardis
and Evan E Eichler},
title = {Sequencing human-gibbon breakpoints of synteny reveals mosaic new
insertions at rearrangement sites},
journal = {Genome Res.},
year = {2009},
volume = {19},
pages = {178--190},
number = {2},
month = {Feb},
abstract = {The gibbon genome exhibits extensive karyotypic diversity with an
increased rate of chromosomal rearrangements during evolution. In
an effort to understand the mechanistic origin and implications of
these rearrangement events, we sequenced 24 synteny breakpoint regions
in the white-cheeked gibbon (Nomascus leucogenys, NLE) in the form
of high-quality BAC insert sequences (4.2 Mbp). While there is a
significant deficit of breakpoints in genes, we identified seven
human gene structures involved in signaling pathways (DEPDC4, GNG10),
phospholipid metabolism (ENPP5, PLSCR2), beta-oxidation (ECH1), cellular
structure and transport (HEATR4), and transcription (ZNF461), that
have been disrupted in the NLE gibbon lineage. Notably, only three
of these genes show the expected evolutionary signatures of pseudogenization.
Sequence analysis of the breakpoints suggested both nonclassical
nonhomologous end-joining (NHEJ) and replication-based mechanisms
of rearrangement. A substantial number (11/24) of human-NLE gibbon
breakpoints showed new insertions of gibbon-specific repeats and
mosaic structures formed from disparate sequences including segmental
duplications, LINE, SINE, and LTR elements. Analysis of these sites
provides a model for a replication-dependent repair mechanism for
double-strand breaks (DSBs) at rearrangement sites and insights into
the structure and formation of primate segmental duplications at
sites of genomic rearrangements during evolution.},
doi = {10.1101/gr.086041.108},
pdf = {../local/Girirajan2009Sequencing.pdf},
file = {Girirajan2009Sequencing.pdf:Girirajan2009Sequencing.pdf:PDF},
institution = {Department of Genome Sciences, Howard Hughes Medical Institute, University
of Washington School of Medicine, Seattle, Washington 98195, USA.},
keywords = {ngs},
owner = {jp},
pii = {gr.086041.108},
pmid = {19029537},
timestamp = {2009.10.09},
url = {http://dx.doi.org/10.1101/gr.086041.108}
}
@article{Harismendy2009Evaluation,
author = {Harismendy, O. and Ng, P. C. and Strausberg, R. L. and Wang, X. and
Stockwell, T. B. and Beeson, K. Y. and Schork, N. J. and Murray,
S. S. and Topol, E. J. and Levy, S. and Frazer, K. A.},
title = {Evaluation of next generation sequencing platforms for population
targeted sequencing studies.},
journal = {Genome Biol.},
year = {2009},
volume = {10},
pages = {R32},
number = {3},
abstract = {Next generation sequencing (NGS) platforms are currently being utilized
for targeted sequencing of candidate genes or genomic intervals to
perform sequence-based association studies. To evaluate these platforms
for this application, we analyzed human sequence generated by the
Roche 454, Illumina GA, and the ABI SOLiD technologies for the same
260 kb in four individuals.Local sequence characteristics contribute
to systematic variability in sequence coverage (>100-fold difference
in per-base coverage), resulting in patterns for each NGS technology
that are highly correlated between samples. A comparison of the base
calls to 88 kb of overlapping ABI 3730xL Sanger sequence generated
for the same samples showed that the NGS platforms all have high
sensitivity, identifying >95\% of variant sites. At high coverage,
depth base calling errors are systematic, resulting from local sequence
contexts; as the coverage is lowered additional 'random sampling'
errors in base calling occur.Our study provides important insights
into systematic biases and data variability that need to be considered
when utilizing NGS platforms for population targeted sequencing studies.},
doi = {10.1186/gb-2009-10-3-r32},
pdf = {../local/Harismendy2009Evaluation.pdf},
file = {Harismendy2009Evaluation.pdf:Harismendy2009Evaluation.pdf:PDF},
institution = {Scripps Genomic Medicine, Scripps Translational Science Institute,
The Scripps Research Institute, La Jolla, CA 92037, USA. oharis@scripps.edu},
keywords = {ngs},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {gb-2009-10-3-r32},
pmid = {19327155},
timestamp = {2011.10.28},
url = {http://dx.doi.org/10.1186/gb-2009-10-3-r32}
}
@article{Homouz20133D,
author = {Homouz, D. and Kudlicki, A. S.},
title = {The {3D} Organization of the Yeast Genome Correlates with Co-Expression
and Reflects Functional Relations between Genes},
journal = {PLoS ONE},
year = {2013},
volume = {8},
pages = {e54699},
number = {1},
month = {01},
abstract = {The spatial organization of eukaryotic genomes is thought to play
an important role in regulating gene expression. The recent advances
in experimental methods including chromatin capture techniques, as
well as the large amounts of accumulated gene expression data allow
studying the relationship between spatial organization of the genome
and co-expression of protein-coding genes. To analyse this genome-wide
relationship at a single gene resolution, we combined the interchromosomal
DNA contacts in the yeast genome measured by Duan et al. with a comprehensive
collection of 1,496 gene expression datasets. We find significant
enhancement of co-expression among genes with contact links. The
co-expression is most prominent when two gene loci fall within 1,000
base pairs from the observed contact. We also demonstrate an enrichment
of inter-chromosomal links between functionally related genes, which
suggests that the non random nature of the genome organization serves
to facilitate coordinated transcription in groups of genes.
},
doi = {10.1371/journal.pone.0054699},
pdf = {../local/Homouz20133D.pdf},
file = {Homouz20133D.pdf:Homouz20133D.pdf:PDF},
keywords = {hic, ngs},
owner = {nelle},
publisher = {Public Library of Science},
timestamp = {2013.03.30},
url = {http://dx.doi.org/10.1371/journal.pone.0054699}
}
@article{Hormozdiari2009Combinatorial,
author = {Fereydoun Hormozdiari and Can Alkan and Evan E Eichler and S. Cenk
Sahinalp},
title = {Combinatorial algorithms for structural variation detection in high-throughput
sequenced genomes.},
journal = {Genome Res.},
year = {2009},
volume = {19},
pages = {1270--1278},
number = {7},
month = {Jul},
abstract = {Recent studies show that along with single nucleotide polymorphisms
and small indels, larger structural variants among human individuals
are common. The Human Genome Structural Variation Project aims to
identify and classify deletions, insertions, and inversions (>5 Kbp)
in a small number of normal individuals with a fosmid-based paired-end
sequencing approach using traditional sequencing technologies. The
realization of new ultra-high-throughput sequencing platforms now
makes it feasible to detect the full spectrum of genomic variation
among many individual genomes, including cancer patients and others
suffering from diseases of genomic origin. Unfortunately, existing
algorithms for identifying structural variation (SV) among individuals
have not been designed to handle the short read lengths and the errors
implied by the "next-gen" sequencing (NGS) technologies. In this
paper, we give combinatorial formulations for the SV detection between
a reference genome sequence and a next-gen-based, paired-end, whole
genome shotgun-sequenced individual. We describe efficient algorithms
for each of the formulations we give, which all turn out to be fast
and quite reliable; they are also applicable to all next-gen sequencing
methods (Illumina, 454 Life Sciences [Roche], ABI SOLiD, etc.) and
traditional capillary sequencing technology. We apply our algorithms
to identify SV among individual genomes very recently sequenced by
Illumina technology.},
doi = {10.1101/gr.088633.108},
pdf = {../local/Hormozdiari2009Combinatorial.pdf},
file = {Hormozdiari2009Combinatorial.pdf:Hormozdiari2009Combinatorial.pdf:PDF},
institution = {School of Computing Science, Simon Fraser University, Burnaby, British
Columbia, Canada V5A 1S6.},
keywords = {ngs},
owner = {jp},
pii = {gr.088633.108},
pmid = {19447966},
timestamp = {2009.10.09},
url = {http://dx.doi.org/10.1101/gr.088633.108}
}
@article{Horner2009Bioinformatics,
author = {Horner, D. S. and Pavesi, G. and Castrignan{\`o}, T. and De Meo,
P. D. and Liuni, S. and Sammeth, M. and Picardi, E. and Pesole, G.},
title = {Bioinformatics approaches for genomics and post genomics applications
of next-generation sequencing.},
journal = {Brief Bioinform},
year = {2009},
month = {Oct},
abstract = {Technical advances such as the development of molecular cloning, Sanger
sequencing, PCR and oligonucleotide microarrays are key to our current
capacity to sequence, annotate and study complete organismal genomes.
Recent years have seen the development of a variety of so-called
'next-generation' sequencing platforms, with several others anticipated
to become available shortly. The previously unimaginable scale and
economy of these methods, coupled with their enthusiastic uptake
by the scientific community and the potential for further improvements
in accuracy and read length, suggest that these technologies are
destined to make a huge and ongoing impact upon genomic and post-genomic
biology. However, like the analysis of microarray data and the assembly
and annotation of complete genome sequences from conventional sequencing
data, the management and analysis of next-generation sequencing data
requires (and indeed has already driven) the development of informatics
tools able to assemble, map, and interpret huge quantities of relatively
or extremely short nucleotide sequence data. Here we provide a broad
overview of bioinformatics approaches that have been introduced for
several genomics and functional genomics applications of next-generation
sequencing.},
doi = {10.1093/bib/bbp046},
pdf = {../local/Horner2009Bioinformatics.pdf},
file = {Horner2009Bioinformatics.pdf:Horner2009Bioinformatics.pdf:PDF},
keywords = {ngs},
language = {eng},
medline-pst = {aheadofprint},
owner = {jp},
pii = {bbp046},
pmid = {19864250},
timestamp = {2010.01.07},
url = {http://dx.doi.org/10.1093/bib/bbp046}
}
@article{Jiang2009Statistical,
author = {Jiang, H. and Wong, W. H.},
title = {Statistical inferences for isoform expression in {RNA-Seq}.},
journal = {Bioinformatics},
year = {2009},
volume = {25},
pages = {1026--1032},
number = {8},
month = {Apr},
abstract = {SUMMARY: The development of RNA sequencing (RNA-Seq) makes it possible
for us to measure transcription at an unprecedented precision and
throughput. However, challenges remain in understanding the source
and distribution of the reads, modeling the transcript abundance
and developing efficient computational methods. In this article,
we develop a method to deal with the isoform expression estimation
problem. The count of reads falling into a locus on the genome annotated
with multiple isoforms is modeled as a Poisson variable. The expression
of each individual isoform is estimated by solving a convex optimization
problem and statistical inferences about the parameters are obtained
from the posterior distribution by importance sampling. Our results
show that isoform expression inference in RNA-Seq is possible by
employing appropriate statistical methods.},
doi = {10.1093/bioinformatics/btp113},
pdf = {../local/Jiang2009Statistical.pdf},
file = {Jiang2009Statistical.pdf:Jiang2009Statistical.pdf:PDF},
institution = {Institute for Computational and Mathematical Engineering and Department
of Statistics, Stanford University, Stanford, CA 94305, USA.},
keywords = {ngs, rnaseq},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {btp113},
pmid = {19244387},
timestamp = {2012.03.06},
url = {http://dx.doi.org/10.1093/bioinformatics/btp113}
}
@article{Korbel2009PEMer,
author = {Korbel, J. and Abyzov, A. and Mu, X. and Carriero, N. and Cayting,
P. and Zhang, Z. and Snyder, Z. and Gerstein, M.},
title = {{PEMer}: a computational framework with simulation-based error models
for inferring genomic structural variants from massive paired-end
sequencing data.},
journal = {Genome Biol.},
year = {2009},
volume = {10},
pages = {R23},
number = {2},
month = {Feb},
abstract = {ABSTRACT: Personal-genomics endeavors, such as the 1000 Genomes project,
are generating maps of genomic structural variants by analyzing ends
of massively sequenced genome fragments. To process these we developed
Paired-End Mapper (PEMer; http://sv.gersteinlab.org/pemer). This
comprises an analysis pipeline, compatible with several next-generation
sequencing platforms; simulation-based error models, yielding confidence-values
for each structural variant; and a back-end database. The simulations
demonstrated high structural variant reconstruction efficiency for
PEMer's coverage-adjusted multi-cutoff scoring-strategy and showed
its relative insensitivity to base-calling errors.},
doi = {10.1186/gb-2009-10-2-r23},
pdf = {../local/Korbel2009PEMer.pdf},
file = {Korbel2009PEMer.pdf:Korbel2009PEMer.pdf:PDF},
institution = {Gene Expression Unit, European Molecular Biology Laboratory (EMBL),
Meyerhofstr,, Heidelberg, 69117, Germany. korbel@embl.de.},
keywords = {ngs},
owner = {jp},
pii = {gb-2009-10-2-r23},
pmid = {19236709},
timestamp = {2009.10.09},
url = {http://dx.doi.org/10.1186/gb-2009-10-2-r23}
}
@article{Korbel2007Paired-end,
author = {Jan O Korbel and Alexander Eckehart Urban and Jason P Affourtit and
Brian Godwin and Fabian Grubert and Jan Fredrik Simons and Philip
M Kim and Dean Palejev and Nicholas J Carriero and Lei Du and Bruce
E Taillon and Zhoutao Chen and Andrea Tanzer and A. C Eugenia Saunders
and Jianxiang Chi and Fengtang Yang and Nigel P Carter and Matthew
E Hurles and Sherman M Weissman and Timothy T Harkins and Mark B
Gerstein and Michael Egholm and Michael Snyder},
title = {Paired-end mapping reveals extensive structural variation in the
human genome.},
journal = {Science},
year = {2007},
volume = {318},
pages = {420--426},
number = {5849},
month = {Oct},
abstract = {Structural variation of the genome involves kilobase- to megabase-sized
deletions, duplications, insertions, inversions, and complex combinations
of rearrangements. We introduce high-throughput and massive paired-end
mapping (PEM), a large-scale genome-sequencing method to identify
structural variants (SVs) approximately 3 kilobases (kb) or larger
that combines the rescue and capture of paired ends of 3-kb fragments,
massive 454 sequencing, and a computational approach to map DNA reads
onto a reference genome. PEM was used to map SVs in an African and
in a putatively European individual and identified shared and divergent
SVs relative to the reference genome. Overall, we fine-mapped more
than 1000 SVs and documented that the number of SVs among humans
is much larger than initially hypothesized; many of the SVs potentially
affect gene function. The breakpoint junction sequences of more than
200 SVs were determined with a novel pooling strategy and computational
analysis. Our analysis provided insights into the mechanisms of SV
formation in humans.},
doi = {10.1126/science.1149504},
pdf = {../local/Korbel2007Paired-end.pdf},
file = {Korbel2007Paired-end.pdf:Korbel2007Paired-end.pdf:PDF},
institution = {Molecular Biophysics and Biochemistry Department, Yale University,
New Haven, CT 06520, USA.},
keywords = {ngs},
owner = {jp},
pii = {1149504},
pmid = {17901297},
timestamp = {2009.10.09},
url = {http://dx.doi.org/10.1126/science.1149504}
}
@article{Langmead2009Ultrafast,
author = {Langmead, B. and Trapnell, C. and Pop, M. and Salzberg, S. L.},
title = {Ultrafast and memory-efficient alignment of short {DNA} sequences
to the human genome.},
journal = {Genome Biol},
year = {2009},
volume = {10},
pages = {R25},
number = {3},
__markedentry = {[jp:]},
abstract = {Bowtie is an ultrafast, memory-efficient alignment program for aligning
short DNA sequence reads to large genomes. For the human genome,
Burrows-Wheeler indexing allows Bowtie to align more than 25 million
reads per CPU hour with a memory footprint of approximately 1.3 gigabytes.
Bowtie extends previous Burrows-Wheeler techniques with a novel quality-aware
backtracking algorithm that permits mismatches. Multiple processor
cores can be used simultaneously to achieve even greater alignment
speeds. Bowtie is open source (http://bowtie.cbcb.umd.edu).},
doi = {10.1186/gb-2009-10-3-r25},
pdf = {../local/Langmead2009Ultrafast.pdf},
file = {Langmead2009Ultrafast.pdf:Langmead2009Ultrafast.pdf:PDF},
institution = {Center for Bioinformatics and Computational Biology, Institute for
Advanced Computer Studies, University of Maryland, College Park,
MD 20742, USA. langmead@cs.umd.edu},
keywords = {ngs},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {gb-2009-10-3-r25},
pmid = {19261174},
timestamp = {2013.03.29},
url = {http://dx.doi.org/10.1186/gb-2009-10-3-r25}
}
@article{Li2008Mapping,
author = {Li, H. and Ruan, J. and Durbin, R.},
title = {Mapping short {DNA} sequencing reads and calling variants using mapping
quality scores.},
journal = {Genome Res.},
year = {2008},
volume = {18},
pages = {1851--1858},
number = {11},
month = {Nov},
abstract = {New sequencing technologies promise a new era in the use of DNA sequence.
However, some of these technologies produce very short reads, typically
of a few tens of base pairs, and to use these reads effectively requires
new algorithms and software. In particular, there is a major issue
in efficiently aligning short reads to a reference genome and handling
ambiguity or lack of accuracy in this alignment. Here we introduce
the concept of mapping quality, a measure of the confidence that
a read actually comes from the position it is aligned to by the mapping
algorithm. We describe the software MAQ that can build assemblies
by mapping shotgun short reads to a reference genome, using quality
scores to derive genotype calls of the consensus sequence of a diploid
genome, e.g., from a human sample. MAQ makes full use of mate-pair
information and estimates the error probability of each read alignment.
Error probabilities are also derived for the final genotype calls,
using a Bayesian statistical model that incorporates the mapping
qualities, error probabilities from the raw sequence quality scores,
sampling of the two haplotypes, and an empirical model for correlated
errors at a site. Both read mapping and genotype calling are evaluated
on simulated data and real data. MAQ is accurate, efficient, versatile,
and user-friendly. It is freely available at http://maq.sourceforge.net.},
doi = {10.1101/gr.078212.108},
pdf = {../local/Li2008Mapping.pdf},
file = {Li2008Mapping.pdf:Li2008Mapping.pdf:PDF},
institution = {The Wellcome Trust Sanger Institute, Hinxton CB10 1SA, United Kingdom.},
keywords = {ngs},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {gr.078212.108},
pmid = {18714091},
timestamp = {2011.10.28},
url = {http://dx.doi.org/10.1101/gr.078212.108}
}
@article{Li2011Sparse,
author = {Li, J. J. and Jiang, C.-R. and Brown, J. B. and Huang, H. and Bickel,
P. J.},
title = {Sparse linear modeling of next-generation {mRNA} sequencing ({RNA-Seq})
data for isoform discovery and abundance estimation},
journal = {Proc. Natl. Acad. Sci. USA},
year = {2011},
volume = {108},
pages = {19867--19872},
number = {50},
month = dec,
abstract = {{Since the inception of next-generation mRNA sequencing (RNA-Seq)
technology, various attempts have been made to utilize RNA-Seq data
in assembling full-length mRNA isoforms de novo and estimating abundance
of isoforms. However, for genes with more than a few exons, the problem
tends to be challenging and often involves identifiability issues
in statistical modeling. We have developed a statistical method called
â sparse linear modeling of RNA-Seq data for isoform discovery
and abundance estimationâ (SLIDE) that takes exon boundaries and
RNA-Seq data as input to discern the set of mRNA isoforms that are
most likely to present in an RNA-Seq sample. SLIDE is based on a
linear model with a design matrix that models the sampling probability
of RNA-Seq reads from different mRNA isoforms. To tackle the model
unidentifiability issue, SLIDE uses a modified Lasso procedure for
parameter estimation. Compared with deterministic isoform assembly
algorithms (e.g., Cufflinks), SLIDE considers the stochastic aspects
of RNA-Seq reads in exons from different isoforms and thus has increased
power in detecting more novel isoforms. Another advantage of SLIDE
is its flexibility of incorporating other transcriptomic data such
as RACE, CAGE, and EST into its model to further increase isoform
discovery accuracy. SLIDE can also work downstream of other RNA-Seq
assembly algorithms to integrate newly discovered genes and exons.
Besides isoform discovery, SLIDE sequentially uses the same linear
model to estimate the abundance of discovered isoforms. Simulation
and real data studies show that SLIDE performs as well as or better
than major competitors in both isoform discovery and abundance estimation.
The SLIDE software package is available at https://sites.google.com/site/jingyijli/SLIDE.zip.}},
citeulike-article-id = {10102447},
citeulike-linkout-0 = {http://dx.doi.org/10.1073/pnas.1113972108},
citeulike-linkout-1 = {http://www.pnas.org/content/early/2011/11/23/1113972108.abstract},
citeulike-linkout-2 = {http://www.pnas.org/content/early/2011/11/23/1113972108.full.pdf},
citeulike-linkout-3 = {http://www.pnas.org/cgi/content/abstract/108/50/19867},
citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/22135461},
citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=22135461},
day = {13},
doi = {10.1073/pnas.1113972108},
pdf = {../local/Li2011Sparse.pdf},
file = {Li2011Sparse.pdf:Li2011Sparse.pdf:PDF},
issn = {1091-6490},
keywords = {ngs, rnaseq},
pmid = {22135461},
posted-at = {2011-12-16 22:07:32},
priority = {2},
publisher = {National Academy of Sciences},
url = {http://dx.doi.org/10.1073/pnas.1113972108}
}
@article{Li2009SNP,
author = {Li, R. and Li, Y. and Fang, X. and Yang, H. and Wang, J. and Kristiansen,
K. and Wang, J.},
title = {{SNP} detection for massively parallel whole-genome resequencing.},
journal = {Genome Res.},
year = {2009},
volume = {19},
pages = {1124--1132},
number = {6},
month = {Jun},
abstract = {Next-generation massively parallel sequencing technologies provide
ultrahigh throughput at two orders of magnitude lower unit cost than
capillary Sanger sequencing technology. One of the key applications
of next-generation sequencing is studying genetic variation between
individuals using whole-genome or target region resequencing. Here,
we have developed a consensus-calling and SNP-detection method for
sequencing-by-synthesis Illumina Genome Analyzer technology. We designed
this method by carefully considering the data quality, alignment,
and experimental errors common to this technology. All of this information
was integrated into a single quality score for each base under Bayesian
theory to measure the accuracy of consensus calling. We tested this
methodology using a large-scale human resequencing data set of 36x
coverage and assembled a high-quality nonrepetitive consensus sequence
for 92.25\% of the diploid autosomes and 88.07\% of the haploid X
chromosome. Comparison of the consensus sequence with Illumina human
1M BeadChip genotyped alleles from the same DNA sample showed that
98.6\% of the 37,933 genotyped alleles on the X chromosome and 98\%
of 999,981 genotyped alleles on autosomes were covered at 99.97\%
and 99.84\% consistency, respectively. At a low sequencing depth,
we used prior probability of dbSNP alleles and were able to improve
coverage of the dbSNP sites significantly as compared to that obtained
using a nonimputation model. Our analyses demonstrate that our method
has a very low false call rate at any sequencing depth and excellent
genome coverage at a high sequencing depth.},
doi = {10.1101/gr.088013.108},
pdf = {../local/Li2009SNP.pdf},
file = {Li2009SNP.pdf:Li2009SNP.pdf:PDF},
institution = {Beijing Genomics Institute at Shenzhen, Shenzhen 518000, China},
keywords = {ngs},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {gr.088013.108},
pmid = {19420381},
timestamp = {2011.10.28},
url = {http://dx.doi.org/10.1101/gr.088013.108}
}
@article{Li2011IsoLasso,
author = {Li, W. and Feng, J. and Jiang, T.},
title = {IsoLasso: a {LASSO} regression approach to {RNA-Seq} based transcriptome
assembly.},
journal = {J Comput Biol},
year = {2011},
volume = {18},
pages = {1693--1707},
number = {11},
month = {Nov},
__markedentry = {[jp:6]},
abstract = {The new second generation sequencing technology revolutionizes many
biology-related research fields and poses various computational biology
challenges. One of them is transcriptome assembly based on RNA-Seq
data, which aims at reconstructing all full-length mRNA transcripts
simultaneously from millions of short reads. In this article, we
consider three objectives in transcriptome assembly: the maximization
of prediction accuracy, minimization of interpretation, and maximization
of completeness. The first objective, the maximization of prediction
accuracy, requires that the estimated expression levels based on
assembled transcripts should be as close as possible to the observed
ones for every expressed region of the genome. The minimization of
interpretation follows the parsimony principle to seek as few transcripts
in the prediction as possible. The third objective, the maximization
of completeness, requires that the maximum number of mapped reads
(or ?expressed segments? in gene models) be explained by (i.e., contained
in) the predicted transcripts in the solution. Based on the above
three objectives, we present IsoLasso, a new RNA-Seq based transcriptome
assembly tool. IsoLasso is based on the well-known LASSO algorithm,
a multivariate regression method designated to seek a balance between
the maximization of prediction accuracy and the minimization of interpretation.
By including some additional constraints in the quadratic program
involved in LASSO, IsoLasso is able to make the set of assembled
transcripts as complete as possible. Experiments on simulated and
real RNA-Seq datasets show that IsoLasso achieves, simultaneously,
higher sensitivity and precision than the state-of-art transcript
assembly tools.},
doi = {10.1089/cmb.2011.0171},
pdf = {../local/Li2011IsoLasso.pdf},
file = {Li2011IsoLasso.pdf:Li2011IsoLasso.pdf:PDF},
institution = {Department of Computer Science and Engineering, University of California,
Riverside, Riverside, CA 92507, USA. liw@cs.ucr.edu},
keywords = {ngs, rnaseq},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pmid = {21951053},
timestamp = {2013.03.29},
url = {http://dx.doi.org/10.1089/cmb.2011.0171}
}
@article{Lieberman-Aiden2009Comprehensive,
author = {Erez Lieberman-Aiden and Nynke L van Berkum and Louise Williams and
Maxim Imakaev and Tobias Ragoczy and Agnes Telling and Ido Amit and
Bryan R Lajoie and Peter J Sabo and Michael O Dorschner and Richard
Sandstrom and Bradley Bernstein and M. A. Bender and Mark Groudine
and Andreas Gnirke and John Stamatoyannopoulos and Leonid A Mirny
and Eric S Lander and Job Dekker},
title = {Comprehensive mapping of long-range interactions reveals folding
principles of the human genome.},
journal = {Science},
year = {2009},
volume = {326},
pages = {289--293},
number = {5950},
month = {Oct},
abstract = {We describe Hi-C, a method that probes the three-dimensional architecture
of whole genomes by coupling proximity-based ligation with massively
parallel sequencing. We constructed spatial proximity maps of the
human genome with Hi-C at a resolution of 1 megabase. These maps
confirm the presence of chromosome territories and the spatial proximity
of small, gene-rich chromosomes. We identified an additional level
of genome organization that is characterized by the spatial segregation
of open and closed chromatin to form two genome-wide compartments.
At the megabase scale, the chromatin conformation is consistent with
a fractal globule, a knot-free, polymer conformation that enables
maximally dense packing while preserving the ability to easily fold
and unfold any genomic locus. The fractal globule is distinct from
the more commonly used globular equilibrium model. Our results demonstrate
the power of Hi-C to map the dynamic conformations of whole genomes.},
doi = {10.1126/science.1181369},
pdf = {../local/Lieberman-Aiden2009Comprehensive.pdf},
file = {Lieberman-Aiden2009Comprehensive.pdf:Lieberman-Aiden2009Comprehensive.pdf:PDF},
institution = {Broad Institute of Harvard and Massachusetts Institute of Technology
(MIT), MA 02139, USA.},
keywords = {hic, ngs},
owner = {phupe},
pii = {326/5950/289},
pmid = {19815776},
timestamp = {2010.08.26},
url = {http://dx.doi.org/10.1126/science.1181369}
}
@article{McKernan2009Sequence,
author = {Kevin Judd McKernan and Heather E Peckham and Gina L Costa and Stephen
F McLaughlin and Yutao Fu and Eric F Tsung and Christopher R Clouser
and Cisyla Duncan and Jeffrey K Ichikawa and Clarence C Lee and Zheng
Zhang and Swati S Ranade and Eileen T Dimalanta and Fiona C Hyland
and Tanya D Sokolsky and Lei Zhang and Andrew Sheridan and Haoning
Fu and Cynthia L Hendrickson and Bin Li and Lev Kotler and Jeremy
R Stuart and Joel A Malek and Jonathan M Manning and Alena A Antipova
and Damon S Perez and Michael P Moore and Kathleen C Hayashibara
and Michael R Lyons and Robert E Beaudoin and Brittany E Coleman
and Michael W Laptewicz and Adam E Sannicandro and Michael D Rhodes
and Rajesh K Gottimukkala and Shan Yang and Vineet Bafna and Ali
Bashir and Andrew MacBride and Can Alkan and Jeffrey M Kidd and Evan
E Eichler and Martin G Reese and Francisco M De La Vega and Alan
P Blanchard},
title = {Sequence and structural variation in a human genome uncovered by
short-read, massively parallel ligation sequencing using two-base
encoding.},
journal = {Genome Res.},
year = {2009},
volume = {19},
pages = {1527--1541},
number = {9},
month = {Sep},
abstract = {We describe the genome sequencing of an anonymous individual of African
origin using a novel ligation-based sequencing assay that enables
a unique form of error correction that improves the raw accuracy
of the aligned reads to >99.9\%, allowing us to accurately call SNPs
with as few as two reads per allele. We collected several billion
mate-paired reads yielding approximately 18x haploid coverage of
aligned sequence and close to 300x clone coverage. Over 98\% of the
reference genome is covered with at least one uniquely placed read,
and 99.65\% is spanned by at least one uniquely placed mate-paired
clone. We identify over 3.8 million SNPs, 19\% of which are novel.
Mate-paired data are used to physically resolve haplotype phases
of nearly two-thirds of the genotypes obtained and produce phased
segments of up to 215 kb. We detect 226,529 intra-read indels, 5590
indels between mate-paired reads, 91 inversions, and four gene fusions.
We use a novel approach for detecting indels between mate-paired
reads that are smaller than the standard deviation of the insert
size of the library and discover deletions in common with those detected
with our intra-read approach. Dozens of mutations previously described
in OMIM and hundreds of nonsynonymous single-nucleotide and structural
variants in genes previously implicated in disease are identified
in this individual. There is more genetic variation in the human
genome still to be uncovered, and we provide guidance for future
surveys in populations and cancer biopsies.},
doi = {10.1101/gr.091868.109},
pdf = {../local/McKernan2009Sequence.pdf},
file = {McKernan2009Sequence.pdf:McKernan2009Sequence.pdf:PDF},
institution = {Life Technologies, Beverly, Massachusetts 01915, USA. Kevin.McKernan@appliedbiosystems.com},
keywords = {ngs},
owner = {jp},
pii = {gr.091868.109},
pmid = {19546169},
timestamp = {2009.10.09},
url = {http://dx.doi.org/10.1101/gr.091868.109}
}
@article{Metzker2010Sequencing,
author = {Metzker, M. L.},
title = {Sequencing technologies - the next generation.},
journal = {Nat. Rev. Genet.},
year = {2010},
volume = {11},
pages = {31--46},
number = {1},
month = {Jan},
abstract = {Demand has never been greater for revolutionary technologies that
deliver fast, inexpensive and accurate genome information. This challenge
has catalysed the development of next-generation sequencing (NGS)
technologies. The inexpensive production of large volumes of sequence
data is the primary advantage over conventional methods. Here, I
present a technical review of template preparation, sequencing and
imaging, genome alignment and assembly approaches, and recent advances
in current and near-term commercially available NGS instruments.
I also outline the broad range of applications for NGS technologies,
in addition to providing guidelines for platform selection to address
biological questions of interest.},
doi = {10.1038/nrg2626},
institution = { Human Genetics, Baylor College of Medicine, Houston, Texas 77030,
USA. mmetzker@bcm.edu},
keywords = {ngs},
language = {eng},
medline-pst = {ppublish},
owner = {philippe},
pii = {nrg2626},
pmid = {19997069},
timestamp = {2010.07.27},
url = {http://dx.doi.org/10.1038/nrg2626}
}
@article{Mezlini2013iReckon,
author = {Mezlini, A. M. and Smith, E. J. M. and Fiume, M. and Buske, O. and
Savich, G. L. and Shah, S. and Aparicio, S. and Chiang, D. Y. and
Goldenberg, A. and Brudno, M.},
title = {{iReckon}: Simultaneous isoform discovery and abundance estimation
from {RNA}-seq data.},
journal = {Genome Res},
year = {2013},
volume = {23},
pages = {519--529},
number = {3},
month = {Mar},
abstract = {High-throughput RNA sequencing (RNA-seq) promises to revolutionize
our understanding of genes and their role in human disease by characterizing
the RNA content of tissues and cells. The realization of this promise,
however, is conditional on the development of effective computational
methods for the identification and quantification of transcripts
from incomplete and noisy data. In this article, we introduce iReckon,
a method for simultaneous determination of the isoforms and estimation
of their abundances. Our probabilistic approach incorporates multiple
biological and technical phenomena, including novel isoforms, intron
retention, unspliced pre-mRNA, PCR amplification biases, and multimapped
reads. iReckon utilizes regularized expectation-maximization to accurately
estimate the abundances of known and novel isoforms. Our results
on simulated and real data demonstrate a superior ability to discover
novel isoforms with a significantly reduced number of false-positive
predictions, and our abundance accuracy prediction outmatches that
of other state-of-the-art tools. Furthermore, we have applied iReckon
to two cancer transcriptome data sets, a triple-negative breast cancer
patient sample and the MCF7 breast cancer cell line, and show that
iReckon is able to reconstruct the complex splicing changes that
were not previously identified. QT-PCR validations of the isoforms
detected in the MCF7 cell line confirmed all of iReckon's predictions
and also showed strong agreement (r = 0.94) with the predicted abundances.},
doi = {10.1101/gr.142232.112},
pdf = {../local/Mezlini2013iReckon.pdf},
file = {Mezlini2013iReckon.pdf:Mezlini2013iReckon.pdf:PDF},
institution = {Department of Computer Science, University of Toronto, Ontario M5S
2E4, Canada;},
keywords = {ngs, rnaseq},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {gr.142232.112},
pmid = {23204306},
timestamp = {2013.03.29},
url = {http://dx.doi.org/10.1101/gr.142232.112}
}
@article{Morin2008Application,
author = {Ryan D Morin and Michael D O'Connor and Malachi Griffith and Florian
Kuchenbauer and Allen Delaney and Anna-Liisa Prabhu and Yongjun Zhao
and Helen McDonald and Thomas Zeng and Martin Hirst and Connie J
Eaves and Marco A Marra},
title = {Application of massively parallel sequencing to microRNA profiling
and discovery in human embryonic stem cells.},
journal = {Genome Res},
year = {2008},
volume = {18},
pages = {610--621},
number = {4},
month = {Apr},
abstract = {MicroRNAs (miRNAs) are emerging as important, albeit poorly characterized,
regulators of biological processes. Key to further elucidation of
their roles is the generation of more complete lists of their numbers
and expression changes in different cell states. Here, we report
a new method for surveying the expression of small RNAs, including
microRNAs, using Illumina sequencing technology. We also present
a set of methods for annotating sequences deriving from known miRNAs,
identifying variability in mature miRNA sequences, and identifying
sequences belonging to previously unidentified miRNA genes. Application
of this approach to RNA from human embryonic stem cells obtained
before and after their differentiation into embryoid bodies revealed
the sequences and expression levels of 334 known plus 104 novel miRNA
genes. One hundred seventy-one known and 23 novel microRNA sequences
exhibited significant expression differences between these two developmental
states. Owing to the increased number of sequence reads, these libraries
represent the deepest miRNA sampling to date, spanning nearly six
orders of magnitude of expression. The predicted targets of those
miRNAs enriched in either sample shared common features. Included
among the high-ranked predicted gene targets are those implicated
in differentiation, cell cycle control, programmed cell death, and
transcriptional regulation.},
doi = {10.1101/gr.7179508},
pdf = {../local/Morin2008Application.pdf},
file = {Morin2008Application.pdf:Morin2008Application.pdf:PDF},
institution = {Genome Sciences Centre, BC Cancer Agency, Vancouver, British Columbia
V5Z 1L3, Canada.},
keywords = {ngs, sirna},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {gr.7179508},
pmid = {18285502},
timestamp = {2009.10.28},
url = {http://dx.doi.org/10.1101/gr.7179508}
}
@article{Nielsen2011Genotype,
author = {Nielsen, R. and Paul, J. S. and Albrechtsen, A. and Song, Y. S.},
title = {Genotype and {SNP} calling from next-generation sequencing data.},
journal = {Nat. Rev. Genet.},
year = {2011},
volume = {12},
pages = {443--451},
number = {6},
month = {Jun},
abstract = {Meaningful analysis of next-generation sequencing (NGS) data, which
are produced extensively by genetics and genomics studies, relies
crucially on the accurate calling of SNPs and genotypes. Recently
developed statistical methods both improve and quantify the considerable
uncertainty associated with genotype calling, and will especially
benefit the growing number of studies using low- to medium-coverage
data. We review these methods and provide a guide for their use in
NGS studies.},
doi = {10.1038/nrg2986},
pdf = {../local/Nielsen2011Genotype.pdf},
file = {Nielsen2011Genotype.pdf:Nielsen2011Genotype.pdf:PDF},
institution = {Department of Integrative Biology, University of California, Berkeley,
CA 94720, USA. rasmus_nielsen@berkeley.edu},
keywords = {ngs},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {nrg2986},
pmid = {21587300},
timestamp = {2011.10.27},
url = {http://dx.doi.org/10.1038/nrg2986}
}
@article{Praz2009CleanEx:,
author = {Viviane Praz and Philipp Bucher},
title = {CleanEx: new data extraction and merging tools based on MeSH term
annotation.},
journal = {Nucleic Acids Res},
year = {2009},
volume = {37},
pages = {D880--D884},
number = {Database issue},
month = {Jan},
abstract = {The CleanEx expression database (http://www.cleanex.isb-sib.ch) provides
access to public gene expression data via unique gene names as well
as via experiments biomedical characteristics. To reach this, a dual
annotation of both sequences and experiments has been generated.
First, the system links official gene symbols to any kind of sequences
used for gene expression measurements (cDNA, Affymetrix, oligonucleotide
arrays, SAGE or MPSS tags, Expressed Sequence Tags or other mRNA
sequences, etc.). For the biomedical annotation, we re-annotate each
experiment from the CleanEx database with the MeSH (Medical Subject
Headings) terms, primarily used by NLM (National Library of Medicine)
for indexing articles for the MEDLINE/PubMED database. This annotation
allows a fast and easy retrieval of expression data with common biological
or medical features. The numerical data can then be exported as matrix-like
tab-delimited text files. Data can be extracted from either one dataset
or from heterogeneous datasets.},
doi = {10.1093/nar/gkn878},
institution = {ISREC, Swiss Institute of Bioinformatics, Boveresses 155, Epalinges,
VD 1066, Switzerland. viviane.praz@unil.ch},
keywords = {Animals; Chromosome Mapping; Databases, Genetic; Gene Expression Profiling;
Humans; Medical Subject Headings; Mice; Oligonucleotide Array Sequence
Analysis; Software},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {gkn878},
pmid = {19073704},
timestamp = {2011.09.21},
url = {http://dx.doi.org/10.1093/nar/gkn878}
}
@article{Roberts2011Identification,
author = {Roberts, A. and Pimentel, H. and Trapnell, C. and Pachter, L.},
title = {Identification of novel transcripts in annotated genomes using {RNA-Seq}.},
journal = {Bioinformatics},
year = {2011},
volume = {27},
pages = {2325--2329},
number = {17},
month = {Sep},
abstract = {We describe a new 'reference annotation based transcript assembly'
problem for RNA-Seq data that involves assembling novel transcripts
in the context of an existing annotation. This problem arises in
the analysis of expression in model organisms, where it is desirable
to leverage existing annotations for discovering novel transcripts.
We present an algorithm for reference annotation-based transcript
assembly and show how it can be used to rapidly investigate novel
transcripts revealed by RNA-Seq in comparison with a reference annotation.The
methods described in this article are implemented in the Cufflinks
suite of software for RNA-Seq, freely available from http://bio.math.berkeley.edu/cufflinks.
The software is released under the BOOST license.cole@broadinstitute.org;
lpachter@math.berkeley.eduSupplementary data are available at Bioinformatics
online.},
doi = {10.1093/bioinformatics/btr355},
pdf = {../local/Roberts2011Identification.pdf},
file = {Roberts2011Identification.pdf:Roberts2011Identification.pdf:PDF},
institution = {Department of Computer Science, UC Berkeley, Berkeley, CA, USA.},
keywords = {ngs, rnaseq},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {btr355},
pmid = {21697122},
timestamp = {2013.03.29},
url = {http://dx.doi.org/10.1093/bioinformatics/btr355}
}
@article{Roberts2011Improving,
author = {Roberts, A. and Trapnell, C. and Donaghey, J. and Rinn, J. L. and
Pachter, L.},
title = {Improving {RNA-Seq} expression estimates by correcting for fragment
bias.},
journal = {Genome Biol},
year = {2011},
volume = {12},
pages = {R22},
number = {3},
abstract = {The biochemistry of RNA-Seq library preparation results in cDNA fragments
that are not uniformly distributed within the transcripts they represent.
This non-uniformity must be accounted for when estimating expression
levels, and we show how to perform the needed corrections using a
likelihood based approach. We find improvements in expression estimates
as measured by correlation with independently performed qRT-PCR and
show that correction of bias leads to improved replicability of results
across libraries and sequencing technologies.},
doi = {10.1186/gb-2011-12-3-r22},
pdf = {../local/Roberts2011Improving.pdf},
file = {Roberts2011Improving.pdf:Roberts2011Improving.pdf:PDF},
institution = {Department of Computer Science, 387 Soda Hall, UC Berkeley, Berkeley,
CA 94720, USA.},
keywords = {ngs, rnaseq},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {gb-2011-12-3-r22},
pmid = {21410973},
timestamp = {2013.03.29},
url = {http://dx.doi.org/10.1186/gb-2011-12-3-r22}
}
@article{Shah2009Mutational,
author = {Shah, S. P. and Morin, R. D. and Khattra, J. and Prentice, L. and
Pugh, T. and Burleigh, A. and Delaney, A. and Gelmon, K. and Guliany,
R. and Senz, J. and Steidl, C. and Holt, R.A . and Jones, S. and
Sun, M. and Leung, G. and Moore, R. and Severson, T. and Taylor,
G. A. and Teschendorff, A. E. and Tse, K. and Turashvili, G. and
Varhol, R. and Warren, R. L. and Watson, P. and Zhao, Y. and Caldas,
C. and Huntsman, D. and Hirst, M. and Marra, M. A. and Aparicio,
A.},
title = {Mutational evolution in a lobular breast tumour profiled at single
nucleotide resolution},
journal = {Nature},
year = {2009},
volume = {461},
pages = {809--813},
number = {7265},
month = {Oct},
abstract = {Recent advances in next generation sequencing have made it possible
to precisely characterize all somatic coding mutations that occur
during the development and progression of individual cancers. Here
we used these approaches to sequence the genomes (>43-fold coverage)
and transcriptomes of an oestrogen-receptor-alpha-positive metastatic
lobular breast cancer at depth. We found 32 somatic non-synonymous
coding mutations present in the metastasis, and measured the frequency
of these somatic mutations in DNA from the primary tumour of the
same patient, which arose 9 years earlier. Five of the 32 mutations
(in ABCB11, HAUS3, SLC24A4, SNX4 and PALB2) were prevalent in the
DNA of the primary tumour removed at diagnosis 9 years earlier, six
(in KIF1C, USP28, MYH8, MORC1, KIAA1468 and RNASEH2A) were present
at lower frequencies (1-13\%), 19 were not detected in the primary
tumour, and two were undetermined. The combined analysis of genome
and transcriptome data revealed two new RNA-editing events that recode
the amino acid sequence of SRP9 and COG3. Taken together, our data
show that single nucleotide mutational heterogeneity can be a property
of low or intermediate grade primary breast cancers and that significant
evolution can occur with disease progression.},
doi = {10.1038/nature08489},
pdf = {../local/Shah2009Mutational.pdf},
file = {Shah2009Mutational.pdf:Shah2009Mutational.pdf:PDF},
institution = {Molecular Oncology, BC Cancer Agency, 675 West 10th Avenue, Vancouver
V5Z 1L3, Canada.},
keywords = {ngs},
owner = {jp},
pii = {nature08489},
pmid = {19812674},
timestamp = {2009.10.12},
url = {http://dx.doi.org/10.1038/nature08489}
}
@article{Spyrou2009BayesPeak,
author = {Christiana Spyrou and Rory Stark and Andy G Lynch and Simon Tavaré},
title = {BayesPeak: Bayesian analysis of ChIP-seq data.},
journal = {BMC Bioinformatics},
year = {2009},
volume = {10},
pages = {299},
abstract = {BACKGROUND: High-throughput sequencing technology has become popular
and widely used to study protein and DNA interactions. Chromatin
immunoprecipitation, followed by sequencing of the resulting samples,
produces large amounts of data that can be used to map genomic features
such as transcription factor binding sites and histone modifications.
METHODS: Our proposed statistical algorithm, BayesPeak, uses a fully
Bayesian hidden Markov model to detect enriched locations in the
genome. The structure accommodates the natural features of the Solexa/Illumina
sequencing data and allows for overdispersion in the abundance of
reads in different regions. Moreover, a control sample can be incorporated
in the analysis to account for experimental and sequence biases.
Markov chain Monte Carlo algorithms are applied to estimate the posterior
distributions of the model parameters, and posterior probabilities
are used to detect the sites of interest. CONCLUSION: We have presented
a flexible approach for identifying peaks from ChIP-seq reads, suitable
for use on both transcription factor binding and histone modification
data. Our method estimates probabilities of enrichment that can be
used in downstream analysis. The method is assessed using experimentally
verified data and is shown to provide high-confidence calls with
low false positive rates.},
doi = {10.1186/1471-2105-10-299},
pdf = {../local/Spyrou2009BayesPeak.pdf},
file = {Spyrou2009BayesPeak.pdf:Spyrou2009BayesPeak.pdf:PDF},
institution = {Statistical Laboratory, Centre for Mathematical Sciences, Wilberforce
Road, Cambridge, UK. C.Spyrou@statslab.cam.ac.uk},
keywords = {ngs},
language = {eng},
medline-pst = {epublish},
owner = {jp},
pii = {1471-2105-10-299},
pmid = {19772557},
timestamp = {2009.10.29},
url = {http://dx.doi.org/10.1186/1471-2105-10-299}
}
@article{Trapnell2013Differential,
author = {Trapnell, C. and Hendrickson, D. G. and Sauvageau, M. and Goff, L.
and Rinn, J. L. and Pachter, L.},
title = {Differential analysis of gene regulation at transcript resolution
with {RNA-seq}.},
journal = {Nat Biotechnol},
year = {2013},
volume = {31},
pages = {46--53},
number = {1},
month = {Jan},
abstract = {Differential analysis of gene and transcript expression using high-throughput
RNA sequencing (RNA-seq) is complicated by several sources of measurement
variability and poses numerous statistical challenges. We present
Cuffdiff 2, an algorithm that estimates expression at transcript-level
resolution and controls for variability evident across replicate
libraries. Cuffdiff 2 robustly identifies differentially expressed
transcripts and genes and reveals differential splicing and promoter-preference
changes. We demonstrate the accuracy of our approach through differential
analysis of lung fibroblasts in response to loss of the developmental
transcription factor HOXA1, which we show is required for lung fibroblast
and HeLa cell cycle progression. Loss of HOXA1 results in significant
expression level changes in thousands of individual transcripts,
along with isoform switching events in key regulators of the cell
cycle. Cuffdiff 2 performs robust differential analysis in RNA-seq
experiments at transcript resolution, revealing a layer of regulation
not readily observable with other high-throughput technologies.},
doi = {10.1038/nbt.2450},
pdf = {../local/Trapnell2013Differential.pdf},
file = {Trapnell2013Differential.pdf:Trapnell2013Differential.pdf:PDF},
institution = {Department of Stem Cell and Regenerative Biology, Harvard University,
Cambridge, Massachusetts, USA.},
keywords = {ngs, rnaseq},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {nbt.2450},
pmid = {23222703},
timestamp = {2013.03.29},
url = {http://dx.doi.org/10.1038/nbt.2450}
}
@article{Trapnell2009TopHat,
author = {Trapnell, C. and Pachter, L. and Salzberg, S. L.},
title = {{TopHat}: discovering splice junctions with {RNA-Seq}.},
journal = {Bioinformatics},
year = {2009},
volume = {25},
pages = {1105--1111},
number = {9},
month = {May},
abstract = {A new protocol for sequencing the messenger RNA in a cell, known as
RNA-Seq, generates millions of short sequence fragments in a single
run. These fragments, or 'reads', can be used to measure levels of
gene expression and to identify novel splice variants of genes. However,
current software for aligning RNA-Seq data to a genome relies on
known splice junctions and cannot identify novel ones. TopHat is
an efficient read-mapping algorithm designed to align reads from
an RNA-Seq experiment to a reference genome without relying on known
splice sites.We mapped the RNA-Seq reads from a recent mammalian
RNA-Seq experiment and recovered more than 72\% of the splice junctions
reported by the annotation-based software from that study, along
with nearly 20,000 previously unreported junctions. The TopHat pipeline
is much faster than previous systems, mapping nearly 2.2 million
reads per CPU hour, which is sufficient to process an entire RNA-Seq
experiment in less than a day on a standard desktop computer. We
describe several challenges unique to ab initio splice site discovery
from RNA-Seq reads that will require further algorithm development.TopHat
is free, open-source software available from http://tophat.cbcb.umd.edu.Supplementary
data are available at Bioinformatics online.},
doi = {10.1093/bioinformatics/btp120},
pdf = {../local/Trapnell2009TopHat.pdf},
file = {Trapnell2009TopHat.pdf:Trapnell2009TopHat.pdf:PDF},
institution = {Center for Bioinformatics and Computational Biology, University of
Maryland, College Park, MD 20742, USA. cole@cs.umd.edu},
keywords = {ngs, rnaseq},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {btp120},
pmid = {19289445},
timestamp = {2013.03.29},
url = {http://dx.doi.org/10.1093/bioinformatics/btp120}
}
@article{Trapnell2012Differential,
author = {Trapnell, C. and Roberts, A. and Goff, L. and Pertea, G. and Kim,
D. and Kelley, D. R. and Pimentel, H. and Salzberg, S. L. and Rinn,
J. L. and Pachter, L.},
title = {Differential gene and transcript expression analysis of {RNA-seq}
experiments with {TopHat} and {Cufflinks}.},
journal = {Nat Protoc},
year = {2012},
volume = {7},
pages = {562--578},
number = {3},
month = {Mar},
abstract = {Recent advances in high-throughput cDNA sequencing (RNA-seq) can reveal
new genes and splice variants and quantify expression genome-wide
in a single assay. The volume and complexity of data from RNA-seq
experiments necessitate scalable, fast and mathematically principled
analysis software. TopHat and Cufflinks are free, open-source software
tools for gene discovery and comprehensive expression analysis of
high-throughput mRNA sequencing (RNA-seq) data. Together, they allow
biologists to identify new genes and new splice variants of known
ones, as well as compare gene and transcript expression under two
or more conditions. This protocol describes in detail how to use
TopHat and Cufflinks to perform such analyses. It also covers several
accessory tools and utilities that aid in managing data, including
CummeRbund, a tool for visualizing RNA-seq analysis results. Although
the procedure assumes basic informatics skills, these tools assume
little to no background with RNA-seq analysis and are meant for novices
and experts alike. The protocol begins with raw sequencing reads
and produces a transcriptome assembly, lists of differentially expressed
and regulated genes and transcripts, and publication-quality visualizations
of analysis results. The protocol's execution time depends on the
volume of transcriptome sequencing data and available computing resources
but takes less than 1 d of computer time for typical experiments
and ∼1 h of hands-on time.},
doi = {10.1038/nprot.2012.016},
pdf = {../local/Trapnell2012Differential.pdf},
file = {Trapnell2012Differential.pdf:Trapnell2012Differential.pdf:PDF},
institution = {Broad Institute of MIT and Harvard, Cambridge, Massachusetts, USA.
cole@broadinstitute.org},
keywords = {ngs, rnaseq},
owner = {laurent},
pii = {nprot.2012.016},
pmid = {22383036},
timestamp = {2012.04.11},
url = {http://dx.doi.org/10.1038/nprot.2012.016}
}
@article{Trapnell2010Transcript,
author = {Trapnell, C. and Williams, B. A. and Pertea, G. and Mortazavi, A.
and Kwan, G. and {van Baren}, M. J. and Salzberg, S. L. and Wold,
B. J. and Pachter, L.},
title = {Transcript assembly and quantification by RNA-Seq reveals unannotated
transcripts and isoform switching during cell differentiation.},
journal = {Nat Biotechnol},
year = {2010},
volume = {28},
pages = {511--515},
number = {5},
month = {May},
abstract = {High-throughput mRNA sequencing (RNA-Seq) promises simultaneous transcript
discovery and abundance estimation. However, this would require algorithms
that are not restricted by prior gene annotations and that account
for alternative transcription and splicing. Here we introduce such
algorithms in an open-source software program called Cufflinks. To
test Cufflinks, we sequenced and analyzed >430 million paired 75-bp
RNA-Seq reads from a mouse myoblast cell line over a differentiation
time series. We detected 13,692 known transcripts and 3,724 previously
unannotated ones, 62\% of which are supported by independent expression
data or by homologous genes in other species. Over the time series,
330 genes showed complete switches in the dominant transcription
start site (TSS) or splice isoform, and we observed more subtle shifts
in 1,304 other genes. These results suggest that Cufflinks can illuminate
the substantial regulatory flexibility and complexity in even this
well-studied model of muscle development and that it can improve
transcriptome-based genome annotation.},
doi = {10.1038/nbt.1621},
pdf = {../local/Trapnell2010Transcript.pdf},
file = {Trapnell2010Transcript.pdf:Trapnell2010Transcript.pdf:PDF},
institution = {Department of Computer Science, University of Maryland, College Park,
Maryland, USA.},
keywords = {ngs, rnaseq},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {nbt.1621},
pmid = {20436464},
timestamp = {2012.03.06},
url = {http://dx.doi.org/10.1038/nbt.1621}
}
@article{Tuteja2009Extracting,
author = {Geetu Tuteja and Peter White and Jonathan Schug and Klaus H Kaestner},
title = {Extracting transcription factor targets from ChIP-Seq data.},
journal = {Nucleic Acids Res},
year = {2009},
volume = {37},
pages = {e113},
number = {17},
month = {Sep},
abstract = {ChIP-Seq technology, which combines chromatin immunoprecipitation
(ChIP) with massively parallel sequencing, is rapidly replacing ChIP-on-chip
for the genome-wide identification of transcription factor binding
events. Identifying bound regions from the large number of sequence
tags produced by ChIP-Seq is a challenging task. Here, we present
GLITR (GLobal Identifier of Target Regions), which accurately identifies
enriched regions in target data by calculating a fold-change based
on random samples of control (input chromatin) data. GLITR uses a
classification method to identify regions in ChIP data that have
a peak height and fold-change which do not resemble regions in an
input sample. We compare GLITR to several recent methods and show
that GLITR has improved sensitivity for identifying bound regions
closely matching the consensus sequence of a given transcription
factor, and can detect bona fide transcription factor targets missed
by other programs. We also use GLITR to address the issue of sequencing
depth, and show that sequencing biological replicates identifies
far more binding regions than re-sequencing the same sample.},
doi = {10.1093/nar/gkp536},
pdf = {../local/Tuteja2009Extracting.pdf},
file = {Tuteja2009Extracting.pdf:Tuteja2009Extracting.pdf:PDF},
institution = {Department of Genetics and Institute of Diabetes, Obesity and Metabolism,
University of Pennsylvania School of Medicine, Philadelphia, PA 19104,
USA.},
keywords = {ngs},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {gkp536},
pmid = {19553195},
timestamp = {2009.10.30},
url = {http://dx.doi.org/10.1093/nar/gkp536}
}
@article{Wang2008diploid,
author = {Wang, Jun and Wang, Wei and Li, Ruiqiang and Li, Yingrui and Tian,
Geng and Goodman, Laurie and Fan, Wei and Zhang, Junqing and Li,
Jun and Zhang, Juanbin and Guo, Yiran and Feng, Binxiao and Li, Heng
and Lu, Yao and Fang, Xiaodong and Liang, Huiqing and Du, Zhenglin
and Li, Dong and Zhao, Yiqing and Hu, Yujie and Yang, Zhenzhen and
Zheng, Hancheng and Hellmann, Ines and Inouye, Michael and Pool,
John and Yi, Xin and Zhao, Jing and Duan, Jinjie and Zhou, Yan and
Qin, Junjie and Ma, Lijia and Li, Guoqing and Yang, Zhentao and Zhang,
Guojie and Yang, Bin and Yu, Chang and Liang, Fang and Li, Wenjie
and Li, Shaochuan and Li, Dawei and Ni, Peixiang and Ruan, Jue and
Li, Qibin and Zhu, Hongmei and Liu, Dongyuan and Lu, Zhike and Li,
Ning and Guo, Guangwu and Zhang, J. and Ye, J. and Fang, L. and Hao,
Q. and Chen, Q. and Liang, Y. and Su, Y. and San, A. and Ping, C.
and Yang, S. and Chen, F. and Li, L. and Zhou, K. and Zheng, H. and
Ren, Y. and Yang, L. and Gao, Y. and Yang, G. and Li, Z. and Feng,
X. and Kristiansen, K. and Wong, G. K.-S. and Nielsen, R. and Durbin,
R. and Bolund, L. and Zhang, X. and Li, S. and Yang, H. and Wang,
J.},
title = {The diploid genome sequence of an {A}sian individual.},
journal = {Nature},
year = {2008},
volume = {456},
pages = {60--65},
number = {7218},
month = {Nov},
abstract = {Here we present the first diploid genome sequence of an Asian individual.
The genome was sequenced to 36-fold average coverage using massively
parallel sequencing technology. We aligned the short reads onto the
NCBI human reference genome to 99.97\% coverage, and guided by the
reference genome, we used uniquely mapped reads to assemble a high-quality
consensus sequence for 92\% of the Asian individual's genome. We
identified approximately 3 million single-nucleotide polymorphisms
(SNPs) inside this region, of which 13.6\% were not in the dbSNP
database. Genotyping analysis showed that SNP identification had
high accuracy and consistency, indicating the high sequence quality
of this assembly. We also carried out heterozygote phasing and haplotype
prediction against HapMap CHB and JPT haplotypes (Chinese and Japanese,
respectively), sequence comparison with the two available individual
genomes (J. D. Watson and J. C. Venter), and structural variation
identification. These variations were considered for their potential
biological impact. Our sequence data and analyses demonstrate the
potential usefulness of next-generation sequencing technologies for
personal genomics.},
doi = {10.1038/nature07484},
institution = {Beijing Genomics Institute at Shenzhen, Shenzhen 518000, China. wangj@genomics.org.cn},
keywords = {ngs},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {nature07484},
pmid = {18987735},
timestamp = {2011.10.28},
url = {http://dx.doi.org/10.1038/nature07484}
}
@article{Wang2009RNA,
author = {Wang, Z. and Gerstein, M. and Snyder, M.},
title = {{RNA-Seq}: a revolutionary tool for transcriptomics.},
journal = {Nat. Rev. Genet.},
year = {2009},
volume = {10},
pages = {57--63},
number = {1},
month = {Jan},
abstract = {RNA-Seq is a recently developed approach to transcriptome profiling
that uses deep-sequencing technologies. Studies using this method
have already altered our view of the extent and complexity of eukaryotic
transcriptomes. RNA-Seq also provides a far more precise measurement
of levels of transcripts and their isoforms than other methods. This
article describes the RNA-Seq approach, the challenges associated
with its application, and the advances made so far in characterizing
several eukaryote transcriptomes.},
doi = {10.1038/nrg2484},
pdf = {../local/Wang2009RNA.pdf},
file = {Wang2009RNA.pdf:Wang2009RNA.pdf:PDF},
institution = {Department of Molecular, Cellular and Developmental Biology, Yale
University, 219 Prospect Street, New Haven, Connecticut 06520, USA.},
keywords = {ngs, rnaseq},
owner = {ljacob},
pii = {nrg2484},
pmid = {19015660},
timestamp = {2009.09.14},
url = {http://dx.doi.org/10.1038/nrg2484}
}
@article{Xie2009CNV-seq,
author = {Chao Xie and Martti T Tammi},
title = {CNV-seq, a new method to detect copy number variation using high-throughput
sequencing.},
journal = {BMC Bioinformatics},
year = {2009},
volume = {10},
pages = {80},
abstract = {BACKGROUND: DNA copy number variation (CNV) has been recognized as
an important source of genetic variation. Array comparative genomic
hybridization (aCGH) is commonly used for CNV detection, but the
microarray platform has a number of inherent limitations. RESULTS:
Here, we describe a method to detect copy number variation using
shotgun sequencing, CNV-seq. The method is based on a robust statistical
model that describes the complete analysis procedure and allows the
computation of essential confidence values for detection of CNV.
Our results show that the number of reads, not the length of the
reads is the key factor determining the resolution of detection.
This favors the next-generation sequencing methods that rapidly produce
large amount of short reads. CONCLUSION: Simulation of various sequencing
methods with coverage between 0.1x to 8x show overall specificity
between 91.7 - 99.9\%, and sensitivity between 72.2 - 96.5\%. We
also show the results for assessment of CNV between two individual
human genomes.},
doi = {10.1186/1471-2105-10-80},
pdf = {../local/Xie2009CNV-seq.pdf},
file = {Xie2009CNV-seq.pdf:Xie2009CNV-seq.pdf:PDF},
institution = {Department of Biological Sciences, National University of Singapore,
Singapore. xie@nus.edu.sg},
keywords = {ngs},
owner = {jp},
pii = {1471-2105-10-80},
pmid = {19267900},
timestamp = {2009.10.09},
url = {http://dx.doi.org/10.1186/1471-2105-10-80}
}
@article{Yaffe2011Probabilistic,
author = {Yaffe, E. and Tanay, A.},
title = {Probabilistic modeling of {Hi-C} contact maps eliminates systematic
biases to characterize global chromosomal architecture},
journal = {Nat. Genet.},
year = {2011},
volume = {43},
pages = {1059--1065},
number = {11},
abstract = {Hi-C experiments measure the probability of physical proximity between
pairs of chromosomal loci on a genomic scale. We report on several
systematic biases that substantially affect the Hi-C experimental
procedure, including the distance between restriction sites, the
GC content of trimmed ligation junctions and sequence uniqueness.
To address these biases, we introduce an integrated probabilistic
background model and develop algorithms to estimate its parameters
and renormalize Hi-C data. Analysis of corrected human lymphoblast
contact maps provides genome-wide evidence for interchromosomal aggregation
of active chromatin marks, including DNase-hypersensitive sites and
transcriptionally active foci. We observe extensive long-range (up
to 400 kb) cis interactions at active promoters and derive asymmetric
contact profiles next to transcription start sites and CTCF binding
sites. Clusters of interacting chromosomal domains suggest physical
separation of centromere-proximal and centromere-distal regions.
These results provide a computational basis for the inference of
chromosomal architectures from Hi-C experiments.},
doi = {10.1038/ng.947},
pdf = {../local/Yaffe2011Probabilistic.pdf},
file = {Yaffe2011Probabilistic.pdf:Yaffe2011Probabilistic.pdf:PDF},
issn = {1061-4036},
keywords = {hic, ngs},
owner = {nelle},
url = {http://dx.doi.org/10.1038/ng.947},
urldate = {2012-01-11}
}
@article{Yoon2009Sensitive,
author = {Seungtai Yoon and Zhenyu Xuan and Vladimir Makarov and Kenny Ye and
Jonathan Sebat},
title = {Sensitive and accurate detection of copy number variants using read
depth of coverage.},
journal = {Genome Res.},
year = {2009},
volume = {19},
pages = {1586--1592},
number = {9},
month = {Sep},
abstract = {Methods for the direct detection of copy number variation (CNV) genome-wide
have become effective instruments for identifying genetic risk factors
for disease. The application of next-generation sequencing platforms
to genetic studies promises to improve sensitivity to detect CNVs
as well as inversions, indels, and SNPs. New computational approaches
are needed to systematically detect these variants from genome sequence
data. Existing sequence-based approaches for CNV detection are primarily
based on paired-end read mapping (PEM) as reported previously by
Tuzun et al. and Korbel et al. Due to limitations of the PEM approach,
some classes of CNVs are difficult to ascertain, including large
insertions and variants located within complex genomic regions. To
overcome these limitations, we developed a method for CNV detection
using read depth of coverage. Event-wise testing (EWT) is a method
based on significance testing. In contrast to standard segmentation
algorithms that typically operate by performing likelihood evaluation
for every point in the genome, EWT works on intervals of data points,
rapidly searching for specific classes of events. Overall false-positive
rate is controlled by testing the significance of each possible event
and adjusting for multiple testing. Deletions and duplications detected
in an individual genome by EWT are examined across multiple genomes
to identify polymorphism between individuals. We estimated error
rates using simulations based on real data, and we applied EWT to
the analysis of chromosome 1 from paired-end shotgun sequence data
(30x) on five individuals. Our results suggest that analysis of read
depth is an effective approach for the detection of CNVs, and it
captures structural variants that are refractory to established PEM-based
methods.},
doi = {10.1101/gr.092981.109},
pdf = {../local/Yoon2009Sensitive.pdf},
file = {Yoon2009Sensitive.pdf:Yoon2009Sensitive.pdf:PDF},
institution = {Cold Spring Harbor Laboratory, Cold Spring Harbor, New York 11724,
USA.},
keywords = {ngs},
owner = {jp},
pii = {gr.092981.109},
pmid = {19657104},
timestamp = {2009.10.09},
url = {http://dx.doi.org/10.1101/gr.092981.109}
}
@article{Zhang2012Spatial,
author = {Zhang, Y. and McCord, R. A. and Ho, Y.-J. and Lajoie, B. R. and Hildebrand,
D. G. and Simon, A. C. and Becker, M. S. and Alt, F. W. and Dekker,
J.},
title = {Spatial Organization of the Mouse Genome and Its Role in Recurrent
Chromosomal Translocations},
journal = {Cell},
year = {2012},
volume = {148},
pages = {908 - 921},
number = {5},
abstract = {Summary The extent to which the three-dimensional organization of
the genome contributes to chromosomal translocations is an important
question in cancer genomics. We generated a high-resolution Hi-C
spatial organization map of the G1-arrested mouse pro-B cell genome
and used high-throughput genome-wide translocation sequencing to
map translocations from target DNA double-strand breaks (DSBs) within
it. RAG endonuclease-cleaved antigen-receptor loci are dominant translocation
partners for target DSBs regardless of genomic position, reflecting
high-frequency DSBs at these loci and their colocalization in a fraction
of cells. To directly assess spatial proximity contributions, we
normalized genomic DSBs via ionizing radiation. Under these conditions,
translocations were highly enriched in cis along single chromosomes
containing target DSBs and within other chromosomes and subchromosomal
domains in a manner directly related to pre-existing spatial proximity.
By combining two high-throughput genomic methods in a genetically
tractable system, we provide a new lens for viewing cancer genomes.},
doi = {10.1016/j.cell.2012.02.002},
pdf = {../local/Zhang2012Spatial.pdf},
file = {Zhang2012Spatial.pdf:Zhang2012Spatial.pdf:PDF},
issn = {0092-8674},
keywords = {hic, ngs},
owner = {nelle},
url = {http://www.sciencedirect.com/science/article/pii/S0092867412001584}
}
@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.