{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T14:02:28Z","timestamp":1776434548203,"version":"3.51.2"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"17","license":[{"start":{"date-parts":[[2021,3,3]],"date-time":"2021-03-03T00:00:00Z","timestamp":1614729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Integrative multi-feature fusion analysis on biomedical data has gained much attention recently. In breast cancer, existing studies have demonstrated that combining genomic mRNA data and DNA methylation data can better stratify cancer patients with distinct prognosis than using single signature. However, those existing methods are simply combining these gene features in series and have ignored the correlations between separate omics dimensions over time.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In the present study, we propose an adaptive multi-task learning method, which combines the Cox loss task with the ordinal loss task, for survival prediction of breast cancer patients using multi-modal learning instead of performing survival analysis on each feature dataset. First, we use local maximum quasi-clique merging (lmQCM) algorithm to reduce the mRNA and methylation feature dimensions and extract cluster eigengenes respectively. Then, we add an auxiliary ordinal loss to the original Cox model to improve the ability to optimize the learning process in training and regularization. The auxiliary loss helps to reduce the vanishing gradient problem for earlier layers and helps to decrease the loss of the primary task. Meanwhile, we use an adaptive weights approach to multi-task learning which weighs multiple loss functions by considering the homoscedastic uncertainty of each task. Finally, we build an ordinal cox hazards model for survival analysis and use long short-term memory (LSTM) method to predict patients\u2019 survival risk. We use the cross-validation method and the concordance index (C-index) for assessing the prediction effect. Stringent cross-verification testing processes for the benchmark dataset and two additional datasets demonstrate that the developed approach is effective, achieving very competitive performance with existing approaches.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>https:\/\/github.com\/bhioswego\/ML_ordCOX.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btab140","type":"journal-article","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T20:15:21Z","timestamp":1614629721000},"page":"2601-2608","source":"Crossref","is-referenced-by-count":36,"title":["Integrative survival analysis of breast cancer with gene expression and DNA methylation data"],"prefix":"10.1093","volume":"37","author":[{"given":"Isabelle","family":"Bichindaritz","sequence":"first","affiliation":[{"name":"Intelligent Bio Systems Laboratory, Biomedical and Health Informatics, Department of Computer Science, State University of New York at Oswego , Syracuse, NY 13202, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1135-2939","authenticated-orcid":false,"given":"Guanghui","family":"Liu","sequence":"additional","affiliation":[{"name":"Intelligent Bio Systems Laboratory, Biomedical and Health Informatics, Department of Computer Science, State University of New York at Oswego , Syracuse, NY 13202, USA"}]},{"given":"Christopher","family":"Bartlett","sequence":"additional","affiliation":[{"name":"Intelligent Bio Systems Laboratory, Biomedical and Health Informatics, Department of Computer Science, State University of New York at Oswego , Syracuse, NY 13202, USA"}]}],"member":"286","published-online":{"date-parts":[[2021,3,3]]},"reference":[{"key":"2023051609204221000_btab140-B1","doi-asserted-by":"crossref","first-page":"1076","DOI":"10.3923\/pjbs.2008.1076.1084","article-title":"Assessment of gastric cancer survival: using an artificial hierarchical neural network","volume":"11","author":"Amiri","year":"2008","journal-title":"Pak. J. Biol. Sci"},{"key":"2023051609204221000_btab140-B2","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1186\/gm567","article-title":"A BRCA1-mutation associated DNA methylation signature in blood cells predicts sporadic breast cancer incidence and survival","volume":"6","author":"Anjum","year":"2014","journal-title":"Genome Med"},{"key":"2023051609204221000_btab140-B3","doi-asserted-by":"crossref","first-page":"10690","DOI":"10.1038\/srep10690","article-title":"New breast cancer prognostic factors identified by computer-aided image analysis of HE stained histopathology images","volume":"5","author":"Chen","year":"2015","journal-title":"Sci. Rep"},{"key":"2023051609204221000_btab140-B4","doi-asserted-by":"crossref","first-page":"e91","DOI":"10.1158\/0008-5472.CAN-17-0313","article-title":"Integrative analysis of histopathological images and genomic data predicts clear cell renal cell carcinoma prognosis","volume":"77","author":"Cheng","year":"2017","journal-title":"Cancer Res"},{"key":"2023051609204221000_btab140-B5","doi-asserted-by":"crossref","first-page":"baw160","DOI":"10.1093\/database\/baw160","article-title":"FirebrowseR: an R client to the Broad Institute\u2019s Firehose Pipeline","volume":"2017","author":"Deng","year":"2017","journal-title":"Database"},{"key":"2023051609204221000_btab140-B6","doi-asserted-by":"crossref","first-page":"936","DOI":"10.1016\/j.eururo.2014.06.053","article-title":"Systematic evaluation of the prognostic impact and intratumour heterogeneity of clear cell renal cell carcinoma biomarkers","volume":"66","author":"Gulati","year":"2014","journal-title":"Eur. Urol"},{"key":"2023051609204221000_btab140-B7","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":"2023051609204221000_btab140-B8","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1214\/08-AOAS169","article-title":"Random survival forests","volume":"2","author":"Ishwaran","year":"2008","journal-title":"Ann. Appl. Stat"},{"key":"2023051609204221000_btab140-B9","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1186\/s13048-015-0171-1","article-title":"Integrative network analysis for survival-associated gene-gene interactions across multiple genomic profiles in ovarian cancer","volume":"8","author":"Jeong","year":"2015","journal-title":"J. Ovarian Res"},{"key":"2023051609204221000_btab140-B10","doi-asserted-by":"crossref","first-page":"2360","DOI":"10.1093\/bioinformatics\/btu316","article-title":"A systems-level integrative framework for genome-wide DNA methylation and gene expression data identifies differential gene expression modules under epigenetic control","volume":"30","author":"Jiao","year":"2014","journal-title":"Bioinformatics"},{"key":"2023051609204221000_btab140-B11","first-page":"2","article-title":"Deep survival: a deep cox proportional hazards network","volume":"1050","author":"Katzman","year":"2016","journal-title":"Stat"},{"key":"2023051609204221000_btab140-B12","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s12874-018-0482-1","article-title":"DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network","volume":"18","author":"Katzman","year":"2018","journal-title":"BMC Med. Res. Methodol"},{"key":"2023051609204221000_btab140-B13","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1093\/jamia\/ocw165","article-title":"Using knowledge-driven genomic interactions for multi-omics data analysis: metadimensional models for predicting clinical outcomes in ovarian carcinoma","volume":"24","author":"Kim","year":"2017","journal-title":"J. Am. Med. Inf. Assoc"},{"key":"2023051609204221000_btab140-B14","doi-asserted-by":"crossref","first-page":"5464","DOI":"10.1158\/1078-0432.CCR-04-0488","article-title":"Using protein expressions to predict survival in clear cell renal carcinoma","volume":"10","author":"Kim","year":"2004","journal-title":"Clin. Cancer Res"},{"key":"2023051609204221000_btab140-B15","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1186\/s12920-018-0389-z","article-title":"Integrative pathway-based survival prediction utilizing the interaction between gene expression and DNA methylation in breast cancer","volume":"11","author":"Kim","year":"2018","journal-title":"BMC Med. Genomics"},{"key":"2023051609204221000_btab140-B16","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.csbj.2014.11.005","article-title":"Machine learning applications in cancer prognosis and prediction","volume":"13","author":"Kourou","year":"2015","journal-title":"Comput. Struct. Biotechnol. J"},{"key":"2023051609204221000_btab140-B17","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":"2023051609204221000_btab140-B18","doi-asserted-by":"crossref","DOI":"10.1002\/0471458546","volume-title":"Statistical Methods for Survival Data Analysis","author":"Lee","year":"2003"},{"key":"2023051609204221000_btab140-B19","doi-asserted-by":"publisher","author":"Li","year":"2016","DOI":"10.1145\/2939672.2939857"},{"key":"2023051609204221000_btab140-B20","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1093\/biomet\/80.3.557","article-title":"Checking the Cox model with cumulative sums of martingale-based residuals","volume":"80","author":"Lin","year":"1993","journal-title":"Biometrika"},{"key":"2023051609204221000_btab140-B21","doi-asserted-by":"crossref","first-page":"1966","DOI":"10.1109\/TCBB.2019.2917429","article-title":"Bioimage-based Prediction of Protein Subcellular Location in Human Tissue with Ensemble Features and Deep Networks","volume":"17","author":"Liu","year":"2020","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf"},{"key":"2023051609204221000_btab140-B22","first-page":"5","article-title":"Genomic imprinting and patterns of disease inheritance","volume":"1","author":"Lobo","year":"2008","journal-title":"Nat. Educ"},{"key":"2023051609204221000_btab140-B23","author":"Papoudakis","year":"2018"},{"key":"2023051609204221000_btab140-B24","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/s10014-017-0282-z","article-title":"A comprehensive review of paediatric low-grade diffuse glioma: pathology, molecular genetics and treatment","volume":"34","author":"Ryall","year":"2017","journal-title":"Brain Tumor Pathol"},{"key":"2023051609204221000_btab140-B25","first-page":"648","author":"Shao","year":"2018"},{"key":"2023051609204221000_btab140-B26","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1016\/j.molonc.2012.07.007","article-title":"DNA methylation and microRNA dysregulation in cancer","volume":"6","author":"Suzuki","year":"2012","journal-title":"Mol. Oncol"},{"key":"2023051609204221000_btab140-B27","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1111\/j.0006-341X.2000.00227.x","article-title":"Estimation in a Cox proportional hazards cure model","volume":"56","author":"Sy","year":"2000","journal-title":"Biometrics"},{"key":"2023051609204221000_btab140-B28","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1002\/(SICI)1097-0258(19970228)16:4<385::AID-SIM380>3.0.CO;2-3","article-title":"The lasso method for variable selection in the Cox model","volume":"16","author":"Tibshirani","year":"1997","journal-title":"Stat. Med"},{"key":"2023051609204221000_btab140-B29","first-page":"A68","article-title":"The Cancer Genome Atlas (TCGA): an immeasurable source of knowledge","volume":"19","author":"Tomczak","year":"2015","journal-title":"Contemporary Oncol"},{"key":"2023051609204221000_btab140-B30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3214306","article-title":"Machine learning for survival analysis: a survey","volume":"51","author":"Wang","year":"2019","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"2023051609204221000_btab140-B31","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/S0167-9473(99)00098-5","article-title":"Comparison of the performance of neural network methods and Cox regression for censored survival data","volume":"34","author":"Xiang","year":"2000","journal-title":"Comput. Stat. Data Anal"},{"key":"2023051609204221000_btab140-B32","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1016\/j.ccr.2014.07.028","article-title":"Gene body methylation can alter gene expression and is a therapeutic target in cancer","volume":"26","author":"Yang","year":"2014","journal-title":"Cancer Cell"},{"key":"2023051609204221000_btab140-B33","doi-asserted-by":"crossref","first-page":"12474","DOI":"10.1038\/ncomms12474","article-title":"Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features","volume":"7","author":"Yu","year":"2016","journal-title":"Nat. Commun"},{"key":"2023051609204221000_btab140-B34","doi-asserted-by":"crossref","first-page":"157ra143","DOI":"10.1126\/scitranslmed.3004330","article-title":"Quantitative image analysis of cellular heterogeneity in breast tumors complements genomic profiling","volume":"4","author":"Yuan","year":"2012","journal-title":"Sci. Transl. Med"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab140\/36647218\/btab140.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/17\/2601\/50339018\/btab140.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/17\/2601\/50339018\/btab140.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T09:23:25Z","timestamp":1684229005000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/17\/2601\/6157728"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,3,3]]},"references-count":34,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2021,9,9]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab140","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,9,1]]},"published":{"date-parts":[[2021,3,3]]}}}