{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:58:21Z","timestamp":1764784701227,"version":"3.37.3"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"24","license":[{"start":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T00:00:00Z","timestamp":1626739200000},"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872300","62031003"],"award-info":[{"award-number":["61872300","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":[[2021,12,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Alternative splicing creates the considerable proteomic diversity and complexity on relatively limited genome. Proteoforms translated from alternatively spliced isoforms of a gene actually execute the biological functions of this gene, which reflect the functional knowledge of genes at a finer granular level. Recently, some computational approaches have been proposed to differentiate isoform functions using sequence and expression data. However, their performance is far from being desirable, mainly due to the imbalance and lack of annotations at isoform-level, and the difficulty of modeling gene\u2013isoform relations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Result<\/jats:title><jats:p>We propose a deep multi-instance learning-based framework (DMIL-IsoFun) to differentiate the functions of isoforms. DMIL-IsoFun firstly introduces a multi-instance learning convolution neural network trained with isoform sequences and gene-level annotations to extract the feature vectors and initialize the annotations of isoforms, and then uses a class-imbalance Graph Convolution Network to refine the annotations of individual isoforms based on the isoform co-expression network and extracted features. Extensive experimental results show that DMIL-IsoFun improves the Smin and Fmax of state-of-the-art solutions by at least 29.6% and 40.8%. The effectiveness of DMIL-IsoFun is further confirmed on a testbed of human multiple-isoform genes, and maize isoforms related with photosynthesis.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>The code and data are available at http:\/\/www.sdu-idea.cn\/codes.php?name=DMIL-Isofun.<\/jats:p><\/jats:sec><jats:sec><jats:title>Supplementary information<\/jats:title><jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btab532","type":"journal-article","created":{"date-parts":[[2021,7,16]],"date-time":"2021-07-16T19:11:38Z","timestamp":1626462698000},"page":"4818-4825","source":"Crossref","is-referenced-by-count":15,"title":["DMIL-IsoFun: predicting isoform function using deep multi-instance learning"],"prefix":"10.1093","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1667-6705","authenticated-orcid":false,"given":"Guoxian","family":"Yu","sequence":"first","affiliation":[{"name":"School of Software, Shandong University , Jinan 250101, China"},{"name":"College of Computer and Information Sciences, Southwest University , Chongqing 400715, China"},{"name":"Computer, Electrical, and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology , Thuwal, Saudi Arabia"}]},{"given":"Guangjie","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University , Jinan 250101, China"},{"name":"College of Computer and Information Sciences, Southwest University , Chongqing 400715, China"}]},{"given":"Xiangliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer, Electrical, and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology , Thuwal, Saudi Arabia"}]},{"given":"Carlotta","family":"Domeniconi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, George Mason University , Fairfax, VA 22030, USA"}]},{"given":"Maozu","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture , Beijing, China"}]}],"member":"286","published-online":{"date-parts":[[2021,7,20]]},"reference":[{"key":"2023051607130838700_btab532-B1","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"Bengio","year":"2003","journal-title":"J. Mach. Learn. Res"},{"key":"2023051607130838700_btab532-B2","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":"2023051607130838700_btab532-B3","doi-asserted-by":"crossref","first-page":"i284","DOI":"10.1093\/bioinformatics\/btz367","article-title":"DIFFUSE: predicting isoform functions from sequences and expression profiles via deep learning","volume":"35","author":"Chen","year":"2019","journal-title":"Bioinformatics"},{"key":"2023051607130838700_btab532-B4","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4939-3743-1","volume-title":"The Gene Ontology Handbook","author":"Dessimoz","year":"2017"},{"key":"2023051607130838700_btab532-B5","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":"2023051607130838700_btab532-B6","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/S0168-9525(00)02176-4","article-title":"Alternative splicing: increasing diversity in the proteomic world","volume":"17","author":"Graveley","year":"2001","journal-title":"Trends Genet"},{"key":"2023051607130838700_btab532-B7","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.yjmcc.2017.01.002","article-title":"CaMKii\u03b4 subtypes differentially regulate infarct formation following ex vivo myocardial ischemia\/reperfusion through NF-\u03bab and TNF-\u03b1","volume":"103","author":"Gray","year":"2017","journal-title":"J. Mol. Cell. Cardiol"},{"key":"2023051607130838700_btab532-B8","doi-asserted-by":"crossref","first-page":"24722","DOI":"10.1074\/jbc.M001783200","article-title":"Overexpression of SERCA2b in the heart leads to an increase in sarcoplasmic reticulum calcium transport function and increased cardiac contractility","volume":"275","author":"Greene","year":"2000","journal-title":"J. Biol. Chem"},{"key":"2023051607130838700_btab532-B9","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"2023051607130838700_btab532-B10","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1186\/s13059-016-1037-6","article-title":"An expanded evaluation of protein function prediction methods shows an improvement in accuracy","volume":"17","author":"Jiang","year":"2016","journal-title":"Genome Biol"},{"key":"2023051607130838700_btab532-B11","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11103-004-7792-x","article-title":"Biochemical and molecular characterization of photosystem i deficiency in the ncs6 mitochondrial mutant of maize","volume":"57","author":"Jiao","year":"2005","journal-title":"Plant Mol. Biol"},{"key":"2023051607130838700_btab532-B12","article-title":"Semi-supervised classification with graph convolutional networks","volume":"pp. 1\u201310","author":"Kipf","year":"2017","journal-title":"in ICLR."},{"key":"2023051607130838700_btab532-B13","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 Bioinformatics"},{"key":"2023051607130838700_btab532-B14","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":"2023051607130838700_btab532-B15","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":"2023051607130838700_btab532-B16","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal loss for dense object detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"2023051607130838700_btab532-B17","first-page":"345","author":"Luo","year":"2017","journal-title":"ACM KDD"},{"key":"2023051607130838700_btab532-B18","doi-asserted-by":"crossref","first-page":"4873","DOI":"10.1093\/nar\/gkp471","article-title":"Stochastic noise in splicing machinery","volume":"37","author":"Melamud","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2023051607130838700_btab532-B19","doi-asserted-by":"crossref","first-page":"5541","DOI":"10.1021\/bi3007065","article-title":"Tailoring of membrane proteins by alternative splicing of pre-mrna","volume":"51","author":"Mittendorf","year":"2012","journal-title":"Biochemistry"},{"key":"2023051607130838700_btab532-B20","doi-asserted-by":"crossref","first-page":"e1002957","DOI":"10.1371\/journal.pcbi.1002957","article-title":"Functional knowledge transfer for high-accuracy prediction of under-studied biological processes","volume":"9","author":"Park","year":"2013","journal-title":"PLoS Comput. Biol"},{"key":"2023051607130838700_btab532-B21","doi-asserted-by":"crossref","first-page":"2535","DOI":"10.1093\/bioinformatics\/bty1017","article-title":"DeepIsoFun: a deep domain adaptation approach to predict isoform functions","volume":"35","author":"Shaw","year":"2019","journal-title":"Bioinformatics"},{"key":"2023051607130838700_btab532-B22","doi-asserted-by":"crossref","first-page":"1106","DOI":"10.1126\/science.aat1884","article-title":"Proteoforms as the next proteomics currency","volume":"359","author":"Smith","year":"2018","journal-title":"Science"},{"key":"2023051607130838700_btab532-B23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-016-1060-7","article-title":"A benchmark for RNA-seq quantification pipelines","volume":"17","author":"Teng","year":"2016","journal-title":"Genome Biol"},{"key":"2023051607130838700_btab532-B24","doi-asserted-by":"crossref","first-page":"838","DOI":"10.1161\/hh2101.098466","article-title":"Replacement of the muscle-specific sarcoplasmic reticulum ca2+-ATPase isoform serca2a by the nonmuscle SERCA2b homologue causes mild concentric hypertrophy and impairs contraction-relaxation of the heart","volume":"89","author":"Ver Heyen","year":"2001","journal-title":"Circ. Res"},{"key":"2023051607130838700_btab532-B25","doi-asserted-by":"crossref","first-page":"1864","DOI":"10.1093\/bioinformatics\/btz847","article-title":"Differentiating isoform functions with collaborative matrix factorization","volume":"36","author":"Wang","year":"2020","journal-title":"Bioinformatics"},{"key":"2023051607130838700_btab532-B26","doi-asserted-by":"crossref","first-page":"e28","DOI":"10.1161\/CIRCRESAHA.116.304682","article-title":"Mitochondrial reprogramming induced by caMKII mediates hypertrophy decompensation","volume":"116","author":"Westenbrink","year":"2015","journal-title":"Circ. Res"},{"key":"2023051607130838700_btab532-B27","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1016\/j.cell.2016.01.029","article-title":"Widespread expansion of protein interaction capabilities by alternative splicing","volume":"164","author":"Yang","year":"2016","journal-title":"Cell"},{"key":"2023051607130838700_btab532-B28","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1093\/bioinformatics\/btz535","article-title":"Isoform function prediction based on bi-random walks on a heterogeneous network","volume":"36","author":"Yu","year":"2020","journal-title":"Bioinformatics"},{"key":"2023051607130838700_btab532-B29","doi-asserted-by":"crossref","first-page":"2797","DOI":"10.1002\/int.22402","article-title":"Imbalance deep multi-instance learning for predicting isoform\u2013Cisoform interactions","volume":"36","author":"Yu","year":"2021","journal-title":"Int. J. Intell. Syst"},{"key":"2023051607130838700_btab532-B30","doi-asserted-by":"crossref","first-page":"400","DOI":"10.3389\/fgene.2020.00400","article-title":"A literature review of gene function prediction by modeling gene ontology","volume":"11","author":"Zhao","year":"2020","journal-title":"Front. Genet"},{"key":"2023051607130838700_btab532-B31","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1186\/s12859-020-03745-6","article-title":"Predicting functions of maize proteins using graph convolutional network","volume":"21","author":"Zhou","year":"2020","journal-title":"BMC Bioinformatics"},{"key":"2023051607130838700_btab532-B32","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1186\/s13059-019-1835-8","article-title":"The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens","volume":"20","author":"Zhou","year":"2019","journal-title":"Genome Biol"},{"key":"2023051607130838700_btab532-B33","doi-asserted-by":"crossref","first-page":"2291","DOI":"10.1016\/j.artint.2011.10.002","article-title":"Multi-instance multi-label learning","volume":"176","author":"Zhou","year":"2012","journal-title":"Artif. Intell"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab532\/40301521\/btab532.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/24\/4818\/50334724\/btab532.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/24\/4818\/50334724\/btab532.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T04:50:51Z","timestamp":1699246251000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/24\/4818\/6324304"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,7,20]]},"references-count":33,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2021,12,11]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab532","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2021,12,15]]},"published":{"date-parts":[[2021,7,20]]}}}