{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T18:46:03Z","timestamp":1776105963213,"version":"3.50.1"},"reference-count":24,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012337","name":"Nanhu Scholars Program for Young Scholars of Xinyang Normal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012337","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Integrating high-dimensional multi-omics data is essential for uncovering the coordinated molecular mechanisms underlying cancer progression and improving survival prediction. DNA methylation and mRNA expression represent two tightly coupled regulatory layers; however, many existing approaches either model them independently or rely on linear assumptions that fail to capture the nonlinear cross-omics structure. Here, we propose MT-ADSCCA, a multitask adaptive deep sparse canonical correlation analysis framework that jointly learns correlated latent representations, selects interpretable multi-omics biomarkers, and supports downstream survival modeling. MT-ADSCCA embeds sparse CCA into a nonlinear encoder architecture and uses uncertainty-guided adaptive weighting to stabilize multi-objective training. The selected features were subsequently modeled using a BiLSTM\u2013Cox survival network with genes ordered by chromosomal coordinates to capture local genomic dependencies. We evaluated MT-ADSCCA using event-stratified nested 10-fold cross-validation across three TCGA cohorts: breast invasive carcinoma (BRCA), glioma (GBMLGG), and pan-kidney carcinoma (KIPAN), including 485, 563, and 652 matched multi-omics samples, respectively. MT-ADSCCA achieved the highest concordance indices across all cohorts, outperforming six feature-selection baselines (DA, WGCNA, lmQCM, CCA, OSCCA, DeepCorrSurv) and four survival-model baselines (LASSO-Cox, RSF, MTLSA, DeepSurv). Kaplan\u2013Meier analyses further confirmed a clear separation between the predicted high- and low-risk groups. The selected canonical features were enriched in biologically coherent functional categories, supporting the interpretability of the learned patterns. Together, these results demonstrate that MT-ADSCCA provides a robust and interpretable framework for multi-omics integration and cancer prognosis prediction.<\/jats:p>","DOI":"10.1371\/journal.pone.0346274","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:24:25Z","timestamp":1776101065000},"page":"e0346274","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-task adaptive deep sparse canonical correlation analysis for multi-omics cancer survival prediction"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7868-6135","authenticated-orcid":true,"given":"Yan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zimo","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"issue":"2","key":"pone.0346274.ref001","article-title":"An Integrated TCGA Pan-Cancer Clinical Data Resource to Drive High-Quality Survival Outcome Analytics","volume":"173","author":"J Liu","year":"2018","journal-title":"Cell"},{"issue":"6","key":"pone.0346274.ref002","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":"H Suzuki","year":"2012","journal-title":"Mol Oncol"},{"key":"pone.0346274.ref003","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":"SY Kim","year":"2018","journal-title":"BMC Med Genomics"},{"issue":"2","key":"pone.0346274.ref004","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1037\/h0058165","article-title":"The most predictable criterion.","volume":"26","author":"H Hotelling","year":"1935","journal-title":"Journal of Educational Psychology"},{"key":"pone.0346274.ref005","volume-title":"Non-negative Matrix Factorization in Multimodality Data for Segmentation and Label Prediction. 16th Computer vision winter workshop","author":"Z Akata","year":"2011"},{"issue":"5","key":"pone.0346274.ref006","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1016\/j.imavis.2006.04.014","article-title":"Locality preserving CCA with applications to data visualization and pose estimation","volume":"25","author":"T Sun","year":"2007","journal-title":"Image and Vision Computing"},{"issue":"04","key":"pone.0346274.ref007","doi-asserted-by":"crossref","first-page":"3938","DOI":"10.1609\/aaai.v34i04.5808","article-title":"Cross-Modal Subspace Clustering via Deep Canonical Correlation Analysis","volume":"34","author":"Q Gao","year":"2020","journal-title":"AAAI"},{"issue":"1","key":"pone.0346274.ref008","doi-asserted-by":"crossref","DOI":"10.2202\/1544-6115.1470","article-title":"Extensions of sparse canonical correlation analysis with applications to genomic data","volume":"8","author":"DM Witten","year":"2009","journal-title":"Stat Appl Genet Mol Biol"},{"key":"pone.0346274.ref009","first-page":"55","volume-title":"Deep canonical correlation analysis. Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28; Atlanta, GA, USA: JMLR.org","author":"G Andrew","year":"2013"},{"key":"pone.0346274.ref010","volume-title":"Deep Multilingual Correlation for Improved Word Embeddings","author":"A Lu","year":"2015"},{"key":"pone.0346274.ref011","first-page":"2015","volume-title":"Unsupervised learning of acoustic features via deep canonical correlation analysis","author":"W Wang"},{"issue":"157","key":"pone.0346274.ref012","doi-asserted-by":"crossref","DOI":"10.1126\/scitranslmed.3004330","article-title":"Quantitative image analysis of cellular heterogeneity in breast tumors complements genomic profiling","volume":"4","author":"Y Yuan","year":"2012","journal-title":"Sci Transl Med"},{"key":"pone.0346274.ref013","first-page":"13","author":"V Subramanian","year":"2021","journal-title":"Multimodal fusion using sparse cca for breast cancer survival prediction"},{"issue":"2","key":"pone.0346274.ref014","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1093\/bioinformatics\/bty535","article-title":"Compound-protein interaction prediction with end-to-end learning of neural networks for graphs and sequences","volume":"35","author":"M Tsubaki","year":"2019","journal-title":"Bioinformatics"},{"issue":"21","key":"pone.0346274.ref015","doi-asserted-by":"crossref","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":"J Cheng","year":"2017","journal-title":"Cancer Res"},{"key":"pone.0346274.ref016","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":"P Langfelder","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"pone.0346274.ref017","first-page":"1096","volume-title":"Extracting and composing robust features with denoising autoencoders. Proceedings of the 25th international conference on Machine learning; Helsinki, Finland: Association for Computing Machinery","author":"P Vincent","year":"2008"},{"issue":"1","key":"pone.0346274.ref018","article-title":"ADAGE-Based Integration of Publicly Available Pseudomonas aeruginosa Gene Expression Data with Denoising Autoencoders Illuminates Microbe-Host Interactions","volume":"1","author":"J Tan","year":"2016","journal-title":"mSystems"},{"key":"pone.0346274.ref019","volume-title":"Deep correlational learning for survival prediction from multi-modality data","author":"J Yao","year":"2017"},{"key":"pone.0346274.ref020","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":"J-M Chen","year":"2015","journal-title":"Sci Rep"},{"key":"pone.0346274.ref021","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":"K-H Yu","year":"2016","journal-title":"Nat Commun"},{"key":"pone.0346274.ref022","article-title":"The Cancer Genome Atlas (TCGA): an immeasurable source of knowledge","volume":"19","author":"K Tomczak","year":"2015","journal-title":"Contemporary Oncology (Poznan, Poland)"},{"key":"pone.0346274.ref023","doi-asserted-by":"crossref","DOI":"10.1093\/database\/baw160","article-title":"FirebrowseR: an R client to the Broad Institute\u2019s Firehose Pipeline","volume":"2017","author":"M Deng","year":"2017","journal-title":"Database: the journal of biological databases and curation"},{"key":"pone.0346274.ref024","volume-title":"Statistical power analysis for the behavioral sciences","author":"J Cohen","year":"1988","edition":"2"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0346274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:24:32Z","timestamp":1776101072000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0346274"}},"subtitle":[],"editor":[{"given":"Amgad","family":"Muneer","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":24,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0346274","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,13]]}}}