{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T20:10:19Z","timestamp":1790021419783,"version":"4.0.1"},"reference-count":52,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Bioinform Biotech"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Ovarian cancer remains one of the most lethal gynecologic malignancies, largely due to pronounced molecular heterogeneity, nonspecific clinical presentation, and frequent diagnosis at advanced stages. Multiomics profiling\u2014including genomics, transcriptomics, and epigenomics\u2014offers a powerful avenue for characterizing this complexity and enabling more precise patient stratification.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to address key challenges in multiomics analysis, including high dimensionality, cross-modality heterogeneity, limited sample size, and the lack of effective approaches for survival stratification of patients with ovarian cancer through deep representation learning.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We analyzed multiomics data from The Cancer Genome Atlas and developed a 5-stage deep learning pipeline centered on variational autoencoders (VAEs) for nonlinear dimensionality reduction and latent representation learning. A graph convolutional neural network component is described as a proposed extension for modeling interaction-aware representations but was not empirically evaluated in this study. Latent embeddings derived from the VAE were clustered using k-means, and their prognostic relevance was assessed using Cox proportional hazards modeling and Kaplan-Meier survival analysis.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Following correction of a clinical-molecular harmonization issue, the final matched cohort comprised 291 patients. Silhouette analysis identified k=2 as the optimal clustering solution (silhouette=0.272). Kaplan-Meier analysis demonstrated significantly different overall survival between the two clusters (log-rank\n \u03c7<\/jats:italic>\n 2<\/jats:sup>\n 1<\/jats:sub>\n =10.0;\n P<\/jats:italic>\n =.002). Cox proportional hazards modeling estimated a hazard ratio of 0.519 (95% CI 0.343\u20100.785;\n P<\/jats:italic>\n =.002), indicating that patients assigned to cluster 1 exhibited an approximately 48% lower hazard of death than those in cluster 0. These results demonstrate that the learned latent representations capture prognostically relevant structure within the integrated multiomics data.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The proposed VAE-based framework identified 2 prognostically distinct patient subgroups with significantly different overall survival. These findings demonstrate the potential of deep generative representation learning for multiomics-based survival stratification in ovarian cancer and provide a foundation for future validation in independent cohorts and the evaluation of graph-based extensions.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/89069","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T19:43:37Z","timestamp":1790019817000},"page":"e89069-e89069","source":"Crossref","is-referenced-by-count":0,"title":["Deep Generative and Graph-Based Representation Learning for Multiomics Survival Stratification in Ovarian Cancer: Secondary Analysis"],"prefix":"10.2196","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6393-6346","authenticated-orcid":false,"given":"Carlos","family":"Marino","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3334-0015","authenticated-orcid":false,"given":"Claudia","family":"Diaz Paz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"issue":"3","key":"R1","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","journal-title":"CA Cancer J Clin"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.1016\/j.puhe.2024.10.033","article-title":"Global cancer statistics of young adults and its changes in the past decade: incidence and mortality from GLOBOCAN 2022","volume":"237","author":"Li","journal-title":"Public Health"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109250","article-title":"Ovarian cancer data analysis using deep learning: a systematic review","volume":"138","author":"Hira","journal-title":"Eng Appl Artif Intell"},{"key":"R4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2022.104001","article-title":"Multi-omics approaches for biomarker discovery in early ovarian cancer diagnosis","volume":"79","author":"Xiao","journal-title":"EBioMedicine"},{"key":"R5","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1179829","article-title":"Editorial: Application and innovation of multiomics technologies in clinical oncology","volume":"13","author":"Li","journal-title":"Front Oncol"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-biodatasci-020722-115651","article-title":"An overview of deep generative models in functional and evolutionary genomics","volume":"6","author":"Yelmen","journal-title":"Annu Rev Biomed Data Sci"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","DOI":"10.1080\/09581596.2025.2488119","article-title":"Hurdles in the personalized medicine implementation path: public\u2019s literacy and misconceptions of whole genomic sequencing test","volume":"35","author":"Ramadan","journal-title":"Crit Public Health"},{"issue":"6","key":"R8","doi-asserted-by":"publisher","first-page":"974","DOI":"10.1515\/cclm-2022-1147","article-title":"From research cohorts to the patient - a role for \u201comics\u201d in diagnostics and laboratory medicine?","volume":"61","author":"Vogeser","journal-title":"Clin Chem Lab Med"},{"issue":"6","key":"R9","doi-asserted-by":"publisher","first-page":"2822","DOI":"10.3390\/ijms22062822","article-title":"A detailed catalogue of multi-omics methodologies for identification of putative biomarkers and causal molecular networks in translational cancer research","volume":"22","author":"Vlachavas","journal-title":"Int J Mol Sci"},{"issue":"6","key":"R10","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1016\/j.fertnstert.2018.04.027","article-title":"Introduction: personalized medicine: what is it and what are the challenges?","volume":"109","author":"Sigman","journal-title":"Fertil Steril"},{"issue":"3","key":"R11","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1097\/01.JU.0000553669.64428.19","article-title":"Re: Introduction: personalized medicine: what is it and what are the challenges?","volume":"201","author":"Niederberger","journal-title":"J Urol"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6939-14-55","article-title":"What is personalized medicine: sharpening a vague term based on a systematic literature review","volume":"14","author":"Schleidgen","journal-title":"BMC Med Ethics"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10768-5","article-title":"Revolutionizing personalized medicine with generative AI: a systematic review","volume":"57","author":"Ghebrehiwet","journal-title":"Artif Intell Rev"},{"issue":"8","key":"R14","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.32604\/biocell.2025.065891","article-title":"Technological innovations and multi-omics approaches in cancer research: a comprehensive review","volume":"49","author":"Velmurugan","journal-title":"BIOCELL"},{"issue":"1","key":"R15","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-023-00494-6","article-title":"Autosurv: interpretable deep learning framework for cancer survival analysis incorporating clinical and multi-omics data","volume":"8","author":"Jiang","journal-title":"NPJ Precis Oncol"},{"issue":"10","key":"R16","doi-asserted-by":"publisher","first-page":"4067","DOI":"10.1007\/s00204-025-04118-9","article-title":"An integrative multi-omics study to identify candidate DNA methylation biomarkers associated with gastric cancer prognosis","volume":"99","author":"Gu","journal-title":"Arch Toxicol"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","DOI":"10.1080\/07853890.2025.2494671","article-title":"Molecular targets and mechanisms of traditional Chinese medicine combined with chemotherapy for gastric cancer: a meta-analysis and multi-omics approach","volume":"57","author":"Lin","journal-title":"Ann Med"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-025-06711-z","article-title":"Multi-omics integration and machine learning uncover molecular basal-like subtype of pancreatic cancer and implicate A2ML1 in promoting tumor epithelial-mesenchymal transition","volume":"23","author":"Ge","journal-title":"J Transl Med"},{"issue":"2","key":"R19","doi-asserted-by":"publisher","DOI":"10.3390\/jpm11020149","article-title":"Recent advances in integrative multi-omics research in breast and ovarian cancer","volume":"11","author":"Khella","journal-title":"J Pers Med"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3449814","article-title":"Breast cancer survival prediction modeling based on genomic data: an improved prognosis-driven deep learning approach","volume":"12","author":"Mahmoud","journal-title":"IEEE Access"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsbmb.2025.106815","article-title":"Multi-omics analysis reveals the impact of thrombotic diseases on the occurrence and prognosis of breast cancer","volume":"253","author":"Zhong","journal-title":"J Steroid Biochem Mol Biol"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-025-06662-5","article-title":"Comparative analysis of statistical and deep learning-based multi-omics integration for breast cancer subtype classification","volume":"23","author":"Omran","journal-title":"J Transl Med"},{"issue":"1","key":"R23","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1038\/s41698-025-01029-x","article-title":"Pan-cancer, multi-omic correlates of survival transcending tumor lineage across 11,019 patients reveal targets and pathways","volume":"9","author":"Zhang","journal-title":"NPJ Precis Onc"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107220","article-title":"The prediction of drug sensitivity by multi-omics fusion reveals the heterogeneity of drug response in pan-cancer","volume":"163","author":"Wang","journal-title":"Comput Biol Med"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2025.1549656","article-title":"Multi-omics analysis and experiments uncover the link between cancer intrinsic drivers, stemness, and immunotherapy in ovarian cancer with validation in a pan-cancer census","volume":"16","author":"Li","journal-title":"Front Immunol"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1574037","article-title":"Validation of machine learning-based models to predict and explain the risk of ovarian cancer: a multicentric study on -mutated patients undergoing risk-reducing salpingo-oophorectomy","volume":"15","author":"Loizzi","journal-title":"Front Oncol"},{"issue":"13","key":"R27","doi-asserted-by":"publisher","first-page":"5961","DOI":"10.3390\/ijms26135961","article-title":"Ovarian cancer: multi-omics data integration","volume":"26","author":"Kliuchnikova","journal-title":"Int J Mol Sci"},{"key":"R28","doi-asserted-by":"publisher","DOI":"10.1109\/access.2025.3540769","article-title":"Comparative analysis of multi-omics integration using graph neural networks for cancer classification","volume":"13","author":"Alharbi","journal-title":"IEEE Access"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","DOI":"10.1080\/01443615.2023.2171778","article-title":"Assessing the clinical utility of multi-omics data for predicting serous ovarian cancer prognosis","volume":"43","author":"Zhang","journal-title":"J Obstet Gynaecol"},{"issue":"3","key":"R30","doi-asserted-by":"publisher","DOI":"10.1002\/cnr2.70138","article-title":"Comparing the effectiveness of artificial intelligence models in predicting ovarian cancer survival: a systematic review","volume":"8","author":"Asadi","journal-title":"Cancer Rep (Hoboken)"},{"issue":"1","key":"R31","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-59670-8","article-title":"Identification of cancer risk groups through multi-omics integration using autoencoder and tensor analysis","volume":"14","author":"Braytee","journal-title":"Sci Rep"},{"issue":"12","key":"R32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0315924","article-title":"DFASGCNS: a prognostic model for ovarian cancer prediction based on dual fusion channels and stacked graph convolution","volume":"19","author":"Wang","journal-title":"PLoS One"},{"issue":"1","key":"R33","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-021-00968-x","article-title":"Deep learning in cancer diagnosis, prognosis and treatment selection","volume":"13","author":"Tran","journal-title":"Genome Med"},{"issue":"1","key":"R34","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02665-2","article-title":"Enhanced ovarian cancer survival prediction using temporal analysis and graph neural networks","volume":"24","author":"Ghantasala","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"R35","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-85285-4","article-title":"Integrated multi-omics analysis of ovarian cancer using variational autoencoders","volume":"11","author":"Hira","journal-title":"Sci Rep"},{"issue":"23","key":"R36","doi-asserted-by":"publisher","first-page":"12801","DOI":"10.3390\/app132312801","article-title":"Multivariate and dimensionality-reduction-based machine learning techniques for tumor classification of RNA-Seq data","volume":"13","author":"Al-khassaweneh","journal-title":"Appl Sci"},{"issue":"4","key":"R37","doi-asserted-by":"publisher","first-page":"583","DOI":"10.17654\/0972361725024","article-title":"Unveiling hidden insights: dimensionality reduction for prostate cancer data with PCA and Gaussian mixture model","volume":"92","author":"Kalantan","journal-title":"Adv Appl Stat"},{"issue":"10","key":"R38","doi-asserted-by":"publisher","first-page":"7609","DOI":"10.1007\/s00432-023-04699-x","article-title":"Automatic breast cancer diagnosis based on hybrid dimensionality reduction technique and ensemble classification","volume":"149","author":"Li","journal-title":"J Cancer Res Clin Oncol"},{"issue":"3","key":"R39","doi-asserted-by":"publisher","first-page":"31","DOI":"10.22937\/IJCSNS.2021.21.3.4","article-title":"Dimensionality reduction of RNA-Seq data","volume":"21","author":"Al-Turaiki","journal-title":"Int J Comput Sci Netw Secur"},{"key":"R40","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2019.01205","article-title":"Variational autoencoders for cancer data integration: design principles and computational practice","volume":"10","author":"Simidjievski","journal-title":"Front Genet"},{"issue":"1","key":"R41","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-025-06230-0","article-title":"A densely connected framework for cancer subtype classification","volume":"26","author":"Li","journal-title":"BMC Bioinformatics"},{"issue":"5","key":"R42","doi-asserted-by":"publisher","first-page":"2497","DOI":"10.1002\/mp.13497","article-title":"Combining handcrafted features with latent variables in machine learning for prediction of radiation-induced lung damage","volume":"46","author":"Cui","journal-title":"Med Phys"},{"issue":"1","key":"R43","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac790","article-title":"bmVAE: a variational autoencoder method for clustering single-cell mutation data","volume":"39","author":"Yan","journal-title":"Bioinformatics"},{"key":"R44","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3354809","article-title":"A systematic review of graph neural network in healthcare-based applications: recent advances, trends, and future directions","volume":"12","author":"Paul","journal-title":"IEEE Access"},{"key":"R45","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2021.3122522","article-title":"Graph signal processing, graph neural network and graph learning on biological data: a systematic review","volume":"16","author":"Li","journal-title":"IEEE Rev Biomed Eng"},{"issue":"24","key":"R46","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15245858","article-title":"Graph neural networks in cancer and oncology research: emerging and future trends","volume":"15","author":"Gogoshin","journal-title":"Cancers (Basel)"},{"key":"R47","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymeth.2023.02.011","article-title":"Local augmented graph neural network for multi-omics cancer prognosis prediction and analysis","volume":"213","author":"Zhang","journal-title":"Methods"},{"key":"R48","unstructured":"The Cancer Genome Atlas Program: human subjects protection and data access policies. National Cancer Institute. 2014. URL: https:\/\/www.cancer.gov\/about-nci\/organization\/ccg\/research\/structural-genomics\/tcga\/history\/policies\/tcga-human-subjects-data-policies.pdf [Accessed 28-08-2026]"},{"key":"R49","unstructured":"Goldman M . Explore TCGA, GDC, and other public cancer genomics resources. University of California, Santa Cruz. 2019. URL: https:\/\/xena.ucsc.edu\/public\/ [Accessed 28-08-2026]"},{"key":"R50","unstructured":"\u00c9tica de la investigaci\u00f3n e integridad cient\u00edfica [Webpage in Spanish]. Vicerrectorado de Investigaci\u00f3n, Pontificia Universidad Cat\u00f3lica del Per\u00fa. URL: https:\/\/investigacion.pucp.edu.pe\/etica-e-integridad\/?utm_source=chatgpt.com [Accessed 28-08-2026]"},{"key":"R51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3567081","article-title":"Comparative study of machine learning and deep learning models for early prediction of ovarian cancer","volume":"13","author":"Dhingra","journal-title":"IEEE Access"},{"key":"R52","unstructured":"TCGA-ovarian-MultiOmics-DeepLearning. GitHub. URL: https:\/\/github.com\/carloshachi777\/multiomics-ovarian-survival [Accessed 04-09-2026]"}],"container-title":["JMIR Bioinformatics and Biotechnology"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T19:43:39Z","timestamp":1790019819000},"score":1,"resource":{"primary":{"URL":"https:\/\/bioinform.jmir.org\/2026\/1\/e89069"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":52,"URL":"https:\/\/doi.org\/10.2196\/89069","relation":{},"ISSN":["2563-3570"],"issn-type":[{"value":"2563-3570","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]},"article-number":"v7i3e89069"}}