{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T21:12:04Z","timestamp":1762377124722,"version":"3.41.2"},"reference-count":49,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T00:00:00Z","timestamp":1649030400000},"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\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072380","62031003"],"award-info":[{"award-number":["62072380","62031003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Predicting differentially expressed genes (DEGs) from epigenetics signal data is the key to understand how epigenetics controls cell functional heterogeneity by gene regulation. This knowledge can help developing \u2018epigenetics drugs\u2019 for complex diseases like cancers. Most of existing machine learning-based methods suffer defects in prediction accuracy, interpretability or training speed. To address these problems, in this paper, we propose a Multiple Self-Attention model for predicting DEGs on Epigenetic data (Epi-MSA). Epi-MSA first uses convolutional neural networks for neighborhood bins information embedding, and then employs multiple self-attention encoders on different input epigenetics factors data to learn which locations of genes are important for predicting DEGs. Next it trains a soft attention module to pick out which epigenetics factors are significant. The attention mechanism makes the model interpretable, and the pure matrix operation of self-attention enables the model to be parallel calculated and speeds up the training. Experiments on datasets from the Roadmap Epigenome Project and BluePrint Data Analysis Portal (BDAP) show that the performance of Epi-MSA is better than existing competitive methods, and Epi-MSA also has a smaller standard deviation, which shows that Epi-MSA is effective and stable. In addition, Epi-MSA has a good interpretability, this is confirmed by referring its attention weight matrix with existing biological knowledge.<\/jats:p>","DOI":"10.1093\/bib\/bbac117","type":"journal-article","created":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T12:10:23Z","timestamp":1646914223000},"source":"Crossref","is-referenced-by-count":5,"title":["Differentially expressed genes prediction by multiple self-attention on epigenetics data"],"prefix":"10.1093","volume":"23","author":[{"given":"Zimo","family":"Huang","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan 250101, China"},{"name":"Joint SDU-NTU Centre for Artificial Intelligence Research, Shandong University, Jinan 250101, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"Joint SDU-NTU Centre for Artificial Intelligence Research, Shandong University, Jinan 250101, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongmin","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan 250101, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maozu","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,4,4]]},"reference":[{"issue":"2","key":"2022051813444375200_ref1","doi-asserted-by":"crossref","first-page":"76","DOI":"10.3390\/genes10020076","article-title":"From genotype to phenotype: through chromatin","volume":"10","author":"Romanowska","year":"2019","journal-title":"Gene"},{"issue":"3","key":"2022051813444375200_ref2","doi-asserted-by":"crossref","first-page":"267","DOI":"10.2217\/epi.11.22","article-title":"Epigenetics and lifestyle","volume":"3","author":"Alegr\u00eda-Torres","year":"2011","journal-title":"Epigenomics"},{"issue":"10","key":"2022051813444375200_ref3","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.1038\/nbt.1685","article-title":"Epigenetic modifications and human disease","volume":"28","author":"Portela","year":"2010","journal-title":"Nat Biotechnol"},{"issue":"12","key":"2022051813444375200_ref4","doi-asserted-by":"crossref","first-page":"1164","DOI":"10.1080\/15592294.2019.1640546","article-title":"Epidrugs: targeting epigenetic marks in cancer treatment","volume":"14","author":"Furtado","year":"2019","journal-title":"Epigenetics"},{"issue":"10","key":"2022051813444375200_ref5","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1038\/s41580-019-0159-6","article-title":"The diverse roles of dna methylation in mammalian development and disease","volume":"20","author":"Greenberg","year":"2019","journal-title":"Nat Rev Mol Cell Biol"},{"key":"2022051813444375200_ref6","first-page":"1","volume-title":"Histone Mutations and Cancer","author":"Zhang","year":"2021"},{"issue":"4","key":"2022051813444375200_ref7","doi-asserted-by":"crossref","first-page":"e322","DOI":"10.1038\/emm.2017.10","article-title":"Dna methylation: an epigenetic mark of cellular memory","volume":"49","author":"Kim","year":"2017","journal-title":"Exp Mol Med"},{"issue":"7643","key":"2022051813444375200_ref8","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1038\/nature21373","article-title":"Intragenic DNA methylation prevents spurious transcription initiation","volume":"543","author":"Neri","year":"2017","journal-title":"Nature"},{"issue":"4","key":"2022051813444375200_ref9","doi-asserted-by":"crossref","first-page":"462","DOI":"10.18632\/oncotarget.497","article-title":"On the presence and role of human gene-body dna methylation","volume":"3","author":"Jjingo","year":"2012","journal-title":"Oncotarget"},{"issue":"16","key":"2022051813444375200_ref10","doi-asserted-by":"crossref","first-page":"2360","DOI":"10.1093\/bioinformatics\/btu316","article-title":"A systems-level integrative framework for genome-wide DNA methylation and gene expression data identifies differential gene expression modules under epigenetic control","volume":"30","author":"Jiao","year":"2014","journal-title":"Bioinformatics"},{"issue":"4","key":"2022051813444375200_ref11","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1016\/j.cell.2007.02.005","article-title":"Chromatin modifications and their function","volume":"128","author":"Kouzarides","year":"2007","journal-title":"Cell"},{"issue":"1","key":"2022051813444375200_ref12","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1152\/japplphysiol.00979.2010","article-title":"Histone modifications and exercise adaptations","volume":"110","author":"McGee","year":"2011","journal-title":"J Appl Physiol"},{"issue":"3","key":"2022051813444375200_ref13","first-page":"441","article-title":"Features that define the best chip-seq peak calling algorithms","volume":"18","author":"Thomas","year":"2017","journal-title":"Brief Bioinform"},{"issue":"3","key":"2022051813444375200_ref14","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1093\/bib\/bbz030","article-title":"Shaping the nebulous enhancer in the era of high-throughput assays and genome editing","volume":"21","author":"Ho","year":"2020","journal-title":"Brief Bioinform"},{"issue":"7153","key":"2022051813444375200_ref15","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1038\/nature06008","article-title":"Genome-wide maps of chromatin state in pluripotent and lineage-committed cells","volume":"448","author":"Mikkelsen","year":"2007","journal-title":"Nature"},{"issue":"5","key":"2022051813444375200_ref16","article-title":"Deciphering the genetic code of DNA methylation","volume":"22","author":"Mengchi Wang","year":"2021","journal-title":"Brief Bioinform"},{"issue":"5","key":"2022051813444375200_ref17","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1093\/bib\/bbq018","article-title":"Next generation sequencing in functional genomics","volume":"11","author":"Werner","year":"2010","journal-title":"Brief Bioinform"},{"issue":"7539","key":"2022051813444375200_ref18","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"},{"issue":"17","key":"2022051813444375200_ref19","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":"2022051813444375200_ref20","first-page":"6785","volume-title":"Advances in Neural Information Processing Systems","author":"Singh","year":"2017"},{"issue":"17","key":"2022051813444375200_ref21","doi-asserted-by":"crossref","first-page":"i891","DOI":"10.1093\/bioinformatics\/bty612","article-title":"Deepdiff: deep-learning for predicting differential gene expression from histone modifications","volume":"34","author":"Sekhon","year":"2018","journal-title":"Bioinformatics"},{"key":"2022051813444375200_ref22","first-page":"2567","volume-title":"International Conference on Pattern Recognition","author":"Symeonidi","year":"2020"},{"issue":"7","key":"2022051813444375200_ref23","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"},{"issue":"1","key":"2022051813444375200_ref24","first-page":"1","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"},{"issue":"2","key":"2022051813444375200_ref25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/gb-2011-12-2-r15","article-title":"A statistical framework for modeling gene expression using chromatin features and application to modencode datasets","volume":"12","author":"Cheng","year":"2011","journal-title":"Genome Biol"},{"issue":"2","key":"2022051813444375200_ref26","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"},{"issue":"9","key":"2022051813444375200_ref27","doi-asserted-by":"crossref","first-page":"1","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"},{"issue":"5","key":"2022051813444375200_ref28","first-page":"1","article-title":"Using epigenomics data to predict gene expression in lung cancer","volume":"16","author":"Li","year":"2015","journal-title":"BMC Bioinformatics"},{"issue":"4","key":"2022051813444375200_ref29","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1080\/15592294.2018.1460034","article-title":"Robust prediction of gene regulation in colorectal cancer tissues from dna methylation profiles","volume":"13","author":"Klett","year":"2018","journal-title":"Epigenetics"},{"key":"2022051813444375200_ref30","first-page":"123","volume-title":"The National Foundation for Science and Technology Development (NAFOSTED) Conference on Information and Computer Science","author":"Ho","year":"2014"},{"key":"2022051813444375200_ref31","first-page":"2399","volume-title":"IEEE International Conference on Bioinformatics and Biomedicine","author":"Xu","year":"2019"},{"issue":"1A","key":"2022051813444375200_ref32","first-page":"A68","article-title":"The cancer genome atlas (tcga): an immeasurable source of knowledge","volume":"19","author":"Tomczak","year":"2015","journal-title":"Contemporary Oncol"},{"issue":"7414","key":"2022051813444375200_ref33","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":"ENCODE Project Consortium","year":"2012","journal-title":"Nature"},{"issue":"8","key":"2022051813444375200_ref34","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"2022051813444375200_ref35","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/978-1-0716-0826-5_3","volume-title":"Artificial Neural Networks","author":"Chicco","year":"2021"},{"key":"2022051813444375200_ref36","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"issue":"5","key":"2022051813444375200_ref37","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1016\/j.cels.2016.10.021","article-title":"The blueprint data analysis portal","volume":"3","author":"Fern\u00e1ndez","year":"2016","journal-title":"Cell Systems"},{"issue":"7","key":"2022051813444375200_ref38","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1038\/nmeth.1226","article-title":"Mapping and quantifying mammalian transcriptomes by RNA-seq","volume":"5","author":"Mortazavi","year":"2008","journal-title":"Nat Methods"},{"key":"2022051813444375200_ref39","first-page":"2980","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Lin","year":"2017"},{"volume-title":"International Conference on Learning Representations","year":"2015","author":"Kingma","key":"2022051813444375200_ref40"},{"issue":"1","key":"2022051813444375200_ref41","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"},{"issue":"7","key":"2022051813444375200_ref42","first-page":"1084","article-title":"Gata6 is essential for endoderm formation from human pluripotent stem cells","volume":"6","author":"Fisher","year":"2017","journal-title":"Biology Open"},{"issue":"3","key":"2022051813444375200_ref43","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1016\/j.cell.2012.12.033","article-title":"Genome-wide chromatin state transitions associated with developmental and environmental cues","volume":"152","author":"Zhu","year":"2013","journal-title":"Cell"},{"issue":"2","key":"2022051813444375200_ref44","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1038\/cr.2018.1","article-title":"Histone h3 lysine 4 monomethylation modulates long-range chromatin interactions at enhancers","volume":"28","author":"Yan","year":"2018","journal-title":"Cell Res"},{"issue":"1","key":"2022051813444375200_ref45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13578-020-0374-z","article-title":"H3k36me3, message from chromatin to DNA damage repair","volume":"10","author":"Sun","year":"2020","journal-title":"Cell Biosci"},{"issue":"7534","key":"2022051813444375200_ref46","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1038\/nature14192","article-title":"Function and information content of DNA methylation","volume":"517","author":"Sch\u00fcbeler","year":"2015","journal-title":"Nature"},{"issue":"6824","key":"2022051813444375200_ref47","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1038\/35065138","article-title":"Selective recognition of methylated lysine 9 on histone h3 by the hp1 chromo domain","volume":"410","author":"Bannister","year":"2001","journal-title":"Nature"},{"issue":"7330","key":"2022051813444375200_ref48","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1038\/nature09784","article-title":"The polycomb complex prc2 and its mark in life","volume":"469","author":"Margueron","year":"2011","journal-title":"Nature"},{"issue":"50","key":"2022051813444375200_ref49","doi-asserted-by":"crossref","first-page":"21931","DOI":"10.1073\/pnas.1016071107","article-title":"Histone h3k27ac separates active from poised enhancers and predicts developmental state","volume":"107","author":"Creyghton","year":"2010","journal-title":"Proc Natl Acad Sci"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/23\/3\/bbac117\/43745194\/bbac117.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/23\/3\/bbac117\/43745194\/bbac117.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,18]],"date-time":"2022-05-18T13:47:15Z","timestamp":1652881635000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbac117\/6563414"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,4]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,5,13]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbac117","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"type":"print","value":"1467-5463"},{"type":"electronic","value":"1477-4054"}],"subject":[],"published-other":{"date-parts":[[2022,5]]},"published":{"date-parts":[[2022,4,4]]},"article-number":"bbac117"}}