{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T10:38:58Z","timestamp":1783420738335,"version":"3.54.6"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"23","license":[{"start":{"date-parts":[[2021,7,13]],"date-time":"2021-07-13T00:00:00Z","timestamp":1626134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100007688","name":"American University of Beirut","doi-asserted-by":"publisher","award":["320154"],"award-info":[{"award-number":["320154"]}],"id":[{"id":"10.13039\/100007688","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007688","name":"American University of Beirut","doi-asserted-by":"publisher","award":["103487"],"award-info":[{"award-number":["103487"]}],"id":[{"id":"10.13039\/100007688","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005993","name":"National Council for Scientific Research","doi-asserted-by":"publisher","award":["103509"],"award-info":[{"award-number":["103509"]}],"id":[{"id":"10.13039\/501100005993","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Identifying histone tail modifications using ChIP-seq is commonly used in time-series experiments in development and disease. These assays, however, cover specific time-points leaving intermediate or early stages with missing information. Although several machine learning methods were developed to predict histone marks, none exploited the dependence that exists in time-series experiments between data generated at specific time-points to extrapolate these findings to time-points where data cannot be generated for lack or scarcity of materials (i.e. early developmental stages).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Here, we train a deep learning model named TempoMAGE, to predict the presence or absence of H3K27ac in open chromatin regions by integrating information from sequence, gene expression, chromatin accessibility and the estimated change in H3K27ac state from a reference time-point. We show that adding reference time-point information systematically improves the overall model\u2019s performance. In addition, sequence signatures extracted from our method were exclusive to the training dataset indicating that our model learned data-specific features. As an application, TempoMAGE was able to predict the activity of enhancers from pre-validated in-vivo dataset highlighting its ability to be used for functional annotation of putative enhancers.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>TempoMAGE is freely available through GitHub at https:\/\/github.com\/pkhoueiry\/TempoMAGE.<\/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\/btab513","type":"journal-article","created":{"date-parts":[[2021,7,9]],"date-time":"2021-07-09T19:15:27Z","timestamp":1625858127000},"page":"4336-4342","source":"Crossref","is-referenced-by-count":4,"title":["TempoMAGE: a deep learning framework that exploits the causal dependency between time-series data to predict histone marks in open chromatin regions at time-points with missing ChIP-seq datasets"],"prefix":"10.1093","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1624-9647","authenticated-orcid":false,"given":"Mohammad","family":"Hallal","sequence":"first","affiliation":[{"name":"Department of Biochemistry and Molecular Genetics, Faculty of Medicine, American University of Beirut , PO Box 11-0236 Beirut, Lebanon"},{"name":"Biomedical Engineering Program, American University of Beirut , PO Box 11-0236 Beirut, Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mariette","family":"Awad","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, American University of Beirut , PO Box 11-0236 Beirut, Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7643-3310","authenticated-orcid":false,"given":"Pierre","family":"Khoueiry","sequence":"additional","affiliation":[{"name":"Department of Biochemistry and Molecular Genetics, Faculty of Medicine, American University of Beirut , PO Box 11-0236 Beirut, Lebanon"},{"name":"Pillar Genomics Institute, Faculty of Medicine, American University of Beirut , PO Box 11-0236 Beirut, Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,7,13]]},"reference":[{"key":"2023061310544859800_btab513-B1","author":"Abadi","year":"2015"},{"key":"2023061310544859800_btab513-B2","doi-asserted-by":"crossref","first-page":"2493","DOI":"10.1093\/bioinformatics\/bth283","article-title":"Analyzing time series gene expression data","volume":"20","author":"Bar-Joseph","year":"2004","journal-title":"Bioinformatics"},{"key":"2023061310544859800_btab513-B3","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1089\/bio.2015.29031.hmm","article-title":"The Genotype-Tissue Expression (GTEx) Project","volume":"13","author":"Carithers","year":"2015","journal-title":"Biopreserv Biobank"},{"key":"2023061310544859800_btab513-B4","doi-asserted-by":"crossref","first-page":"S2","DOI":"10.1186\/s12863-015-0312-y","article-title":"Longitudinal analytical approaches to genetic data","volume":"17","author":"Chiu","year":"2016","journal-title":"BMC Genet"},{"key":"2023061310544859800_btab513-B5"},{"key":"2023061310544859800_btab513-B6","doi-asserted-by":"crossref","first-page":"e34081","DOI":"10.7554\/eLife.34081","article-title":"Tri-methylation of histone H3 lysine 4 facilitates gene expression in ageing cells","volume":"7","author":"Cruz","year":"2018","journal-title":"Elife"},{"key":"2023061310544859800_btab513-B7","first-page":"233","volume-title":"Proceedings of the 23rd International Conference on Machine learning \u2013 ICML \u201906","author":"Davis","year":"2006"},{"key":"2023061310544859800_btab513-B8","doi-asserted-by":"crossref","first-page":"e3742","DOI":"10.7717\/peerj.3742","article-title":"Predicting stimulation-dependent enhancer-promoter interactions fromv ChIP-Seq time course data","volume":"5","author":"Dzida","year":"2017","journal-title":"PeerJ"},{"key":"2023061310544859800_btab513-B9","doi-asserted-by":"crossref","first-page":"2478","DOI":"10.1038\/nprot.2017.124","article-title":"Chromatin-state discovery and genome annotation with ChromHMM","volume":"12","author":"Ernst","year":"2017","journal-title":"Nat. Protoc"},{"key":"2023061310544859800_btab513-B10","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/s13059-018-1485-2","article-title":"ChromTime: modeling spatio-temporaldynamics of chromatin marks","volume":"19","author":"Fiziev","year":"2018","journal-title":"Genome Biol"},{"key":"2023061310544859800_btab513-B11","doi-asserted-by":"crossref","first-page":"1707","DOI":"10.1080\/01431169508954507","article-title":"The effect of training set size and composition on artificial neural network classification","volume":"16","author":"Foody","year":"1995","journal-title":"Int. J. Remote Sens"},{"key":"2023061310544859800_btab513-B12","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1038\/s41586-020-2093-3","article-title":"An atlas of dynamic chromatin landscapes in mouse fetal development","volume":"583","author":"Gorkin","year":"2020","journal-title":"Nature"},{"key":"2023061310544859800_btab513-B13","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1038\/s41588-019-0424-9","article-title":"High-throughput single-cell ChIP-seq identifies heterogeneity of chromatin states in breast cancer","volume":"51","author":"Grosselin","year":"2019","journal-title":"Nat. Genet"},{"key":"2023061310544859800_btab513-B14","doi-asserted-by":"crossref","first-page":"R24","DOI":"10.1186\/gb-2007-8-2-r24","article-title":"Quantifying similarity between motifs","volume":"8","author":"Gupta","year":"2007","journal-title":"Genome Biol"},{"key":"2023061310544859800_btab513-B15","doi-asserted-by":"crossref","first-page":"760","DOI":"10.1038\/s41586-020-2536-x","article-title":"The changing mouse embryo transcriptome at whole tissue and single-cell resolution","volume":"583","author":"He","year":"2020","journal-title":"Nature"},{"key":"2023061310544859800_btab513-B16","doi-asserted-by":"crossref","first-page":"5461","DOI":"10.1523\/JNEUROSCI.4046-06.2007","article-title":"Zic1 and Zic3 regulate medial forebrain development through expansion of neuronal progenitors","volume":"27","author":"Inoue","year":"2007","journal-title":"J. Neurosci"},{"key":"2023061310544859800_btab513-B17","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":"Kelley","year":"2016","journal-title":"Genome Res"},{"key":"2023061310544859800_btab513-B18","doi-asserted-by":"crossref","first-page":"S93","DOI":"10.1002\/gepi.20479","article-title":"Use of longitudinal data in genetic studies in the genome-wide association studies era: summary of group 14","volume":"33","author":"Kerner","year":"2009","journal-title":"Genet. Epidemiol"},{"key":"2023061310544859800_btab513-B21","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1016\/j.cell.2020.09.056","article-title":"Chromatin potential identified by shared single-cell profiling of RNA and chromatin","volume":"183","author":"Ma","year":"2020","journal-title":"Cell"},{"key":"2023061310544859800_btab513-B22","doi-asserted-by":"crossref","first-page":"4638","DOI":"10.3390\/ijms21134638","article-title":"Acquisition of the midbrain dopaminergic neuronal identity","volume":"21","author":"Mesman","year":"2020","journal-title":"Int. J. Mol. Sci"},{"key":"2023061310544859800_btab513-B23","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1038\/nrg3458","article-title":"Enhancers: five essential questions","volume":"14","author":"Pennacchio","year":"2013","journal-title":"Nat. Rev. Genet"},{"key":"2023061310544859800_btab513-B24","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1080\/15476286.2016.1201618","article-title":"Single-cell RNA-sequencing: the future of genome biology is now","volume":"14","author":"Picelli","year":"2017","journal-title":"RNA Biol"},{"key":"2023061310544859800_btab513-B25","doi-asserted-by":"crossref","first-page":"e107","DOI":"10.1093\/nar\/gkw226","article-title":"DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences","volume":"44","author":"Quang","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023061310544859800_btab513-B26","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1515\/sagmb-2014-0074","article-title":"Spatio-temporal model for multiple ChIP-seq experiments","volume":"14","author":"Ranciati","year":"2015","journal-title":"Stat. Appl. Genet. Mol. Biol"},{"key":"2023061310544859800_btab513-B27","doi-asserted-by":"crossref","first-page":"205","DOI":"10.3390\/cells7110205","article-title":"The heterochromatin landscape in migrating cells and the importance of H3K27me3 for associated transcriptome alterations","volume":"7","author":"Segal","year":"2018","journal-title":". Cells"},{"key":"2023061310544859800_btab513-B28","doi-asserted-by":"crossref","first-page":"126","DOI":"10.4161\/nucl.19232","article-title":"Chromatin signatures of active enhancers","volume":"3","author":"Spicuglia","year":"2012","journal-title":"Nucleus"},{"key":"2023061310544859800_btab513-B30","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1038\/s42003-021-01756-4","article-title":"Annotation of chromatin states in 66 complete mouse epigenomes during development","volume":"4","author":"van der Velde","year":"2021","journal-title":"Commun. Biol"},{"key":"2023061310544859800_btab513-B31","doi-asserted-by":"crossref","first-page":"D88","DOI":"10.1093\/nar\/gkl822","article-title":"VISTA Enhancer Browser\u2013a database of tissue-specific human enhancers","volume":"35","author":"Visel","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"2023061310544859800_btab513-B32","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1093\/bioinformatics\/btx105","article-title":"BiRen: predicting enhancers with a deep-learning-based model using the DNA sequence alone","volume":"33","author":"Yang","year":"2017","journal-title":"Bioinformatics"},{"key":"2023061310544859800_btab513-B33","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1186\/s12864-019-5489-4","article-title":"DeepHistone: a deep learning approach to predicting histone modifications","volume":"20","author":"Yin","year":"2019","journal-title":"BMC Genomics"},{"key":"2023061310544859800_btab513-B34","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":"Zhou","year":"2015","journal-title":"Nat. Methods"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab513\/40365677\/btab513.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/23\/4336\/50579574\/btab513.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/23\/4336\/50579574\/btab513.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T10:55:55Z","timestamp":1686653755000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/23\/4336\/6320782"}},"subtitle":[],"editor":[{"given":"Tobias","family":"Marschall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,7,13]]},"references-count":31,"journal-issue":{"issue":"23","published-print":{"date-parts":[[2021,12,7]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab513","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,12,1]]},"published":{"date-parts":[[2021,7,13]]}}}