{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T15:22:07Z","timestamp":1776266527618,"version":"3.50.1"},"reference-count":41,"publisher":"Oxford University Press (OUP)","issue":"16","license":[{"start":{"date-parts":[[2021,2,18]],"date-time":"2021-02-18T00:00:00Z","timestamp":1613606400000},"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":["61902126"],"award-info":[{"award-number":["61902126"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003021","name":"East China University of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003021","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8,25]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>The discovery of cancer subtyping can help explore cancer pathogenesis, determine clinical actionability in treatment, and improve patients' survival rates. However, due to the diversity and complexity of multi-omics data, it is still challenging to develop integrated clustering algorithms for tumor molecular subtyping.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We propose Subtype-GAN, a deep adversarial learning approach based on the multiple-input multiple-output neural network to model the complex omics data accurately. With the latent variables extracted from the neural network, Subtype-GAN uses consensus clustering and the Gaussian Mixture model to identify tumor samples' molecular subtypes. Compared with other state-of-the-art subtyping approaches, Subtype-GAN achieved outstanding performance on the benchmark datasets consisting of \u223c4000 TCGA tumors from 10 types of cancer. We found that on the comparison dataset, the clustering scheme of Subtype-GAN is not always similar to that of the deep learning method AE but is identical to that of NEMO, MCCA, VAE and other excellent approaches. Finally, we applied Subtype-GAN to the BRCA dataset and automatically obtained the number of subtypes and the subtype labels of 1031 BRCA tumors. Through the detailed analysis, we found that the identified subtypes are clinically meaningful and show distinct patterns in the feature space, demonstrating the practicality of Subtype-GAN.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availabilityand implementation<\/jats:title><jats:p>The source codes, the clustering results of Subtype-GAN across the benchmark datasets are available at https:\/\/github.com\/haiyang1986\/Subtype-GAN.<\/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\/btab109","type":"journal-article","created":{"date-parts":[[2021,2,16]],"date-time":"2021-02-16T14:57:36Z","timestamp":1613487456000},"page":"2231-2237","source":"Crossref","is-referenced-by-count":138,"title":["Subtype-GAN: a deep learning approach for integrative cancer subtyping of multi-omics data"],"prefix":"10.1093","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1161-4337","authenticated-orcid":false,"given":"Hai","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, East China University of Science and Technology , Shanghai 200237, China"}]},{"given":"Rui","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Molecular Physiology and Biophysics, Vanderbilt University , Nashville, 37240 TN, USA"},{"name":"Vanderbilt Genetics Institute, Vanderbilt University , Nashville, 37240 TN, USA"}]},{"given":"Dongdong","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, East China University of Science and Technology , Shanghai 200237, China"}]},{"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, East China University of Science and Technology , Shanghai 200237, China"}]}],"member":"286","published-online":{"date-parts":[[2021,2,18]]},"reference":[{"key":"2023051609122570200_btab109-B1","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.ccell.2017.07.007","article-title":"Integrated genomic characterization of pancreatic ductal adenocarcinoma","volume":"32","author":"Aguirre","year":"2017","journal-title":"Cancer Cell"},{"key":"2023051609122570200_btab109-B2","doi-asserted-by":"crossref","first-page":"1681","DOI":"10.1016\/j.cell.2015.05.044","article-title":"Genomic classification of cutaneous melanoma","volume":"161","author":"Akbani","year":"2015","journal-title":"Cell"},{"key":"2023051609122570200_btab109-B3","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/0022-2496(73)90012-6","article-title":"Multidimensional scaling of measures of distance between partitions","volume":"10","author":"Arabie","year":"1973","journal-title":"J. Math. Psychol"},{"key":"2023051609122570200_btab109-B4","doi-asserted-by":"crossref","first-page":"4415","DOI":"10.1158\/1078-0432.CCR-07-0122","article-title":"FOXA1 expression in breast cancer\u2013correlation with luminal subtype A and survival","volume":"13","author":"Badve","year":"2007","journal-title":"Clin Cancer Res"},{"key":"2023051609122570200_btab109-B5","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1016\/j.ccell.2018.03.014","article-title":"A comprehensive pan-cancer molecular study of gynecologic and breast cancers","volume":"33","author":"Berger","year":"2018","journal-title":"Cancer Cell"},{"key":"2023051609122570200_btab109-B6","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1038\/s41571-018-0002-6","article-title":"The emerging clinical relevance of genomics in cancer medicine","volume":"15","author":"Berger","year":"2018","journal-title":"Nat. Rev. Clin. Oncol"},{"key":"2023051609122570200_btab109-B24","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1038\/s41586-020-1969-6","article-title":"Pan-cancer analysis of whole genomes","volume":"578","journal-title":"Nature"},{"key":"2023051609122570200_btab109-B7","doi-asserted-by":"crossref","first-page":"1724","DOI":"10.1016\/j.ajpath.2016.02.023","article-title":"Genomic and epigenomic alterations in cancer","volume":"186","author":"Chakravarthi","year":"2016","journal-title":"Am. J. Pathol"},{"key":"2023051609122570200_btab109-B8","doi-asserted-by":"crossref","first-page":"1248","DOI":"10.1158\/1078-0432.CCR-17-0853","article-title":"Deep learning-based multi-omics integration robustly predicts survival in liver cancer","volume":"24","author":"Chaudhary","year":"2018","journal-title":"Clin Cancer Res"},{"key":"2023051609122570200_btab109-B9","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1093\/bioinformatics\/btz769","article-title":"Deep-learning approach to identifying cancer subtypes using high-dimensional genomic data","volume":"36","author":"Chen","year":"2020","journal-title":"Bioinformatics"},{"key":"2023051609122570200_btab109-B10","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1038\/nature13385","article-title":"Comprehensive molecular profiling of lung adenocarcinoma","volume":"511","author":"Collisson","year":"2014","journal-title":"Nature"},{"key":"2023051609122570200_btab109-B11","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1038\/nature12222","article-title":"Comprehensivemolecular characterization of clear cell renal cell carcinoma","volume":"499","author":"Creighton","year":"2013","journal-title":"Nature"},{"key":"2023051609122570200_btab109-B12","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1038\/bjc.2012.581","article-title":"Cancer heterogeneity: implications for targeted therapeutics","volume":"108","author":"Fisher","year":"2013","journal-title":"Br. J. Cancer"},{"key":"2023051609122570200_btab109-B13","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.cell.2013.03.002","article-title":"Lessons from the cancer genome","volume":"153","author":"Garraway","year":"2013","journal-title":"Cell"},{"key":"2023051609122570200_btab109-B14","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/nature12113","article-title":"Integrated genomic characterization of endometrial carcinoma","volume":"497","author":"Getz","year":"2013","journal-title":"Nature"},{"key":"2023051609122570200_btab109-B15","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014"},{"key":"2023051609122570200_btab109-B16","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.cell.2018.03.022","article-title":"Cell-of-origin patterns dominate the molecular classification of 10,000 tumors from 33 types of cancer","volume":"173","author":"Hoadley","year":"2018","journal-title":"Cell"},{"key":"2023051609122570200_btab109-B17","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1038\/nature08987","article-title":"International network of cancer genome projects","volume":"464","author":"Hudson","year":"2010","journal-title":"Nature"},{"key":"2023051609122570200_btab109-B18","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1186\/s12885-016-2195-3","article-title":"Prognostic value of ERBB4 expression in patients with triple negative breast cancer","volume":"16","author":"Kim","year":"2016","journal-title":"BMC Cancer"},{"key":"2023051609122570200_btab109-B19","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1093\/biostatistics\/kxx017","article-title":"A fully Bayesian latent variable model for integrative clustering analysis of multi-type omics data","volume":"19","author":"Mo","year":"2018","journal-title":"Biostatistics"},{"key":"2023051609122570200_btab109-B20","doi-asserted-by":"crossref","first-page":"4245","DOI":"10.1073\/pnas.1208949110","article-title":"Pattern discovery and cancer gene identification in integrated cancer genomic data","volume":"110","author":"Mo","year":"2013","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051609122570200_btab109-B21","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/A:1023949509487","article-title":"Consensus clustering: a resampling-based method for class discovery and visualization of gene expression microarray data","volume":"52","author":"Monti","year":"2003","journal-title":"Mach. Learn"},{"key":"2023051609122570200_btab109-B22","doi-asserted-by":"crossref","first-page":"2843","DOI":"10.1093\/bioinformatics\/bty1049","article-title":"PINSPlus: a tool for tumor subtype discovery in integrated genomic data","volume":"35","author":"Nguyen","year":"2019","journal-title":"Bioinformatics"},{"key":"2023051609122570200_btab109-B23","doi-asserted-by":"crossref","first-page":"2025","DOI":"10.1101\/gr.215129.116","article-title":"A novel approach for data integration and disease subtyping","volume":"27","author":"Nguyen","year":"2017","journal-title":"Genome Res"},{"key":"2023051609122570200_btab109-B25","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1186\/s13058-014-0429-3","article-title":"Trefoil factor 3 promotes metastatic seeding and predicts poor survival outcome of patients with mammary carcinoma","volume":"16","author":"Pandey","year":"2014","journal-title":"Breast Cancer Res"},{"key":"2023051609122570200_btab109-B26","doi-asserted-by":"crossref","first-page":"2231","DOI":"10.1158\/1078-0432.CCR-19-2184","article-title":"Surfactant expression defines an inflamed subtype of lung adenocarcinoma brain metastases that correlates with prolonged survival","volume":"26","author":"Pocha","year":"2020","journal-title":"Clin. Cancer Res"},{"key":"2023051609122570200_btab109-B27","doi-asserted-by":"crossref","first-page":"10546","DOI":"10.1093\/nar\/gky889","article-title":"Multi-omic and multi-view clustering algorithms: review and cancer benchmark","volume":"46","author":"Rappoport","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2023051609122570200_btab109-B28","doi-asserted-by":"crossref","first-page":"3348","DOI":"10.1093\/bioinformatics\/btz058","article-title":"NEMO: cancer subtyping by integration of partial multi-omic data","volume":"35","author":"Rappoport","year":"2019","journal-title":"Bioinformatics"},{"key":"2023051609122570200_btab109-B29","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1016\/j.cell.2018.07.036","article-title":"Comprehensive molecular characterization of muscle-invasive bladder cancer","volume":"174","author":"Robertson","year":"2018","journal-title":"Cell"},{"key":"2023051609122570200_btab109-B30","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.ccell.2017.12.013","article-title":"Integrative analysis identifies four molecular and clinical subsets in uveal melanoma","volume":"33","author":"Robertson","year":"2018","journal-title":"Cancer Cell"},{"key":"2023051609122570200_btab109-B31","doi-asserted-by":"crossref","first-page":"2906","DOI":"10.1093\/bioinformatics\/btp543","article-title":"Integrative clustering of multiple genomic data types using a joint latent variable model with application to breast and lung cancer subtype analysis","volume":"25","author":"Shen","year":"2009","journal-title":"Bioinformatics"},{"key":"2023051609122570200_btab109-B32","doi-asserted-by":"crossref","first-page":"i268","DOI":"10.1093\/bioinformatics\/btv244","article-title":"Integrating different data types by regularized unsupervised multiple kernel learning with application to cancer subtype discovery","volume":"31","author":"Speicher","year":"2015","journal-title":"Bioinformatics"},{"key":"2023051609122570200_btab109-B33","doi-asserted-by":"crossref","first-page":"1177932219899051","DOI":"10.1177\/1177932219899051","article-title":"Multi-omics data integration, interpretation, and its application","volume":"14","author":"Subramanian","year":"2020","journal-title":"Bioinf. Biol. Insight"},{"key":"2023051609122570200_btab109-B34","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.ccr.2009.12.020","article-title":"Integrated genomic analysis identifies clinically relevant subtypes of glioblastoma characterized by abnormalities in PDGFRA, IDH1, EGFR, and NF1","volume":"17","author":"Verhaak","year":"2010","journal-title":"Cancer Cell"},{"key":"2023051609122570200_btab109-B35","first-page":"80","article-title":"Extracting a biologically relevant latent space from cancer transcriptomes with variational autoencoders","volume":"23","author":"Way","year":"2018","journal-title":"Pac. Symp. Biocomput"},{"key":"2023051609122570200_btab109-B36","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The Cancer Genome Atlas Pan-Cancer analysis project","volume":"45","author":"Weinstein","year":"2013","journal-title":"Nat. Genet"},{"key":"2023051609122570200_btab109-B37","doi-asserted-by":"crossref","first-page":"Article28","DOI":"10.2202\/1544-6115.1470","article-title":"Extensions of sparse canonical correlation analysis with applications to genomic data","volume":"8","author":"Witten","year":"2009","journal-title":"Stat. Appl. Genet. Mol. Biol"},{"key":"2023051609122570200_btab109-B38","doi-asserted-by":"crossref","first-page":"1022","DOI":"10.1186\/s12864-015-2223-8","article-title":"Fast dimension reduction and integrative clustering of multi-omics data using low-rank approximation: application to cancer molecular classification","volume":"16","author":"Wu","year":"2015","journal-title":"BMC Genomics"},{"key":"2023051609122570200_btab109-B39","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1186\/s13059-019-1689-0","article-title":"Machine learning and complex biological data","volume":"20","author":"Xu","year":"2019","journal-title":"Genome Biol"},{"key":"2023051609122570200_btab109-B40","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1186\/s12859-019-3116-7","article-title":"A hierarchical integration deep flexible neural forest framework for cancer subtype classification by integrating multi-omics data","volume":"20","author":"Xu","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2023051609122570200_btab109-B41","doi-asserted-by":"crossref","first-page":"477","DOI":"10.3389\/fgene.2018.00477","article-title":"Deep learning-based multi-omics data integration reveals two prognostic subtypes in high-risk neuroblastoma","volume":"9","author":"Zhang","year":"2018","journal-title":"Front. Genet"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab109\/36411133\/btab109.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/16\/2231\/50339348\/btab109.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/16\/2231\/50339348\/btab109.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T08:35:47Z","timestamp":1697877347000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/16\/2231\/6143031"}},"subtitle":[],"editor":[{"given":"Peter","family":"Robinson","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,2,18]]},"references-count":41,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2021,8,25]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab109","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,8,15]]},"published":{"date-parts":[[2021,2,18]]}}}