{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T06:51:07Z","timestamp":1776322267692,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1008050","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T00:00:00Z","timestamp":1596067200000}}],"reference-count":61,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2020,7,20]],"date-time":"2020-07-20T00:00:00Z","timestamp":1595203200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1008050","type":"journal-article","created":{"date-parts":[[2020,7,20]],"date-time":"2020-07-20T13:33:36Z","timestamp":1595252016000},"page":"e1008050","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":214,"title":["Cross-species regulatory sequence activity prediction"],"prefix":"10.1371","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7782-3548","authenticated-orcid":true,"given":"David R.","family":"Kelley","sequence":"first","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2020,7,20]]},"reference":[{"issue":"7","key":"pcbi.1008050.ref001","doi-asserted-by":"crossref","first-page":"e1003711","DOI":"10.1371\/journal.pcbi.1003711","article-title":"Enhanced regulatory sequence prediction using gapped k-mer features","volume":"10","author":"M Ghandi","year":"2014","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1008050.ref002","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1038\/nbt.3300","article-title":"Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning","volume":"33","author":"B Alipanahi","year":"2015","journal-title":"Nature Biotechnology"},{"key":"pcbi.1008050.ref003","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1038\/ng.3331","article-title":"A method to predict the impact of regulatory variants from DNA sequence","volume":"47","author":"D Lee","year":"2015","journal-title":"Nature Genetics"},{"issue":"7","key":"pcbi.1008050.ref004","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1101\/gr.200535.115","article-title":"Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks","volume":"26","author":"DR Kelley","year":"2016","journal-title":"Genome research"},{"issue":"5","key":"pcbi.1008050.ref005","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1101\/gr.227819.117","article-title":"Sequential regulatory activity prediction across chromosomes with convolutional neural networks","volume":"28","author":"DR Kelley","year":"2018","journal-title":"Genome Research"},{"issue":"10","key":"pcbi.1008050.ref006","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1038\/nmeth.3547","article-title":"Predicting effects of noncoding variants with deep learning\u2013based sequence model","volume":"12","author":"J Zhou","year":"2015","journal-title":"Nature methods"},{"key":"pcbi.1008050.ref007","first-page":"1","article-title":"Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk","volume":"464","author":"J Zhou","year":"2018","journal-title":"Nature Genetics"},{"issue":"10","key":"pcbi.1008050.ref008","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.1038\/s41588-018-0196-7","article-title":"Detecting genome-wide directional effects of transcription factor binding on polygenic disease risk","volume":"50","author":"YA Reshef","year":"2018","journal-title":"Nature genetics"},{"issue":"7","key":"pcbi.1008050.ref009","doi-asserted-by":"crossref","first-page":"107663","DOI":"10.1016\/j.celrep.2020.107663","article-title":"Predicting mRNA abundance directly from genomic sequence using deep convolutional neural networks","volume":"31","author":"V Agarwal","year":"2020","journal-title":"Cell Reports"},{"issue":"3","key":"pcbi.1008050.ref010","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1038\/nbt.2137","article-title":"Systematic dissection and optimization of inducible enhancers in human cells using a massively parallel reporter assay","volume":"30","author":"A Melnikov","year":"2012","journal-title":"Nature Biotechnology"},{"issue":"6","key":"pcbi.1008050.ref011","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1038\/nbt.2205","article-title":"Inferring gene regulatory logic from high-throughput measurements of thousands of systematically designed promoters","volume":"30","author":"E Sharon","year":"2012","journal-title":"Nature biotechnology"},{"issue":"3","key":"pcbi.1008050.ref012","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1038\/nbt.2136","article-title":"Massively parallel functional dissection of mammalian enhancers in vivo","volume":"30","author":"RP Patwardhan","year":"2012","journal-title":"Nature biotechnology"},{"issue":"47","key":"pcbi.1008050.ref013","doi-asserted-by":"crossref","first-page":"19498","DOI":"10.1073\/pnas.1210678109","article-title":"Complex effects of nucleotide variants in a mammalian cis-regulatory element","volume":"109","author":"JC Kwasnieski","year":"2012","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"3","key":"pcbi.1008050.ref014","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1016\/j.cell.2015.09.054","article-title":"Learning the Sequence Determinants of Alternative Splicing from Millions of Random Sequences","volume":"163","author":"AB Rosenberg","year":"2015","journal-title":"Cell"},{"issue":"5900","key":"pcbi.1008050.ref015","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1126\/science.1160930","article-title":"Species-Specific Transcription in Mice Carrying Human Chromosome 21","volume":"322","author":"MD Wilson","year":"2008","journal-title":"Science"},{"issue":"4","key":"pcbi.1008050.ref016","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1038\/nrg3481","article-title":"Evolution of transcription factor binding in metazoans\u2014mechanisms and functional implications","volume":"15","author":"D Villar","year":"2014","journal-title":"Nature Reviews Genetics"},{"issue":"4","key":"pcbi.1008050.ref017","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1016\/j.cell.2018.01.029","article-title":"The Human Transcription Factors","volume":"172","author":"SA Lambert","year":"2018","journal-title":"Cell"},{"issue":"10","key":"pcbi.1008050.ref018","doi-asserted-by":"crossref","first-page":"e1006484","DOI":"10.1371\/journal.pcbi.1006484","article-title":"Prediction of gene regulatory enhancers across species reveals evolutionarily conserved sequence properties","volume":"14","author":"L Chen","year":"2018","journal-title":"PLoS computational biology"},{"key":"pcbi.1008050.ref019","article-title":"Enhancer Identification using Transfer and Adversarial Deep Learning of DNA Sequences","author":"D Cohn","year":"2018","journal-title":"bioRxiv"},{"issue":"7527","key":"pcbi.1008050.ref020","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1038\/nature13992","article-title":"A comparative encyclopedia of DNA elements in the mouse genome","volume":"515","author":"F Yue","year":"2014","journal-title":"Nature"},{"key":"pcbi.1008050.ref021","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"7414","key":"pcbi.1008050.ref022","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":"EP Consortium","year":"2012","journal-title":"Nature"},{"issue":"7539","key":"pcbi.1008050.ref023","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/nature14248","article-title":"Integrative analysis of 111 reference human epigenomes","volume":"518","author":"A Kundaje","year":"2015","journal-title":"Nature"},{"issue":"7493","key":"pcbi.1008050.ref024","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1038\/nature13182","article-title":"A promoter-level mammalian expression atlas","volume":"507","author":"AR Forrest","year":"2014","journal-title":"Nature"},{"issue":"5","key":"pcbi.1008050.ref025","doi-asserted-by":"crossref","first-page":"1309","DOI":"10.1016\/j.cell.2018.06.052","article-title":"A single-cell atlas of in vivo mammalian chromatin accessibility","volume":"174","author":"DA Cusanovich","year":"2018","journal-title":"Cell"},{"key":"pcbi.1008050.ref026","article-title":"Index and biological spectrum of accessible DNA elements in the human genome","author":"W Meuleman","year":"2019","journal-title":"BioRxiv"},{"key":"pcbi.1008050.ref027","doi-asserted-by":"crossref","first-page":"e04837","DOI":"10.7554\/eLife.04837","article-title":"Conservation of transcription factor binding specificities across 600 million years of bilateria evolution","volume":"4","author":"KR Nitta","year":"2015","journal-title":"Elife"},{"issue":"14","key":"pcbi.1008050.ref028","doi-asserted-by":"crossref","first-page":"3425","DOI":"10.3390\/ijms20143425","article-title":"Cross-Cell-Type Prediction of TF-Binding Site by Integrating Convolutional Neural Network and Adversarial Network","volume":"20","author":"G Lan","year":"2019","journal-title":"International journal of molecular sciences"},{"issue":"7675","key":"pcbi.1008050.ref029","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1038\/nature24277","article-title":"Genetic effects on gene expression across human tissues","volume":"550","author":"G Consortium","year":"2017","journal-title":"Nature"},{"issue":"4","key":"pcbi.1008050.ref030","doi-asserted-by":"crossref","first-page":"e2001069","DOI":"10.1371\/journal.pbio.2001069","article-title":"Transcriptional regulatory logic of the diurnal cycle in the mouse liver","volume":"15","author":"JA Sobel","year":"2017","journal-title":"PLoS biology"},{"issue":"458","key":"pcbi.1008050.ref031","doi-asserted-by":"crossref","DOI":"10.1126\/scitranslmed.aat8806","article-title":"A database of tissue-specific rhythmically expressed human genes has potential applications in circadian medicine","volume":"10","author":"MD Ruben","year":"2018","journal-title":"Science Translational Medicine"},{"issue":"D1","key":"pcbi.1008050.ref032","doi-asserted-by":"crossref","first-page":"D1062","DOI":"10.1093\/nar\/gkx1153","article-title":"ClinVar: improving access to variant interpretations and supporting evidence","volume":"46","author":"MJ Landrum","year":"2018","journal-title":"Nucleic acids research"},{"issue":"6","key":"pcbi.1008050.ref033","first-page":"577","article-title":"Human gene mutation database (HGMD): 2003 update","volume":"21","author":"PD Stenson","year":"2003","journal-title":"Human mutation"},{"key":"pcbi.1008050.ref034","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"issue":"7307","key":"pcbi.1008050.ref035","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1038\/nature09266","article-title":"From noncoding variant to phenotype via SORT1 at the 1p13 cholesterol locus","volume":"466","author":"K Musunuru","year":"2010","journal-title":"Nature"},{"key":"pcbi.1008050.ref036","article-title":"Improving the informativeness of Mendelian disease pathogenicity scores for common disease","author":"SS Kim","year":"2020","journal-title":"bioRxiv"},{"key":"pcbi.1008050.ref037","article-title":"A simple new approach to variable selection in regression, with application to genetic fine-mapping","author":"G Wang","year":"2018","journal-title":"bioRxiv"},{"issue":"7571","key":"pcbi.1008050.ref038","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1038\/nature15393","article-title":"A global reference for human genetic variation","volume":"526","author":"GP Consortium","year":"2015","journal-title":"Nature"},{"issue":"2","key":"pcbi.1008050.ref039","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.devcel.2010.01.011","article-title":"Organogenesis and development of the liver","volume":"18","author":"K Si-Tayeb","year":"2010","journal-title":"Developmental cell"},{"issue":"52","key":"pcbi.1008050.ref040","doi-asserted-by":"crossref","first-page":"E12305","DOI":"10.1073\/pnas.1816411115","article-title":"Nuclear receptor HNF4A transrepresses CLOCK: BMAL1 and modulates tissue-specific circadian networks","volume":"115","author":"M Qu","year":"2018","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"1","key":"pcbi.1008050.ref041","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.cell.2015.01.036","article-title":"A century of cholesterol and coronaries: from plaques to genes to statins","volume":"161","author":"JL Goldstein","year":"2015","journal-title":"Cell"},{"issue":"2","key":"pcbi.1008050.ref042","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.neuron.2010.10.006","article-title":"The Simons Simplex Collection: a resource for identification of autism genetic risk factors","volume":"68","author":"GD Fischbach","year":"2010","journal-title":"Neuron"},{"issue":"6420","key":"pcbi.1008050.ref043","doi-asserted-by":"crossref","first-page":"eaat6576","DOI":"10.1126\/science.aat6576","article-title":"Genome-wide de novo risk score implicates promoter variation in autism spectrum disorder","volume":"362","author":"JY An","year":"2018","journal-title":"Science"},{"issue":"6","key":"pcbi.1008050.ref044","doi-asserted-by":"crossref","first-page":"973","DOI":"10.1038\/s41588-019-0420-0","article-title":"Whole-genome deep-learning analysis identifies contribution of noncoding mutations to autism risk","volume":"51","author":"J Zhou","year":"2019","journal-title":"Nature genetics"},{"issue":"7809","key":"pcbi.1008050.ref045","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1038\/s41586-020-2308-7","article-title":"The mutational constraint spectrum quantified from variation in 141,456 humans","volume":"581","author":"KJ Karczewski","year":"2020","journal-title":"Nature"},{"issue":"7","key":"pcbi.1008050.ref046","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1016\/j.cell.2017.11.008","article-title":"YY1 is a structural regulator of enhancer-promoter loops","volume":"171","author":"AS Weintraub","year":"2017","journal-title":"Cell"},{"key":"pcbi.1008050.ref047","article-title":"Predicting 3D genome folding from DNA sequence","author":"G Fudenberg","year":"2019","journal-title":"bioRxiv"},{"issue":"12","key":"pcbi.1008050.ref048","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1038\/s41592-018-0214-9","article-title":"Found In Translation: a machine learning model for mouse-to-human inference","volume":"15","author":"R Normand","year":"2018","journal-title":"Nature methods"},{"issue":"12","key":"pcbi.1008050.ref049","doi-asserted-by":"crossref","first-page":"2077","DOI":"10.1101\/gr.174920.114","article-title":"Alignathon: a competitive assessment of whole-genome alignment methods","volume":"24","author":"D Earl","year":"2014","journal-title":"Genome research"},{"key":"pcbi.1008050.ref050","unstructured":"Kelley, David R. Basenji v0.3; 2019. https:\/\/github.com\/calico\/basenji."},{"issue":"17","key":"pcbi.1008050.ref051","doi-asserted-by":"crossref","first-page":"i884","DOI":"10.1093\/bioinformatics\/bty560","article-title":"fastp: an ultra-fast all-in-one FASTQ preprocessor","volume":"34","author":"S Chen","year":"2018","journal-title":"Bioinformatics"},{"issue":"14","key":"pcbi.1008050.ref052","doi-asserted-by":"crossref","first-page":"1754","DOI":"10.1093\/bioinformatics\/btp324","article-title":"Fast and accurate short read alignment with Burrows\u2013Wheeler transform","volume":"25","author":"H Li","year":"2009","journal-title":"Bioinformatics"},{"issue":"D1","key":"pcbi.1008050.ref053","doi-asserted-by":"crossref","first-page":"D794","DOI":"10.1093\/nar\/gkx1081","article-title":"The Encyclopedia of DNA elements (ENCODE): data portal update","volume":"46","author":"CA Davis","year":"2017","journal-title":"Nucleic acids research"},{"key":"pcbi.1008050.ref054","unstructured":"Smit A, Hubley R, Green P. RepeatMasker Open-4.0; 2015. http:\/\/www.repeatmasker.org."},{"issue":"15","key":"pcbi.1008050.ref055","doi-asserted-by":"crossref","first-page":"2144","DOI":"10.1093\/bioinformatics\/btr354","article-title":"False positive peaks in ChIP-seq and other sequencing-based functional assays caused by unannotated high copy number regions","volume":"27","author":"JK Pickrell","year":"2011","journal-title":"Bioinformatics"},{"issue":"20","key":"pcbi.1008050.ref056","first-page":"e120","article-title":"Umap and Bismap: quantifying genome and methylome mappability","volume":"46","author":"M Karimzadeh","year":"2018","journal-title":"Nucleic acids research"},{"key":"pcbi.1008050.ref057","unstructured":"Hendrycks D, Gimpel K. Gaussian Error Linear Units (GELUs). arXiv preprint arXiv:160608415. 2016;."},{"issue":"3","key":"pcbi.1008050.ref058","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.cell.2018.12.015","article-title":"Predicting splicing from primary sequence with deep learning","volume":"176","author":"K Jaganathan","year":"2019","journal-title":"Cell"},{"key":"pcbi.1008050.ref059","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, et al. Tensorflow: A system for large-scale machine learning. In: 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16); 2016. p. 265\u2013283."},{"issue":"1","key":"pcbi.1008050.ref060","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1101\/gr.809403","article-title":"Human\u2013mouse alignments with BLASTZ","volume":"13","author":"S Schwartz","year":"2003","journal-title":"Genome research"},{"issue":"3","key":"pcbi.1008050.ref061","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1038\/s41588-018-0062-7","article-title":"The human noncoding genome defined by genetic diversity","volume":"50","author":"J Di Iulio","year":"2018","journal-title":"Nature genetics"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1008050","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T00:00:00Z","timestamp":1596067200000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T19:04:37Z","timestamp":1596135877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008050"}},"subtitle":[],"editor":[{"given":"Jian","family":"Ma","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2020,7,20]]},"references-count":61,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2020,7,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1008050","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/660563","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,20]]}}}