Links to Exploration step
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Practical Guidelines for the Comprehensive Analysis of ChIP-seq Data</title><author><name sortKey="Bailey, Timothy" sort="Bailey, Timothy" uniqKey="Bailey T" first="Timothy" last="Bailey">Timothy Bailey</name><affiliation><nlm:aff id="aff1"><addr-line>Institute for Molecular Bioscience, The University of Queensland, Brisbane, Australia</addr-line></nlm:aff></affiliation></author><author><name sortKey="Krajewski, Pawel" sort="Krajewski, Pawel" uniqKey="Krajewski P" first="Pawel" last="Krajewski">Pawel Krajewski</name><affiliation><nlm:aff id="aff2"><addr-line>Department of Biometry and Bioinformatics, Institute of Plant Genetics, Polish Academy of Sciences, Poznań, Poland</addr-line></nlm:aff></affiliation></author><author><name sortKey="Ladunga, Istvan" sort="Ladunga, Istvan" uniqKey="Ladunga I" first="Istvan" last="Ladunga">Istvan Ladunga</name><affiliation><nlm:aff id="aff3"><addr-line>Department of Statistics, Beadle Center, University of Nebraska-Lincoln, Lincoln, Nebraska, United States of America</addr-line></nlm:aff></affiliation></author><author><name sortKey="Lefebvre, Celine" sort="Lefebvre, Celine" uniqKey="Lefebvre C" first="Celine" last="Lefebvre">Celine Lefebvre</name><affiliation><nlm:aff id="aff4"><addr-line>Inserm U981, Cancer Institute Gustave Roussy, Villejuif, France</addr-line></nlm:aff></affiliation></author><author><name sortKey="Li, Qunhua" sort="Li, Qunhua" uniqKey="Li Q" first="Qunhua" last="Li">Qunhua Li</name><affiliation><nlm:aff id="aff5"><addr-line>Department of Statistics, Penn State University, University Park, Pennsylvania, United States of America</addr-line></nlm:aff></affiliation></author><author><name sortKey="Liu, Tao" sort="Liu, Tao" uniqKey="Liu T" first="Tao" last="Liu">Tao Liu</name><affiliation><nlm:aff id="aff6"><addr-line>Department of Biochemistry, University at Buffalo, Buffalo, New York, United States of America</addr-line></nlm:aff></affiliation></author><author><name sortKey="Madrigal, Pedro" sort="Madrigal, Pedro" uniqKey="Madrigal P" first="Pedro" last="Madrigal">Pedro Madrigal</name><affiliation><nlm:aff id="aff2"><addr-line>Department of Biometry and Bioinformatics, Institute of Plant Genetics, Polish Academy of Sciences, Poznań, Poland</addr-line></nlm:aff></affiliation></author><author><name sortKey="Taslim, Cenny" sort="Taslim, Cenny" uniqKey="Taslim C" first="Cenny" last="Taslim">Cenny Taslim</name><affiliation><nlm:aff id="aff7"><addr-line>Department of Biomedical Informatics, The Ohio State University, Columbus, Ohio, United States of America</addr-line></nlm:aff></affiliation></author><author><name sortKey="Zhang, Jie" sort="Zhang, Jie" uniqKey="Zhang J" first="Jie" last="Zhang">Jie Zhang</name><affiliation><nlm:aff id="aff7"><addr-line>Department of Biomedical Informatics, The Ohio State University, Columbus, Ohio, United States of America</addr-line></nlm:aff></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PMC</idno><idno type="pmid">24244136</idno><idno type="pmc">3828144</idno><idno type="url">http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3828144</idno><idno type="RBID">PMC:3828144</idno><idno type="doi">10.1371/journal.pcbi.1003326</idno><date when="2013">2013</date><idno type="wicri:Area/Pmc/Corpus">002860</idno><idno type="wicri:explorRef" wicri:stream="Pmc" wicri:step="Corpus" wicri:corpus="PMC">002860</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a" type="main">Practical Guidelines for the Comprehensive Analysis of ChIP-seq Data</title><author><name sortKey="Bailey, Timothy" sort="Bailey, Timothy" uniqKey="Bailey T" first="Timothy" last="Bailey">Timothy Bailey</name><affiliation><nlm:aff id="aff1"><addr-line>Institute for Molecular Bioscience, The University of Queensland, Brisbane, Australia</addr-line></nlm:aff></affiliation></author><author><name sortKey="Krajewski, Pawel" sort="Krajewski, Pawel" uniqKey="Krajewski P" first="Pawel" last="Krajewski">Pawel Krajewski</name><affiliation><nlm:aff id="aff2"><addr-line>Department of Biometry and Bioinformatics, Institute of Plant Genetics, Polish Academy of Sciences, Poznań, Poland</addr-line></nlm:aff></affiliation></author><author><name sortKey="Ladunga, Istvan" sort="Ladunga, Istvan" uniqKey="Ladunga I" first="Istvan" last="Ladunga">Istvan Ladunga</name><affiliation><nlm:aff id="aff3"><addr-line>Department of Statistics, Beadle Center, University of Nebraska-Lincoln, Lincoln, Nebraska, United States of America</addr-line></nlm:aff></affiliation></author><author><name sortKey="Lefebvre, Celine" sort="Lefebvre, Celine" uniqKey="Lefebvre C" first="Celine" last="Lefebvre">Celine Lefebvre</name><affiliation><nlm:aff id="aff4"><addr-line>Inserm U981, Cancer Institute Gustave Roussy, Villejuif, France</addr-line></nlm:aff></affiliation></author><author><name sortKey="Li, Qunhua" sort="Li, Qunhua" uniqKey="Li Q" first="Qunhua" last="Li">Qunhua Li</name><affiliation><nlm:aff id="aff5"><addr-line>Department of Statistics, Penn State University, University Park, Pennsylvania, United States of America</addr-line></nlm:aff></affiliation></author><author><name sortKey="Liu, Tao" sort="Liu, Tao" uniqKey="Liu T" first="Tao" last="Liu">Tao Liu</name><affiliation><nlm:aff id="aff6"><addr-line>Department of Biochemistry, University at Buffalo, Buffalo, New York, United States of America</addr-line></nlm:aff></affiliation></author><author><name sortKey="Madrigal, Pedro" sort="Madrigal, Pedro" uniqKey="Madrigal P" first="Pedro" last="Madrigal">Pedro Madrigal</name><affiliation><nlm:aff id="aff2"><addr-line>Department of Biometry and Bioinformatics, Institute of Plant Genetics, Polish Academy of Sciences, Poznań, Poland</addr-line></nlm:aff></affiliation></author><author><name sortKey="Taslim, Cenny" sort="Taslim, Cenny" uniqKey="Taslim C" first="Cenny" last="Taslim">Cenny Taslim</name><affiliation><nlm:aff id="aff7"><addr-line>Department of Biomedical Informatics, The Ohio State University, Columbus, Ohio, United States of America</addr-line></nlm:aff></affiliation></author><author><name sortKey="Zhang, Jie" sort="Zhang, Jie" uniqKey="Zhang J" first="Jie" last="Zhang">Jie Zhang</name><affiliation><nlm:aff id="aff7"><addr-line>Department of Biomedical Informatics, The Ohio State University, Columbus, Ohio, United States of America</addr-line></nlm:aff></affiliation></author></analytic><series><title level="j">PLoS Computational Biology</title><idno type="ISSN">1553-734X</idno><idno type="eISSN">1553-7358</idno><imprint><date when="2013">2013</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en"><p>Mapping the chromosomal locations of transcription factors, nucleosomes, histone modifications, chromatin remodeling enzymes, chaperones, and polymerases is one of the key tasks of modern biology, as evidenced by the Encyclopedia of DNA Elements (ENCODE) Project. To this end, chromatin immunoprecipitation followed by high-throughput sequencing (ChIP-seq) is the standard methodology. Mapping such protein-DNA interactions <italic>in vivo</italic> using ChIP-seq presents multiple challenges not only in sample preparation and sequencing but also for computational analysis. Here, we present step-by-step guidelines for the computational analysis of ChIP-seq data. We address all the major steps in the analysis of ChIP-seq data: sequencing depth selection, quality checking, mapping, data normalization, assessment of reproducibility, peak calling, differential binding analysis, controlling the false discovery rate, peak annotation, visualization, and motif analysis. At each step in our guidelines we discuss some of the software tools most frequently used. We also highlight the challenges and problems associated with each step in ChIP-seq data analysis. We present a concise workflow for the analysis of ChIP-seq data in <bold>Figure 1</bold> that complements and expands on the recommendations of the ENCODE and modENCODE projects. Each step in the workflow is described in detail in the following sections.</p></div></front><back><div1 type="bibliography"><listBibl><biblStruct><analytic><author><name sortKey="Johnson, Ds" uniqKey="Johnson D">DS Johnson</name></author><author><name sortKey="Mortazavi, A" uniqKey="Mortazavi A">A Mortazavi</name></author><author><name sortKey="Myers, Rm" uniqKey="Myers R">RM Myers</name></author><author><name sortKey="Wold, B" uniqKey="Wold B">B Wold</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Barski, A" uniqKey="Barski A">A Barski</name></author><author><name sortKey="Cuddapah, S" uniqKey="Cuddapah S">S Cuddapah</name></author><author><name sortKey="Cui, K" uniqKey="Cui K">K Cui</name></author><author><name sortKey="Roth, Ty" uniqKey="Roth T">TY Roth</name></author><author><name sortKey="Schones, De" uniqKey="Schones D">DE Schones</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Robertson, G" uniqKey="Robertson G">G Robertson</name></author><author><name sortKey="Hirst, M" uniqKey="Hirst M">M Hirst</name></author><author><name sortKey="Bainbridge, M" uniqKey="Bainbridge M">M Bainbridge</name></author><author><name sortKey="Bilenky, M" uniqKey="Bilenky M">M Bilenky</name></author><author><name sortKey="Zhao, Y" uniqKey="Zhao Y">Y Zhao</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Mikkelsen, Ts" uniqKey="Mikkelsen T">TS Mikkelsen</name></author><author><name sortKey="Ku, M" uniqKey="Ku M">M Ku</name></author><author><name sortKey="Jaffe, Db" uniqKey="Jaffe D">DB Jaffe</name></author><author><name sortKey="Issac, B" uniqKey="Issac B">B Issac</name></author><author><name sortKey="Lieberman, E" uniqKey="Lieberman E">E Lieberman</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Furey, Ts" uniqKey="Furey T">TS Furey</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Ku, Cs" uniqKey="Ku C">CS Ku</name></author><author><name sortKey="Naidoo, N" uniqKey="Naidoo N">N Naidoo</name></author><author><name sortKey="Wu, M" uniqKey="Wu M">M Wu</name></author><author><name sortKey="Soong, R" uniqKey="Soong R">R Soong</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Landt, Sg" uniqKey="Landt S">SG Landt</name></author><author><name sortKey="Marinov, Gk" uniqKey="Marinov G">GK Marinov</name></author><author><name sortKey="Kundaje, A" uniqKey="Kundaje A">A Kundaje</name></author><author><name sortKey="Kheradpour, P" uniqKey="Kheradpour P">P Kheradpour</name></author><author><name sortKey="Pauli, F" uniqKey="Pauli F">F Pauli</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Chen, Y" uniqKey="Chen Y">Y Chen</name></author><author><name sortKey="Negre, N" uniqKey="Negre N">N Negre</name></author><author><name sortKey="Li, Q" uniqKey="Li Q">Q Li</name></author><author><name sortKey="Mieczkowska, Jo" uniqKey="Mieczkowska J">JO Mieczkowska</name></author><author><name sortKey="Slattery, M" uniqKey="Slattery M">M Slattery</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Kharchenko, Pv" uniqKey="Kharchenko P">PV Kharchenko</name></author><author><name sortKey="Tolstorukov, My" uniqKey="Tolstorukov M">MY Tolstorukov</name></author><author><name sortKey="Park, Pj" uniqKey="Park P">PJ Park</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Daley, T" uniqKey="Daley T">T Daley</name></author><author><name sortKey="Smith, Ad" uniqKey="Smith A">AD Smith</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Langmead, B" uniqKey="Langmead B">B Langmead</name></author><author><name sortKey="Trapnell, C" uniqKey="Trapnell C">C Trapnell</name></author><author><name sortKey="Pop, M" uniqKey="Pop M">M Pop</name></author><author><name sortKey="Salzberg, Sl" uniqKey="Salzberg S">SL Salzberg</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Li, H" uniqKey="Li H">H Li</name></author><author><name sortKey="Durbin, R" uniqKey="Durbin R">R Durbin</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Li, R" uniqKey="Li R">R Li</name></author><author><name sortKey="Li, Y" uniqKey="Li Y">Y Li</name></author><author><name sortKey="Kristiansen, K" uniqKey="Kristiansen K">K Kristiansen</name></author><author><name sortKey="Wang, J" uniqKey="Wang J">J Wang</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Li, H" uniqKey="Li H">H Li</name></author><author><name sortKey="Ruan, J" uniqKey="Ruan J">J Ruan</name></author><author><name sortKey="Durbin, R" uniqKey="Durbin R">R Durbin</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Wang, R" uniqKey="Wang R">R Wang</name></author><author><name sortKey="Hsu, H K" uniqKey="Hsu H">H-K Hsu</name></author><author><name sortKey="Blattler, A" uniqKey="Blattler A">A Blattler</name></author><author><name sortKey="Wang, Y" uniqKey="Wang Y">Y Wang</name></author><author><name sortKey="Lan, X" uniqKey="Lan X">X Lan</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Diaz, A" uniqKey="Diaz A">A Diaz</name></author><author><name sortKey="Nellore, A" uniqKey="Nellore A">A Nellore</name></author><author><name sortKey="Song, Js" uniqKey="Song J">JS Song</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Zhang, Y" uniqKey="Zhang Y">Y Zhang</name></author><author><name sortKey="Liu, T" uniqKey="Liu T">T Liu</name></author><author><name sortKey="Meyer, Ca" uniqKey="Meyer C">CA Meyer</name></author><author><name sortKey="Eeckhoute, J" uniqKey="Eeckhoute J">J Eeckhoute</name></author><author><name sortKey="Johnson, Ds" uniqKey="Johnson D">DS Johnson</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Guo, Y" uniqKey="Guo Y">Y Guo</name></author><author><name sortKey="Mahony, S" uniqKey="Mahony S">S Mahony</name></author><author><name sortKey="Gifford, Dk" uniqKey="Gifford D">DK Gifford</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Jothi, R" uniqKey="Jothi R">R Jothi</name></author><author><name sortKey="Cuddapah, S" uniqKey="Cuddapah S">S Cuddapah</name></author><author><name sortKey="Barski, A" uniqKey="Barski A">A Barski</name></author><author><name sortKey="Cui, K" uniqKey="Cui K">K Cui</name></author><author><name sortKey="Zhao, K" uniqKey="Zhao K">K Zhao</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Pepke, S" uniqKey="Pepke S">S Pepke</name></author><author><name sortKey="Wold, B" uniqKey="Wold B">B Wold</name></author><author><name sortKey="Mortazavi, A" uniqKey="Mortazavi A">A Mortazavi</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Wang, C" uniqKey="Wang C">C Wang</name></author><author><name sortKey="Xu, J" uniqKey="Xu J">J Xu</name></author><author><name sortKey="Zhang, D" uniqKey="Zhang D">D Zhang</name></author><author><name sortKey="Wilson, Za" uniqKey="Wilson Z">ZA Wilson</name></author><author><name sortKey="Zhang, D" uniqKey="Zhang D">D Zhang</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Szalkowski, Am" uniqKey="Szalkowski A">AM Szalkowski</name></author><author><name sortKey="Schmid, Cd" uniqKey="Schmid C">CD Schmid</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Li, Q" uniqKey="Li Q">Q Li</name></author><author><name sortKey="Brown, J" uniqKey="Brown J">J Brown</name></author><author><name sortKey="Huang, H" uniqKey="Huang H">H Huang</name></author><author><name sortKey="Bickel, P" uniqKey="Bickel P">P Bickel</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Rozowsky, J" uniqKey="Rozowsky J">J Rozowsky</name></author><author><name sortKey="Euskirchen, G" uniqKey="Euskirchen G">G Euskirchen</name></author><author><name sortKey="Auerbach, Rk" uniqKey="Auerbach R">RK Auerbach</name></author><author><name sortKey="Zhang, Zd" uniqKey="Zhang Z">ZD Zhang</name></author><author><name sortKey="Gibson, T" uniqKey="Gibson T">T Gibson</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Bardet, Af" uniqKey="Bardet A">AF Bardet</name></author><author><name sortKey="He, Q" uniqKey="He Q">Q He</name></author><author><name sortKey="Zeitlinger, J" uniqKey="Zeitlinger J">J Zeitlinger</name></author><author><name sortKey="Stark, A" uniqKey="Stark A">A Stark</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Labaj, Pp" uniqKey="Labaj P">PP Łabaj</name></author><author><name sortKey="Leparc, Gg" uniqKey="Leparc G">GG Leparc</name></author><author><name sortKey="Linggi, Be" uniqKey="Linggi B">BE Linggi</name></author><author><name sortKey="Markillie, Lm" uniqKey="Markillie L">LM Markillie</name></author><author><name sortKey="Wiley, Hs" uniqKey="Wiley H">HS Wiley</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Sandmann, T" uniqKey="Sandmann T">T Sandmann</name></author><author><name sortKey="Jensen, Lj" uniqKey="Jensen L">LJ Jensen</name></author><author><name sortKey="Jakobsen, Js" uniqKey="Jakobsen J">JS Jakobsen</name></author><author><name sortKey="Karzynski, Mm" uniqKey="Karzynski M">MM Karzynski</name></author><author><name sortKey="Eichenlaub, Mp" uniqKey="Eichenlaub M">MP Eichenlaub</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Taslim, C" uniqKey="Taslim C">C Taslim</name></author><author><name sortKey="Wu, J" uniqKey="Wu J">J Wu</name></author><author><name sortKey="Yan, P" uniqKey="Yan P">P Yan</name></author><author><name sortKey="Singer, G" uniqKey="Singer G">G Singer</name></author><author><name sortKey="Parvin, J" uniqKey="Parvin J">J Parvin</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Quinlan, Ar" uniqKey="Quinlan A">AR Quinlan</name></author><author><name sortKey="Hall, Im" uniqKey="Hall I">IM Hall</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Asz Di, A" uniqKey="Asz Di A">A Aszódi</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Anders, S" uniqKey="Anders S">S Anders</name></author><author><name sortKey="Huber, W" uniqKey="Huber W">W Huber</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Robinson, Md" uniqKey="Robinson M">MD Robinson</name></author><author><name sortKey="Mccarthy, Dj" uniqKey="Mccarthy D">DJ McCarthy</name></author><author><name sortKey="Smyth, Gk" uniqKey="Smyth G">GK Smyth</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Liang, K" uniqKey="Liang K">K Liang</name></author><author><name sortKey="Keles, S" uniqKey="Keles S">S Keles</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Shao, Z" uniqKey="Shao Z">Z Shao</name></author><author><name sortKey="Zhang, Y" uniqKey="Zhang Y">Y Zhang</name></author><author><name sortKey="Yuan, Gc" uniqKey="Yuan G">GC Yuan</name></author><author><name sortKey="Orkin, Sh" uniqKey="Orkin S">SH Orkin</name></author><author><name sortKey="Waxman, Dj" uniqKey="Waxman D">DJ Waxman</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Taslim, C" uniqKey="Taslim C">C Taslim</name></author><author><name sortKey="Huang, T" uniqKey="Huang T">T Huang</name></author><author><name sortKey="Lin, S" uniqKey="Lin S">S Lin</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Xu, H" uniqKey="Xu H">H Xu</name></author><author><name sortKey="Wei, Cl" uniqKey="Wei C">CL Wei</name></author><author><name sortKey="Lin, F" uniqKey="Lin F">F Lin</name></author><author><name sortKey="Sung, Wk" uniqKey="Sung W">WK Sung</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Mendoza Parra, Ma" uniqKey="Mendoza Parra M">MA Mendoza-Parra</name></author><author><name sortKey="Sankar, M" uniqKey="Sankar M">M Sankar</name></author><author><name sortKey="Walia, M" uniqKey="Walia M">M Walia</name></author><author><name sortKey="Gronemeyer, H" uniqKey="Gronemeyer H">H Gronemeyer</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Kuhn, Rm" uniqKey="Kuhn R">RM Kuhn</name></author><author><name sortKey="Haussler, D" uniqKey="Haussler D">D Haussler</name></author><author><name sortKey="Kent, Wj" uniqKey="Kent W">WJ Kent</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Nicol, Jw" uniqKey="Nicol J">JW Nicol</name></author><author><name sortKey="Helt, Ga" uniqKey="Helt G">GA Helt</name></author><author><name sortKey="Blanchard, Sg" uniqKey="Blanchard S">SG Blanchard</name></author><author><name sortKey="Raja, A" uniqKey="Raja A">A Raja</name></author><author><name sortKey="Loraine, Ae" uniqKey="Loraine A">AE Loraine</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Robinson, Jt" uniqKey="Robinson J">JT Robinson</name></author><author><name sortKey="Thorvaldsd Ttir, H" uniqKey="Thorvaldsd Ttir H">H Thorvaldsdóttir</name></author><author><name sortKey="Winckler, W" uniqKey="Winckler W">W Winckler</name></author><author><name sortKey="Guttman, M" uniqKey="Guttman M">M Guttman</name></author><author><name sortKey="Lander, Es" uniqKey="Lander E">ES Lander</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Kent, Wj" uniqKey="Kent W">WJ Kent</name></author><author><name sortKey="Zweig, As" uniqKey="Zweig A">AS Zweig</name></author><author><name sortKey="Barber, G" uniqKey="Barber G">G Barber</name></author><author><name sortKey="Hinrichs, As" uniqKey="Hinrichs A">AS Hinrichs</name></author><author><name sortKey="Karolchik, D" uniqKey="Karolchik D">D Karolchik</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Shin, H" uniqKey="Shin H">H Shin</name></author><author><name sortKey="Liu, T" uniqKey="Liu T">T Liu</name></author><author><name sortKey="Manrai, Ak" uniqKey="Manrai A">AK Manrai</name></author><author><name sortKey="Liu, Xs" uniqKey="Liu X">XS Liu</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Zhu, Lj" uniqKey="Zhu L">LJ Zhu</name></author><author><name sortKey="Gazin, C" uniqKey="Gazin C">C Gazin</name></author><author><name sortKey="Lawson, Nd" uniqKey="Lawson N">ND Lawson</name></author><author><name sortKey="Pages, H" uniqKey="Pages H">H Pages</name></author><author><name sortKey="Lin, Sm" uniqKey="Lin S">SM Lin</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Huang Da, W" uniqKey="Huang Da W">W Huang da</name></author><author><name sortKey="Sherman, Bt" uniqKey="Sherman B">BT Sherman</name></author><author><name sortKey="Lempicki, Ra" uniqKey="Lempicki R">RA Lempicki</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Mclean, Cy" uniqKey="Mclean C">CY McLean</name></author><author><name sortKey="Bristor, D" uniqKey="Bristor D">D Bristor</name></author><author><name sortKey="Hiller, M" uniqKey="Hiller M">M Hiller</name></author><author><name sortKey="Clarke, Sl" uniqKey="Clarke S">SL Clarke</name></author><author><name sortKey="Schaar, Bt" uniqKey="Schaar B">BT Schaar</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Subramanian, A" uniqKey="Subramanian A">A Subramanian</name></author><author><name sortKey="Tamayo, P" uniqKey="Tamayo P">P Tamayo</name></author><author><name sortKey="Mootha, Vk" uniqKey="Mootha V">VK Mootha</name></author><author><name sortKey="Mukherjee, S" uniqKey="Mukherjee S">S Mukherjee</name></author><author><name sortKey="Ebert, Bl" uniqKey="Ebert B">BL Ebert</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Liu, Hw" uniqKey="Liu H">HW Liu</name></author><author><name sortKey="Zhang, J" uniqKey="Zhang J">J Zhang</name></author><author><name sortKey="Heine, Gf" uniqKey="Heine G">GF Heine</name></author><author><name sortKey="Arora, M" uniqKey="Arora M">M Arora</name></author><author><name sortKey="Gulcin Ozer, H" uniqKey="Gulcin Ozer H">H Gulcin Ozer</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Kuttippurathu, L" uniqKey="Kuttippurathu L">L Kuttippurathu</name></author><author><name sortKey="Hsing, M" uniqKey="Hsing M">M Hsing</name></author><author><name sortKey="Liu, Y" uniqKey="Liu Y">Y Liu</name></author><author><name sortKey="Schmidt, B" uniqKey="Schmidt B">B Schmidt</name></author><author><name sortKey="Maskell, Dl" uniqKey="Maskell D">DL Maskell</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Liu, T" uniqKey="Liu T">T Liu</name></author><author><name sortKey="Ortiz, Ja" uniqKey="Ortiz J">JA Ortiz</name></author><author><name sortKey="Taing, L" uniqKey="Taing L">L Taing</name></author><author><name sortKey="Meyer, Ca" uniqKey="Meyer C">CA Meyer</name></author><author><name sortKey="Lee, B" uniqKey="Lee B">B Lee</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Goecks, J" uniqKey="Goecks J">J Goecks</name></author><author><name sortKey="Nekrutenko, A" uniqKey="Nekrutenko A">A Nekrutenko</name></author><author><name sortKey="Taylor, J" uniqKey="Taylor J">J Taylor</name></author><author><name sortKey="Team, G" uniqKey="Team G">G Team</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Blankenberg, D" uniqKey="Blankenberg D">D Blankenberg</name></author><author><name sortKey="Kuster, Gv" uniqKey="Kuster G">GV Kuster</name></author><author><name sortKey="Coraor, N" uniqKey="Coraor N">N Coraor</name></author><author><name sortKey="Ananda, G" uniqKey="Ananda G">G Ananda</name></author><author><name sortKey="Lazarus, R" uniqKey="Lazarus R">R Lazarus</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Giardine, B" uniqKey="Giardine B">B Giardine</name></author><author><name sortKey="Riemer, C" uniqKey="Riemer C">C Riemer</name></author><author><name sortKey="Hardison, Rc" uniqKey="Hardison R">RC Hardison</name></author><author><name sortKey="Burhans, R" uniqKey="Burhans R">R Burhans</name></author><author><name sortKey="Elnitski, L" uniqKey="Elnitski L">L Elnitski</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Van Helden, J" uniqKey="Van Helden J">J van Helden</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Kent, Wj" uniqKey="Kent W">WJ Kent</name></author><author><name sortKey="Sugnet, Cw" uniqKey="Sugnet C">CW Sugnet</name></author><author><name sortKey="Furey, Ts" uniqKey="Furey T">TS Furey</name></author><author><name sortKey="Roskin, Km" uniqKey="Roskin K">KM Roskin</name></author><author><name sortKey="Pringle, Th" uniqKey="Pringle T">TH Pringle</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Kulakovskiy, Iv" uniqKey="Kulakovskiy I">IV Kulakovskiy</name></author><author><name sortKey="Boeva, Va" uniqKey="Boeva V">VA Boeva</name></author><author><name sortKey="Favorov, Av" uniqKey="Favorov A">AV Favorov</name></author><author><name sortKey="Makeev, Vj" uniqKey="Makeev V">VJ Makeev</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Ji, H" uniqKey="Ji H">H Ji</name></author><author><name sortKey="Jiang, H" uniqKey="Jiang H">H Jiang</name></author><author><name sortKey="Ma, W" uniqKey="Ma W">W Ma</name></author><author><name sortKey="Johnson, Ds" uniqKey="Johnson D">DS Johnson</name></author><author><name sortKey="Myers, Rm" uniqKey="Myers R">RM Myers</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Machanick, P" uniqKey="Machanick P">P Machanick</name></author><author><name sortKey="Bailey, Tl" uniqKey="Bailey T">TL Bailey</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Thomas Chollier, M" uniqKey="Thomas Chollier M">M Thomas-Chollier</name></author><author><name sortKey="Herrmann, C" uniqKey="Herrmann C">C Herrmann</name></author><author><name sortKey="Defrance, M" uniqKey="Defrance M">M Defrance</name></author><author><name sortKey="Sand, O" uniqKey="Sand O">O Sand</name></author><author><name sortKey="Thieffry, D" uniqKey="Thieffry D">D Thieffry</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Mahony, S" uniqKey="Mahony S">S Mahony</name></author><author><name sortKey="Benos, Pv" uniqKey="Benos P">PV Benos</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Gupta, S" uniqKey="Gupta S">S Gupta</name></author><author><name sortKey="Stamatoyannopoulos, J" uniqKey="Stamatoyannopoulos J">J Stamatoyannopoulos</name></author><author><name sortKey="Bailey, Tl" uniqKey="Bailey T">TL Bailey</name></author><author><name sortKey="Noble, Ws" uniqKey="Noble W">WS Noble</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Bailey, Tl" uniqKey="Bailey T">TL Bailey</name></author><author><name sortKey="Machanick, P" uniqKey="Machanick P">P Machanick</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Whitington, T" uniqKey="Whitington T">T Whitington</name></author><author><name sortKey="Frith, Mc" uniqKey="Frith M">MC Frith</name></author><author><name sortKey="Johnson, J" uniqKey="Johnson J">J Johnson</name></author><author><name sortKey="Bailey, Tl" uniqKey="Bailey T">TL Bailey</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Grant, Ce" uniqKey="Grant C">CE Grant</name></author><author><name sortKey="Bailey, Tl" uniqKey="Bailey T">TL Bailey</name></author><author><name sortKey="Noble, Ws" uniqKey="Noble W">WS Noble</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Hertz, Gz" uniqKey="Hertz G">GZ Hertz</name></author><author><name sortKey="Stormo, Gd" uniqKey="Stormo G">GD Stormo</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Adli, M" uniqKey="Adli M">M Adli</name></author><author><name sortKey="Bernstein, Be" uniqKey="Bernstein B">BE Bernstein</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Dunham, I" uniqKey="Dunham I">I Dunham</name></author><author><name sortKey="Kundaje, A" uniqKey="Kundaje A">A Kundaje</name></author><author><name sortKey="Alfred, Sf" uniqKey="Alfred S">SF Alfred</name></author><author><name sortKey="Collins, Pj" uniqKey="Collins P">PJ Collins</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Guo, Y" uniqKey="Guo Y">Y Guo</name></author><author><name sortKey="Papachristoudis, G" uniqKey="Papachristoudis G">G Papachristoudis</name></author><author><name sortKey="Altshuler, Rc" uniqKey="Altshuler R">RC Altshuler</name></author><author><name sortKey="Gerber, Gk" uniqKey="Gerber G">GK Gerber</name></author><author><name sortKey="Jaakkola, Ts" uniqKey="Jaakkola T">TS Jaakkola</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Rhee, Hs" uniqKey="Rhee H">HS Rhee</name></author><author><name sortKey="Pugh, Bf" uniqKey="Pugh B">BF Pugh</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Egelhofer, Ta" uniqKey="Egelhofer T">TA Egelhofer</name></author><author><name sortKey="Minoda, A" uniqKey="Minoda A">A Minoda</name></author><author><name sortKey="Klugman, S" uniqKey="Klugman S">S Klugman</name></author><author><name sortKey="Lee, K" uniqKey="Lee K">K Lee</name></author><author><name sortKey="Kolasinska Zwierz, P" uniqKey="Kolasinska Zwierz P">P Kolasinska-Zwierz</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Thurman, Re" uniqKey="Thurman R">RE Thurman</name></author><author><name sortKey="Rynes, E" uniqKey="Rynes E">E Rynes</name></author><author><name sortKey="Humbert, R" uniqKey="Humbert R">R Humbert</name></author><author><name sortKey="Vierstra, J" uniqKey="Vierstra J">J Vierstra</name></author><author><name sortKey="Maurano, Mt" uniqKey="Maurano M">MT Maurano</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Jiao, S" uniqKey="Jiao S">S Jiao</name></author><author><name sortKey="Bailey, Cp" uniqKey="Bailey C">CP Bailey</name></author><author><name sortKey="Zhang, S" uniqKey="Zhang S">S Zhang</name></author><author><name sortKey="Ladunga, I" uniqKey="Ladunga I">I Ladunga</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Wilbanks, Eg" uniqKey="Wilbanks E">EG Wilbanks</name></author><author><name sortKey="Facciotti, Mt" uniqKey="Facciotti M">MT Facciotti</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Schweikert, C" uniqKey="Schweikert C">C Schweikert</name></author><author><name sortKey="Brown, S" uniqKey="Brown S">S Brown</name></author><author><name sortKey="Tang, Z" uniqKey="Tang Z">Z Tang</name></author><author><name sortKey="Smith, Pr" uniqKey="Smith P">PR Smith</name></author><author><name sortKey="Hsu, Df" uniqKey="Hsu D">DF Hsu</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Li, G" uniqKey="Li G">G Li</name></author><author><name sortKey="Fullwood, Mj" uniqKey="Fullwood M">MJ Fullwood</name></author><author><name sortKey="Xu, H" uniqKey="Xu H">H Xu</name></author><author><name sortKey="Mulawadi, Fh" uniqKey="Mulawadi F">FH Mulawadi</name></author><author><name sortKey="Velkov, S" uniqKey="Velkov S">S Velkov</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Van De Werken, Hj" uniqKey="Van De Werken H">HJ van de Werken</name></author><author><name sortKey="Landan, G" uniqKey="Landan G">G Landan</name></author><author><name sortKey="Holwerda, Sj" uniqKey="Holwerda S">SJ Holwerda</name></author><author><name sortKey="Hoichman, M" uniqKey="Hoichman M">M Hoichman</name></author><author><name sortKey="Klous, P" uniqKey="Klous P">P Klous</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Dostie, J" uniqKey="Dostie J">J Dostie</name></author><author><name sortKey="Richmond, Ta" uniqKey="Richmond T">TA Richmond</name></author><author><name sortKey="Arnaout, Ra" uniqKey="Arnaout R">RA Arnaout</name></author><author><name sortKey="Selzer, Rr" uniqKey="Selzer R">RR Selzer</name></author><author><name sortKey="Lee, Wl" uniqKey="Lee W">WL Lee</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Diaz, A" uniqKey="Diaz A">A Diaz</name></author><author><name sortKey="Park, K" uniqKey="Park K">K Park</name></author><author><name sortKey="Lim, Da" uniqKey="Lim D">DA Lim</name></author><author><name sortKey="Song, Js" uniqKey="Song J">JS Song</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="White, Ma" uniqKey="White M">MA White</name></author><author><name sortKey="Myers, Ca" uniqKey="Myers C">CA Myers</name></author><author><name sortKey="Corbo, Jc" uniqKey="Corbo J">JC Corbo</name></author><author><name sortKey="Cohen, Ba" uniqKey="Cohen B">BA Cohen</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Doolittle, Wf" uniqKey="Doolittle W">WF Doolittle</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Zhu, C" uniqKey="Zhu C">C Zhu</name></author><author><name sortKey="Byers, Kj" uniqKey="Byers K">KJ Byers</name></author><author><name sortKey="Mccord, Rp" uniqKey="Mccord R">RP McCord</name></author><author><name sortKey="Shi, Z" uniqKey="Shi Z">Z Shi</name></author><author><name sortKey="Berger, Mf" uniqKey="Berger M">MF Berger</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Jia, C" uniqKey="Jia C">C Jia</name></author><author><name sortKey="Carson, Mb" uniqKey="Carson M">MB Carson</name></author><author><name sortKey="Yu, J" uniqKey="Yu J">J Yu</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Sun, Hq" uniqKey="Sun H">HQ Sun</name></author><author><name sortKey="Low, My" uniqKey="Low M">MY Low</name></author><author><name sortKey="Hsu, Wj" uniqKey="Hsu W">WJ Hsu</name></author><author><name sortKey="Rajapakse, Jc" uniqKey="Rajapakse J">JC Rajapakse</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Yip, Ky" uniqKey="Yip K">KY Yip</name></author><author><name sortKey="Cheng, C" uniqKey="Cheng C">C Cheng</name></author><author><name sortKey="Bhardwaj, N" uniqKey="Bhardwaj N">N Bhardwaj</name></author><author><name sortKey="Brown, Jb" uniqKey="Brown J">JB Brown</name></author><author><name sortKey="Leng, J" uniqKey="Leng J">J Leng</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Cheung, M S" uniqKey="Cheung M">M-S Cheung</name></author><author><name sortKey="Down, Ta" uniqKey="Down T">TA Down</name></author><author><name sortKey="Latorre, I" uniqKey="Latorre I">I Latorre</name></author><author><name sortKey="Ahringer, J" uniqKey="Ahringer J">J Ahringer</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Mui O, Jm" uniqKey="Mui O J">JM Muiño</name></author><author><name sortKey="Kaufmann, K" uniqKey="Kaufmann K">K Kaufmann</name></author><author><name sortKey="Van Ham, Rc" uniqKey="Van Ham R">RC van Ham</name></author><author><name sortKey="Angenent, Gc" uniqKey="Angenent G">GC Angenent</name></author><author><name sortKey="Krajewski, P" uniqKey="Krajewski P">P Krajewski</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Rashid, Nu" uniqKey="Rashid N">NU Rashid</name></author><author><name sortKey="Giresi, Pg" uniqKey="Giresi P">PG Giresi</name></author><author><name sortKey="Ibrahim, Jg" uniqKey="Ibrahim J">JG Ibrahim</name></author><author><name sortKey="Sun, W" uniqKey="Sun W">W Sun</name></author><author><name sortKey="Lieb, Jd" uniqKey="Lieb J">JD Lieb</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Qin, Zs" uniqKey="Qin Z">ZS Qin</name></author><author><name sortKey="Yu, J" uniqKey="Yu J">J Yu</name></author><author><name sortKey="Shen, J" uniqKey="Shen J">J Shen</name></author><author><name sortKey="Maher, Ca" uniqKey="Maher C">CA Maher</name></author><author><name sortKey="Hu, M" uniqKey="Hu M">M Hu</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Spyrou, C" uniqKey="Spyrou C">C Spyrou</name></author><author><name sortKey="Stark, R" uniqKey="Stark R">R Stark</name></author><author><name sortKey="Lynch, Ag" uniqKey="Lynch A">AG Lynch</name></author><author><name sortKey="Tavare, S" uniqKey="Tavare S">S Tavaré</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Salmon Divon, M" uniqKey="Salmon Divon M">M Salmon-Divon</name></author><author><name sortKey="Dvinge, H" uniqKey="Dvinge H">H Dvinge</name></author><author><name sortKey="Tammoja, K" uniqKey="Tammoja K">K Tammoja</name></author><author><name sortKey="Bertone, P" uniqKey="Bertone P">P Bertone</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Zang, C" uniqKey="Zang C">C Zang</name></author><author><name sortKey="Schones, De" uniqKey="Schones D">DE Schones</name></author><author><name sortKey="Zeng, C" uniqKey="Zeng C">C Zeng</name></author><author><name sortKey="Cui, K" uniqKey="Cui K">K Cui</name></author><author><name sortKey="Zhao, K" uniqKey="Zhao K">K Zhao</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Xu, H" uniqKey="Xu H">H Xu</name></author><author><name sortKey="Handoko, L" uniqKey="Handoko L">L Handoko</name></author><author><name sortKey="Wei, X" uniqKey="Wei X">X Wei</name></author><author><name sortKey="Ye, C" uniqKey="Ye C">C Ye</name></author><author><name sortKey="Sheng, J" uniqKey="Sheng J">J Sheng</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Song, Q" uniqKey="Song Q">Q Song</name></author><author><name sortKey="Smith, Ad" uniqKey="Smith A">AD Smith</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Feng, X" uniqKey="Feng X">X Feng</name></author><author><name sortKey="Grossman, R" uniqKey="Grossman R">R Grossman</name></author><author><name sortKey="Stein, L" uniqKey="Stein L">L Stein</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Guttman, M" uniqKey="Guttman M">M Guttman</name></author><author><name sortKey="Garber, M" uniqKey="Garber M">M Garber</name></author><author><name sortKey="Levin, Jz" uniqKey="Levin J">JZ Levin</name></author><author><name sortKey="Donaghey, J" uniqKey="Donaghey J">J Donaghey</name></author><author><name sortKey="Robinson, J" uniqKey="Robinson J">J Robinson</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Baugh, Lr" uniqKey="Baugh L">LR Baugh</name></author><author><name sortKey="Demodena, J" uniqKey="Demodena J">J Demodena</name></author><author><name sortKey="Sternberg, Pw" uniqKey="Sternberg P">PW Sternberg</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Taslim, C" uniqKey="Taslim C">C Taslim</name></author><author><name sortKey="Huang, K" uniqKey="Huang K">K Huang</name></author><author><name sortKey="Huang, T" uniqKey="Huang T">T Huang</name></author><author><name sortKey="Lin, S" uniqKey="Lin S">S Lin</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Nix, D" uniqKey="Nix D">D Nix</name></author><author><name sortKey="Courdy, S" uniqKey="Courdy S">S Courdy</name></author><author><name sortKey="Boucher, K" uniqKey="Boucher K">K Boucher</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Mortazavi, A" uniqKey="Mortazavi A">A Mortazavi</name></author><author><name sortKey="Williams, Ba" uniqKey="Williams B">BA Williams</name></author><author><name sortKey="Mccue, K" uniqKey="Mccue K">K McCue</name></author><author><name sortKey="Schaeffer, L" uniqKey="Schaeffer L">L Schaeffer</name></author><author><name sortKey="Wold, B" uniqKey="Wold B">B Wold</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Liang, K" uniqKey="Liang K">K Liang</name></author><author><name sortKey="Kele, S" uniqKey="Kele S">S Keleş</name></author></analytic></biblStruct></listBibl></div1></back></TEI><pmc article-type="research-article"><pmc-dir>properties open_access</pmc-dir>
<front><journal-meta><journal-id journal-id-type="nlm-ta">PLoS Comput Biol</journal-id><journal-id journal-id-type="iso-abbrev">PLoS Comput. Biol</journal-id><journal-id journal-id-type="publisher-id">plos</journal-id><journal-id journal-id-type="pmc">ploscomp</journal-id><journal-title-group><journal-title>PLoS Computational Biology</journal-title></journal-title-group><issn pub-type="ppub">1553-734X</issn><issn pub-type="epub">1553-7358</issn><publisher><publisher-name>Public Library of Science</publisher-name><publisher-loc>San Francisco, USA</publisher-loc></publisher></journal-meta><article-meta><article-id pub-id-type="pmid">24244136</article-id><article-id pub-id-type="pmc">3828144</article-id><article-id pub-id-type="publisher-id">PCOMPBIOL-D-13-00917</article-id><article-id pub-id-type="doi">10.1371/journal.pcbi.1003326</article-id><article-categories><subj-group subj-group-type="heading"><subject>Education</subject></subj-group></article-categories><title-group><article-title>Practical Guidelines for the Comprehensive Analysis of ChIP-seq Data</article-title></title-group><contrib-group><contrib contrib-type="author"><name><surname>Bailey</surname><given-names>Timothy</given-names></name><xref ref-type="aff" rid="aff1"><sup>1</sup></xref><xref ref-type="corresp" rid="cor1"><sup>*</sup></xref><xref ref-type="author-notes" rid="fn1"><sup>¶</sup></xref></contrib><contrib contrib-type="author"><name><surname>Krajewski</surname><given-names>Pawel</given-names></name><xref ref-type="aff" rid="aff2"><sup>2</sup></xref><xref ref-type="author-notes" rid="fn1"><sup>¶</sup></xref></contrib><contrib contrib-type="author"><name><surname>Ladunga</surname><given-names>Istvan</given-names></name><xref ref-type="aff" rid="aff3"><sup>3</sup></xref><xref ref-type="author-notes" rid="fn1"><sup>¶</sup></xref></contrib><contrib contrib-type="author"><name><surname>Lefebvre</surname><given-names>Celine</given-names></name><xref ref-type="aff" rid="aff4"><sup>4</sup></xref><xref ref-type="author-notes" rid="fn1"><sup>¶</sup></xref></contrib><contrib contrib-type="author"><name><surname>Li</surname><given-names>Qunhua</given-names></name><xref ref-type="aff" rid="aff5"><sup>5</sup></xref><xref ref-type="author-notes" rid="fn1"><sup>¶</sup></xref></contrib><contrib contrib-type="author"><name><surname>Liu</surname><given-names>Tao</given-names></name><xref ref-type="aff" rid="aff6"><sup>6</sup></xref><xref ref-type="author-notes" rid="fn1"><sup>¶</sup></xref></contrib><contrib contrib-type="author"><name><surname>Madrigal</surname><given-names>Pedro</given-names></name><xref ref-type="aff" rid="aff2"><sup>2</sup></xref><xref ref-type="corresp" rid="cor1"><sup>*</sup></xref><xref ref-type="author-notes" rid="fn1"><sup>¶</sup></xref></contrib><contrib contrib-type="author"><name><surname>Taslim</surname><given-names>Cenny</given-names></name><xref ref-type="aff" rid="aff7"><sup>7</sup></xref><xref ref-type="author-notes" rid="fn1"><sup>¶</sup></xref></contrib><contrib contrib-type="author"><name><surname>Zhang</surname><given-names>Jie</given-names></name><xref ref-type="aff" rid="aff7"><sup>7</sup></xref><xref ref-type="author-notes" rid="fn1"><sup>¶</sup></xref></contrib></contrib-group><aff id="aff1"><label>1</label><addr-line>Institute for Molecular Bioscience, The University of Queensland, Brisbane, Australia</addr-line></aff><aff id="aff2"><label>2</label><addr-line>Department of Biometry and Bioinformatics, Institute of Plant Genetics, Polish Academy of Sciences, Poznań, Poland</addr-line></aff><aff id="aff3"><label>3</label><addr-line>Department of Statistics, Beadle Center, University of Nebraska-Lincoln, Lincoln, Nebraska, United States of America</addr-line></aff><aff id="aff4"><label>4</label><addr-line>Inserm U981, Cancer Institute Gustave Roussy, Villejuif, France</addr-line></aff><aff id="aff5"><label>5</label><addr-line>Department of Statistics, Penn State University, University Park, Pennsylvania, United States of America</addr-line></aff><aff id="aff6"><label>6</label><addr-line>Department of Biochemistry, University at Buffalo, Buffalo, New York, United States of America</addr-line></aff><aff id="aff7"><label>7</label><addr-line>Department of Biomedical Informatics, The Ohio State University, Columbus, Ohio, United States of America</addr-line></aff><contrib-group><contrib contrib-type="editor"><name><surname>Lewitter</surname><given-names>Fran</given-names></name><role>Editor</role><xref ref-type="aff" rid="edit1"></xref></contrib></contrib-group><aff id="edit1"><addr-line>Whitehead Institute, United States of America</addr-line></aff><author-notes><corresp id="cor1">* E-mail: <email>t.bailey@imb.uq.edu.au</email> (TB); <email>pmad@igr.poznan.pl</email> (PM)</corresp><fn id="fn1" fn-type="other"><p>¶ All authors contributed equally to this manuscript.</p></fn><fn fn-type="COI-statement"><p>The authors have declared that no competing interests exist.</p></fn></author-notes><pub-date pub-type="collection"><month>11</month><year>2013</year></pub-date><pub-date pub-type="epub"><day>14</day><month>11</month><year>2013</year></pub-date><volume>9</volume><issue>11</issue><elocation-id>e1003326</elocation-id><permissions><copyright-statement>© 2013 Bailey et al</copyright-statement><copyright-year>2013</copyright-year><copyright-holder>Bailey et al</copyright-holder><license xlink:href="http://creativecommons.org/licenses/by/4.0/"><license-p>This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.</license-p></license></permissions><abstract><p>Mapping the chromosomal locations of transcription factors, nucleosomes, histone modifications, chromatin remodeling enzymes, chaperones, and polymerases is one of the key tasks of modern biology, as evidenced by the Encyclopedia of DNA Elements (ENCODE) Project. To this end, chromatin immunoprecipitation followed by high-throughput sequencing (ChIP-seq) is the standard methodology. Mapping such protein-DNA interactions <italic>in vivo</italic> using ChIP-seq presents multiple challenges not only in sample preparation and sequencing but also for computational analysis. Here, we present step-by-step guidelines for the computational analysis of ChIP-seq data. We address all the major steps in the analysis of ChIP-seq data: sequencing depth selection, quality checking, mapping, data normalization, assessment of reproducibility, peak calling, differential binding analysis, controlling the false discovery rate, peak annotation, visualization, and motif analysis. At each step in our guidelines we discuss some of the software tools most frequently used. We also highlight the challenges and problems associated with each step in ChIP-seq data analysis. We present a concise workflow for the analysis of ChIP-seq data in <bold>Figure 1</bold> that complements and expands on the recommendations of the ENCODE and modENCODE projects. Each step in the workflow is described in detail in the following sections.</p></abstract><funding-group><funding-statement>TLB is funded by National Institutes of Health grant R0-1 RR021692-05. PM was supported by the EU Marie Curie Initial Training Network SYSFLO (agreement number 237909). QL is partially supported by National Institutes of Health grants 1UL1 RR033184-01 and R01 GM109453. IL gratefully acknowledges support from UNL IANR. The funders had no role in the preparation of the manuscript.</funding-statement></funding-group><counts><page-count count="8"></page-count></counts></article-meta></front><body><sec id="s2"><title>Introduction to ChIP-seq Technology</title><p>Chromatin immunoprecipitation followed by sequencing (ChIP-seq), first described in 2007 <xref rid="pcbi.1003326-Johnson1" ref-type="bibr">[1]</xref>–<xref rid="pcbi.1003326-Mikkelsen1" ref-type="bibr">[4]</xref>, allows <italic>in vivo</italic> determination of where a protein binds the genome, which can be transcription factors, DNA-binding enzymes, histones, chaperones, or nucleosomes. ChIP-seq first cross-links bound proteins to chromatin, fragments the chromatin, captures the DNA fragments bound to one protein using an antibody specific to it, and sequences the ends of the captured fragments using next-generation sequencing (NGS). Computational mapping of the sequenced DNA identifies the genomic locations of bound DNA-binding enzymes, modified histones, chaperones, nucleosomes, and transcription factors (TFs), thereby illuminating the role of these protein-DNA interactions in gene expression and other cellular processes. The use of NGS provides relatively high resolution, low noise, and high genomic coverage compared with ChIP-chip assays (ChIP followed by microarray hybridization). ChIP-seq is now the most widely used procedure for genome-wide assays of protein-DNA interaction <xref rid="pcbi.1003326-Furey1" ref-type="bibr">[5]</xref>, and its use in mapping histone modifications has been seminal in epigenetics research <xref rid="pcbi.1003326-Ku1" ref-type="bibr">[6]</xref>.<xref ref-type="fig" rid="pcbi-1003326-g001"></xref></p><fig id="pcbi-1003326-g001" orientation="portrait" position="float"><object-id pub-id-type="doi">10.1371/journal.pcbi.1003326.g001</object-id><label>Figure 1</label><caption><title>Workflow for the computational analysis of ChIP-seq.</title></caption><graphic xlink:href="pcbi.1003326.g001"></graphic></fig></sec><sec id="s3"><title>The Analysis of ChIP-seq Data</title><sec id="s3a"><title>Sequencing Depth</title><p>Effective analysis of ChIP-seq data requires sufficient coverage by sequence reads (sequencing depth). The required depth depends mainly on the size of the genome and the number and size of the binding sites of the protein. For mammalian transcription factors (TFs) and chromatin modifications such as enhancer-associated histone marks, which are typically localized at specific, narrow sites and have on the order of thousands of binding sites, 20 million reads may be adequate (4 million reads for worm and fly TFs) <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref>. Proteins with more binding sites (e.g., RNA Pol II) or broader factors, including most histone marks, will require more reads, up to 60 million for mammalian ChIP-seq <xref rid="pcbi.1003326-Chen1" ref-type="bibr">[8]</xref>. Importantly, control samples should be sequenced significantly deeper than the ChIP ones in a TF experiment and in experiments involving diffused broad-domain chromatin data. This is to ensure sufficient coverage of a substantial portion of the genome and non-repetitive autosomal DNA regions. To ensure that the chosen sequencing depth was adequate, a saturation analysis is recommended—the peaks called should be consistent when the next two steps (read mapping and peak calling) are performed on increasing numbers of reads chosen at random from the actual reads. Saturation analysis is built into some peak callers (e.g., SPP <xref rid="pcbi.1003326-Kharchenko1" ref-type="bibr">[9]</xref>). If this shows that the number of reads is not adequate, reads from technical replicate experiments can be combined. To avoid over-sequencing and estimate an optimal sequencing depth, it is important to take into account library complexity. Several tools are available for this purpose. For example, the preseq package allows users to predict the number of redundant reads from a given sequencing depth and how many will be expected from additional sequencing <xref rid="pcbi.1003326-Daley1" ref-type="bibr">[10]</xref>. Similarly, the ENCODE software tools offer a quality metric called the PCR bottleneck coefficient (PBC), defined as the fraction of genomic locations with exactly one unique read versus those covered by at least one unique read.</p></sec><sec id="s3b"><title>Read Mapping and Quality Metrics</title><p>Before mapping the reads to the reference genome, they should be filtered by applying a quality cutoff (<xref ref-type="sec" rid="pcbi-1003326-box001"><bold>Box 1</bold></xref>). The remaining reads should then be mapped using one of the available mappers such as Bowtie <xref rid="pcbi.1003326-Langmead1" ref-type="bibr">[11]</xref>, BWA <xref rid="pcbi.1003326-Li1" ref-type="bibr">[12]</xref>, SOAP <xref rid="pcbi.1003326-Li2" ref-type="bibr">[13]</xref>, or MAQ <xref rid="pcbi.1003326-Li3" ref-type="bibr">[14]</xref>. Recent versions support gapped alignment (e.g., Bowtie2), but detection of indels is not necessary for most ChIP-seq experiments. It is important to consider the percentage of uniquely mapped reads reported by the mapper. The percentage varies between organisms, and for human, mouse, or <italic>Arabidopsis</italic> ChIP-seq data, above 70% uniquely mapped reads is normal, whereas less than 50% may be cause for concern. A low percentage of uniquely mapped reads often is due either to excessive amplification in the PCR step, inadequate read length, or problems with the sequencing platform, but with some ChIPed proteins it may be unavoidable (e.g., if the protein binds frequently in repetitive DNA). The read mappers are designed to allow a (user-settable) number of mismatches in the reads, and it is important to choose this parameter to be appropriate with the NGS platform being used (consult the manufacturer). A final potential cause of high numbers of “multi-mapping” reads is that the protein binds frequently in regions of repeated DNA. In this last case, using paired-end sequencing to reduce the mapping ambiguity may help. It should be kept in mind that multi-mapping reads will be ignored (filtered out) by most peak-calling algorithms (see section “Peak Calling”), although they can drive the discovery of novel binding sites <xref rid="pcbi.1003326-Wang1" ref-type="bibr">[15]</xref>.</p><boxed-text id="pcbi-1003326-box001" position="float" orientation="portrait"><sec id="s3b1a"><title>Box 1. Quality metrics of sequence reads</title><p>Preprocessing of ChIP-seq data will, in general, be similar to that of any other sequencing data and will assess the quality of the raw reads to identify possible sequencing errors or biases (FastQC can be used for an overview of the data quality). Phred quality scores are used to describe the confidence of each base call in each sequence tag, are logarithmically linked to error probabilities, and can be used to filter low-quality reads. After this filtering step, it may also be necessary to trim the end of reads that are of low quality (see sickle, <ext-link ext-link-type="uri" xlink:href="https://github.com/najoshi/sickle">https://github.com/najoshi/sickle</ext-link>). Additionally, library complexity is a common quality measure for ChIP-seq libraries (preseq package <xref rid="pcbi.1003326-Daley1" ref-type="bibr">[10]</xref> or PCR bottleneck coefficient [PBC] from ENCODE tools, <ext-link ext-link-type="uri" xlink:href="https://code.google.com/p/phantompeakqualtools/">https://code.google.com/p/phantompeakqualtools/</ext-link>), and library complexity is linked to many factors such as antibody quality, over-cross-linking, amount of material, sonication, or over-amplification by PCR. The latter can be corrected by systematic identification and removal of redundant reads, which is implemented in many peak callers as it may improve their specificity. Readers may be interested in the Galaxy toolbox, which offers access to many of the tools described here <xref rid="pcbi.1003326-Goecks1" ref-type="bibr">[50]</xref>.</p></sec></boxed-text><p>After mapping, the signal-to-noise ratio (SNR) of the ChIP-seq experiment should be assessed, for example via quality metrics such as strand cross-correlation <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref> or IP enrichment estimation using the software package CHANCE <xref rid="pcbi.1003326-Diaz1" ref-type="bibr">[16]</xref> (<xref ref-type="sec" rid="pcbi-1003326-box002"><bold>Box 2</bold></xref>). These measures will detect several possible failure modes of ChIP-seq: insufficient enrichment by immunoprecipitation step, poor fragment-size selection, or insufficient sequencing depth. Strand cross-correlation analysis is built into some peak callers (e.g., SPP or MACS <xref rid="pcbi.1003326-Zhang1" ref-type="bibr">[17]</xref> [version 2]).</p><boxed-text id="pcbi-1003326-box002" position="float" orientation="portrait"><sec id="s3b2a"><title>Box 2. Quality metrics of read counts</title><p>Strand cross-correlation analysis <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref> assesses data quality by measuring the degree of immunoprecipitated (IP) fragment clustering in ChIP-seq experiments. It is developed based on the observations that (1) a high-quality ChIP-seq experiment often shows a significant clustering of enriched DNA sequence tags at the locations bound by the protein of interest, and that (2) the enriched sequence tags on the forward and reversed strands are positioned at a distance from the binding site center that depends on the fragment size distribution <xref rid="pcbi.1003326-Kharchenko1" ref-type="bibr">[9]</xref>. This method quantifies the degree of clustering by computing the cross-correlation between the two strands, i.e., the Pearson correlation between the strand-specific read density profiles as a function of the shift (<italic>k</italic>) applied to one of the two strands (<bold><xref ref-type="supplementary-material" rid="pcbi.1003326.s002">Figure S1</xref></bold>). The cross-correlation typically peaks at the shift corresponding to the fragment length and the shift corresponding to the read length. The ratio between the cross-correlation at the fragment length and the background cross-correlation, referred to as normalized strand cross-correlation coefficient (NSC), and the ratio between cross-correlation at the fragment length and the cross-correlation at the read length, referred to as relative strand cross-correlation coefficient (RSC), jointly reflect signal-to-noise ratio in the ChIP-seq data. Very successful ChIP experiments generally have NSC>1.05 and RSC>0.8 <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref>, although there can still be significant biological information present in ChIP-seq data not meeting these criteria. Readers may refer to <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref> for prototypical profiles of cross-correlation illustrated on ENCODE data.</p><p>The software CHANCE <xref rid="pcbi.1003326-Diaz1" ref-type="bibr">[16]</xref> assesses IP strength by estimating and comparing the IP reads pulled down by the antibody and the background, using a method called signal extraction scaling <xref rid="pcbi.1003326-Diaz2" ref-type="bibr">[77]</xref>. For each sample, it first bins the genome into non-overlap bins both for the IP and the Input, then partitions the bins into a signal region and a background region by comparing the cumulative distributions of tag counts in the bins of the IP and the Input. It next computes a <italic>p</italic>-value for significance of enrichment according to the percentage allocation of reads in each type of regions. Based on the empirical <italic>p</italic>-value distribution computed from a set of ENCODE IP-Input and Input-input experiments on human data, it estimates a <italic>q</italic>-value by treating the two types of experiments as true positives and false positives, respectively. The <italic>q</italic>-value thus is interpreted as the fraction of comparisons with ENCODE data that show differential enrichment at the level of the user's data but turn out to be technical replicates of the Inputs. The software determines the success of the experiment based on the <italic>q</italic>-values, and also reports some descriptive quality statistics, such as the percentage increase in mean tag density in IP compared to Input and the percentage of the genome classified as signal region. Because the <italic>q</italic>-values are computed based on human data, users should be aware that the <italic>q</italic>-values may not be relevant if their data are generated from other organisms.</p><p>CHANCE also provides a graphical visualization of IP strength with genome coverage, by plotting the empirical cumulative percentage of tags covered by the bins that are sorted in an increasing order of read density for both the IP and the Input. By examining and comparing the IP and Input curves, one may identify quality issues, such as insufficient sequencing depth, amplification bias, and weak IP enrichment.</p></sec></boxed-text></sec><sec id="s3c"><title>Peak Calling</title><p>A pivotal analysis for ChIP-seq is to predict the regions of the genome where the ChIPed protein is bound by finding regions with significant numbers of mapped reads (peaks). A fine balance between sensitivity and specificity depends on choosing an appropriate peak-calling algorithm and normalization method (<xref ref-type="sec" rid="pcbi-1003326-box003"><bold>Boxes 3</bold></xref><bold>–</bold><xref ref-type="sec" rid="pcbi-1003326-box006"><bold>6</bold></xref>, <bold><xref ref-type="supplementary-material" rid="pcbi.1003326.s004">Table S1</xref></bold>, and <xref rid="pcbi.1003326-Guo1" ref-type="bibr">[18]</xref>, <xref rid="pcbi.1003326-Jothi1" ref-type="bibr">[19]</xref>) based on the type of protein ChIPed: point-source factors such as most TFs (<xref ref-type="sec" rid="pcbi-1003326-box003"><bold>Box 3</bold></xref>), broadly enriched factors such as histone marks (<xref ref-type="sec" rid="pcbi-1003326-box004"><bold>Box 4</bold></xref>), and those with both characteristics such as RNA Pol II (<xref ref-type="sec" rid="pcbi-1003326-box005"><bold>Box 5</bold></xref>) <xref rid="pcbi.1003326-Pepke1" ref-type="bibr">[20]</xref>. It is strongly recommended that mapped reads from a control sample be used (e.g., from input DNA), although some peak callers can use GC content or mappability as information necessary to assess the level of non-specific or background binding. Duplicate reads (same 5′ end) can be removed before peak calling to improve specificity (<xref ref-type="sec" rid="pcbi-1003326-box007"><bold>Box 7</bold></xref>). Although some peak callers support both single and paired-end reads (e.g., MACS), others are specifically designed to improve sensitivity and specificity in paired-end sequencing (e.g., SIPeS <xref rid="pcbi.1003326-Wang2" ref-type="bibr">[21]</xref>). Existing peak callers have many user-settable parameters that can greatly affect the number and quality of the peaks called. For instance, the enrichment metric for most peak callers, such as <italic>p</italic>-value or FDR, could be hugely affected by the statistical model used, the sequencing depth, or the actual number of binding sites in the genome. Thus, using the same <italic>p</italic>-value or FDR threshold does not ensure that the numbers of peaks called are comparable across libraries and different peak callers <xref rid="pcbi.1003326-Szalkowski1" ref-type="bibr">[22]</xref>. A better approach is to threshold the irreproducible discovery rate (IDR) <xref rid="pcbi.1003326-Li4" ref-type="bibr">[23]</xref>, which, along with motif analysis, can also aid in choosing the best peak-calling algorithm and parameter settings (see sections “Assessment of Reproducibility” and “Motif Analysis”).</p><boxed-text id="pcbi-1003326-box003" position="float" orientation="portrait"><sec id="s3c1a"><title>Box 3. Peak calling: Punctate-source transcription factors</title><p>Nowadays, since ChIP-seq data of point-source factors are the most abundant type, most peak callers are designed and fine-tuned for these factors. Existing peak callers differ from each other in terms of signal smoothing and background modeling. Because DNA around interaction sites is more easily sheared, the ends of ChIPed DNA fragments would form footprints on DNA whose size is more related to protein-DNA interaction than to size selection during library preparation. Those peak callers able to capture this experiment-specific information can greatly improve accuracy of prediction. For example, peak callers SPP <xref rid="pcbi.1003326-Kharchenko1" ref-type="bibr">[9]</xref> and MACS <xref rid="pcbi.1003326-Zhang1" ref-type="bibr">[17]</xref> (version 2) use cross-correlation to find the lag between reads mapped to the minus and the plus strand as the size of actual protein-DNA interacting regions. After smoothing, background models are then used to remove noise either directly from the control sample or from features of the genome sequence such as GC content or mappability (BEADS <xref rid="pcbi.1003326-Cheung1" ref-type="bibr">[84]</xref>). Peaks are finally called above a user-defined SNR level. Models used for the statistical assessment of enriched regions (peaks) range from Poisson (CSAR <xref rid="pcbi.1003326-Muio1" ref-type="bibr">[85]</xref>), local Poisson (MACS), negative binomial (CisGenome <xref rid="pcbi.1003326-Ji1" ref-type="bibr">[56]</xref>) to zero-inflated negative binomial (ZINBA <xref rid="pcbi.1003326-Rashid1" ref-type="bibr">[86]</xref>), or even extend to more sophisticated machine learning modeling techniques such as Hidden Markov Model (HPeak <xref rid="pcbi.1003326-Qin1" ref-type="bibr">[87]</xref> and BayesPeak <xref rid="pcbi.1003326-Spyrou1" ref-type="bibr">[88]</xref>).</p><p>Most peak-calling algorithms apply a window-based method to detect peaks, so nearby binding events may be erroneously merged. To improve the spatial resolution of binding event predictions, several peak callers use peak shape as a clue. PeakSplitter <xref rid="pcbi.1003326-SalmonDivon1" ref-type="bibr">[89]</xref> can look for local maxima in a broader region containing several sub-peaks. GPS <xref rid="pcbi.1003326-Guo2" ref-type="bibr">[67]</xref> builds a probabilistic model of the distribution of ChIP-seq reads at given peak candidate regions to deconvolve nearby homotypic events. The R packages polyaPeak and NarrowPeaks can analyze the shape of the peaks to re-rank and narrow down the final peak list, respectively. These approaches are highly recommended as a post-processing step after general peak calling for point-source factors.</p></sec></boxed-text><boxed-text id="pcbi-1003326-box004" position="float" orientation="portrait"><sec id="s3c2a"><title>Box 4. Peak calling: Broad enriched regions from histone marks</title><p>Due to the increasing interest in epigenetic regulation, epigenetic marks such as histone modifications, DNA methylation, and chromatin remodeling factors are being explored through ChIP-seq. Some of these marks are enriched strongly in narrow genomic regions (e.g., H3K4me3 at gene promoters), and the peak callers appropriate for point-source factors (discussed in <xref ref-type="sec" rid="pcbi-1003326-box003"><bold>Box 3</bold></xref>) can be used. However, most histone marks tend to have more broadly spreading and weaker patterns (e.g., H3K27me3). Several peak callers are specifically designed for predicting broad regions from ChIP-seq data, including SICER <xref rid="pcbi.1003326-Zang1" ref-type="bibr">[90]</xref>, CCAT <xref rid="pcbi.1003326-Xu2" ref-type="bibr">[91]</xref>, ZINBA, and RSEG <xref rid="pcbi.1003326-Song1" ref-type="bibr">[92]</xref>. Other peak callers including SPP, MACS (version 2), and PeakRanger <xref rid="pcbi.1003326-Feng1" ref-type="bibr">[93]</xref> can also be used with this type of ChIP-seq data by using their options to increase “bandwidth” or to relax the “peak cutoff.”</p><p>For broad marks, the pattern of enrichment should be described as “domains” instead of “peaks” because there are no clearly defined peak summits. An alternative representation of the pattern of mapped reads is hierarchical: combining multiple levels of enrichment. For example, MACS (version 2) and Scripture <xref rid="pcbi.1003326-Guttman1" ref-type="bibr">[94]</xref> (originally designed for RNA-seq) can make narrow calls for strong enrichment inside broader calls for weak enrichment associated with domain boundaries.</p></sec></boxed-text><boxed-text id="pcbi-1003326-box005" position="float" orientation="portrait"><sec id="s3c3a"><title>Box 5. Peak calling: Mixed signals</title><p>There are also some factors (such as RNA Pol II) that bind to DNA in regions with bigger variation. It is known that some RNA Pol II complexes are stalled while others are moving along with active transcription <xref rid="pcbi.1003326-Baugh1" ref-type="bibr">[95]</xref>. In the first case, data ideally should be treated as for a point-source factor, whereas in the second case, the data should be treated as for factors with broad marks. An ideal algorithm should accommodate both patterns, which means peak calling should be more general. Some tools have options for both narrow and broad peak calling, such as SPP, MACS, ZINBA, and PeakRanger. However, with careful parameter tweaking any algorithm suitable for broad peak detection would work for this type of data.</p></sec></boxed-text><boxed-text id="pcbi-1003326-box006" position="float" orientation="portrait"><sec id="s3c4a"><title>Box 6. Normalization</title><p>Whether comparing one ChIP sample against input DNA (sonicated DNA), “mock” ChIP (non-specific antibody, e.g., IgG) in peak calling, or comparing a ChIP sample against another in differential analysis, there are linear and non-linear normalization methods available to make the two samples “comparable” (<bold><xref ref-type="supplementary-material" rid="pcbi.1003326.s005">Table S2</xref></bold>). Although many methodologies focus on normalization to a control sample, none of them make the distinction on the type of control samples used. An intuitive and commonly used linear normalization technique is called sequencing depth normalization. In this method the number of reads is multiplied by a scale factor to make the total reads in different samples the same (see <xref rid="pcbi.1003326-Kharchenko1" ref-type="bibr">[9]</xref>, <xref rid="pcbi.1003326-Taslim3" ref-type="bibr">[96]</xref> for details). A slight modification of the method is used in PeakSeq <xref rid="pcbi.1003326-Rozowsky1" ref-type="bibr">[24]</xref>, where a scale factor is estimated in a region (∼10 Kb) using linear regression. Many other existing methods also use a normalization factor to linearly scale samples, focusing on normalization against control samples (see for example CisGenome <xref rid="pcbi.1003326-Ji1" ref-type="bibr">[56]</xref>, MACS <xref rid="pcbi.1003326-Zhang1" ref-type="bibr">[17]</xref>, and USeq <xref rid="pcbi.1003326-Nix1" ref-type="bibr">[97]</xref>). Another scaling normalization method known as RPKM (Reads per Kilobase of sequence range per Million mapped reads) proposed in <xref rid="pcbi.1003326-Mortazavi1" ref-type="bibr">[98]</xref> adjusts for biases due to the higher probability of reads falling into longer regions.</p><p>A non-linear normalization adjusts for biases with non-linear trend. In a method described in <xref rid="pcbi.1003326-Taslim1" ref-type="bibr">[28]</xref> the data is normalized with respect to mean and variance using locally weighted regression (LOESS). It is based on the assumption that the effect of biological condition change does not cause global binding alterations. This assumption can be applied, for example, when comparing samples with different stages of disease progression, or on samples before and after a certain treatment (see section “Differential Binding Analysis”). A modified version of this non-linear normalization is implemented as MAnorm <xref rid="pcbi.1003326-Shao1" ref-type="bibr">[34]</xref>, assuming that peaks common in the two conditions do not undergo global changes. The R package called POLYPHEMUS <xref rid="pcbi.1003326-MendozaParra1" ref-type="bibr">[37]</xref> has also been developed, implementing two normalization methods: (1) the non-linear method described in <xref rid="pcbi.1003326-Taslim1" ref-type="bibr">[28]</xref> and (2) a Quantile normalization that makes the distribution in different samples the same. Normalization issues are, at present, not fully exploited although they might have a substantial impact on the results <xref rid="pcbi.1003326-Taslim1" ref-type="bibr">[28]</xref>, <xref rid="pcbi.1003326-MendozaParra1" ref-type="bibr">[37]</xref>, <xref rid="pcbi.1003326-Liang2" ref-type="bibr">[99]</xref>.</p></sec></boxed-text><boxed-text id="pcbi-1003326-box007" position="float" orientation="portrait"><sec id="s3c5a"><title>Box 7. Duplicated reads</title><p>Duplicate (identical) reads present a challenge because they can arise from independent DNA fragments or by PCR amplification of a single fragment. In the former case, the duplicate reads are signals, in the latter case they are noise (experimental artefact). A safe solution is to keep a fixed number of hits per genomic location (considering different strands as different locations) according to sequencing depth, and in this way better specificity (fewer false positive peaks) can be achieved <xref rid="pcbi.1003326-Chen1" ref-type="bibr">[8]</xref>. However in terms of estimating the protein's affinity for a given genomic region, it is more reasonable to consider all hits. This can be done in a well-designed pipeline with certain steps before and after peak calling. For example, one can remove a certain number of duplicates to call confident peaks, and then put duplicates back to refine properties of these peaks such as peak height and boundaries.</p></sec></boxed-text></sec><sec id="s3d"><title>Assessment of Reproducibility</title><p>To ensure that experimental results are reproducible, it is recommended to perform at least two biological replicates of each ChIP-seq experiment and examine the reproducibility of both the reads and identified peaks <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref>, <xref rid="pcbi.1003326-Rozowsky1" ref-type="bibr">[24]</xref>. The reproducibility of the reads can be measured by computing the Pearson correlation coefficient (PCC) of the (mapped) read counts at each genomic position <xref rid="pcbi.1003326-Bardet1" ref-type="bibr">[25]</xref>. The range of PCC is typically from 0.3–0.4 (for unrelated samples) to >0.9 (for replicate samples in high-quality experiments). Low values typically suggest one or both replicates may be of low quality. However, this quantity can be dominated by a small number of very highly enriched regions, so it may not reflect the reproducibility for regions that are less enriched <xref rid="pcbi.1003326-abaj1" ref-type="bibr">[26]</xref>. Thus it is important to remove the artefact regions with high ChIP signals, such as regions near centromeres, telomeres, satellite repeats, and ENCODE and 1000 Genomes blacklisted regions, before computing the PCC. To measure the reproducibility at the level of peak calling, IDR analysis (<xref ref-type="sec" rid="pcbi-1003326-box008"><bold>Box 8</bold></xref>) <xref rid="pcbi.1003326-Li4" ref-type="bibr">[23]</xref> can be applied to the two sets of peaks identified from a pair of replicates. This analysis assesses the rank consistency of identified peaks between replicates, and outputs the number of peaks that pass a user-specified reproducibility threshold (e.g., IDR = 0.05). It has been reported that using a reproducibility-based metric (e.g., IDR) rather than an enrichment-based metric (e.g., FDR or <italic>p</italic>-value) makes the numbers of peaks declared more comparable across experiments <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref>. In addition, IDR analysis can also be used for comparing and selecting peak callers <xref rid="pcbi.1003326-Chen1" ref-type="bibr">[8]</xref>, <xref rid="pcbi.1003326-Li4" ref-type="bibr">[23]</xref> and identifying experiments with low quality <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref>.</p><boxed-text id="pcbi-1003326-box008" position="float" orientation="portrait"><sec id="s3d1a"><title>Box 8. Irreproducible discovery rate (IDR)</title><p>Given a set of peak calls for a pair of replicate data sets, the peaks can be ranked based on a criterion of significance, such as the <italic>p</italic>-value, the <italic>q</italic>-value, or the fold enrichment. Significant peaks generally are ranked more consistently across the replicates than the peaks with low significance. This provides an indicator of the transition from real signal to noise. IDR <xref rid="pcbi.1003326-Li4" ref-type="bibr">[23]</xref> quantifies this transition by classifying peaks into a reproducible and an irreproducible group, where the peaks in the reproducible group should be ranked higher and more consistently across replicates than the irreproducible group (<bold><xref ref-type="supplementary-material" rid="pcbi.1003326.s003">Figure S2</xref></bold>). It assigns each signal a reproducibility index, which estimates its probability to be reproducible, and also reports the expected rate of irreproducible discoveries in the selected peaks (referred to as IDR) in a fashion analogous to that of false discovery rate (FDR). An R package for computing IDR is given in <xref rid="pcbi.1003326-Li4" ref-type="bibr">[23]</xref>. Prototypical examples illustrated using ENCODE data may be found in <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref>. When using IDR, a relatively relaxed peak-calling threshold is advised because the IDR algorithm requires sampling of both signal and noise distributions to assess the reproducibility of peaks.</p><p>A major advantage of the IDR method is that it is independent of the peak-calling algorithms and can be applied to a variety of significance criteria, across labs and platforms. It has been shown that it produces a stable threshold that is more consistent across laboratories, antibodies, and analysis protocols (e.g., peak callers) than FDR measures <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref>.</p></sec></boxed-text></sec><sec id="s3e"><title>Differential Binding Analysis</title><p>Comparative ChIP-seq analysis of an increasing number of protein-bound regions across conditions or tissues is expected with the steady raise of NGS projects. For example, temporal or developmental designs of ChIP-seq experiments can provide different snapshots of a binding signal for the same TF, uncovering stage-specific patterns of gene regulation <xref rid="pcbi.1003326-Sandmann1" ref-type="bibr">[27]</xref>, <xref rid="pcbi.1003326-Taslim1" ref-type="bibr">[28]</xref>. With this in mind, one should note that the simple binary overlap of two sets of peaks (e.g., BEDTools <xref rid="pcbi.1003326-Quinlan1" ref-type="bibr">[29]</xref>) does not represent the optimal approach when comparing peaks <xref rid="pcbi.1003326-Bardet1" ref-type="bibr">[25]</xref>.</p><p>Two alternatives have been proposed. The first one—qualitative—implements hypothesis testing on multiple overlapping sets of peaks <xref rid="pcbi.1003326-Aszdi1" ref-type="bibr">[30]</xref>, therefore extending the two-set overlap approach mentioned above. The second one—quantitative—proposes the analysis of differential binding between conditions based on the total counts of reads in peak regions or on the read densities, i.e., counts of reads overlapping at individual genomic positions (<bold><xref ref-type="supplementary-material" rid="pcbi.1003326.s006">Table S3</xref></bold> and <xref rid="pcbi.1003326-Anders1" ref-type="bibr">[31]</xref>, <xref rid="pcbi.1003326-Robinson1" ref-type="bibr">[32]</xref>). The direct calculation of differentially bound regions between treatment samples without controls (i.e., using one of them as a control) is not recommended because highly enriched regions could be identified due to artefacts or different chromatin structure and not due to true binding events.</p><p>Typically, both methodologies assume that significant (see section “Peak Calling”) and reproducible (see section “Assessment of Reproducibility”) peaks have been found in advance independently for each condition. In order to increase sensitivity for detecting differentially bound regions (at the expense of increasing the number of false positives), more relaxed thresholds can be used to find peaks at each condition. Then, depending on the biological question, the sets of peaks called in any of the conditions can be considered separately, or collapsed into one or more meaningful lists of consensus peak regions. One can use the qualitative approach to get an initial overview of differential binding. However, peaks identified in all conditions will never be declared as differentially bound sites by this approach based just on the positions of the peaks <xref rid="pcbi.1003326-Liang1" ref-type="bibr">[33]</xref>. The quantitative approach works with read counts (e.g., DBChIP <xref rid="pcbi.1003326-Liang1" ref-type="bibr">[33]</xref>) or read densities (e.g., MAnorm <xref rid="pcbi.1003326-Shao1" ref-type="bibr">[34]</xref>) computed over peak regions, and has higher computational cost, but is recommended as it provides precise statistical assessment of differential binding across conditions (e.g., <italic>p</italic>-values or <italic>q</italic>-values linked to read-enrichment fold changes). It is strongly advised to verify that the data fulfill the requirements of the software chosen for the analysis. For instance, DIME <xref rid="pcbi.1003326-Taslim2" ref-type="bibr">[35]</xref> assumes that a significant proportion of peaks are common to the conditions under comparison, MAnorm assumes that peaks that are common in both conditions do not change significantly, while other methodologies may expect a constant number of peaks across conditions <xref rid="pcbi.1003326-Bardet1" ref-type="bibr">[25]</xref>. Importantly, with some tools only two conditions can be submitted simultaneously for comparison (e.g., MAnorm), and some may perform better depending on the protein ChIPed (e.g., ChIPDiff <xref rid="pcbi.1003326-Xu1" ref-type="bibr">[36]</xref> for histone marks and POLYPHEMUS <xref rid="pcbi.1003326-MendozaParra1" ref-type="bibr">[37]</xref> for RNA Pol II).</p></sec><sec id="s3f"><title>Peak Annotation</title><p>The aim of the annotation is to associate the ChIP-seq peaks with functionally relevant genomic regions, such as gene promoters, transcription start sites, intergenic regions, etc. In the first step, one uploads the peaks and reads (in an appropriate format, e.g., BED or GFF for peaks, WIG or bedGraph for normalized read coverage; see <bold><xref ref-type="supplementary-material" rid="pcbi.1003326.s001">Text S1</xref></bold> and <xref rid="pcbi.1003326-Kuhn1" ref-type="bibr">[38]</xref>–<xref rid="pcbi.1003326-Kent1" ref-type="bibr">[41]</xref>) to a genome browser, where regions can be manually examined in search for associations with annotated genomic features. If comparable data (e.g., ChIP-qPCR) is available, it can be compared with the ChIP-seq peaks and reads manually in the browser as well. A systematic analysis can also be performed using tools in packages such as BEDTools to compute the distance from each peak to the nearest landmark (e.g., TSS), or to identify the genes within a given distance of a peak. The output of such “location analyses,” obtained for instance using CEAS <xref rid="pcbi.1003326-Shin1" ref-type="bibr">[42]</xref> or the Bioconductor package ChIPpeakAnno <xref rid="pcbi.1003326-Zhu1" ref-type="bibr">[43]</xref>, can be further correlated with expression data (e.g., to determine if proximity of a gene to a peak is correlated with its expression) or subjected to a gene ontology analysis (e.g., to determine if the ChIPed protein is involved in particular biological processes). Gene ontology analysis can be done using DAVID <xref rid="pcbi.1003326-Huangda1" ref-type="bibr">[44]</xref>, GREAT <xref rid="pcbi.1003326-McLean1" ref-type="bibr">[45]</xref>, or GSEA <xref rid="pcbi.1003326-Subramanian1" ref-type="bibr">[46]</xref>. Sometimes, the reads densities relative to a specific annotated feature are plotted and compared across different samples, thus revealing protein-binding pattern differences between them <xref rid="pcbi.1003326-Liu1" ref-type="bibr">[47]</xref>.</p></sec><sec id="s3g"><title>Motif Analysis</title><p>Motif analysis is useful for much more than just identifying the causal DNA-binding motif in TF ChIP-seq peaks. When the motif of the ChIPed protein is already known, motif analysis provides validation of the success of the experiment. Even when the motif is not known beforehand, identifying a centrally located motif in a large fraction of the peaks by motif analysis is indicative of a successful experiment. Motif analysis can also identify the DNA-binding motifs of other proteins that bind in complex or in conjunction with the ChIPed protein, illuminating the mechanisms of transcriptional regulation. Motif analysis is also useful with histone modification ChIP-seq because it can discover unanticipated sequence signals associated with such marks. <bold><xref ref-type="supplementary-material" rid="pcbi.1003326.s007">Table S4</xref></bold> and <xref rid="pcbi.1003326-Kuttippurathu1" ref-type="bibr">[48]</xref>, <xref rid="pcbi.1003326-Liu2" ref-type="bibr">[49]</xref> list a small sample of the publicly available tools for motif analysis.</p><p>Motif analysis is applied to the genomic regions identified by peak-calling algorithms. Hence, the first step in motif analysis is to assemble a set of genomic sequences in FASTA format corresponding to all the significant ChIP-seq peaks <xref rid="pcbi.1003326-Goecks1" ref-type="bibr">[50]</xref>–<xref rid="pcbi.1003326-Kent2" ref-type="bibr">[54]</xref>. The second step in motif analysis is motif discovery and it is advisable to input the peak sequences to two or more of the many algorithms able to discover sequence motifs in unaligned DNA sequences <xref rid="pcbi.1003326-Kulakovskiy1" ref-type="bibr">[55]</xref>–<xref rid="pcbi.1003326-ThomasChollier1" ref-type="bibr">[58]</xref>, as the algorithms have complementary strengths and weaknesses. Some motif discovery algorithms form part of pipelines that perform several motif analysis steps (e.g., MEME-ChIP <xref rid="pcbi.1003326-Machanick1" ref-type="bibr">[57]</xref> and peak-motifs <xref rid="pcbi.1003326-ThomasChollier1" ref-type="bibr">[58]</xref>), including word-based motif discovery algorithms and motif enrichment algorithms that can identify motifs present in only a small fraction of the peaks. Following motif discovery, comparing the discovered motifs with known DNA motifs using motif comparison software <xref rid="pcbi.1003326-Mahony1" ref-type="bibr">[59]</xref>, <xref rid="pcbi.1003326-Gupta1" ref-type="bibr">[60]</xref> is useful to confirm the presence of the ChIPed TF motif if its (or its TF-family) binding motif is known. The results will also provide hints about other TFs that bind near the ChIPed TF. Next, central motif enrichment analysis will determine if other known DNA motifs are enriched near the centers (or summits) of the ChIP-seq peaks <xref rid="pcbi.1003326-Bailey1" ref-type="bibr">[61]</xref>. It can also be useful to perform local motif enrichment analysis on regions centered on genomic landmarks such as transcription start sites overlapped by ChIP-seq peaks <xref rid="pcbi.1003326-Bailey1" ref-type="bibr">[61]</xref>. Additionally, a motif spacing analysis detects preferred distances and arrangements of pairs of motifs that can be indicative of physical interactions between TFs <xref rid="pcbi.1003326-Whitington1" ref-type="bibr">[62]</xref>. Finally, motif prediction maps and visualizes the genomic locations of the motifs in each of the ChIP-seq regions <xref rid="pcbi.1003326-Grant1" ref-type="bibr">[63]</xref>, <xref rid="pcbi.1003326-Hertz1" ref-type="bibr">[64]</xref>. In this step, the discovered or enriched motifs are used to scan the ChIP-seq peak regions, and the coordinates of the matches are uploaded to a genome browser for visualization.</p></sec></sec><sec id="s4"><title>Outlook</title><p>The challenges of ChIP-seq require novel experimental, statistical, and computational solutions. Ongoing advances will allow ChIP-seq to analyze samples containing far fewer cells, greatly expanding its applicability in areas such as embryology and development where large samples are prohibitively expensive or difficult to obtain. Nano-ChIP-seq can analyze a sample as small as 10,000 cells <xref rid="pcbi.1003326-Adli1" ref-type="bibr">[65]</xref>. No less critical is to trim today's peaks that are much wider than the actual transcription factor binding sites. This is necessary to distinguish artefacts from bona fide joint binding events: most transcription factors competitively, cooperatively, or co-bind with other transcription factors, the transcriptional machinery, or cofactors. The effects of context-dependent regulatory mechanisms can fundamentally differ from the effects of individual binding events <xref rid="pcbi.1003326-Encode1" ref-type="bibr">[66]</xref>. To address this issue, the Genome Positioning System (GPS) resolves closely spaced peaks using a segmented expectation maximization algorithm <xref rid="pcbi.1003326-Guo2" ref-type="bibr">[67]</xref>. A promising experimental method for localizing narrow peaks is ChIP-exo that uses bacteriophage λ exonuclease to digest the ends of DNA fragments not bound to protein <xref rid="pcbi.1003326-Rhee1" ref-type="bibr">[68]</xref>.</p><p>The number of false positive peaks can be reduced both experimentally and computationally. Improving antibody specificity is a long-term endeavor, and despite impressive progress, still a quarter of histone modification antibodies fail the specificity test <xref rid="pcbi.1003326-Egelhofer1" ref-type="bibr">[69]</xref>. Another way to eliminate massive amounts of false positive peaks is to limit the regulatory binding sites to nucleosome-depleted regions, which are accessible for regulator binding. These regions are mapped by DNase I hypersensitivity sequencing (DNase-seq) and similar techniques: Thurman et al. found that 94% of the human transcription factor binding sites fell into DNase hypersensitivity regions with only a few exceptions like the transcription factors ZNF274, KAP1, and SETDB1, which also bind to closed chromatin <xref rid="pcbi.1003326-Thurman1" ref-type="bibr">[70]</xref>. False positive peaks are also due to unrealistic <italic>p</italic>-values (and hence FDRs) coming from unrealistic statistical models used in most methods <xref rid="pcbi.1003326-Jiao1" ref-type="bibr">[71]</xref>. The computational analysis of peak calling is still in its infancy, expanding the diverse and condition-specific performance of the methods <xref rid="pcbi.1003326-Wilbanks1" ref-type="bibr">[72]</xref>, <xref rid="pcbi.1003326-Schweikert1" ref-type="bibr">[73]</xref>, therefore we recommend using several methods for peak calling.</p><p>Perhaps the most important novel developments are related to the detection and analyses of distal regulatory regions, which are distant in sequence but brought close in 3-D space by DNA bending. To reveal such 3-D mechanisms of transcriptional regulation, two major techniques have emerged: chromatin interaction analysis by paired-end tags (CHIA-PET) <xref rid="pcbi.1003326-Li5" ref-type="bibr">[74]</xref> and chromosome conformation capture assays such as circular chromosome conformation capture (4C) <xref rid="pcbi.1003326-vandeWerken1" ref-type="bibr">[75]</xref> or chromosome conformation capture carbon copy (5C) <xref rid="pcbi.1003326-Dostie1" ref-type="bibr">[76]</xref>.</p><p>Biological functions of binding sites are not necessarily indicated by the reproducibility of peaks or FDR/IDR values (<xref ref-type="sec" rid="pcbi-1003326-box008"><bold>Box 8</bold></xref>, <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref>, <xref rid="pcbi.1003326-Li4" ref-type="bibr">[23]</xref>, <xref rid="pcbi.1003326-Diaz2" ref-type="bibr">[77]</xref>, <xref rid="pcbi.1003326-White1" ref-type="bibr">[78]</xref>). This issue re-emerged during the ENCODE Project that produced unprecedented regulatory information <xref rid="pcbi.1003326-Encode1" ref-type="bibr">[66]</xref>, <xref rid="pcbi.1003326-Doolittle1" ref-type="bibr">[79]</xref> under rigorous quality standards <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref>. DNA-protein binding is dynamic, and the measured strength of a binding event depends (among other things) on the fraction of cells in the (often inhomogeneous) sample where it occurs, as well as the proportion of the time it is occupied in a given cell. Hence, “weak” binding sites, regardless of what significance threshold is used, may have strong biological functions <xref rid="pcbi.1003326-Zhu2" ref-type="bibr">[80]</xref>–<xref rid="pcbi.1003326-Sun1" ref-type="bibr">[82]</xref>. ChIP-seq will also detect <italic>indirect</italic> DNA binding by the protein (via another protein or complex), so predicted sites <italic>not</italic> containing the motif may also be functional. Finally, binding does not necessarily imply function, so it will remain necessary to use additional information (such as expression or chromatin conformation data) to reliably infer the function of individual binding events <xref rid="pcbi.1003326-Yip1" ref-type="bibr">[83]</xref>.</p><p>The diverse experimental and computational methods discussed here are revolutionizing our understanding of the complex networks that, by regulating transcription, impact translation and almost all biological processes.</p></sec><sec sec-type="supplementary-material" id="s5"><title>Supporting Information</title><supplementary-material content-type="local-data" id="pcbi.1003326.s001"><label>Text S1</label><caption><p><bold>Standard graphing track data formats for genome browser visualization.</bold></p><p>(DOCX)</p></caption><media xlink:href="pcbi.1003326.s001.docx"><caption><p>Click here for additional data file.</p></caption></media></supplementary-material><supplementary-material content-type="local-data" id="pcbi.1003326.s002"><label>Figure S1</label><caption><p><bold>Assessment of read quality using strand cross-correlation.</bold> Strand cross-correlation is computed as the Pearson correlation between the positive and the negative strand profiles at different strand shift distances, <italic>k</italic>. The cross-correlation (panel A) usually peaks at two distances of shift, one corresponding to the read length, and one to the average fragment length of the library. The absolute and relative height of the two peaks is useful for assessing IP enrichment. Adapted from Landt et al. <xref rid="pcbi.1003326-Landt1" ref-type="bibr">[7]</xref>.</p><p>(TIF)</p></caption><media xlink:href="pcbi.1003326.s002.tif"><caption><p>Click here for additional data file.</p></caption></media></supplementary-material><supplementary-material content-type="local-data" id="pcbi.1003326.s003"><label>Figure S2</label><caption><p><bold>The irreproducible discovery rate (IDR) framework for assessing reproducibility of ChIP-seq data sets.</bold> Panel A shows a scatterplot of the significance scores of peaks identified in two replicate ChIP-seq experiments. The IDR method classifies peaks into reproducible (black) and irreproducible (red) groups, and computes for each peak the probability that the peak belongs to the irreproducible group. It ranks and selects peaks according to this probability, and computes IDR, the expected rate of irreproducible discoveries in the selected peaks. Panel B shows the estimated IDR at different rank thresholds when the peaks are sorted by the original significance score.</p><p>(TIF)</p></caption><media xlink:href="pcbi.1003326.s003.tif"><caption><p>Click here for additional data file.</p></caption></media></supplementary-material><supplementary-material content-type="local-data" id="pcbi.1003326.s004"><label>Table S1</label><caption><p><bold>Examples of peak callers employed in ChIP-seq.</bold> The list includes tools that allow the processing and post-processing of diverse types of narrow read-enriched regions (peaks), broad enriched regions (domains), and mixed signals such as in RNA Pol II ChIP-seq.</p><p>(DOCX)</p></caption><media xlink:href="pcbi.1003326.s004.docx"><caption><p>Click here for additional data file.</p></caption></media></supplementary-material><supplementary-material content-type="local-data" id="pcbi.1003326.s005"><label>Table S2</label><caption><p><bold>Normalization methods for the comparative analysis of ChIP-seq data sets.</bold></p><p>(DOCX)</p></caption><media xlink:href="pcbi.1003326.s005.docx"><caption><p>Click here for additional data file.</p></caption></media></supplementary-material><supplementary-material content-type="local-data" id="pcbi.1003326.s006"><label>Table S3</label><caption><p><bold>Software packages for the analysis of differential binding in ChIP-seq.</bold> The table shows examples of algorithms available for differential binding analysis using ChIP-seq data.</p><p>(DOCX)</p></caption><media xlink:href="pcbi.1003326.s006.docx"><caption><p>Click here for additional data file.</p></caption></media></supplementary-material><supplementary-material content-type="local-data" id="pcbi.1003326.s007"><label>Table S4</label><caption><p><bold>Software tools for motif analysis of ChIP-seq peaks and their uses.</bold> The table gives examples of publicly available software tools for performing motif analysis on ChIP-seq peaks or nearby genes. The tools are grouped by the major task (“category”), and checkmarks indicate the specific steps that each tool performs. Web-based motif discovery input size limits—ChIPMunk: unknown; CompleteMOTIFS: 500,000 base pairs; MEME-ChIP: 50,000,000 base pairs; peak-motifs: no limit; Cistrome: 5,000 peaks.</p><p>(DOCX)</p></caption><media xlink:href="pcbi.1003326.s007.docx"><caption><p>Click here for additional data file.</p></caption></media></supplementary-material></sec></body><back><ref-list><title>References</title><ref id="pcbi.1003326-Johnson1"><label>1</label><mixed-citation publication-type="journal"><name><surname>Johnson</surname><given-names>DS</given-names></name>, <name><surname>Mortazavi</surname><given-names>A</given-names></name>, <name><surname>Myers</surname><given-names>RM</given-names></name>, <name><surname>Wold</surname><given-names>B</given-names></name> (<year>2007</year>) <article-title>Genome-wide mapping of in vivo protein–DNA interactions</article-title>. <source>Science</source><volume>316</volume>: <fpage>1497</fpage>–<lpage>1502</lpage>.<pub-id pub-id-type="pmid">17540862</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Barski1"><label>2</label><mixed-citation publication-type="journal"><name><surname>Barski</surname><given-names>A</given-names></name>, <name><surname>Cuddapah</surname><given-names>S</given-names></name>, <name><surname>Cui</surname><given-names>K</given-names></name>, <name><surname>Roth</surname><given-names>TY</given-names></name>, <name><surname>Schones</surname><given-names>DE</given-names></name>, <etal>et al</etal> (<year>2007</year>) <article-title>High-resolution profiling of histone methylations in the human genome</article-title>. <source>Cell</source><volume>129</volume>: <fpage>823</fpage>–<lpage>837</lpage>.<pub-id pub-id-type="pmid">17512414</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Robertson1"><label>3</label><mixed-citation publication-type="journal"><name><surname>Robertson</surname><given-names>G</given-names></name>, <name><surname>Hirst</surname><given-names>M</given-names></name>, <name><surname>Bainbridge</surname><given-names>M</given-names></name>, <name><surname>Bilenky</surname><given-names>M</given-names></name>, <name><surname>Zhao</surname><given-names>Y</given-names></name>, <etal>et al</etal> (<year>2007</year>) <article-title>Genome-wide profiles of STAT1 DNA association using chromatin immunoprecipitation and massively parallel sequencing</article-title>. <source>Nat Methods</source><volume>4</volume>: <fpage>651</fpage>–<lpage>657</lpage>.<pub-id pub-id-type="pmid">17558387</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Mikkelsen1"><label>4</label><mixed-citation publication-type="journal"><name><surname>Mikkelsen</surname><given-names>TS</given-names></name>, <name><surname>Ku</surname><given-names>M</given-names></name>, <name><surname>Jaffe</surname><given-names>DB</given-names></name>, <name><surname>Issac</surname><given-names>B</given-names></name>, <name><surname>Lieberman</surname><given-names>E</given-names></name>, <etal>et al</etal> (<year>2007</year>) <article-title>Genome-wide maps of chromatin state in pluripotent and lineage-committed cells</article-title>. <source>Nature</source><volume>448</volume>: <fpage>553</fpage>–<lpage>560</lpage>.<pub-id pub-id-type="pmid">17603471</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Furey1"><label>5</label><mixed-citation publication-type="journal"><name><surname>Furey</surname><given-names>TS</given-names></name> (<year>2012</year>) <article-title>ChIP-seq and beyond: new and improved methodologies to detect and characterize protein-DNA interactions</article-title>. <source>Nat Rev Genet</source><volume>13</volume>: <fpage>840</fpage>–<lpage>852</lpage>.<pub-id pub-id-type="pmid">23090257</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Ku1"><label>6</label><mixed-citation publication-type="journal"><name><surname>Ku</surname><given-names>CS</given-names></name>, <name><surname>Naidoo</surname><given-names>N</given-names></name>, <name><surname>Wu</surname><given-names>M</given-names></name>, <name><surname>Soong</surname><given-names>R</given-names></name> (<year>2011</year>) <article-title>Studying the epigenome using next generation sequencing</article-title>. <source>J Med Genet</source><volume>48</volume>: <fpage>721</fpage>–<lpage>730</lpage>.<pub-id pub-id-type="pmid">21825079</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Landt1"><label>7</label><mixed-citation publication-type="journal"><name><surname>Landt</surname><given-names>SG</given-names></name>, <name><surname>Marinov</surname><given-names>GK</given-names></name>, <name><surname>Kundaje</surname><given-names>A</given-names></name>, <name><surname>Kheradpour</surname><given-names>P</given-names></name>, <name><surname>Pauli</surname><given-names>F</given-names></name>, <etal>et al</etal> (<year>2012</year>) <article-title>ChIP-seq guidelines and practices of the ENCODE and modENCODE consortia</article-title>. <source>Genome Res</source><volume>22</volume>: <fpage>1813</fpage>–<lpage>1831</lpage>.<pub-id pub-id-type="pmid">22955991</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Chen1"><label>8</label><mixed-citation publication-type="journal"><name><surname>Chen</surname><given-names>Y</given-names></name>, <name><surname>Negre</surname><given-names>N</given-names></name>, <name><surname>Li</surname><given-names>Q</given-names></name>, <name><surname>Mieczkowska</surname><given-names>JO</given-names></name>, <name><surname>Slattery</surname><given-names>M</given-names></name>, <etal>et al</etal> (<year>2012</year>) <article-title>Systematic evaluation of factors influencing ChIP-seq fidelity</article-title>. <source>Nat Methods</source><volume>9</volume>: <fpage>609</fpage>–<lpage>614</lpage>.<pub-id pub-id-type="pmid">22522655</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Kharchenko1"><label>9</label><mixed-citation publication-type="journal"><name><surname>Kharchenko</surname><given-names>PV</given-names></name>, <name><surname>Tolstorukov</surname><given-names>MY</given-names></name>, <name><surname>Park</surname><given-names>PJ</given-names></name> (<year>2008</year>) <article-title>Design and analysis of ChIP-seq experiments for DNA-binding proteins</article-title>. <source>Nat Biotechnol</source><volume>26</volume>: <fpage>1351</fpage>–<lpage>1359</lpage>.<pub-id pub-id-type="pmid">19029915</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Daley1"><label>10</label><mixed-citation publication-type="journal"><name><surname>Daley</surname><given-names>T</given-names></name>, <name><surname>Smith</surname><given-names>AD</given-names></name> (<year>2013</year>) <article-title>Predicting the molecular complexity of sequencing libraries</article-title>. <source>Nat Methods</source><volume>10</volume>: <fpage>325</fpage>–<lpage>327</lpage>.<pub-id pub-id-type="pmid">23435259</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Langmead1"><label>11</label><mixed-citation publication-type="journal"><name><surname>Langmead</surname><given-names>B</given-names></name>, <name><surname>Trapnell</surname><given-names>C</given-names></name>, <name><surname>Pop</surname><given-names>M</given-names></name>, <name><surname>Salzberg</surname><given-names>SL</given-names></name> (<year>2009</year>) <article-title>Ultrafast and memory-efficient alignment of short DNA sequences to the human genome</article-title>. <source>Genome Biol</source><volume>10</volume>: <fpage>R25</fpage>.<pub-id pub-id-type="pmid">19261174</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Li1"><label>12</label><mixed-citation publication-type="journal"><name><surname>Li</surname><given-names>H</given-names></name>, <name><surname>Durbin</surname><given-names>R</given-names></name> (<year>2009</year>) <article-title>Fast and accurate short read alignment with Burrows-Wheeler transform</article-title>. <source>Bioinformatics</source><volume>25</volume>: <fpage>1754</fpage>–<lpage>1760</lpage>.<pub-id pub-id-type="pmid">19451168</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Li2"><label>13</label><mixed-citation publication-type="journal"><name><surname>Li</surname><given-names>R</given-names></name>, <name><surname>Li</surname><given-names>Y</given-names></name>, <name><surname>Kristiansen</surname><given-names>K</given-names></name>, <name><surname>Wang</surname><given-names>J</given-names></name> (<year>2008</year>) <article-title>SOAP: short oligonucleotide alignment program</article-title>. <source>Bioinformatics</source><volume>24</volume>: <fpage>713</fpage>–<lpage>714</lpage>.<pub-id pub-id-type="pmid">18227114</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Li3"><label>14</label><mixed-citation publication-type="journal"><name><surname>Li</surname><given-names>H</given-names></name>, <name><surname>Ruan</surname><given-names>J</given-names></name>, <name><surname>Durbin</surname><given-names>R</given-names></name> (<year>2008</year>) <article-title>Mapping short DNA sequencing reads and calling variants using mapping quality scores</article-title>. <source>Genome Res</source><volume>18</volume>: <fpage>1851</fpage>–<lpage>1858</lpage>.<pub-id pub-id-type="pmid">18714091</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Wang1"><label>15</label><mixed-citation publication-type="journal"><name><surname>Wang</surname><given-names>R</given-names></name>, <name><surname>Hsu</surname><given-names>H-K</given-names></name>, <name><surname>Blattler</surname><given-names>A</given-names></name>, <name><surname>Wang</surname><given-names>Y</given-names></name>, <name><surname>Lan</surname><given-names>X</given-names></name>, <etal>et al</etal> (<year>2013</year>) <article-title>LOcating Non-Unique matched Tags (LONUT) to improve the detection of the enriched regions for ChIP-seq data</article-title>. <source>PLoS ONE</source><volume>8</volume>: <fpage>e67788</fpage><comment>doi:<ext-link ext-link-type="uri" xlink:href="http://dx.doi.org/10.1371/journal.pone.0067788">10.1371/journal.pone.0067788</ext-link></comment><pub-id pub-id-type="pmid">23825685</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Diaz1"><label>16</label><mixed-citation publication-type="journal"><name><surname>Diaz</surname><given-names>A</given-names></name>, <name><surname>Nellore</surname><given-names>A</given-names></name>, <name><surname>Song</surname><given-names>JS</given-names></name> (<year>2012</year>) <article-title>CHANCE: comprehensive software for quality control and validation of ChIP-seq data</article-title>. <source>Genome Biol</source><volume>13</volume>: <fpage>R98</fpage>.<pub-id pub-id-type="pmid">23068444</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Zhang1"><label>17</label><mixed-citation publication-type="journal"><name><surname>Zhang</surname><given-names>Y</given-names></name>, <name><surname>Liu</surname><given-names>T</given-names></name>, <name><surname>Meyer</surname><given-names>CA</given-names></name>, <name><surname>Eeckhoute</surname><given-names>J</given-names></name>, <name><surname>Johnson</surname><given-names>DS</given-names></name>, <etal>et al</etal> (<year>2008</year>) <article-title>Model-based analysis of ChIP-Seq (MACS)</article-title>. <source>Genome Biol</source><volume>9</volume>: <fpage>R137</fpage>.<pub-id pub-id-type="pmid">18798982</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Guo1"><label>18</label><mixed-citation publication-type="journal"><name><surname>Guo</surname><given-names>Y</given-names></name>, <name><surname>Mahony</surname><given-names>S</given-names></name>, <name><surname>Gifford</surname><given-names>DK</given-names></name> (<year>2012</year>) <article-title>High resolution genome wide binding event finding and motif discovery reveals transcription factor spatial binding constraints</article-title>. <source>PLoS Comput Biol</source><volume>8</volume>: <fpage>e1002638</fpage><comment>doi:<ext-link ext-link-type="uri" xlink:href="http://dx.doi.org/10.1371/journal.pcbi.1002638">10.1371/journal.pcbi.1002638</ext-link></comment><pub-id pub-id-type="pmid">22912568</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Jothi1"><label>19</label><mixed-citation publication-type="journal"><name><surname>Jothi</surname><given-names>R</given-names></name>, <name><surname>Cuddapah</surname><given-names>S</given-names></name>, <name><surname>Barski</surname><given-names>A</given-names></name>, <name><surname>Cui</surname><given-names>K</given-names></name>, <name><surname>Zhao</surname><given-names>K</given-names></name> (<year>2008</year>) <article-title>Genome-wide identification of in vivo protein-DNA binding sites from ChIP-Seq data</article-title>. <source>Nucleic Acids Res</source><volume>36</volume>: <fpage>5221</fpage>–<lpage>5231</lpage>.<pub-id pub-id-type="pmid">18684996</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Pepke1"><label>20</label><mixed-citation publication-type="journal"><name><surname>Pepke</surname><given-names>S</given-names></name>, <name><surname>Wold</surname><given-names>B</given-names></name>, <name><surname>Mortazavi</surname><given-names>A</given-names></name> (<year>2009</year>) <article-title>Computation for ChIP-seq and RNA-seq studies</article-title>. <source>Nat Methods</source><volume>6</volume>: <fpage>S22</fpage>–<lpage>S32</lpage>.<pub-id pub-id-type="pmid">19844228</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Wang2"><label>21</label><mixed-citation publication-type="journal"><name><surname>Wang</surname><given-names>C</given-names></name>, <name><surname>Xu</surname><given-names>J</given-names></name>, <name><surname>Zhang</surname><given-names>D</given-names></name>, <name><surname>Wilson</surname><given-names>ZA</given-names></name>, <name><surname>Zhang</surname><given-names>D</given-names></name> (<year>2010</year>) <article-title>An effective approach for identification of in vivo protein-DNA binding sites from paired-end ChIP-Seq data</article-title>. <source>BMC Bioinformatics</source><volume>11</volume>: <fpage>81</fpage>.<pub-id pub-id-type="pmid">20144209</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Szalkowski1"><label>22</label><mixed-citation publication-type="journal"><name><surname>Szalkowski</surname><given-names>AM</given-names></name>, <name><surname>Schmid</surname><given-names>CD</given-names></name> (<year>2011</year>) <article-title>Rapid innovation in ChIP-seq peak-calling algorithms is outdistancing benchmarking efforts</article-title>. <source>Brief Bioinform</source><volume>12</volume>: <fpage>626</fpage>–<lpage>633</lpage>.<pub-id pub-id-type="pmid">21059603</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Li4"><label>23</label><mixed-citation publication-type="journal"><name><surname>Li</surname><given-names>Q</given-names></name>, <name><surname>Brown</surname><given-names>J</given-names></name>, <name><surname>Huang</surname><given-names>H</given-names></name>, <name><surname>Bickel</surname><given-names>P</given-names></name> (<year>2011</year>) <article-title>Measuring reproducibility of high-throughput experiments</article-title>. <source>Ann Appl Stat</source><volume>5</volume>: <fpage>1752</fpage>–<lpage>1779</lpage>.</mixed-citation></ref><ref id="pcbi.1003326-Rozowsky1"><label>24</label><mixed-citation publication-type="journal"><name><surname>Rozowsky</surname><given-names>J</given-names></name>, <name><surname>Euskirchen</surname><given-names>G</given-names></name>, <name><surname>Auerbach</surname><given-names>RK</given-names></name>, <name><surname>Zhang</surname><given-names>ZD</given-names></name>, <name><surname>Gibson</surname><given-names>T</given-names></name>, <etal>et al</etal> (<year>2009</year>) <article-title>PeakSeq enables systematic scoring of ChIP-seq experiments relative to controls</article-title>. <source>Nat Biotechnol</source><volume>27</volume>: <fpage>66</fpage>–<lpage>75</lpage>.<pub-id pub-id-type="pmid">19122651</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Bardet1"><label>25</label><mixed-citation publication-type="journal"><name><surname>Bardet</surname><given-names>AF</given-names></name>, <name><surname>He</surname><given-names>Q</given-names></name>, <name><surname>Zeitlinger</surname><given-names>J</given-names></name>, <name><surname>Stark</surname><given-names>A</given-names></name> (<year>2011</year>) <article-title>A computational pipeline for comparative ChIP-seq analyses</article-title>. <source>Nat Protoc</source><volume>7</volume>: <fpage>45</fpage>–<lpage>61</lpage>.<pub-id pub-id-type="pmid">22179591</pub-id></mixed-citation></ref><ref id="pcbi.1003326-abaj1"><label>26</label><mixed-citation publication-type="journal"><name><surname>Łabaj</surname><given-names>PP</given-names></name>, <name><surname>Leparc</surname><given-names>GG</given-names></name>, <name><surname>Linggi</surname><given-names>BE</given-names></name>, <name><surname>Markillie</surname><given-names>LM</given-names></name>, <name><surname>Wiley</surname><given-names>HS</given-names></name>, <etal>et al</etal> (<year>2011</year>) <article-title>Characterization and improvement of RNA-Seq precision in quantitative transcript expression profiling</article-title>. <source>Bioinformatics</source><volume>27</volume>: <fpage>i383</fpage>–<lpage>i391</lpage>.<pub-id pub-id-type="pmid">21685096</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Sandmann1"><label>27</label><mixed-citation publication-type="journal"><name><surname>Sandmann</surname><given-names>T</given-names></name>, <name><surname>Jensen</surname><given-names>LJ</given-names></name>, <name><surname>Jakobsen</surname><given-names>JS</given-names></name>, <name><surname>Karzynski</surname><given-names>MM</given-names></name>, <name><surname>Eichenlaub</surname><given-names>MP</given-names></name>, <etal>et al</etal> (<year>2006</year>) <article-title>A temporal map of transcription factor activity: mef2 directly regulates target genes at all stages of muscle development</article-title>. <source>Dev Cell</source><volume>10</volume>: <fpage>797</fpage>–<lpage>807</lpage>.<pub-id pub-id-type="pmid">16740481</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Taslim1"><label>28</label><mixed-citation publication-type="journal"><name><surname>Taslim</surname><given-names>C</given-names></name>, <name><surname>Wu</surname><given-names>J</given-names></name>, <name><surname>Yan</surname><given-names>P</given-names></name>, <name><surname>Singer</surname><given-names>G</given-names></name>, <name><surname>Parvin</surname><given-names>J</given-names></name>, <etal>et al</etal> (<year>2009</year>) <article-title>Comparative study on ChIP-seq data: normalization and binding pattern characterization</article-title>. <source>Bioinformatics</source><volume>25</volume>: <fpage>2334</fpage>–<lpage>2340</lpage>.<pub-id pub-id-type="pmid">19561022</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Quinlan1"><label>29</label><mixed-citation publication-type="journal"><name><surname>Quinlan</surname><given-names>AR</given-names></name>, <name><surname>Hall</surname><given-names>IM</given-names></name> (<year>2010</year>) <article-title>BEDTools: a flexible suite of utilities for comparing genomic features</article-title>. <source>Bioinformatics</source><volume>26</volume>: <fpage>841</fpage>–<lpage>842</lpage>.<pub-id pub-id-type="pmid">20110278</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Aszdi1"><label>30</label><mixed-citation publication-type="journal"><name><surname>Aszódi</surname><given-names>A</given-names></name> (<year>2012</year>) <article-title>MULTOVL: fast multiple overlaps of genomic regions</article-title>. <source>Bioinformatics</source><volume>28</volume>: <fpage>3318</fpage>–<lpage>3319</lpage>.<pub-id pub-id-type="pmid">23071271</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Anders1"><label>31</label><mixed-citation publication-type="journal"><name><surname>Anders</surname><given-names>S</given-names></name>, <name><surname>Huber</surname><given-names>W</given-names></name> (<year>2010</year>) <article-title>Differential expression analysis for sequence count data</article-title>. <source>Genome Biol</source><volume>11</volume>: <fpage>R106</fpage>.<pub-id pub-id-type="pmid">20979621</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Robinson1"><label>32</label><mixed-citation publication-type="journal"><name><surname>Robinson</surname><given-names>MD</given-names></name>, <name><surname>McCarthy</surname><given-names>DJ</given-names></name>, <name><surname>Smyth</surname><given-names>GK</given-names></name> (<year>2010</year>) <article-title>edgeR: a Bioconductor package for differential expression analysis of digital gene expression data</article-title>. <source>Bioinformatics</source><volume>26</volume>: <fpage>139</fpage>–<lpage>140</lpage>.<pub-id pub-id-type="pmid">19910308</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Liang1"><label>33</label><mixed-citation publication-type="journal"><name><surname>Liang</surname><given-names>K</given-names></name>, <name><surname>Keles</surname><given-names>S</given-names></name> (<year>2012</year>) <article-title>Detecting differential binding of transcription factors with ChIP-seq</article-title>. <source>Bioinformatics</source><volume>28</volume>: <fpage>121</fpage>–<lpage>122</lpage>.<pub-id pub-id-type="pmid">22057161</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Shao1"><label>34</label><mixed-citation publication-type="journal"><name><surname>Shao</surname><given-names>Z</given-names></name>, <name><surname>Zhang</surname><given-names>Y</given-names></name>, <name><surname>Yuan</surname><given-names>GC</given-names></name>, <name><surname>Orkin</surname><given-names>SH</given-names></name>, <name><surname>Waxman</surname><given-names>DJ</given-names></name> (<year>2012</year>) <article-title>MAnorm: a robust model for quantitative comparison of ChIP-Seq data sets</article-title>. <source>Genome Biol</source><volume>13</volume>: <fpage>R16</fpage>.<pub-id pub-id-type="pmid">22424423</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Taslim2"><label>35</label><mixed-citation publication-type="journal"><name><surname>Taslim</surname><given-names>C</given-names></name>, <name><surname>Huang</surname><given-names>T</given-names></name>, <name><surname>Lin</surname><given-names>S</given-names></name> (<year>2011</year>) <article-title>DIME: R-package for identifying differential ChIP-seq based on an ensemble of mixture models</article-title>. <source>Bioinformatics</source><volume>27</volume>: <fpage>1569</fpage>–<lpage>1570</lpage>.<pub-id pub-id-type="pmid">21471015</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Xu1"><label>36</label><mixed-citation publication-type="journal"><name><surname>Xu</surname><given-names>H</given-names></name>, <name><surname>Wei</surname><given-names>CL</given-names></name>, <name><surname>Lin</surname><given-names>F</given-names></name>, <name><surname>Sung</surname><given-names>WK</given-names></name> (<year>2008</year>) <article-title>An HMM approach to genome-wide identification of differential histone modification sites from ChIP-seq data</article-title>. <source>Bioinformatics</source><volume>24</volume>: <fpage>2344</fpage>–<lpage>2349</lpage>.<pub-id pub-id-type="pmid">18667444</pub-id></mixed-citation></ref><ref id="pcbi.1003326-MendozaParra1"><label>37</label><mixed-citation publication-type="journal"><name><surname>Mendoza-Parra</surname><given-names>MA</given-names></name>, <name><surname>Sankar</surname><given-names>M</given-names></name>, <name><surname>Walia</surname><given-names>M</given-names></name>, <name><surname>Gronemeyer</surname><given-names>H</given-names></name> (<year>2012</year>) <article-title>POLYPHEMUS: R package for comparative analysis of RNA polymerase II ChIP-seq profiles by non-linear normalization</article-title>. <source>Nucleic Acids Res</source><volume>40</volume>: <fpage>e30</fpage>.<pub-id pub-id-type="pmid">22156059</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Kuhn1"><label>38</label><mixed-citation publication-type="journal"><name><surname>Kuhn</surname><given-names>RM</given-names></name>, <name><surname>Haussler</surname><given-names>D</given-names></name>, <name><surname>Kent</surname><given-names>WJ</given-names></name> (<year>2013</year>) <article-title>The UCSC genome browser and associated tools</article-title>. <source>Brief Bioinform</source><volume>14</volume>: <fpage>144</fpage>–<lpage>161</lpage>.<pub-id pub-id-type="pmid">22908213</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Nicol1"><label>39</label><mixed-citation publication-type="journal"><name><surname>Nicol</surname><given-names>JW</given-names></name>, <name><surname>Helt</surname><given-names>GA</given-names></name>, <name><surname>Blanchard</surname><given-names>SG</given-names><suffix>Jr</suffix></name>, <name><surname>Raja</surname><given-names>A</given-names></name>, <name><surname>Loraine</surname><given-names>AE</given-names></name> (<year>2009</year>) <article-title>The Integrated Genome Browser: free software for distribution and exploration of genome-scale datasets</article-title>. <source>Bioinformatics</source><volume>25</volume>: <fpage>2730</fpage>–<lpage>2731</lpage>.<pub-id pub-id-type="pmid">19654113</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Robinson2"><label>40</label><mixed-citation publication-type="journal"><name><surname>Robinson</surname><given-names>JT</given-names></name>, <name><surname>Thorvaldsdóttir</surname><given-names>H</given-names></name>, <name><surname>Winckler</surname><given-names>W</given-names></name>, <name><surname>Guttman</surname><given-names>M</given-names></name>, <name><surname>Lander</surname><given-names>ES</given-names></name>, <etal>et al</etal> (<year>2011</year>) <article-title>Integrative genomics viewer</article-title>. <source>Nat Biotechnol</source><volume>29</volume>: <fpage>24</fpage>–<lpage>26</lpage>.<pub-id pub-id-type="pmid">21221095</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Kent1"><label>41</label><mixed-citation publication-type="journal"><name><surname>Kent</surname><given-names>WJ</given-names></name>, <name><surname>Zweig</surname><given-names>AS</given-names></name>, <name><surname>Barber</surname><given-names>G</given-names></name>, <name><surname>Hinrichs</surname><given-names>AS</given-names></name>, <name><surname>Karolchik</surname><given-names>D</given-names></name> (<year>2010</year>) <article-title>BigWig and BigBed: enabling browsing of large distributed datasets</article-title>. <source>Bioinformatics</source><volume>26</volume>: <fpage>2204</fpage>–<lpage>2207</lpage>.<pub-id pub-id-type="pmid">20639541</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Shin1"><label>42</label><mixed-citation publication-type="journal"><name><surname>Shin</surname><given-names>H</given-names></name>, <name><surname>Liu</surname><given-names>T</given-names></name>, <name><surname>Manrai</surname><given-names>AK</given-names></name>, <name><surname>Liu</surname><given-names>XS</given-names></name> (<year>2009</year>) <article-title>CEAS: cis-regulatory element annotation system</article-title>. <source>Bioinformatics</source><volume>25</volume>: <fpage>2605</fpage>–<lpage>2606</lpage>.<pub-id pub-id-type="pmid">19689956</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Zhu1"><label>43</label><mixed-citation publication-type="journal"><name><surname>Zhu</surname><given-names>LJ</given-names></name>, <name><surname>Gazin</surname><given-names>C</given-names></name>, <name><surname>Lawson</surname><given-names>ND</given-names></name>, <name><surname>Pages</surname><given-names>H</given-names></name>, <name><surname>Lin</surname><given-names>SM</given-names></name>, <etal>et al</etal> (<year>2010</year>) <article-title>ChIPpeakAnno: a Bioconductor package to annotate ChIP-seq and Chip-chip data</article-title>. <source>BMC Bioinformatics</source><volume>11</volume>: <fpage>237</fpage>.<pub-id pub-id-type="pmid">20459804</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Huangda1"><label>44</label><mixed-citation publication-type="journal"><name><surname>Huang da</surname><given-names>W</given-names></name>, <name><surname>Sherman</surname><given-names>BT</given-names></name>, <name><surname>Lempicki</surname><given-names>RA</given-names></name> (<year>2009</year>) <article-title>Systematic and integrative analysis of large gene lists using DAVID bioinformatics resources</article-title>. <source>Nat Protoc</source><volume>4</volume>: <fpage>44</fpage>–<lpage>57</lpage>.<pub-id pub-id-type="pmid">19131956</pub-id></mixed-citation></ref><ref id="pcbi.1003326-McLean1"><label>45</label><mixed-citation publication-type="journal"><name><surname>McLean</surname><given-names>CY</given-names></name>, <name><surname>Bristor</surname><given-names>D</given-names></name>, <name><surname>Hiller</surname><given-names>M</given-names></name>, <name><surname>Clarke</surname><given-names>SL</given-names></name>, <name><surname>Schaar</surname><given-names>BT</given-names></name>, <etal>et al</etal> (<year>2010</year>) <article-title>GREAT improves functional interpretation of cis-regulatory regions</article-title>. <source>Nat Biotechnol</source><volume>28</volume>: <fpage>495</fpage>–<lpage>501</lpage>.<pub-id pub-id-type="pmid">20436461</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Subramanian1"><label>46</label><mixed-citation publication-type="journal"><name><surname>Subramanian</surname><given-names>A</given-names></name>, <name><surname>Tamayo</surname><given-names>P</given-names></name>, <name><surname>Mootha</surname><given-names>VK</given-names></name>, <name><surname>Mukherjee</surname><given-names>S</given-names></name>, <name><surname>Ebert</surname><given-names>BL</given-names></name>, <etal>et al</etal> (<year>2005</year>) <article-title>Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles</article-title>. <source>Proc Natl Acad Sci U S A</source><volume>102</volume>: <fpage>15545</fpage>–<lpage>15550</lpage>.<pub-id pub-id-type="pmid">16199517</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Liu1"><label>47</label><mixed-citation publication-type="journal"><name><surname>Liu</surname><given-names>HW</given-names></name>, <name><surname>Zhang</surname><given-names>J</given-names></name>, <name><surname>Heine</surname><given-names>GF</given-names></name>, <name><surname>Arora</surname><given-names>M</given-names></name>, <name><surname>Gulcin Ozer</surname><given-names>H</given-names></name>, <etal>et al</etal> (<year>2012</year>) <article-title>Chromatin modification by SUMO-1 stimulates the promoters of translation machinery genes</article-title>. <source>Nucleic Acids Res</source><volume>40</volume>: <fpage>10172</fpage>–<lpage>10186</lpage>.<pub-id pub-id-type="pmid">22941651</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Kuttippurathu1"><label>48</label><mixed-citation publication-type="journal"><name><surname>Kuttippurathu</surname><given-names>L</given-names></name>, <name><surname>Hsing</surname><given-names>M</given-names></name>, <name><surname>Liu</surname><given-names>Y</given-names></name>, <name><surname>Schmidt</surname><given-names>B</given-names></name>, <name><surname>Maskell</surname><given-names>DL</given-names></name>, <etal>et al</etal> (<year>2011</year>) <article-title>CompleteMOTIFs: DNA motif discovery platform for transcription factor binding experiments</article-title>. <source>Bioinformatics</source><volume>27</volume>: <fpage>715</fpage>–<lpage>717</lpage>.<pub-id pub-id-type="pmid">21183585</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Liu2"><label>49</label><mixed-citation publication-type="journal"><name><surname>Liu</surname><given-names>T</given-names></name>, <name><surname>Ortiz</surname><given-names>JA</given-names></name>, <name><surname>Taing</surname><given-names>L</given-names></name>, <name><surname>Meyer</surname><given-names>CA</given-names></name>, <name><surname>Lee</surname><given-names>B</given-names></name>, <etal>et al</etal> (<year>2011</year>) <article-title>Cistrome: an integrative platform for transcriptional regulation studies</article-title>. <source>Genome Biol</source><volume>12</volume>: <fpage>R83</fpage>.<pub-id pub-id-type="pmid">21859476</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Goecks1"><label>50</label><mixed-citation publication-type="journal"><name><surname>Goecks</surname><given-names>J</given-names></name>, <name><surname>Nekrutenko</surname><given-names>A</given-names></name>, <name><surname>Taylor</surname><given-names>J</given-names></name>, <name><surname>Team</surname><given-names>G</given-names></name> (<year>2010</year>) <article-title>Galaxy: a comprehensive approach for supporting accessible, reproducible, and transparent computational research in the life sciences</article-title>. <source>Genome Biol</source><volume>11</volume>: <fpage>R86</fpage>.<pub-id pub-id-type="pmid">20738864</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Blankenberg1"><label>51</label><mixed-citation publication-type="journal"><name><surname>Blankenberg</surname><given-names>D</given-names></name>, <name><surname>Kuster</surname><given-names>GV</given-names></name>, <name><surname>Coraor</surname><given-names>N</given-names></name>, <name><surname>Ananda</surname><given-names>G</given-names></name>, <name><surname>Lazarus</surname><given-names>R</given-names></name>, <etal>et al</etal> (<year>2010</year>) <article-title>Galaxy: a web-based genome analysis tool for experimentalists</article-title>. <source>Curr Protoc Mol Biol Chapter</source><volume>19</volume>: <fpage>Unit 19.10.1</fpage>–<lpage>Unit 19.1021</lpage>.</mixed-citation></ref><ref id="pcbi.1003326-Giardine1"><label>52</label><mixed-citation publication-type="journal"><name><surname>Giardine</surname><given-names>B</given-names></name>, <name><surname>Riemer</surname><given-names>C</given-names></name>, <name><surname>Hardison</surname><given-names>RC</given-names></name>, <name><surname>Burhans</surname><given-names>R</given-names></name>, <name><surname>Elnitski</surname><given-names>L</given-names></name>, <etal>et al</etal> (<year>2005</year>) <article-title>Galaxy: a platform for interactive large-scale genome analysis</article-title>. <source>Genome Res</source><volume>15</volume>: <fpage>1451</fpage>–<lpage>1455</lpage>.<pub-id pub-id-type="pmid">16169926</pub-id></mixed-citation></ref><ref id="pcbi.1003326-vanHelden1"><label>53</label><mixed-citation publication-type="journal"><name><surname>van Helden</surname><given-names>J</given-names></name> (<year>2003</year>) <article-title>Regulatory sequence analysis tools</article-title>. <source>Nucleic Acids Res</source><volume>31</volume>: <fpage>3593</fpage>–<lpage>3596</lpage>.<pub-id pub-id-type="pmid">12824373</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Kent2"><label>54</label><mixed-citation publication-type="journal"><name><surname>Kent</surname><given-names>WJ</given-names></name>, <name><surname>Sugnet</surname><given-names>CW</given-names></name>, <name><surname>Furey</surname><given-names>TS</given-names></name>, <name><surname>Roskin</surname><given-names>KM</given-names></name>, <name><surname>Pringle</surname><given-names>TH</given-names></name>, <etal>et al</etal> (<year>2002</year>) <article-title>The human genome browser at UCSC</article-title>. <source>Genome Res</source><volume>12</volume>: <fpage>996</fpage>–<lpage>1006</lpage>.<pub-id pub-id-type="pmid">12045153</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Kulakovskiy1"><label>55</label><mixed-citation publication-type="journal"><name><surname>Kulakovskiy</surname><given-names>IV</given-names></name>, <name><surname>Boeva</surname><given-names>VA</given-names></name>, <name><surname>Favorov</surname><given-names>AV</given-names></name>, <name><surname>Makeev</surname><given-names>VJ</given-names></name> (<year>2010</year>) <article-title>Deep and wide digging for binding motifs in ChIP-Seq data</article-title>. <source>Bioinformatics</source><volume>26</volume>: <fpage>2622</fpage>–<lpage>2623</lpage>.<pub-id pub-id-type="pmid">20736340</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Ji1"><label>56</label><mixed-citation publication-type="journal"><name><surname>Ji</surname><given-names>H</given-names></name>, <name><surname>Jiang</surname><given-names>H</given-names></name>, <name><surname>Ma</surname><given-names>W</given-names></name>, <name><surname>Johnson</surname><given-names>DS</given-names></name>, <name><surname>Myers</surname><given-names>RM</given-names></name>, <etal>et al</etal> (<year>2008</year>) <article-title>An integrated software system for analyzing ChIP-chip and ChIP-seq data</article-title>. <source>Nat Biotechnol</source><volume>26</volume>: <fpage>1293</fpage>–<lpage>1300</lpage>.<pub-id pub-id-type="pmid">18978777</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Machanick1"><label>57</label><mixed-citation publication-type="journal"><name><surname>Machanick</surname><given-names>P</given-names></name>, <name><surname>Bailey</surname><given-names>TL</given-names></name> (<year>2011</year>) <article-title>MEME-ChIP: motif analysis of large DNA datasets</article-title>. <source>Bioinformatics</source><volume>27</volume>: <fpage>1696</fpage>–<lpage>1697</lpage>.<pub-id pub-id-type="pmid">21486936</pub-id></mixed-citation></ref><ref id="pcbi.1003326-ThomasChollier1"><label>58</label><mixed-citation publication-type="journal"><name><surname>Thomas-Chollier</surname><given-names>M</given-names></name>, <name><surname>Herrmann</surname><given-names>C</given-names></name>, <name><surname>Defrance</surname><given-names>M</given-names></name>, <name><surname>Sand</surname><given-names>O</given-names></name>, <name><surname>Thieffry</surname><given-names>D</given-names></name>, <etal>et al</etal> (<year>2011</year>) <article-title>RSAT peak-motifs: motif analysis in full-size ChIP-seq datasets</article-title>. <source>Nucleic Acids Res</source><volume>40</volume>: <fpage>e31</fpage>.<pub-id pub-id-type="pmid">22156162</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Mahony1"><label>59</label><mixed-citation publication-type="journal"><name><surname>Mahony</surname><given-names>S</given-names></name>, <name><surname>Benos</surname><given-names>PV</given-names></name> (<year>2007</year>) <article-title>STAMP: a web tool for exploring DNA-binding motif similarities</article-title>. <source>Nucleic Acids Res</source><volume>35</volume>: <fpage>W253</fpage>–<lpage>W258</lpage>.<pub-id pub-id-type="pmid">17478497</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Gupta1"><label>60</label><mixed-citation publication-type="journal"><name><surname>Gupta</surname><given-names>S</given-names></name>, <name><surname>Stamatoyannopoulos</surname><given-names>J</given-names></name>, <name><surname>Bailey</surname><given-names>TL</given-names></name>, <name><surname>Noble</surname><given-names>WS</given-names></name> (<year>2007</year>) <article-title>Quantifying similarity between motifs</article-title>. <source>Genome Biol</source><volume>8</volume>: <fpage>R24</fpage>.<pub-id pub-id-type="pmid">17324271</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Bailey1"><label>61</label><mixed-citation publication-type="journal"><name><surname>Bailey</surname><given-names>TL</given-names></name>, <name><surname>Machanick</surname><given-names>P</given-names></name> (<year>2012</year>) <article-title>Inferring direct DNA binding from ChIP-seq</article-title>. <source>Nucleic Acids Res</source><volume>40</volume>: <fpage>e128</fpage>.<pub-id pub-id-type="pmid">22610855</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Whitington1"><label>62</label><mixed-citation publication-type="journal"><name><surname>Whitington</surname><given-names>T</given-names></name>, <name><surname>Frith</surname><given-names>MC</given-names></name>, <name><surname>Johnson</surname><given-names>J</given-names></name>, <name><surname>Bailey</surname><given-names>TL</given-names></name> (<year>2011</year>) <article-title>Inferring transcription factor complexes from ChIP-seq data</article-title>. <source>Nucleic Acids Res</source><volume>39</volume>: <fpage>e98</fpage>.<pub-id pub-id-type="pmid">21602262</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Grant1"><label>63</label><mixed-citation publication-type="journal"><name><surname>Grant</surname><given-names>CE</given-names></name>, <name><surname>Bailey</surname><given-names>TL</given-names></name>, <name><surname>Noble</surname><given-names>WS</given-names></name> (<year>2011</year>) <article-title>FIMO: scanning for occurrences of a given motif</article-title>. <source>Bioinformatics</source><volume>27</volume>: <fpage>1017</fpage>–<lpage>1018</lpage>.<pub-id pub-id-type="pmid">21330290</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Hertz1"><label>64</label><mixed-citation publication-type="journal"><name><surname>Hertz</surname><given-names>GZ</given-names></name>, <name><surname>Stormo</surname><given-names>GD</given-names></name> (<year>1999</year>) <article-title>Identifying DNA and protein patterns with statistically significant alignments of multiple sequences</article-title>. <source>Bioinformatics</source><volume>15</volume>: <fpage>563</fpage>–<lpage>577</lpage>.<pub-id pub-id-type="pmid">10487864</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Adli1"><label>65</label><mixed-citation publication-type="journal"><name><surname>Adli</surname><given-names>M</given-names></name>, <name><surname>Bernstein</surname><given-names>BE</given-names></name> (<year>2011</year>) <article-title>Whole-genome chromatin profiling from limited numbers of cells using nano-ChIP-seq</article-title>. <source>Nat Protoc</source><volume>6</volume>: <fpage>1656</fpage>–<lpage>1668</lpage>.<pub-id pub-id-type="pmid">21959244</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Encode1"><label>66</label><mixed-citation publication-type="journal"><collab>Encode Project Consortium</collab> (<year>2012</year>) <name><surname>Dunham</surname><given-names>I</given-names></name>, <name><surname>Kundaje</surname><given-names>A</given-names></name>, <name><surname>Alfred</surname><given-names>SF</given-names></name>, <name><surname>Collins</surname><given-names>PJ</given-names></name>, <etal>et al</etal> (<year>2012</year>) <article-title>An integrated encyclopedia of DNA elements in the human genome</article-title>. <source>Nature</source><volume>489</volume>: <fpage>57</fpage>–<lpage>74</lpage>.<pub-id pub-id-type="pmid">22955616</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Guo2"><label>67</label><mixed-citation publication-type="journal"><name><surname>Guo</surname><given-names>Y</given-names></name>, <name><surname>Papachristoudis</surname><given-names>G</given-names></name>, <name><surname>Altshuler</surname><given-names>RC</given-names></name>, <name><surname>Gerber</surname><given-names>GK</given-names></name>, <name><surname>Jaakkola</surname><given-names>TS</given-names></name>, <etal>et al</etal> (<year>2010</year>) <article-title>Discovering homotypic binding events at high spatial resolution</article-title>. <source>Bioinformatics</source><volume>26</volume>: <fpage>3028</fpage>–<lpage>3034</lpage>.<pub-id pub-id-type="pmid">20966006</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Rhee1"><label>68</label><mixed-citation publication-type="journal"><name><surname>Rhee</surname><given-names>HS</given-names></name>, <name><surname>Pugh</surname><given-names>BF</given-names></name> (<year>2011</year>) <article-title>Comprehensive genome-wide protein-DNA interactions detected at single-nucleotide resolution</article-title>. <source>Cell</source><volume>147</volume>: <fpage>1408</fpage>–<lpage>1419</lpage>.<pub-id pub-id-type="pmid">22153082</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Egelhofer1"><label>69</label><mixed-citation publication-type="journal"><name><surname>Egelhofer</surname><given-names>TA</given-names></name>, <name><surname>Minoda</surname><given-names>A</given-names></name>, <name><surname>Klugman</surname><given-names>S</given-names></name>, <name><surname>Lee</surname><given-names>K</given-names></name>, <name><surname>Kolasinska-Zwierz</surname><given-names>P</given-names></name>, <etal>et al</etal> (<year>2011</year>) <article-title>An assessment of histone-modification antibody quality</article-title>. <source>Nat Struct Mol Biol</source><volume>18</volume>: <fpage>91</fpage>–<lpage>93</lpage>.<pub-id pub-id-type="pmid">21131980</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Thurman1"><label>70</label><mixed-citation publication-type="journal"><name><surname>Thurman</surname><given-names>RE</given-names></name>, <name><surname>Rynes</surname><given-names>E</given-names></name>, <name><surname>Humbert</surname><given-names>R</given-names></name>, <name><surname>Vierstra</surname><given-names>J</given-names></name>, <name><surname>Maurano</surname><given-names>MT</given-names></name>, <etal>et al</etal> (<year>2012</year>) <article-title>The accessible chromatin landscape of the human genome</article-title>. <source>Nature</source><volume>489</volume>: <fpage>75</fpage>–<lpage>82</lpage>.<pub-id pub-id-type="pmid">22955617</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Jiao1"><label>71</label><mixed-citation publication-type="journal"><name><surname>Jiao</surname><given-names>S</given-names></name>, <name><surname>Bailey</surname><given-names>CP</given-names></name>, <name><surname>Zhang</surname><given-names>S</given-names></name>, <name><surname>Ladunga</surname><given-names>I</given-names></name> (<year>2010</year>) <article-title>Probabilistic peak calling and controlling false discovery rate estimations in transcription factor binding site mapping from ChIP-seq</article-title>. <source>Methods Mol Biol</source><volume>674</volume>: <fpage>161</fpage>–<lpage>177</lpage>.<pub-id pub-id-type="pmid">20827591</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Wilbanks1"><label>72</label><mixed-citation publication-type="journal"><name><surname>Wilbanks</surname><given-names>EG</given-names></name>, <name><surname>Facciotti</surname><given-names>MT</given-names></name> (<year>2010</year>) <article-title>Evaluation of algorithm performance in ChIP-seq peak detection</article-title>. <source>PLoS ONE</source><volume>5</volume>: <fpage>e11471</fpage><comment>doi:<ext-link ext-link-type="uri" xlink:href="http://dx.doi.org/10.1371/journal.pone.0011471">10.1371/journal.pone.0011471</ext-link></comment><pub-id pub-id-type="pmid">20628599</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Schweikert1"><label>73</label><mixed-citation publication-type="journal"><name><surname>Schweikert</surname><given-names>C</given-names></name>, <name><surname>Brown</surname><given-names>S</given-names></name>, <name><surname>Tang</surname><given-names>Z</given-names></name>, <name><surname>Smith</surname><given-names>PR</given-names></name>, <name><surname>Hsu</surname><given-names>DF</given-names></name> (<year>2012</year>) <article-title>Combining multiple ChIP-seq peak detection systems using combinatorial fusion</article-title>. <source>BMC Genomics</source><volume>13 Suppl 8</volume>: <fpage>S12</fpage>.</mixed-citation></ref><ref id="pcbi.1003326-Li5"><label>74</label><mixed-citation publication-type="journal"><name><surname>Li</surname><given-names>G</given-names></name>, <name><surname>Fullwood</surname><given-names>MJ</given-names></name>, <name><surname>Xu</surname><given-names>H</given-names></name>, <name><surname>Mulawadi</surname><given-names>FH</given-names></name>, <name><surname>Velkov</surname><given-names>S</given-names></name>, <etal>et al</etal> (<year>2010</year>) <article-title>ChIA-PET tool for comprehensive chromatin interaction analysis with paired-end tag sequencing</article-title>. <source>Genome Biol</source><volume>11</volume>: <fpage>R22</fpage>.<pub-id pub-id-type="pmid">20181287</pub-id></mixed-citation></ref><ref id="pcbi.1003326-vandeWerken1"><label>75</label><mixed-citation publication-type="journal"><name><surname>van de Werken</surname><given-names>HJ</given-names></name>, <name><surname>Landan</surname><given-names>G</given-names></name>, <name><surname>Holwerda</surname><given-names>SJ</given-names></name>, <name><surname>Hoichman</surname><given-names>M</given-names></name>, <name><surname>Klous</surname><given-names>P</given-names></name>, <etal>et al</etal> (<year>2012</year>) <article-title>Robust 4C-seq data analysis to screen for regulatory DNA interactions</article-title>. <source>Nat Methods</source><volume>9</volume>: <fpage>969</fpage>–<lpage>972</lpage>.<pub-id pub-id-type="pmid">22961246</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Dostie1"><label>76</label><mixed-citation publication-type="journal"><name><surname>Dostie</surname><given-names>J</given-names></name>, <name><surname>Richmond</surname><given-names>TA</given-names></name>, <name><surname>Arnaout</surname><given-names>RA</given-names></name>, <name><surname>Selzer</surname><given-names>RR</given-names></name>, <name><surname>Lee</surname><given-names>WL</given-names></name>, <etal>et al</etal> (<year>2006</year>) <article-title>Chromosome Conformation Capture Carbon Copy (5C): a massively parallel solution for mapping interactions between genomic elements</article-title>. <source>Genome Res</source><volume>16</volume>: <fpage>1299</fpage>–<lpage>1309</lpage>.<pub-id pub-id-type="pmid">16954542</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Diaz2"><label>77</label><mixed-citation publication-type="journal"><name><surname>Diaz</surname><given-names>A</given-names></name>, <name><surname>Park</surname><given-names>K</given-names></name>, <name><surname>Lim</surname><given-names>DA</given-names></name>, <name><surname>Song</surname><given-names>JS</given-names></name> (<year>2012</year>) <article-title>Normalization, bias correction, and peak calling for ChIP-seq</article-title>. <source>Stat Appl Genet Mol Biol</source><volume>11</volume>: <fpage>Article 9</fpage>.</mixed-citation></ref><ref id="pcbi.1003326-White1"><label>78</label><mixed-citation publication-type="journal"><name><surname>White</surname><given-names>MA</given-names></name>, <name><surname>Myers</surname><given-names>CA</given-names></name>, <name><surname>Corbo</surname><given-names>JC</given-names></name>, <name><surname>Cohen</surname><given-names>BA</given-names></name> (<year>2013</year>) <article-title>Massively parallel in vivo enhancer assay reveals that highly local features determine the cis-regulatory function of ChIP-seq peaks</article-title>. <source>Proc Natl Acad Sci U S A</source><volume>110</volume>: <fpage>11952</fpage>–<lpage>11957</lpage>.<pub-id pub-id-type="pmid">23818646</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Doolittle1"><label>79</label><mixed-citation publication-type="journal"><name><surname>Doolittle</surname><given-names>WF</given-names></name> (<year>2013</year>) <article-title>Is junk DNA bunk? A critique of ENCODE</article-title>. <source>Proc Natl Acad Sci U S A</source><volume>110</volume>: <fpage>5294</fpage>–<lpage>5300</lpage>.<pub-id pub-id-type="pmid">23479647</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Zhu2"><label>80</label><mixed-citation publication-type="journal"><name><surname>Zhu</surname><given-names>C</given-names></name>, <name><surname>Byers</surname><given-names>KJ</given-names></name>, <name><surname>McCord</surname><given-names>RP</given-names></name>, <name><surname>Shi</surname><given-names>Z</given-names></name>, <name><surname>Berger</surname><given-names>MF</given-names></name>, <etal>et al</etal> (<year>2009</year>) <article-title>High-resolution DNA-binding specificity analysis of yeast transcription factors</article-title>. <source>Genome Res</source><volume>19</volume>: <fpage>556</fpage>–<lpage>566</lpage>.<pub-id pub-id-type="pmid">19158363</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Jia1"><label>81</label><mixed-citation publication-type="journal"><name><surname>Jia</surname><given-names>C</given-names></name>, <name><surname>Carson</surname><given-names>MB</given-names></name>, <name><surname>Yu</surname><given-names>J</given-names></name> (<year>2013</year>) <article-title>A fast weak motif-finding algorithm based on community detection in graphs</article-title>. <source>BMC Bioinformatics</source><volume>14</volume>: <fpage>227</fpage>.<pub-id pub-id-type="pmid">23865838</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Sun1"><label>82</label><mixed-citation publication-type="journal"><name><surname>Sun</surname><given-names>HQ</given-names></name>, <name><surname>Low</surname><given-names>MY</given-names></name>, <name><surname>Hsu</surname><given-names>WJ</given-names></name>, <name><surname>Rajapakse</surname><given-names>JC</given-names></name> (<year>2010</year>) <article-title>RecMotif: a novel fast algorithm for weak motif discovery</article-title>. <source>BMC Bioinformatics</source><volume>11 Suppl 11</volume>: <fpage>S8</fpage>.</mixed-citation></ref><ref id="pcbi.1003326-Yip1"><label>83</label><mixed-citation publication-type="journal"><name><surname>Yip</surname><given-names>KY</given-names></name>, <name><surname>Cheng</surname><given-names>C</given-names></name>, <name><surname>Bhardwaj</surname><given-names>N</given-names></name>, <name><surname>Brown</surname><given-names>JB</given-names></name>, <name><surname>Leng</surname><given-names>J</given-names></name>, <etal>et al</etal> (<year>2012</year>) <article-title>Classification of human genomic regions based on experimentally determined binding sites of more than 100 transcription-related factors</article-title>. <source>Genome Biol</source><volume>13</volume>: <fpage>R48</fpage>.<pub-id pub-id-type="pmid">22950945</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Cheung1"><label>84</label><mixed-citation publication-type="journal"><name><surname>Cheung</surname><given-names>M-S</given-names></name>, <name><surname>Down</surname><given-names>TA</given-names></name>, <name><surname>Latorre</surname><given-names>I</given-names></name>, <name><surname>Ahringer</surname><given-names>J</given-names></name> (<year>2011</year>) <article-title>Systematic bias in high-throughput sequencing data and its correction by BEADS</article-title>. <source>Nucleic Acids Res</source><volume>39</volume>: <fpage>e103</fpage>.<pub-id pub-id-type="pmid">21646344</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Muio1"><label>85</label><mixed-citation publication-type="journal"><name><surname>Muiño</surname><given-names>JM</given-names></name>, <name><surname>Kaufmann</surname><given-names>K</given-names></name>, <name><surname>van Ham</surname><given-names>RC</given-names></name>, <name><surname>Angenent</surname><given-names>GC</given-names></name>, <name><surname>Krajewski</surname><given-names>P</given-names></name> (<year>2011</year>) <article-title>ChIP-seq Analysis in R (CSAR): an R package for the statistical detection of protein-bound genomic regions</article-title>. <source>Plant Methods</source><volume>7</volume>: <fpage>11</fpage>.<pub-id pub-id-type="pmid">21554688</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Rashid1"><label>86</label><mixed-citation publication-type="journal"><name><surname>Rashid</surname><given-names>NU</given-names></name>, <name><surname>Giresi</surname><given-names>PG</given-names></name>, <name><surname>Ibrahim</surname><given-names>JG</given-names></name>, <name><surname>Sun</surname><given-names>W</given-names></name>, <name><surname>Lieb</surname><given-names>JD</given-names></name> (<year>2011</year>) <article-title>ZINBA integrates local covariates with DNA-seq data to identify broad and narrow regions of enrichment, even within amplified genomic regions</article-title>. <source>Genome Biol</source><volume>12</volume>: <fpage>R67</fpage>.<pub-id pub-id-type="pmid">21787385</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Qin1"><label>87</label><mixed-citation publication-type="journal"><name><surname>Qin</surname><given-names>ZS</given-names></name>, <name><surname>Yu</surname><given-names>J</given-names></name>, <name><surname>Shen</surname><given-names>J</given-names></name>, <name><surname>Maher</surname><given-names>CA</given-names></name>, <name><surname>Hu</surname><given-names>M</given-names></name>, <etal>et al</etal> (<year>2010</year>) <article-title>HPeak: an HMM-based algorithm for defining read-enriched regions in ChIP-Seq data</article-title>. <source>BMC Bioinformatics</source><volume>11</volume>: <fpage>369</fpage>.<pub-id pub-id-type="pmid">20598134</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Spyrou1"><label>88</label><mixed-citation publication-type="journal"><name><surname>Spyrou</surname><given-names>C</given-names></name>, <name><surname>Stark</surname><given-names>R</given-names></name>, <name><surname>Lynch</surname><given-names>AG</given-names></name>, <name><surname>Tavaré</surname><given-names>S</given-names></name> (<year>2009</year>) <article-title>BayesPeak: Bayesian analysis of ChIP-seq data</article-title>. <source>BMC Bioinformatics</source><volume>10</volume>: <fpage>299</fpage>.<pub-id pub-id-type="pmid">19772557</pub-id></mixed-citation></ref><ref id="pcbi.1003326-SalmonDivon1"><label>89</label><mixed-citation publication-type="journal"><name><surname>Salmon-Divon</surname><given-names>M</given-names></name>, <name><surname>Dvinge</surname><given-names>H</given-names></name>, <name><surname>Tammoja</surname><given-names>K</given-names></name>, <name><surname>Bertone</surname><given-names>P</given-names></name> (<year>2010</year>) <article-title>PeakAnalyzer: genome-wide annotation of chromatin binding and modification loci</article-title>. <source>BMC Bioinformatics</source><volume>11</volume>: <fpage>415</fpage>.<pub-id pub-id-type="pmid">20691053</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Zang1"><label>90</label><mixed-citation publication-type="journal"><name><surname>Zang</surname><given-names>C</given-names></name>, <name><surname>Schones</surname><given-names>DE</given-names></name>, <name><surname>Zeng</surname><given-names>C</given-names></name>, <name><surname>Cui</surname><given-names>K</given-names></name>, <name><surname>Zhao</surname><given-names>K</given-names></name>, <etal>et al</etal> (<year>2009</year>) <article-title>A clustering approach for identification of enriched domains from histone modification ChIP-Seq data</article-title>. <source>Bioinformatics</source><volume>25</volume>: <fpage>1952</fpage>–<lpage>1958</lpage>.<pub-id pub-id-type="pmid">19505939</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Xu2"><label>91</label><mixed-citation publication-type="journal"><name><surname>Xu</surname><given-names>H</given-names></name>, <name><surname>Handoko</surname><given-names>L</given-names></name>, <name><surname>Wei</surname><given-names>X</given-names></name>, <name><surname>Ye</surname><given-names>C</given-names></name>, <name><surname>Sheng</surname><given-names>J</given-names></name>, <etal>et al</etal> (<year>2010</year>) <article-title>A signal-noise model for significance analysis of ChIP-seq with negative control</article-title>. <source>Bioinformatics</source><volume>26</volume>: <fpage>1199</fpage>–<lpage>1204</lpage>.<pub-id pub-id-type="pmid">20371496</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Song1"><label>92</label><mixed-citation publication-type="journal"><name><surname>Song</surname><given-names>Q</given-names></name>, <name><surname>Smith</surname><given-names>AD</given-names></name> (<year>2011</year>) <article-title>Identifying dispersed epigenomic domains from ChIP-Seq data</article-title>. <source>Bioinformatics</source><volume>27</volume>: <fpage>870</fpage>–<lpage>871</lpage>.<pub-id pub-id-type="pmid">21325299</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Feng1"><label>93</label><mixed-citation publication-type="journal"><name><surname>Feng</surname><given-names>X</given-names></name>, <name><surname>Grossman</surname><given-names>R</given-names></name>, <name><surname>Stein</surname><given-names>L</given-names></name> (<year>2011</year>) <article-title>PeakRanger: a cloud-enabled peak caller for ChIP-seq data</article-title>. <source>BMC Bioinformatics</source><volume>12</volume>: <fpage>139</fpage>.<pub-id pub-id-type="pmid">21554709</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Guttman1"><label>94</label><mixed-citation publication-type="journal"><name><surname>Guttman</surname><given-names>M</given-names></name>, <name><surname>Garber</surname><given-names>M</given-names></name>, <name><surname>Levin</surname><given-names>JZ</given-names></name>, <name><surname>Donaghey</surname><given-names>J</given-names></name>, <name><surname>Robinson</surname><given-names>J</given-names></name>, <etal>et al</etal> (<year>2010</year>) <article-title>Ab initio reconstruction of cell type-specific transcriptomes in mouse reveals the conserved multi-exonic structure of lincRNAs</article-title>. <source>Nat Biotechnol</source><volume>28</volume>: <fpage>503</fpage>–<lpage>510</lpage>.<pub-id pub-id-type="pmid">20436462</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Baugh1"><label>95</label><mixed-citation publication-type="journal"><name><surname>Baugh</surname><given-names>LR</given-names></name>, <name><surname>Demodena</surname><given-names>J</given-names></name>, <name><surname>Sternberg</surname><given-names>PW</given-names></name> (<year>2009</year>) <article-title>RNA Pol II accumulates at promoters of growth genes during developmental arrest</article-title>. <source>Science</source><volume>324</volume>: <fpage>92</fpage>–<lpage>94</lpage>.<pub-id pub-id-type="pmid">19251593</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Taslim3"><label>96</label><mixed-citation publication-type="journal"><name><surname>Taslim</surname><given-names>C</given-names></name>, <name><surname>Huang</surname><given-names>K</given-names></name>, <name><surname>Huang</surname><given-names>T</given-names></name>, <name><surname>Lin</surname><given-names>S</given-names></name> (<year>2012</year>) <article-title>Analyzing ChIP-seq data: preprocessing, normalization, differential identification, and binding pattern characterization</article-title>. <source>Methods Mol Biol</source><volume>802</volume>: <fpage>275</fpage>–<lpage>291</lpage>.<pub-id pub-id-type="pmid">22130887</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Nix1"><label>97</label><mixed-citation publication-type="journal"><name><surname>Nix</surname><given-names>D</given-names></name>, <name><surname>Courdy</surname><given-names>S</given-names></name>, <name><surname>Boucher</surname><given-names>K</given-names></name> (<year>2008</year>) <article-title>Empirical methods for controlling false positives and estimating confidence in ChIP-Seq peaks</article-title>. <source>BMC Bioinformatics</source><volume>9</volume>: <fpage>523</fpage>.<pub-id pub-id-type="pmid">19061503</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Mortazavi1"><label>98</label><mixed-citation publication-type="journal"><name><surname>Mortazavi</surname><given-names>A</given-names></name>, <name><surname>Williams</surname><given-names>BA</given-names></name>, <name><surname>McCue</surname><given-names>K</given-names></name>, <name><surname>Schaeffer</surname><given-names>L</given-names></name>, <name><surname>Wold</surname><given-names>B</given-names></name> (<year>2008</year>) <article-title>Mapping and quantifying mammalian transcriptomes by RNA-Seq</article-title>. <source>Nat Methods</source><volume>5</volume>: <fpage>621</fpage>–<lpage>628</lpage>.<pub-id pub-id-type="pmid">18516045</pub-id></mixed-citation></ref><ref id="pcbi.1003326-Liang2"><label>99</label><mixed-citation publication-type="journal"><name><surname>Liang</surname><given-names>K</given-names></name>, <name><surname>Keleş</surname><given-names>S</given-names></name> (<year>2012</year>) <article-title>Normalization of ChIP-seq data with control</article-title>. <source>BMC Bioinformatics</source><volume>13</volume>: <fpage>199</fpage>.<pub-id pub-id-type="pmid">22883957</pub-id></mixed-citation></ref></ref-list></back></pmc></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Asie/explor/AustralieFrV1/Data/Pmc/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002860 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Pmc/Corpus/biblio.hfd -nk 002860 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Asie
|area= AustralieFrV1
|flux= Pmc
|étape= Corpus
|type= RBID
|clé=
|texte=
}}
| This area was generated with Dilib version V0.6.33. |  |