{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:23:39Z","timestamp":1791912219526,"version":"4.3.4"},"reference-count":52,"publisher":"Oxford University Press (OUP)","issue":"14","license":[{"start":{"date-parts":[[2019,7,8]],"date-time":"2019-07-08T00:00:00Z","timestamp":1562544000000},"content-version":"vor","delay-in-days":7,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1646333"],"award-info":[{"award-number":["IIS-1646333"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772197, 31671369, 31770775, 61872216, 61472205 and 81630103"],"award-info":[{"award-number":["61772197, 31671369, 31770775, 61872216, 61472205 and 81630103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFC0910404 and 2018YFC0910405"],"award-info":[{"award-number":["2018YFC0910404 and 2018YFC0910405"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,7,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Alternative splicing generates multiple isoforms from a single gene, greatly increasing the functional diversity of a genome. Although gene functions have been well studied, little is known about the specific functions of isoforms, making accurate prediction of isoform functions highly desirable. However, the existing approaches to predicting isoform functions are far from satisfactory due to at least two reasons: (i) unlike genes, isoform-level functional annotations are scarce. (ii) The information of isoform functions is concealed in various types of data including isoform sequences, co-expression relationship among isoforms, etc.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In this study, we present a novel approach, DIFFUSE (Deep learning-based prediction of IsoForm FUnctions from Sequences and Expression), to predict isoform functions. To integrate various types of data, our approach adopts a hybrid framework by first using a deep neural network (DNN) to predict the functions of isoforms from their genomic sequences and then refining the prediction using a conditional random field (CRF) based on co-expression relationship. To overcome the lack of isoform-level ground truth labels, we further propose an iterative semi-supervised learning algorithm to train both the DNN and CRF together. Our extensive computational experiments demonstrate that DIFFUSE could effectively predict the functions of isoforms and genes. It achieves an average area under the receiver operating characteristics curve of 0.840 and area under the precision\u2013recall curve of 0.581 over 4184 GO functional categories, which are significantly higher than the state-of-the-art methods. We further validate the prediction results by analyzing the correlation between functional similarity, sequence similarity, expression similarity and structural similarity, as well as the consistency between the predicted functions and some well-studied functional features of isoform sequences.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>https:\/\/github.com\/haochenucr\/DIFFUSE.<\/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\/btz367","type":"journal-article","created":{"date-parts":[[2019,5,9]],"date-time":"2019-05-09T19:21:53Z","timestamp":1557429713000},"page":"i284-i294","source":"Crossref","is-referenced-by-count":39,"title":["DIFFUSE: predicting isoform functions from sequences and expression profiles via deep learning"],"prefix":"10.1093","volume":"35","author":[{"given":"Hao","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Compute Science and Engineering, University of California, Riverside, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dipan","family":"Shaw","sequence":"additional","affiliation":[{"name":"Department of Compute Science and Engineering, University of California, Riverside, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyang","family":"Zeng","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongbo","family":"Bu","sequence":"additional","affiliation":[{"name":"Key Lab of Intelligent Information Process, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3833-4498","authenticated-orcid":false,"given":"Tao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Compute Science and Engineering, University of California, Riverside, CA, USA"},{"name":"Bioinformatics Division, BNRIST\/Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,7,5]]},"reference":[{"key":"2023062712363332000_btz367-B1","first-page":"265","article-title":"TensorFlow: a system for large-scale machine learning","volume":"16","author":"Abadi","year":"2016","journal-title":"OSDI"},{"key":"2023062712363332000_btz367-B2","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","article-title":"Gapped BLAST and PSI-BLAST: a new generation of protein database search programs","volume":"25","author":"Altschul","year":"1997","journal-title":"Nucleic Acids Res"},{"key":"2023062712363332000_btz367-B3","first-page":"943","author":"Andrews","year":"2002"},{"key":"2023062712363332000_btz367-B4","doi-asserted-by":"crossref","first-page":"13567","DOI":"10.1073\/pnas.240463497","article-title":"Zinc plays a key role in human and bacterial GTP cyclohydrolase I","volume":"97","author":"Auerbach","year":"2000","journal-title":"Proc. Natl. Acad. Sci"},{"key":"2023062712363332000_btz367-B5","doi-asserted-by":"crossref","first-page":"D154","DOI":"10.1093\/nar\/gki070","article-title":"The universal protein resource (UniProt)","volume":"33","author":"Bairoch","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2023062712363332000_btz367-B6","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"Bengio","year":"2003","journal-title":"J. Mach. Learn. Res"},{"key":"2023062712363332000_btz367-B7","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/978-1-4939-3167-5_2","volume-title":"Plant Bioinformatics","author":"Boutet","year":"2016"},{"key":"2023062712363332000_btz367-B8","doi-asserted-by":"crossref","first-page":"bav120","DOI":"10.1093\/database\/bav120","article-title":"The UniProtKB guide to the human proteome","volume":"2016","author":"Breuza","year":"2016","journal-title":"Database"},{"key":"2023062712363332000_btz367-B9","doi-asserted-by":"crossref","first-page":"2235","DOI":"10.1093\/bioinformatics\/btu144","article-title":"GOssTo: a stand-alone application and a web tool for calculating semantic similarities on the Gene Ontology","volume":"30","author":"Caniza","year":"2014","journal-title":"Bioinformatics"},{"key":"2023062712363332000_btz367-B10","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/S0378-1119(99)00435-7","article-title":"Alternative splicing regulates the production of ARD-1 endoribonuclease and NIPP-1, an inhibitor of protein phosphatase-1, as isoforms encoded by the same gene","volume":"240","author":"Chang","year":"1999","journal-title":"Gene"},{"key":"2023062712363332000_btz367-B11","doi-asserted-by":"crossref","first-page":"D258","DOI":"10.1093\/nar\/gkh036","article-title":"The Gene Ontology (GO) database and informatics resource","volume":"32","author":"Consortium","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2023062712363332000_btz367-B12","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1016\/j.jmb.2006.01.048","article-title":"Crystal structure of the N domain of human somatic angiotensin I-converting enzyme provides a structural basis for domain-specific inhibitor design","volume":"357","author":"Corradi","year":"2006","journal-title":"J. Mol. Biol"},{"key":"2023062712363332000_btz367-B13","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.bbrc.2009.07.106","article-title":"Subcellular localization of adenosine kinase in mammalian cells: the long isoform of AdK is localized in the nucleus","volume":"388","author":"Cui","year":"2009","journal-title":"Biochem. Biophys. Res. Commun"},{"key":"2023062712363332000_btz367-B14","doi-asserted-by":"crossref","first-page":"18507","DOI":"10.1074\/jbc.M601751200","article-title":"Identification and characterization of AIFsh2, a mitochondrial apoptosis-inducing factor (AIF) isoform with NADH oxidase activity","volume":"281","author":"Delettre","year":"2006","journal-title":"J. Biol. Chem"},{"key":"2023062712363332000_btz367-B15","doi-asserted-by":"crossref","first-page":"2250","DOI":"10.1093\/bioinformatics\/btq402","article-title":"Fast overlapping of protein contact maps by alignment of eigenvectors","volume":"26","author":"Di Lena","year":"2010","journal-title":"Bioinformatics"},{"key":"2023062712363332000_btz367-B16","doi-asserted-by":"crossref","first-page":"e1003314.","DOI":"10.1371\/journal.pcbi.1003314","article-title":"Systematically differentiating functions for alternatively spliced isoforms through integrating RNA-seq data","volume":"9","author":"Eksi","year":"2013","journal-title":"PLoS Comput. Biol"},{"key":"2023062712363332000_btz367-B17","doi-asserted-by":"crossref","first-page":"884","DOI":"10.1016\/j.molcel.2012.05.037","article-title":"Tissue-specific alternative splicing remodels protein\u2013protein interaction networks","volume":"46","author":"Ellis","year":"2012","journal-title":"Mol. Cell"},{"key":"2023062712363332000_btz367-B18","first-page":"346","volume-title":"European Conference on Computer Vision","author":"He","year":"2014"},{"key":"2023062712363332000_btz367-B19","doi-asserted-by":"crossref","first-page":"D286","DOI":"10.1093\/nar\/gkv1248","article-title":"eggNOG 4.5: a hierarchical orthology framework with improved functional annotations for eukaryotic, prokaryotic and viral sequences","volume":"44","author":"Huerta-Cepas","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023062712363332000_btz367-B20","doi-asserted-by":"crossref","first-page":"D1057","DOI":"10.1093\/nar\/gku1113","article-title":"The GOA database: Gene Ontology annotation updates for 2015","volume":"43","author":"Huntley","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2023062712363332000_btz367-B21","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1002\/prot.22458","article-title":"Structure is three to ten times more conserved than sequence\u2014a study of structural response in protein cores","volume":"77","author":"Illerg\u00e5rd","year":"2009","journal-title":"Proteins"},{"key":"2023062712363332000_btz367-B22","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1093\/nar\/28.1.27","article-title":"KEGG: kyoto encyclopedia of genes and genomes","volume":"28","author":"Kanehisa","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2023062712363332000_btz367-B23","author":"Kingma","year":"2014"},{"key":"2023062712363332000_btz367-B24","author":"Kotikalapudi","year":"2017"},{"key":"2023062712363332000_btz367-B25","first-page":"109","author":"Kr\u00e4henb\u00fchl","year":"2011"},{"key":"2023062712363332000_btz367-B26","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1093\/bioinformatics\/btx624","article-title":"DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier","volume":"34","author":"Kulmanov","year":"2017","journal-title":"Bioinformatics"},{"key":"2023062712363332000_btz367-B27","doi-asserted-by":"crossref","first-page":"39.","DOI":"10.1186\/1471-2105-10-39","article-title":"Protein domain organisation: adding order","volume":"10","author":"Kummerfeld","year":"2009","journal-title":"BMC Bioinform"},{"key":"2023062712363332000_btz367-B28","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1142\/9789813207813_0025","volume-title":"Pacific Symposium on Biocomputing 2017","author":"Lanchantin","year":"2017"},{"key":"2023062712363332000_btz367-B29","doi-asserted-by":"crossref","first-page":"559.","DOI":"10.1186\/1471-2105-9-559","article-title":"WGCNA: an R package for weighted correlation network analysis","volume":"9","author":"Langfelder","year":"2008","journal-title":"BMC Bioinform"},{"key":"2023062712363332000_btz367-B30","doi-asserted-by":"crossref","first-page":"D19","DOI":"10.1093\/nar\/gkq1019","article-title":"The sequence read archive","volume":"39","author":"Leinonen","year":"2011","journal-title":"Nucleic Acids Res"},{"key":"2023062712363332000_btz367-B31","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1016\/j.tig.2014.05.005","article-title":"The emerging era of genomic data integration for analyzing splice isoform function","volume":"30","author":"Li","year":"2014","journal-title":"Trends Genet"},{"key":"2023062712363332000_btz367-B32","doi-asserted-by":"crossref","first-page":"e39","DOI":"10.1093\/nar\/gkt1362","article-title":"High-resolution functional annotation of human transcriptome: predicting isoform functions by a novel multiple instance-based label propagation method","volume":"42","author":"Li","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023062712363332000_btz367-B33","first-page":"1024","article-title":"A proteogenomic approach to understand splice isoform functions through sequence and expression-based computational modeling","volume":"17","author":"Li","year":"2016","journal-title":"Briefings Bioinform"},{"key":"2023062712363332000_btz367-B34","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1145\/3097983.3097984","volume-title":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Luo","year":"2017"},{"key":"2023062712363332000_btz367-B35","doi-asserted-by":"crossref","first-page":"D222","DOI":"10.1093\/nar\/gku1221","article-title":"CDD: NCBI\u2019s conserved domain database","volume":"43","author":"Marchler-Bauer","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2023062712363332000_btz367-B36","doi-asserted-by":"crossref","first-page":"S4.","DOI":"10.1186\/gb-2008-9-s1-s4","article-title":"GeneMANIA: a real-time multiple association network integration algorithm for predicting gene function","volume":"9","author":"Mostafavi","year":"2008","journal-title":"Genome Biol"},{"key":"2023062712363332000_btz367-B37","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1002\/prot.23175","article-title":"RaptorX: exploiting structure information for protein alignment by statistical inference","volume":"79","author":"Peng","year":"2011","journal-title":"Proteins"},{"key":"2023062712363332000_btz367-B38","doi-asserted-by":"crossref","first-page":"D130","DOI":"10.1093\/nar\/gkr1079","article-title":"NCBI Reference Sequences (RefSeq): current status, new features and genome annotation policy","volume":"40","author":"Pruitt","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023062712363332000_btz367-B39","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1111\/j.1742-4658.2007.05635.x","article-title":"Tissue expression and biochemical characterization of human 2-amino 3-carboxymuconate 6-semialdehyde decarboxylase, a key enzyme in tryptophan catabolism","volume":"274","author":"Pucci","year":"2007","journal-title":"FEBS J"},{"key":"2023062712363332000_btz367-B40","author":"Shaw","year":"2018"},{"key":"2023062712363332000_btz367-B41","author":"Simonyan","year":"2013"},{"key":"2023062712363332000_btz367-B42","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res"},{"key":"2023062712363332000_btz367-B43","first-page":"bby047","article-title":"Exploring the functional impact of alternative splicing on human protein isoforms using available annotation sources","author":"Sulakhe","year":"2018","journal-title":"Brief. Bioinform"},{"key":"2023062712363332000_btz367-B44","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1561\/2200000013","article-title":"An introduction to conditional random fields","volume":"4","author":"Sutton","year":"2012","journal-title":"Found. Trends Mach. Learn"},{"key":"2023062712363332000_btz367-B45","doi-asserted-by":"crossref","first-page":"R75.","DOI":"10.1186\/gb-2004-5-10-r75","article-title":"Alternative splicing of mouse transcription factors affects their DNA-binding domain architecture and is tissue specific","volume":"5","author":"Taneri","year":"2004","journal-title":"Genome Biol"},{"key":"2023062712363332000_btz367-B46","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1093\/nar\/28.1.33","article-title":"The COG database: a tool for genome-scale analysis of protein functions and evolution","volume":"28","author":"Tatusov","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2023062712363332000_btz367-B47","doi-asserted-by":"crossref","first-page":"470.","DOI":"10.1038\/nature07509","article-title":"Alternative isoform regulation in human tissue transcriptomes","volume":"456","author":"Wang","year":"2008","journal-title":"Nature"},{"key":"2023062712363332000_btz367-B48","doi-asserted-by":"crossref","first-page":"e1005324.","DOI":"10.1371\/journal.pcbi.1005324","article-title":"Accurate de novo prediction of protein contact map by ultra-deep learning model","volume":"13","author":"Wang","year":"2017","journal-title":"PLoS Comput. Biol"},{"key":"2023062712363332000_btz367-B49","doi-asserted-by":"crossref","first-page":"3593","DOI":"10.1093\/bioinformatics\/btw513","article-title":"SDEAP: a splice graph based differential transcript expression analysis tool for population data","volume":"32","author":"Yang","year":"2016","journal-title":"Bioinformatics"},{"key":"2023062712363332000_btz367-B50","doi-asserted-by":"crossref","first-page":"i234","DOI":"10.1093\/bioinformatics\/btx247","article-title":"TITER: predicting translation initiation sites by deep learning","volume":"33","author":"Zhang","year":"2017","journal-title":"Bioinformatics"},{"key":"2023062712363332000_btz367-B51","first-page":"1529","author":"Zheng","year":"2015"},{"key":"2023062712363332000_btz367-B52","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1145\/279232.279236","article-title":"Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization","volume":"23","author":"Zhu","year":"1997","journal-title":"ACM Trans. Math. Softw"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/14\/i284\/50721450\/bioinformatics_35_14_i284.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/14\/i284\/50721450\/bioinformatics_35_14_i284.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T12:37:38Z","timestamp":1687869458000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/14\/i284\/5529254"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":52,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2019,7,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btz367","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,7]]},"published":{"date-parts":[[2019,7]]}}}