{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T03:29:31Z","timestamp":1768274971631,"version":"3.49.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T00:00:00Z","timestamp":1650931200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T00:00:00Z","timestamp":1650931200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Histone Mark Modifications (HMs) are crucial actors in gene regulation, as they actively remodel chromatin to modulate transcriptional activity: aberrant combinatorial patterns of HMs have been connected with several diseases, including cancer. HMs are, however, reversible modifications: understanding their role in disease would allow the design of \u2018epigenetic drugs\u2019 for specific, non-invasive treatments. Standard statistical techniques were not entirely successful in extracting representative features from raw HM signals over gene locations. On the other hand, deep learning approaches allow for effective automatic feature extraction, but at the expense of model interpretation.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Here, we propose ShallowChrome, a novel computational pipeline to model transcriptional regulation via HMs in both an accurate and interpretable way. We attain state-of-the-art results on the binary classification of gene transcriptional states over 56 cell-types from the REMC database, largely outperforming recent deep learning approaches. We interpret our models by extracting insightful gene-specific regulative patterns, and we analyse them for the specific case of the PAX5 gene over three differentiated blood cell lines. Finally, we compare the patterns we obtained with the characteristic emission patterns of ChromHMM, and show that ShallowChrome is able to coherently rank groups of chromatin states w.r.t. their transcriptional activity.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>In this work we demonstrate that it is possible to model HM-modulated gene expression regulation in a highly accurate, yet interpretable way. Our feature extraction algorithm leverages on data downstream the identification of enriched regions to retrieve gene-wise, statistically significant and dynamically located features for each HM. These features are highly predictive of gene transcriptional state, and allow for accurate modeling by computationally efficient logistic regression models. These models allow a direct inspection and a rigorous interpretation, helping to formulate quantifiable hypotheses.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12859-022-04687-x","type":"journal-article","created":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T10:03:38Z","timestamp":1650967418000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Accurate and highly interpretable prediction of gene expression from histone modifications"],"prefix":"10.1186","volume":"23","author":[{"given":"Fabrizio","family":"Frasca","sequence":"first","affiliation":[]},{"given":"Matteo","family":"Matteucci","sequence":"additional","affiliation":[]},{"given":"Michele","family":"Leone","sequence":"additional","affiliation":[]},{"given":"Marco J.","family":"Morelli","sequence":"additional","affiliation":[]},{"given":"Marco","family":"Masseroli","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,4,26]]},"reference":[{"issue":"1","key":"4687_CR1","first-page":"199","volume":"1","author":"T Phillips","year":"2008","unstructured":"Phillips T. Regulation of transcription and gene expression in eukaryotes. Nature Educ. 2008;1(1):199.","journal-title":"Nature Educ"},{"issue":"10","key":"4687_CR2","doi-asserted-by":"publisher","first-page":"1885","DOI":"10.1038\/emboj.2011.135","volume":"30","author":"B van Steensel","year":"2011","unstructured":"van Steensel B. Chromatin: constructing the big picture. EMBO J. 2011;30(10):1885\u201395.","journal-title":"EMBO J"},{"issue":"3","key":"4687_CR3","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1038\/cr.2011.22","volume":"21","author":"A Bannister","year":"2011","unstructured":"Bannister A, Kouzarides T. Regulation of chromatin by histone modifications. Cell Res. 2011;21(3):381\u201395. https:\/\/doi.org\/10.1038\/cr.2011.22.","journal-title":"Cell Res"},{"key":"4687_CR4","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.1038\/nature04048","volume":"436","author":"A Bannister","year":"2005","unstructured":"Bannister A, Kouzarides T. Reversing histone methylation. Nature. 2005;436:1103\u20136. https:\/\/doi.org\/10.1038\/nature04048.","journal-title":"Nature"},{"issue":"1","key":"4687_CR5","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1002\/bies.950140103","volume":"14","author":"EM Bradbury","year":"1992","unstructured":"Bradbury EM. Reversible histone modifications and the chromosome cell cycle. BioEssays. 1992;14(1):9\u201316. https:\/\/doi.org\/10.1002\/bies.950140103.","journal-title":"BioEssays"},{"key":"4687_CR6","doi-asserted-by":"publisher","first-page":"588","DOI":"10.3389\/fphar.2019.00588","volume":"10","author":"A Patnaik","year":"2019","unstructured":"Patnaik A. Drugs targeting epigenetic modifications and plausible therapeutic strategies against colorectal cancer. Front Pharmacol. 2019;10:588.","journal-title":"Front Pharmacol"},{"key":"4687_CR7","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/978-94-007-4525-4_13","volume":"61","author":"JL Miller","year":"2013","unstructured":"Miller JL, Grant PA. The role of DNA methylation and histone modifications in transcriptional regulation in humans. Subcell Biochem. 2013;61:289\u2013317. https:\/\/doi.org\/10.1007\/978-94-007-4525-4_13.","journal-title":"Subcell Biochem"},{"issue":"1","key":"4687_CR8","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.1038\/s41467-018-03538-9","volume":"9","author":"E Sodersten","year":"2018","unstructured":"Sodersten E, et al. A comprehensive map coupling histone modifications with gene regulation in adult dopaminergic and serotonergic neurons. Nat Commun. 2018;9(1):1226. https:\/\/doi.org\/10.1038\/s41467-018-03538-9.","journal-title":"Nat Commun"},{"issue":"Suppl 10","key":"4687_CR9","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1186\/s12864-018-5278-5","volume":"19","author":"L Zhang","year":"2018","unstructured":"Zhang L, et al. Revealing transcription factor and histone modification co-localization and dynamics across cell lines by integrating ChIP-seq and RNA-seq data. BMC Genomics. 2018;19(Suppl 10):914. https:\/\/doi.org\/10.1186\/s12864-018-5278-5.","journal-title":"BMC Genomics"},{"issue":"17","key":"4687_CR10","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1093\/bioinformatics\/btw427","volume":"32","author":"R Singh","year":"2016","unstructured":"Singh R, et al. DeepChrome: Deep-learning for predicting gene expression from histone modifications. Bioinformatics. 2016;32(17):639\u201348. https:\/\/doi.org\/10.1093\/bioinformatics\/btw427.","journal-title":"Bioinformatics"},{"key":"4687_CR11","doi-asserted-by":"publisher","first-page":"6785","DOI":"10.1101\/329334","volume":"30","author":"R Singh","year":"2017","unstructured":"Singh R, et al. Attend and predict: Understanding gene regulation by selective attention on chromatin. Adv Neural Inf Process Syst. 2017;30:6785\u201395. https:\/\/doi.org\/10.1101\/329334.","journal-title":"Adv Neural Inf Process Syst"},{"issue":"12","key":"4687_CR12","doi-asserted-by":"publisher","first-page":"2478","DOI":"10.1038\/nprot.2017.124","volume":"12","author":"J Ernst","year":"2017","unstructured":"Ernst J, Kellis M. Chromatin-state discovery and genome annotation with ChromHMM. Nat Protoc. 2017;12(12):2478\u201392. https:\/\/doi.org\/10.1038\/nprot.2017.124.","journal-title":"Nat Protoc"},{"key":"4687_CR13","doi-asserted-by":"publisher","first-page":"2926","DOI":"10.1073\/pnas.0909344107","volume":"107","author":"R Karlic","year":"2010","unstructured":"Karlic R, et al. Histone modification levels are predictive for gene expression. Proc Natl Acad Sci USA. 2010;107:2926\u201331. https:\/\/doi.org\/10.1073\/pnas.0909344107.","journal-title":"Proc Natl Acad Sci USA"},{"issue":"Suppl 1","key":"4687_CR14","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/1471-2105-12-S1-S29","volume":"12","author":"I Costa","year":"2011","unstructured":"Costa I, et al. Predicting gene expression in T cell differentiation from histone modifications and transcription factor binding affinities by linear mixture models. BMC Bioinformatics. 2011;12(Suppl 1):29. https:\/\/doi.org\/10.1186\/1471-2105-12-S1-S29.","journal-title":"BMC Bioinformatics"},{"issue":"2","key":"4687_CR15","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/gb-2011-12-2-r15","volume":"12","author":"C Cheng","year":"2016","unstructured":"Cheng C. A statistical framework for modeling gene expression using chromatin features and application to modENCODE datasets. Genome Biol. 2016;12(2):15. https:\/\/doi.org\/10.1186\/gb-2011-12-2-r15.","journal-title":"Genome Biol"},{"issue":"9","key":"4687_CR16","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/gb-2012-13-9-r53","volume":"13","author":"X Dong","year":"2012","unstructured":"Dong X, et al. Modeling gene expression using chromatin features in various cellular contexts. Genome Biol. 2012;13(9):53. https:\/\/doi.org\/10.1186\/gb-2012-13-9-r53.","journal-title":"Genome Biol"},{"issue":"17","key":"4687_CR17","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1093\/bioinformatics\/bty612","volume":"34","author":"A Sekhon","year":"2018","unstructured":"Sekhon A, et al. DeepDiff: DEEP-learning for predicting DIFFerential gene expression from histone modifications. Bioinformatics. 2018;34(17):891\u2013900. https:\/\/doi.org\/10.1093\/bioinformatics\/bty612.","journal-title":"Bioinformatics"},{"key":"4687_CR18","unstructured":"Bahdanau D, et al. Neural machine translation by jointly learning to align and translate. In International Conference on Learning Representations, 2015;1\u201315."},{"issue":"7539","key":"4687_CR19","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/nature14248","volume":"518","author":"A Kundaje","year":"2015","unstructured":"Kundaje A, et al. Integrative analysis of 111 reference human epigenomes. Nature. 2015;518(7539):317\u201330. https:\/\/doi.org\/10.1038\/nature14248.","journal-title":"Nature"},{"issue":"9","key":"4687_CR20","doi-asserted-by":"publisher","first-page":"1728","DOI":"10.1038\/nprot.2012.101","volume":"7","author":"J Feng","year":"2012","unstructured":"Feng J, et al. Identifying ChIP-seq enrichment using MACS. Nat Protoc. 2012;7(9):1728\u201340. https:\/\/doi.org\/10.1038\/nprot.2012.101.","journal-title":"Nat Protoc"},{"issue":"6","key":"4687_CR21","doi-asserted-by":"publisher","first-page":"996","DOI":"10.1101\/gr.229102","volume":"12","author":"W Kent","year":"2002","unstructured":"Kent W, et al. The human genome browser at UCSC. Genome Res. 2002;12(6):996\u20131006. https:\/\/doi.org\/10.1101\/gr.229102.","journal-title":"Genome Res"},{"issue":"10","key":"4687_CR22","doi-asserted-by":"publisher","first-page":"1411","DOI":"10.1002\/mc.22384","volume":"55","author":"A-Y Kim","year":"2015","unstructured":"Kim A-Y, et al. The TFG-TEC oncoprotein induces transcriptional activation of the human \u03b2-enolase gene via chromatin modification of the promoter region. Mol Carcinog. 2015;55(10):1411\u201323. https:\/\/doi.org\/10.1002\/mc.22384.","journal-title":"Mol Carcinog"},{"issue":"1","key":"4687_CR23","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1186\/s12864-017-4353-7","volume":"18","author":"A Sharifi-Zarchi","year":"2017","unstructured":"Sharifi-Zarchi A, et al. DNA methylation regulates discrimination of enhancers from promoters through a H3K4me1-H3K4me3 seesaw mechanism. BMC Genomics. 2017;18(1):964. https:\/\/doi.org\/10.1186\/s12864-017-4353-7.","journal-title":"BMC Genomics"},{"issue":"2","key":"4687_CR24","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/s0092-8674(02)00822-x","volume":"110","author":"S Lomvardas","year":"2002","unstructured":"Lomvardas S, Thanos D. Modifying gene expression programs by altering core promoter chromatin architecture. Cell. 2002;110(2):261\u201371. https:\/\/doi.org\/10.1016\/s0092-8674(02)00822-x.","journal-title":"Cell"},{"key":"4687_CR25","first-page":"4765","volume":"30","author":"SM Lundberg","year":"2017","unstructured":"Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4765\u201374.","journal-title":"Adv Neural Inf Process Syst"},{"key":"4687_CR26","first-page":"8676","volume":"31","author":"Y Lu","year":"2018","unstructured":"Lu Y, et al. DeepPINK: reproducible feature selection in deep neural networks. Adv Neural Inf Process Syst. 2018;31:8676\u201386.","journal-title":"Adv Neural Inf Process Syst"},{"issue":"10","key":"4687_CR27","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1038\/nbt1010-1045","volume":"28","author":"B Bernstein","year":"2010","unstructured":"Bernstein B, et al. The NIH Roadmap Epigenomics Mapping Consortium. Nat Biotechnol. 2010;28(10):1045\u20138. https:\/\/doi.org\/10.1038\/nbt1010-1045.","journal-title":"Nat Biotechnol"},{"issue":"12","key":"4687_CR28","doi-asserted-by":"publisher","first-page":"1881","DOI":"10.1093\/bioinformatics\/btv048","volume":"31","author":"M Masseroli","year":"2015","unstructured":"Masseroli M, et al. GenoMetric Query Language: a novel approach to large-scale genomic data management. Bioinformatics. 2015;31(12):1881\u20138. https:\/\/doi.org\/10.1093\/bioinformatics\/btv048.","journal-title":"Bioinformatics"},{"issue":"5","key":"4687_CR29","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1093\/bioinformatics\/bty688","volume":"35","author":"M Masseroli","year":"2019","unstructured":"Masseroli M, et al. Processing of big heterogeneous genomic datasets for tertiary analysis of Next Generation Sequencing data. Bioinformatics. 2019;35(5):729\u201336. https:\/\/doi.org\/10.1093\/bioinformatics\/bty688.","journal-title":"Bioinformatics"},{"issue":"5","key":"4687_CR30","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1038\/ni1454","volume":"8","author":"C Cobaleda","year":"2007","unstructured":"Cobaleda C, et al. Pax5 the guardian of B cell identity and function. Nat Immunol. 2007;8(5):463\u201370. https:\/\/doi.org\/10.1038\/ni1454.","journal-title":"Nat Immunol"},{"issue":"12","key":"4687_CR31","doi-asserted-by":"publisher","first-page":"8222","DOI":"10.4049\/jimmunol.178.12.8221-a","volume":"178","author":"M Fuxa","year":"2007","unstructured":"Fuxa M, Busslinger M. Reporter gene insertions reveal a strictly B lymphoid-specific expression pattern of Pax5 in support of its B cell identity function. J Immunol. 2007;178(12):8222\u20138. https:\/\/doi.org\/10.4049\/jimmunol.178.12.8221-a.","journal-title":"J Immunol"},{"issue":"1","key":"4687_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0092-8674(00)80599-1","volume":"98","author":"K Struhl","year":"1999","unstructured":"Struhl K. Fundamentally different logic of gene regulation in eukaryotes and prokaryotes. Cell. 1999;98(1):1\u20134. https:\/\/doi.org\/10.1016\/S0092-8674(00)80599-1.","journal-title":"Cell"},{"issue":"2","key":"4687_CR33","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1002\/hep.30211","volume":"69","author":"R Hlady","year":"2018","unstructured":"Hlady R, et al. Integrating the epigenome to identify novel drivers of hepatocellular carcinoma. Hepatology. 2018;69(2):639\u201352. https:\/\/doi.org\/10.1002\/hep.30211.","journal-title":"Hepatology"},{"issue":"3","key":"4687_CR34","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1038\/s41388-018-0450-6","volume":"38","author":"M Long","year":"2018","unstructured":"Long M, et al. The miR-96 and RAR\u03b3 signaling axis governs androgen signaling and prostate cancer progression. Oncogene. 2018;38(3):421\u201344. https:\/\/doi.org\/10.1038\/s41388-018-0450-6.","journal-title":"Oncogene"},{"issue":"1","key":"4687_CR35","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1530\/ey.16.5.7","volume":"51","author":"P Heyn","year":"2019","unstructured":"Heyn P, et al. Gain-of-function DNMT3A mutations cause microcephalic dwarfism and hypermethylation of Polycomb-regulated regions. Nat Genet. 2019;51(1):96\u2013105. https:\/\/doi.org\/10.1530\/ey.16.5.7.","journal-title":"Nat Genet"},{"issue":"7","key":"4687_CR36","doi-asserted-by":"publisher","first-page":"107663","DOI":"10.1016\/j.celrep.2020.107663","volume":"31","author":"V Agarwal","year":"2020","unstructured":"Agarwal V, Shendure J. Predicting mRNA abundance directly from genomic sequence using deep convolutional neural networks. Cell Rep. 2020;31(7):107663. https:\/\/doi.org\/10.1016\/j.celrep.2020.107663.","journal-title":"Cell Rep"},{"issue":"8","key":"4687_CR37","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1038\/s41588-018-0160-6","volume":"50","author":"J Zhou","year":"2018","unstructured":"Zhou J, et al. Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk. Nat Genet. 2018;50(8):1171\u20139. https:\/\/doi.org\/10.1038\/s41588-018-0160-6.","journal-title":"Nat Genet"},{"issue":"10","key":"4687_CR38","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1038\/s41592-021-01252-x","volume":"18","author":"\u017d Avsec","year":"2021","unstructured":"Avsec \u017d, et al. Effective gene expression prediction from sequence by integrating long-range interactions. Nat Meth. 2021;18(10):1196\u2013203. https:\/\/doi.org\/10.1038\/s41592-021-01252-x.","journal-title":"Nat Meth"},{"key":"4687_CR39","doi-asserted-by":"publisher","unstructured":"Zeng W, et al. Integrating distal and proximal information to predict gene expression via a densely connected convolutional neural network. Bioinformatics. 2019. https:\/\/doi.org\/10.1093\/bioinformatics\/btz562.","DOI":"10.1093\/bioinformatics\/btz562"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-022-04687-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-022-04687-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-022-04687-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T10:04:29Z","timestamp":1650967469000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-022-04687-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,26]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["4687"],"URL":"https:\/\/doi.org\/10.1186\/s12859-022-04687-x","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,26]]},"assertion":[{"value":"21 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable (public data).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to publish"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"151"}}