{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T11:41:39Z","timestamp":1684150899115},"reference-count":52,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2018,8,2]],"date-time":"2018-08-02T00:00:00Z","timestamp":1533168000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Federal Ministry of Education and Research in Germany","award":["01DP17005"],"award-info":[{"award-number":["01DP17005"]}]},{"name":"Cluster of Excellence on Multimodal Computing and Interaction","award":["EXC248"],"award-info":[{"award-number":["EXC248"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,2,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Modeling of Transcription Factor (TF) binding from both ChIP-seq and chromatin accessibility data has become prevalent in computational biology. Several models have been proposed to generate new hypotheses on transcriptional regulation. However, there is no distinct approach to derive TF binding scores from ChIP-seq and open chromatin experiments. Here, we review biases of various scoring approaches and their effects on the interpretation and reliability of predictive gene expression models.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We generated predictive models for gene expression using ChIP-seq and DNase1-seq data from DEEP and ENCODE. Via randomization experiments, we identified confounders in TF gene scores derived from both ChIP-seq and DNase1-seq data. We reviewed correction approaches for both data types, which reduced the influence of identified confounders without harm to model performance. Also, our analyses highlighted further quality control measures, in addition to model performance, that may help to assure model reliability and to avoid misinterpretation in future studies.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The software used in this study is available online at https:\/\/github.com\/SchulzLab\/TEPIC.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/bty674","type":"journal-article","created":{"date-parts":[[2018,8,2]],"date-time":"2018-08-02T12:11:27Z","timestamp":1533211887000},"page":"711-719","source":"Crossref","is-referenced-by-count":11,"title":["On the problem of confounders in modeling gene expression"],"prefix":"10.1093","volume":"35","author":[{"given":"Florian","family":"Schmidt","sequence":"first","affiliation":[{"name":"High-througput Genomics and Systems Biology, Cluster of Excellence on Multimodal Computing and Interaction, Saarland Informatics Campus, Saarbr\u00fccken, Germany"},{"name":"Department of Computational Biology and Applied Algorithmics, Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbr\u00fccken, Germany"},{"name":"Graduate School for Computer Science, Saarland Informatics Campus, Saarbr\u00fccken, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcel H","family":"Schulz","sequence":"additional","affiliation":[{"name":"High-througput Genomics and Systems Biology, Cluster of Excellence on Multimodal Computing and Interaction, Saarland Informatics Campus, Saarbr\u00fccken, Germany"},{"name":"Department of Computational Biology and Applied Algorithmics, Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbr\u00fccken, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2018,8,2]]},"reference":[{"key":"2023051511011793500_bty674-B1","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1038\/nbt.2153","article-title":"BLUEPRINT to decode the epigenetic signature written in blood","volume":"30","author":"Adams","year":"2012","journal-title":"Nat. Biotechnol"},{"key":"2023051511011793500_bty674-B2","doi-asserted-by":"crossref","first-page":"R166.","DOI":"10.1186\/gb-2008-9-11-r166","article-title":"Egr1 regulates the coordinated expression of numerous EGF receptor target genes as identified by ChIP-on-chip","volume":"9","author":"Arora","year":"2008","journal-title":"Genome Biol"},{"key":"2023051511011793500_bty674-B3","doi-asserted-by":"crossref","first-page":"e1005921.","DOI":"10.1371\/journal.pcbi.1005921","article-title":"Probing instructions for expression regulation in gene nucleotide compositions","volume":"14","author":"Bessiere","year":"2018","journal-title":"PLoS Comput. Biol"},{"key":"2023051511011793500_bty674-B4","doi-asserted-by":"crossref","first-page":"9103","DOI":"10.1073\/pnas.1408293111","article-title":"Structural and functional insight into TAF1-TAF7, a subcomplex of transcription factor II D","volume":"111","author":"Bhattacharya","year":"2014","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051511011793500_bty674-B5","doi-asserted-by":"crossref","first-page":"1828","DOI":"10.1111\/j.1471-4159.2006.04010.x","article-title":"The transcriptional repressor REST is a critical regulator of the neurosecretory phenotype","volume":"98","author":"Bruce","year":"2006","journal-title":"J. Neurochem"},{"key":"2023051511011793500_bty674-B6","doi-asserted-by":"crossref","DOI":"10.1186\/1756-8935-7-36","article-title":"Predicting expression: the complementary power of histone modification and transcription factor binding data","volume":"7","author":"Budden","year":"2014","journal-title":"Epigenet. Chromatin"},{"key":"2023051511011793500_bty674-B7","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1093\/bib\/bbu034","article-title":"Predictive modelling of gene expression from transcriptional regulatory elements","volume":"16","author":"Budden","year":"2015","journal-title":"Brief. Bioinform"},{"key":"2023051511011793500_bty674-B8","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1101\/gr.136838.111","article-title":"Understanding transcriptional regulation by integrative analysis of transcription factor binding data","volume":"22","author":"Cheng","year":"2012","journal-title":"Genome Res"},{"key":"2023051511011793500_bty674-B9","doi-asserted-by":"crossref","first-page":"S29.","DOI":"10.1186\/1471-2105-12-S1-S29","article-title":"Predicting gene expression in T cell differentiation from histone modifications and transcription factor binding affinities by linear mixture models","volume":"12","author":"Costa","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2023051511011793500_bty674-B10","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1093\/bioinformatics\/btr614","article-title":"Epigenetic priors for identifying active transcription factor binding sites","volume":"28","author":"Cuellar-Partida","year":"2012","journal-title":"Bioinformatics"},{"key":"2023051511011793500_bty674-B11","first-page":"9110","article-title":"Maps of context-dependent putative regulatory regions and genomic signal interactions","volume":"44","author":"Diamanti","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023051511011793500_bty674-B12","doi-asserted-by":"crossref","first-page":"Article 9.","DOI":"10.1515\/1544-6115.1750","article-title":"Normalization, bias correction, and peak calling for ChIP-seq","volume":"11","author":"Diaz","year":"2012","journal-title":"Stat. Appl. Genet. Mol. Biol"},{"key":"2023051511011793500_bty674-B13","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/nature11247","article-title":"An integrated encyclopedia of DNA elements in the human genome","volume":"489","author":"Dunham","year":"2012","journal-title":"Nature"},{"key":"2023051511011793500_bty674-B14","doi-asserted-by":"crossref","first-page":"1148","DOI":"10.1016\/j.immuni.2016.10.022","article-title":"Epigenomic profiling of human cd4+ t cells supports a linear differentiation model and highlights molecular regulators of memory development","volume":"45","author":"Durek","year":"2016","journal-title":"Immunity"},{"key":"2023051511011793500_bty674-B15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v033.i01","article-title":"Regularization paths for generalized linear models via coordinate descent","volume":"33","author":"Friedman","year":"2010","journal-title":"J. Stat. Software"},{"key":"2023051511011793500_bty674-B16","doi-asserted-by":"crossref","first-page":"11.","DOI":"10.1186\/1752-0509-1-11","article-title":"Reconstructing gene-regulatory networks from time series, knock-out data, and prior knowledge","volume":"1","author":"Geier","year":"2007","journal-title":"BMC Systems Biol"},{"key":"2023051511011793500_bty674-B17","doi-asserted-by":"crossref","first-page":"2941","DOI":"10.1101\/gad.1239304","article-title":"A role for E2F6 in distinguishing G1\/S- and G2\/M-specific transcription","volume":"18","author":"Giangrande","year":"2004","journal-title":"Genes Dev"},{"key":"2023051511011793500_bty674-B18","doi-asserted-by":"crossref","first-page":"9612","DOI":"10.1093\/nar\/gku648","article-title":"Architectural proteins CTCF and cohesin have distinct roles in modulating the higher order structure and expression of the CFTR locus","volume":"42","author":"Gosalia","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023051511011793500_bty674-B19","doi-asserted-by":"crossref","first-page":"2595","DOI":"10.1093\/bioinformatics\/btv153","article-title":"PRROC: computing and visualizing precision-recall and receiver operating characteristic curves in r","volume":"31","author":"Grau","year":"2015","journal-title":"Bioinformatics"},{"key":"2023051511011793500_bty674-B20","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1038\/nmeth.3772","article-title":"Analysis of computational footprinting methods for DNase sequencing experiments","volume":"13","author":"Gusmao","year":"2016","journal-title":"Nat. Methods"},{"key":"2023051511011793500_bty674-B21","volume-title":"Causality: Philosophical Theory Meets Scientific Practice","author":"Illari","year":"2014"},{"key":"2023051511011793500_bty674-B22","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1073\/pnas.78.1.143","article-title":"DNase I hypersensitive sites in Drosophila chromatin occur at the 5\u2019 ends of regions of transcription","volume":"78","author":"Keene","year":"1981","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051511011793500_bty674-B23","doi-asserted-by":"crossref","first-page":"2976","DOI":"10.1093\/nar\/gkt1249","article-title":"Systematic discovery and characterization of regulatory motifs in ENCODE TF binding experiments","volume":"42","author":"Kheradpour","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023051511011793500_bty674-B24","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1016\/j.cell.2006.12.048","article-title":"Analysis of the vertebrate insulator protein CTCF-binding sites in the human genome","volume":"128","author":"Kim","year":"2007","journal-title":"Cell"},{"key":"2023051511011793500_bty674-B25","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1198\/jasa.2011.ap09706","article-title":"A statistical framework for the analysis of ChIP-Seq data","volume":"106","author":"Kuan","year":"2011","journal-title":"J. Am. Stat. Assoc"},{"key":"2023051511011793500_bty674-B26","doi-asserted-by":"crossref","first-page":"D116","DOI":"10.1093\/nar\/gkv1249","article-title":"HOCOMOCO: expansion and enhancement of the collection of transcription factor binding sites models","volume":"44","author":"Kulakovskiy","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023051511011793500_bty674-B27","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/nature14248","article-title":"Integrative analysis of 111 reference human epigenomes","volume":"518","author":"Kundaje","year":"2015","journal-title":"Nature"},{"key":"2023051511011793500_bty674-B28","doi-asserted-by":"crossref","first-page":"S10.","DOI":"10.1186\/1471-2105-16-S5-S10","article-title":"Using epigenomics data to predict gene expression in lung cancer","volume":"16","author":"Li","year":"2015","journal-title":"BMC Bioinformatics"},{"key":"2023051511011793500_bty674-B29","doi-asserted-by":"crossref","first-page":"e1000039.","DOI":"10.1371\/journal.pcbi.1000039","article-title":"Statistical modeling of transcription factor binding affinities predicts regulatory interactions","volume":"4","author":"Manke","year":"2008","journal-title":"PLoS Comput. Biol"},{"key":"2023051511011793500_bty674-B30","doi-asserted-by":"crossref","first-page":"D110","DOI":"10.1093\/nar\/gkv1176","article-title":"JASPAR 2016: a major expansion and update of the open-access database of transcription factor binding profiles","volume":"44","author":"Mathelier","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023051511011793500_bty674-B31","doi-asserted-by":"crossref","first-page":"2789","DOI":"10.1093\/bioinformatics\/bts529","article-title":"Genome-wide in silico prediction of gene expression","volume":"28","author":"McLeay","year":"2012","journal-title":"Bioinformatics"},{"key":"2023051511011793500_bty674-B32","doi-asserted-by":"crossref","first-page":"637.","DOI":"10.1186\/s12864-016-2940-7","article-title":"Motif oriented high-resolution analysis of ChIP-seq data reveals the topological order of CTCF and cohesin proteins on DNA","volume":"17","author":"Nagy","year":"2016","journal-title":"BMC Genomics"},{"key":"2023051511011793500_bty674-B33","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1101\/gr.135129.111","article-title":"Predicting cell-type-specific gene expression from regions of open chromatin","volume":"22","author":"Natarajan","year":"2012","journal-title":"Genome Res"},{"key":"2023051511011793500_bty674-B34","doi-asserted-by":"crossref","first-page":"11000","DOI":"10.1093\/nar\/gku801","article-title":"Creating and validating cis-regulatory maps of tissue-specific gene expression regulation","volume":"42","author":"O'Connor","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023051511011793500_bty674-B35","doi-asserted-by":"crossref","first-page":"21521","DOI":"10.1073\/pnas.0904863106","article-title":"ChIP-Seq of transcription factors predicts absolute and differential gene expression in embryonic stem cells","volume":"106","author":"Ouyang","year":"2009","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051511011793500_bty674-B36","doi-asserted-by":"crossref","first-page":"e83506.","DOI":"10.1371\/journal.pone.0083506","article-title":"Widespread misinterpretable ChIP-seq bias in yeast","volume":"8","author":"Park","year":"2013","journal-title":"PLoS One"},{"key":"2023051511011793500_bty674-B37","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1101\/gr.112623.110","article-title":"Accurate inference of transcription factor binding from DNA sequence and chromatin accessibility data","volume":"21","author":"Pique-Regi","year":"2011","journal-title":"Genome Res"},{"key":"2023051511011793500_bty674-B38","doi-asserted-by":"crossref","first-page":"33.","DOI":"10.1186\/s13072-015-0028-2","article-title":"BIDCHIPS: bias decomposition and removal from ChIP-seq data clarifies true binding signal and its functional correlates","volume":"8","author":"Ramachandran","year":"2015","journal-title":"Epigenetics Chromatin"},{"key":"2023051511011793500_bty674-B39","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1093\/bioinformatics\/btl565","article-title":"Predicting transcription factor affinities to DNA from a biophysical model","volume":"23","author":"Roider","year":"2007","journal-title":"Bioinformatics"},{"key":"2023051511011793500_bty674-B40","doi-asserted-by":"crossref","first-page":"80.","DOI":"10.1186\/1741-7007-9-80","article-title":"Clustered ChIP-Seq-defined transcription factor binding sites and histone modifications map distinct classes of regulatory elements","volume":"9","author":"Rye","year":"2011","journal-title":"BMC Biol"},{"key":"2023051511011793500_bty674-B41","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1093\/nar\/gkw1061","article-title":"Combining transcription factor binding affinities with open-chromatin data for accurate gene expression prediction","volume":"45","author":"Schmidt","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2023051511011793500_bty674-B42","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1038\/35099076","article-title":"The ETS-domain transcription factor family","volume":"2","author":"Sharrocks","year":"2001","journal-title":"Nat. Rev. Mol. Cell Biol"},{"key":"2023051511011793500_bty674-B43","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1038\/nbt.2798","article-title":"Discovery of directional and nondirectional pioneer transcription factors by modeling DNase profile magnitude and shape","volume":"32","author":"Sherwood","year":"2014","journal-title":"Nat. Biotechnol"},{"key":"2023051511011793500_bty674-B44","doi-asserted-by":"crossref","first-page":"i639","DOI":"10.1093\/bioinformatics\/btw427","article-title":"DeepChrome: deep-learning for predicting gene expression from histone modifications","volume":"32","author":"Singh","year":"2016","journal-title":"Bioinformatics"},{"key":"2023051511011793500_bty674-B45","doi-asserted-by":"crossref","first-page":"1260419.","DOI":"10.1126\/science.1260419","article-title":"Proteomics. Tissue-based map of the human proteome","volume":"347","author":"Uhlen","year":"2015","journal-title":"Science"},{"key":"2023051511011793500_bty674-B46","doi-asserted-by":"crossref","first-page":"357.","DOI":"10.1186\/s12859-017-1766-x","article-title":"Correcting nucleotide-specific biases in high-throughput sequencing data","volume":"18","author":"Wang","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"2023051511011793500_bty674-B47","doi-asserted-by":"crossref","first-page":"2502","DOI":"10.1038\/nprot.2013.150","article-title":"Target analysis by integration of transcriptome and ChIP-seq data with BETA","volume":"8","author":"Wang","year":"2013","journal-title":"Nat. Protoc"},{"key":"2023051511011793500_bty674-B48","doi-asserted-by":"crossref","first-page":"R106","DOI":"10.1093\/hmg\/ddw208","article-title":"Proteomics to study DNA-bound and chromatin-associated gene regulatory complexes","volume":"25","author":"Wierer","year":"2016","journal-title":"Hum. Mol. Genet"},{"key":"2023051511011793500_bty674-B49","doi-asserted-by":"crossref","first-page":"2365","DOI":"10.1105\/tpc.16.00158","article-title":"EGRINs (Environmental Gene Regulatory Influence Networks) in rice that function in the response to water deficit, high temperature, and agricultural environments","volume":"28","author":"Wilkins","year":"2016","journal-title":"Plant Cell"},{"key":"2023051511011793500_bty674-B50","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1016\/j.cell.2013.07.034","article-title":"Transcription factor binding in human cells occurs in dense clusters formed around cohesin anchor sites","volume":"154","author":"Yan","year":"2013","journal-title":"Cell"},{"key":"2023051511011793500_bty674-B51","doi-asserted-by":"crossref","first-page":"11865","DOI":"10.1093\/nar\/gku810","article-title":"Explicit DNase sequence bias modeling enables high-resolution transcription factor footprint detection","volume":"42","author":"Yardimci","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023051511011793500_bty674-B52","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","year":"2005","journal-title":"J. R. Stat. Soc., Ser. B"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/4\/711\/50321730\/bioinformatics_35_4_711.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/4\/711\/50321730\/bioinformatics_35_4_711.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T11:03:34Z","timestamp":1684148614000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/4\/711\/5064106"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2018,8,2]]},"references-count":52,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,2,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty674","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,2,15]]},"published":{"date-parts":[[2018,8,2]]}}}