{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:53:38Z","timestamp":1774893218731,"version":"3.50.1"},"reference-count":55,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2021,11,26]],"date-time":"2021-11-26T00:00:00Z","timestamp":1637884800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Israeli Council for Higher Education (CHE) via Data Science Research Center"},{"DOI":"10.13039\/501100005005","name":"Ben-Gurion University of the Negev","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005005","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,1,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>messenger RNA (mRNA) degradation plays critical roles in post-transcriptional gene regulation. A major component of mRNA degradation is determined by 3\u2032-UTR elements. Hence, researchers are interested in studying mRNA dynamics as a function of 3\u2032-UTR elements. A recent study measured the mRNA degradation dynamics of tens of thousands of 3\u2032-UTR sequences using a massively parallel reporter assay. However, the computational approach used to model mRNA degradation was based on a simplifying assumption of a linear degradation rate. Consequently, the underlying mechanism of 3\u2032-UTR elements is still not fully understood.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Here, we developed deep neural networks to predict mRNA degradation dynamics and interpreted the networks to identify regulatory elements in the 3\u2032-UTR and their positional effect. Given an input of a 110\u2009nt-long 3\u2032-UTR sequence and an initial mRNA level, the model predicts mRNA levels of eight consecutive time points. Our deep neural networks significantly improved prediction performance of mRNA degradation dynamics compared with extant methods for the task. Moreover, we demonstrated that models predicting the dynamics of two identical 3\u2032-UTR sequences, differing by their poly(A) tail, performed better than single-task models. On the interpretability front, by using Integrated Gradients, our convolutional neural networks (CNNs) models identified known and novel cis-regulatory sequence elements of mRNA degradation. By applying a novel systematic evaluation of model interpretability, we demonstrated that the recurrent neural network models are inferior to the CNN models in terms of interpretability and that random initialization ensemble improves both prediction and interoperability performance. Moreover, using a mutagenesis analysis, we newly discovered the positional effect of various 3\u2032-UTR elements.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>All the code developed through this study is available at github.com\/OrensteinLab\/DeepUTR\/.<\/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\/btab800","type":"journal-article","created":{"date-parts":[[2021,11,22]],"date-time":"2021-11-22T20:12:33Z","timestamp":1637611953000},"page":"1087-1101","source":"Crossref","is-referenced-by-count":6,"title":["Computational modeling of mRNA degradation dynamics using deep neural networks"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7113-0684","authenticated-orcid":false,"given":"Ofir","family":"Yaish","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Ben-Gurion University of the Negev , Beer-Sheva 8410501, Israel"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3583-3112","authenticated-orcid":false,"given":"Yaron","family":"Orenstein","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Ben-Gurion University of the Negev , Beer-Sheva 8410501, Israel"}]}],"member":"286","published-online":{"date-parts":[[2021,11,26]]},"reference":[{"key":"2023020108511958800_btab800-B1","doi-asserted-by":"crossref","first-page":"1466","DOI":"10.1093\/bioinformatics\/btx781","article-title":"DNCON2: improved protein contact prediction using two-level deep convolutional neural networks","volume":"34","author":"Adhikari","year":"2018","journal-title":"Bioinformatics"},{"key":"2023020108511958800_btab800-B2","first-page":"2623","author":"Akiba","year":"2019"},{"key":"2023020108511958800_btab800-B3","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":"Alipanahi","year":"2015","journal-title":"Nat. Biotechnol"},{"key":"2023020108511958800_btab800-B1240295","doi-asserted-by":"publisher","first-page":"2249","DOI":"10.1016\/j.csda.2007.08.015","article-title":"Empirical characterization of random forest variable importance measures","volume":"52","author":"Archer","year":"2008","journal-title":"Computational Statistics & Data Analysis"},{"key":"2023020108511958800_btab800-B4","first-page":"233","author":"Arpit","year":"2017"},{"key":"2023020108511958800_btab800-B5","doi-asserted-by":"crossref","first-page":"e0141287","DOI":"10.1371\/journal.pone.0141287","article-title":"Continuous distributed representation of biological sequences for deep proteomics and genomics","volume":"10","author":"Asgari","year":"2015","journal-title":"PLoS One"},{"key":"2023020108511958800_btab800-B6","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1038\/s41594-018-0091-z","article-title":"Analyses of mRNA structure dynamics identify embryonic gene regulatory programs","volume":"25","author":"Beaudoin","year":"2018","journal-title":"Nat. Struct. Mol. Biol"},{"key":"2023020108511958800_btab800-B7","doi-asserted-by":"crossref","first-page":"i638","DOI":"10.1093\/bioinformatics\/bty600","article-title":"A deep neural network approach for learning intrinsic protein\u2013RNA binding preferences","volume":"34","author":"Ben-Bassat","year":"2018","journal-title":"Bioinformatics"},{"key":"2023020108511958800_btab800-B8","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn"},{"key":"2023020108511958800_btab800-B9","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1002\/wrna.40","article-title":"Mechanisms of deadenylation-dependent decay","volume":"2","author":"Chen","year":"2011","journal-title":"Wiley Interdiscip. Rev. RNA"},{"key":"2023020108511958800_btab800-B10","author":"Chen","year":"2017"},{"key":"2023020108511958800_btab800-B11","author":"Cho","year":"2014"},{"key":"2023020108511958800_btab800-B12","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1080\/15476286.2016.1225645","article-title":"A position-specific 3\u2032 UTR sequence that accelerates mRNA decay","volume":"13","author":"Geissler","year":"2016","journal-title":"RNA Biol"},{"key":"2023020108511958800_btab800-B13","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1101\/gr.247494.118","article-title":"Deep neural networks for interpreting RNA-binding protein target preferences","volume":"30","author":"Ghanbari","year":"2020","journal-title":"Genome Res"},{"key":"2023020108511958800_btab800-B14","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1126\/science.aad8711","article-title":"Messenger RNA modifications: form, distribution, and function","volume":"352","author":"Gilbert","year":"2016","journal-title":"Science"},{"key":"2023020108511958800_btab800-B15","doi-asserted-by":"crossref","first-page":"i629","DOI":"10.1093\/bioinformatics\/bty575","article-title":"Discovering epistatic feature interactions from neural network models of regulatory DNA sequences","volume":"34","author":"Greenside","year":"2018","journal-title":"Bioinformatics"},{"key":"2023020108511958800_btab800-B16","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1038\/nrm.2017.91","article-title":"Codon optimality, bias and usage in translation and mRNA decay","volume":"19","author":"Hanson","year":"2018","journal-title":"Nat. Rev. Mol. Cell Biol"},{"key":"2023020108511958800_btab800-B17","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":"2023020108511958800_btab800-B18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-020-02055-7","article-title":"Enhanced Integrated Gradients: improving interpretability of deep learning models using splicing codes as a case study","volume":"21","author":"Jha","year":"2020","journal-title":"Genome Biol"},{"key":"2023020108511958800_btab800-B19","doi-asserted-by":"crossref","first-page":"e1000832","DOI":"10.1371\/journal.pcbi.1000832","article-title":"RNAcontext: a new method for learning the sequence and structure binding preferences of RNA-binding proteins","volume":"6","author":"Kazan","year":"2010","journal-title":"PLoS Comput. Biol"},{"key":"2023020108511958800_btab800-B20","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":"2023020108511958800_btab800-B21","doi-asserted-by":"crossref","first-page":"2605","DOI":"10.1093\/bioinformatics\/bty166","article-title":"DeepSol: a deep learning framework for sequence-based protein solubility prediction","volume":"34","author":"Khurana","year":"2018","journal-title":"Bioinformatics"},{"key":"2023020108511958800_btab800-B22","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.coisb.2020.04.001","article-title":"Deep learning for inferring transcription factor binding sites","volume":"19","author":"Koo","year":"2020","journal-title":"Curr. Opin. Syst. Biol"},{"key":"2023020108511958800_btab800-B23","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1038\/s42256-020-00291-x","article-title":"Improving representations of genomic sequence motifs in convolutional networks with exponential activations","volume":"3","author":"Koo","year":"2021","journal-title":"Nat. Mach. Intell"},{"key":"2023020108511958800_btab800-B24","first-page":"657437","year":"2019"},{"key":"2023020108511958800_btab800-B25","doi-asserted-by":"crossref","first-page":"e1008925","DOI":"10.1371\/journal.pcbi.1008925","article-title":"Global importance analysis: an interpretability method to quantify importance of genomic features in deep neural networks","volume":"17","author":"Koo","year":"2021","journal-title":"PLoS Comput. Biol"},{"key":"2023020108511958800_btab800-B26","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"2023020108511958800_btab800-B27","doi-asserted-by":"crossref","first-page":"i121","DOI":"10.1093\/bioinformatics\/btu277","article-title":"Deep learning of the tissue-regulated splicing code","volume":"30","author":"Leung","year":"2014","journal-title":"Bioinformatics"},{"key":"2023020108511958800_btab800-B28","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1186\/1748-7188-6-26","article-title":"ViennaRNA Package 2.0","volume":"6","author":"Lorenz","year":"2011","journal-title":"Algorithms Mol. Biol"},{"key":"2023020108511958800_btab800-B29","first-page":"4765","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017","journal-title":", pp."},{"key":"2023020108511958800_btab800-B30","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell"},{"key":"2023020108511958800_btab800-B31","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1146\/annurev-genet-120116-024704","article-title":"Regulation by 3\u2032-untranslated regions","volume":"51","author":"Mayr","year":"2017","journal-title":"Annu. Rev. Genet"},{"key":"2023020108511958800_btab800-B32","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1016\/j.molcel.2016.02.027","article-title":"Codon usage and 3\u2032 UTR length determine maternal mRNA stability in zebrafish","volume":"61","author":"Mishima","year":"2016","journal-title":"Mol. Cell"},{"key":"2023020108511958800_btab800-B33","author":"Novak","year":"2018"},{"key":"2023020108511958800_btab800-B34","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1186\/s12859-017-1561-8","article-title":"RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach","volume":"18","author":"Pan","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"2023020108511958800_btab800-B35","author":"Petti","year":"2021"},{"key":"2023020108511958800_btab800-B36","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1016\/j.cell.2007.12.038","article-title":"A combinatorial code for CPE-mediated translational control","volume":"132","author":"Piqu\u00e9","year":"2008","journal-title":"Cell"},{"key":"2023020108511958800_btab800-B37","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1016\/j.molcel.2017.11.014","article-title":"A massively parallel reporter assay of 3\u2032 UTR sequences identifies in vivo rules for mRNA degradation","volume":"68","author":"Rabani","year":"2017","journal-title":"Mol. Cell"},{"key":"2023020108511958800_btab800-B38","author":"Savinov","year":"2021"},{"key":"2023020108511958800_btab800-B39","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1038\/nrg3160","article-title":"Regulation of cytoplasmic mRNA decay","volume":"13","author":"Schoenberg","year":"2012","journal-title":"Nat. Rev. Genet"},{"key":"2023020108511958800_btab800-B40","author":"Shrikumar","year":"2017"},{"key":"2023020108511958800_btab800-B41","author":"Shrikumar","year":"2018"},{"key":"2023020108511958800_btab800-B42","author":"Sundararajan","year":"2017"},{"key":"2023020108511958800_btab800-B43","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.devcel.2006.10.005","article-title":"SMAUG is a major regulator of maternal mRNA destabilization in Drosophila and its translation is activated by the PAN GU kinase","volume":"12","author":"Tadros","year":"2007","journal-title":"Dev. Cell"},{"key":"2023020108511958800_btab800-B44","doi-asserted-by":"crossref","first-page":"2272","DOI":"10.1093\/bioinformatics\/btz921","article-title":"Logomaker: beautiful sequence logos in Python","volume":"36","author":"Tareen","year":"2020","journal-title":"Bioinformatics"},{"key":"2023020108511958800_btab800-B45","doi-asserted-by":"crossref","first-page":"R93","DOI":"10.1186\/gb-2010-11-9-r93","article-title":"Genome-wide analysis of mRNA decay patterns during early Drosophila development","volume":"11","author":"Thomsen","year":"2010","journal-title":"Genome Biol"},{"key":"2023020108511958800_btab800-B46","first-page":"267","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Stat. Soc. Ser. B (Methodological)"},{"key":"2023020108511958800_btab800-B47","author":"Tseng","year":"2020"},{"key":"2023020108511958800_btab800-B48","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.1101\/gr.245159.118","article-title":"Genome wide analysis of 3\u2032 UTR sequence elements and proteins regulating mRNA stability during maternal-to-zygotic transition in zebrafish","volume":"29","author":"Vejnar","year":"2019","journal-title":"Genome Res"},{"key":"2023020108511958800_btab800-B49","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.fsigen.2017.02.009","article-title":"DNA methylation-based forensic age prediction using artificial neural networks and next generation sequencing","volume":"28","author":"Vidaki","year":"2017","journal-title":"Forensic Sci. Int. Genet"},{"key":"2023020108511958800_btab800-B50","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1016\/0092-8674(91)90368-9","article-title":"RNA regulatory elements mediate control of Drosophila body pattern by the posterior morphogen nanos","volume":"67","author":"Wharton","year":"1991","journal-title":"Cell"},{"key":"2023020108511958800_btab800-B51","first-page":"271","volume-title":"Curr. Top. Dev. Biol","author":"Yang","year":"2015"},{"key":"2023020108511958800_btab800-B52","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1038\/nmeth.4121","article-title":"RESA identifies mRNA-regulatory sequences at high resolution","volume":"14","author":"Yartseva","year":"2017","journal-title":"Nat. Methods"},{"key":"2023020108511958800_btab800-B53","author":"Zhang","year":"2016"},{"key":"2023020108511958800_btab800-B54","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1038\/nmeth.3547","article-title":"Predicting effects of noncoding variants with deep learning-based sequence model","volume":"12","author":"Zhou","year":"2015","journal-title":"Nat. Methods"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab800\/41772781\/btab800.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/4\/1087\/49007662\/btab800.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/4\/1087\/49007662\/btab800.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T20:09:54Z","timestamp":1675282194000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/4\/1087\/6443108"}},"subtitle":[],"editor":[{"given":"Teresa","family":"Przytycka","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,11,26]]},"references-count":55,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,1,27]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab800","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,2,15]]},"published":{"date-parts":[[2021,11,26]]}}}