{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T18:50:54Z","timestamp":1768416654342,"version":"3.49.0"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"17","license":[{"start":{"date-parts":[[2018,9,9]],"date-time":"2018-09-09T00:00:00Z","timestamp":1536451200000},"content-version":"vor","delay-in-days":8,"URL":"https:\/\/academic.oup.com\/journals\/pages\/about_us\/legal\/notices"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF CAREER","award":["1453580"],"award-info":[{"award-number":["1453580"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Computational methods that predict differential gene expression from histone modification signals are highly desirable for understanding how histone modifications control the functional heterogeneity of cells through influencing differential gene regulation. Recent studies either failed to capture combinatorial effects on differential prediction or primarily only focused on cell type-specific analysis. In this paper we develop a novel attention-based deep learning architecture, DeepDiff, that provides a unified and end-to-end solution to model and to interpret how dependencies among histone modifications control the differential patterns of gene regulation. DeepDiff uses a hierarchy of multiple Long Short-Term Memory (LSTM) modules to encode the spatial structure of input signals and to model how various histone modifications cooperate automatically. We introduce and train two levels of attention jointly with the target prediction, enabling DeepDiff to attend differentially to relevant modifications and to locate important genome positions for each modification. Additionally, DeepDiff introduces a novel deep-learning based multi-task formulation to use the cell-type-specific gene expression predictions as auxiliary tasks, encouraging richer feature embeddings in our primary task of differential expression prediction.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Using data from Roadmap Epigenomics Project (REMC) for ten different pairs of cell types, we show that DeepDiff significantly outperforms the state-of-the-art baselines for differential gene expression prediction. The learned attention weights are validated by observations from previous studies about how epigenetic mechanisms connect to differential gene expression.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Codes and results are available at deepchrome.org.<\/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\/bty612","type":"journal-article","created":{"date-parts":[[2018,7,14]],"date-time":"2018-07-14T11:45:03Z","timestamp":1531568703000},"page":"i891-i900","source":"Crossref","is-referenced-by-count":68,"title":["DeepDiff: DEEP-learning for predicting DIFFerential gene expression from histone modifications"],"prefix":"10.1093","volume":"34","author":[{"given":"Arshdeep","family":"Sekhon","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Virginia, Charlottesville, VA, USA"}]},{"given":"Ritambhara","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Virginia, Charlottesville, VA, USA"}]},{"given":"Yanjun","family":"Qi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Virginia, Charlottesville, VA, USA"}]}],"member":"286","published-online":{"date-parts":[[2018,9,8]]},"reference":[{"key":"2023061402421984500_bty612-B1","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1038\/cr.2011.22","article-title":"Regulation of chromatin by histone modifications","volume":"21","author":"Bannister","year":"2011","journal-title":"Cell Res."},{"key":"2023061402421984500_bty612-B2","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach. Learn."},{"key":"2023061402421984500_bty612-B3","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1093\/nar\/gkr752","article-title":"Modeling the relative relationship of transcription factor binding and histone modifications to gene expression levels in mouse embryonic stem cells","volume":"40","author":"Cheng","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"2023061402421984500_bty612-B4","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Advances in Neural Information Processing Systems, Proceeding NIPS'15 Proceedings of the 28th International Conference on Neural Information Processing Systems","author":"Chorowski","year":"2015"},{"key":"2023061402421984500_bty612-B5","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1038\/nrn755","article-title":"Control of goal-directed and stimulus-driven attention in the brain","volume":"3","author":"Corbetta","year":"2002","journal-title":"Nat. Rev. Neurosci."},{"key":"2023061402421984500_bty612-B6","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":"2023061402421984500_bty612-B7","doi-asserted-by":"crossref","first-page":"R53","DOI":"10.1186\/gb-2012-13-9-r53","article-title":"Modeling gene expression using chromatin features in various cellular contexts","volume":"13","author":"Dong","year":"2012","journal-title":"Genome Biol."},{"key":"2023061402421984500_bty612-B8","first-page":"0473","article-title":"Neural machine translation by jointly learning to align and translate","volume":"1409","author":"Dzmitry","year":"2014","journal-title":"arXiv Preprint arXiv"},{"key":"2023061402421984500_bty612-B9","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1038\/nature02625","article-title":"Epigenetics in human disease and prospects for epigenetic therapy","volume":"429","author":"Egger","year":"2004","journal-title":"Nature"},{"key":"2023061402421984500_bty612-B10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IJCNN.2013.6706954","article-title":"A neural network based algorithm for gene expression prediction from chromatin structure","volume-title":"The 2013 International Joint Conference on Neural Networks (IJCNN)","author":"Frasca","year":"2013"},{"key":"2023061402421984500_bty612-B11","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1038\/nature14252","article-title":"Conserved epigenomic signals in mice and humans reveal immune basis of Alzheimer\u2019s disease","volume":"518","author":"Gjoneska","year":"2015","journal-title":"Nature"},{"key":"2023061402421984500_bty612-B12","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1186\/s12864-016-2970-1","article-title":"The transposable element environment of human genes is associated with histone and expression changes in cancer","volume":"17","author":"Gr\u00e9goire","year":"2016","journal-title":"BMC Genomics"},{"key":"2023061402421984500_bty612-B13","first-page":"1735","article-title":"Dimensionality reduction by learning an invariant mapping","volume-title":"2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","author":"Hadsell","year":"2006"},{"key":"2023061402421984500_bty612-B14","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/978-3-319-14633-1_9","article-title":"Combinatorial roles of DNA methylation and histone modifications on gene expression","volume-title":"Some Current Advanced Researches on Information and Computer Science in Vietnam","author":"Ho","year":"2015"},{"key":"2023061402421984500_bty612-B15","first-page":"1735","volume-title":"Long Short-Term Memory","author":"Hochreiter","year":"1997"},{"key":"2023061402421984500_bty612-B16","article-title":"Ask, attend and answer: exploring question-guided spatial attention for visual question answering","volume-title":"ECCV","author":"Huijuan","year":"2016"},{"key":"2023061402421984500_bty612-B17","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Advances in Neural Information Processing Systems","author":"Ilya","year":"2014"},{"key":"2023061402421984500_bty612-B18","article-title":"Multiple Object Recognition with Visual Attention","author":"Jimmy","year":"2014"},{"key":"2023061402421984500_bty612-B19","doi-asserted-by":"crossref","first-page":"2926","DOI":"10.1073\/pnas.0909344107","article-title":"Histone modification levels are predictive for gene expression","volume":"107","author":"Karli\u0107","year":"2010","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023061402421984500_bty612-B20","first-page":"77","article-title":"Show, attend and tell: neural image caption generation with visual attention","volume-title":"ICML","author":"Xu","year":"2015"},{"key":"2023061402421984500_bty612-B21","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1101\/gr.5704207","article-title":"The landscape of histone modifications across 1% of the human genome in five human cell lines","volume":"17","author":"Koch","year":"2007","journal-title":"Genome Res."},{"key":"2023061402421984500_bty612-B22","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1023\/A:1008280620621","article-title":"Overcoming the myopia of inductive learning algorithms with relieff","volume":"7","author":"Kononenko","year":"1997","journal-title":"Appl. Intell."},{"key":"2023061402421984500_bty612-B23","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":"2023061402421984500_bty612-B24","first-page":"146","article-title":"Stochastic learning","volume-title":"Advanced Lectures on Machine Learning","author":"L\u00e9on","year":"2004"},{"key":"2023061402421984500_bty612-B25","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":"2023061402421984500_bty612-B26","article-title":"Describing videos by exploiting temporal structure","volume-title":"2015 IEEE International Conference on Computer Vision (ICCV)","author":"Li","year":"2015"},{"key":"2023061402421984500_bty612-B27","first-page":"1412","article-title":"Effective approaches to attention-based neural machine translation","volume-title":"Empirical Methods in Natural Language Processing (EMNLP)","author":"Minh-Thang","year":"2015"},{"key":"2023061402421984500_bty612-B28","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/B978-0-12-801564-3.00005-5","article-title":"Computational methods used in systems biology","volume-title":"Systems Biology in Toxicology and Environmental Health","author":"Meisner","year":"2015"},{"key":"2023061402421984500_bty612-B29","first-page":"952","article-title":"Constrained stochastic space search method for parameter estimation in biological networks","volume":"4","author":"Omony","year":"2014","journal-title":"Adam Method Stochastic Optim."},{"key":"2023061402421984500_bty612-B30","first-page":"2692","article-title":"Pointer networks","volume-title":"Advances in Neural Information Processing Systems","author":"Oriol","year":"2015"},{"key":"2023061402421984500_bty612-B31","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"2023061402421984500_bty612-B33","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":"2023061402421984500_bty612-B32","first-page":"6785","article-title":"Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems, Long Beach, CA, USA","author":"Singh","year":"2017"},{"key":"2023061402421984500_bty612-B34","first-page":"2204","article-title":"Recurrent models of visual attention","volume-title":"Advances in Neural Information Processing Systems","author":"Volodymyr","year":"2014"},{"key":"2023061402421984500_bty612-B35","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1038\/nri3173","article-title":"The molecular basis of the memory t cell response: differential gene expression and its epigenetic regulation","volume":"12","author":"Weng","year":"2012","journal-title":"Nat. Rev. Immunol."},{"key":"2023061402421984500_bty612-B36","first-page":"1480","volume-title":"Hierarchical Attention Networks for Document Classification","author":"Zichao","year":"2016"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/17\/i891\/50582639\/bioinformatics_34_17_i891.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/17\/i891\/50582639\/bioinformatics_34_17_i891.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T02:43:24Z","timestamp":1686710604000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/17\/i891\/5093224"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,1]]},"references-count":36,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2018,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty612","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,9,1]]},"published":{"date-parts":[[2018,9,1]]}}}