{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T03:46:19Z","timestamp":1779335179134,"version":"3.51.4"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:00:00Z","timestamp":1767139200000},"content-version":"vor","delay-in-days":60,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"JSPS KAKENHI","award":["22H03691"],"award-info":[{"award-number":["22H03691"]}]},{"name":"JST SPRING","award":["JPMJSP2108"],"award-info":[{"award-number":["JPMJSP2108"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Effective cancer subtype classification from multi-omics data remains challenging due to incomplete omics data and limited sample sizes. While graph convolutional networks (GCNs) have been used to incorporate inter-sample relationships for enhancing small-sample classification, their performance deteriorates when a certain omics modality is entirely missing. Here, we propose MOGEDN, a novel framework for cancer subtype classification using multi-omics encoder\u2013decoder networks designed to reconstruct the latent features of missing omics data. The reconstructed features are integrated with available omics features to enable robust prediction under small-sample and missing-omics settings. We develop a step-wise algorithm to pretrain our model with diverse cancer types then to finetune for a specific cancer type while incorporating inter-sample and cross-omics dependencies. Evaluated on TCGA cancer datasets including subtypes with fewer than 50 samples, MOGEDEN consistently outperforms state-of-the-art baselines in accuracy and F1 scores. Moreover, MOGEDN\u2019s feature analysis provides two complementary biomarker sets: biomarkers shared across diverse cancer types in the pretraining phase; and biomarkers for a specific cancer type in the finetuning phase, facilitating model interpretability, and biological findings. These results highlight decoder-based imputation as a powerful approach to enhance multi-omics learning, delivering accurate classification, robust few-shot performance, and multi-scale biomarker discovery in incomplete multi-omics cohorts.<\/jats:p>","DOI":"10.1093\/bib\/bbaf698","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T12:44:51Z","timestamp":1765889091000},"source":"Crossref","is-referenced-by-count":1,"title":["MOGEDN: small-sample cancer subtype classification with encoder\u2013decoder networks for missing-omics recovery and biomarker discovery"],"prefix":"10.1093","volume":"26","author":[{"given":"Dingnan","family":"Jin","sequence":"first","affiliation":[{"name":"Graduate School of Frontier Sciences, The University of Tokyo , 5-1-5 Kashiwanoha, Kashiwa, Chiba 277-0882 ,","place":["Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4853-0153","authenticated-orcid":false,"given":"Yutaka","family":"Saito","sequence":"additional","affiliation":[{"name":"Graduate School of Frontier Sciences, The University of Tokyo , 5-1-5 Kashiwanoha, Kashiwa, Chiba 277-0882 ,","place":["Japan"]},{"name":"Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology (AIST) , 2-4-7 Aomi, Koto-ku, Tokyo 135-0064 ,","place":["Japan"]},{"name":"School of Frontier Engineering, Kitasato University , 1-15-1 Kitazato, Minami-ku, Sagamihara, Kanagawa 252-0373 ,","place":["Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,12,31]]},"reference":[{"key":"2025123023154286600_ref1","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1016\/j.cell.2014.06.049","article-title":"Multiplatform analysis of 12 cancer types reveals molecular classification within and across tissues of origin","volume":"158","author":"Hoadley","year":"2014","journal-title":"Cell"},{"key":"2025123023154286600_ref2","doi-asserted-by":"publisher","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":"2025123023154286600_ref3","doi-asserted-by":"publisher","first-page":"10051","DOI":"10.18632\/oncotarget.7067","article-title":"Pan-cancer analysis of intratumor heterogeneity as a prognostic determinant of survival","volume":"7","author":"Morris","year":"2016","journal-title":"Oncotarget"},{"key":"2025123023154286600_ref4","doi-asserted-by":"publisher","first-page":"160","DOI":"10.3390\/genes16020160","article-title":"Evaluation of pan-cancer immune heterogeneity based on DNA methylation","volume":"16","author":"Zhou","year":"2025","journal-title":"Genes (Basel)"},{"key":"2025123023154286600_ref5","doi-asserted-by":"publisher","first-page":"e1007669","DOI":"10.1371\/journal.pgen.1007669","article-title":"Pan-cancer inference of intra-tumor heterogeneity reveals associations with different forms of genomic instability","volume":"14","author":"Raynaud","year":"2018","journal-title":"PLoS Genet"},{"key":"2025123023154286600_ref6","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The cancer genome atlas pan-cancer analysis project","volume":"45","author":"The Cancer Genome Atlas Research Network","year":"2013","journal-title":"Nat Genet"},{"key":"2025123023154286600_ref7","doi-asserted-by":"publisher","first-page":"68","DOI":"10.5114\/wo.2014.47136","article-title":"ReviewThe cancer genome atlas (TCGA): an immeasurable source of knowledge","volume":"1A","author":"Tomczak","year":"2015","journal-title":"Contemp Oncol"},{"key":"2025123023154286600_ref8","doi-asserted-by":"publisher","first-page":"1098308","DOI":"10.3389\/frai.2023.1098308","article-title":"Missing data in multi-omics integration: recent advances through artificial intelligence","volume":"6","author":"Flores","year":"2023","journal-title":"Front Artif Intell"},{"key":"2025123023154286600_ref9","doi-asserted-by":"publisher","first-page":"1496","DOI":"10.3390\/biomedicines12071496","article-title":"Navigating challenges and opportunities in multi-omics integration for personalized healthcare","volume":"12","author":"Mohr","year":"2024","journal-title":"Biomedicines"},{"key":"2025123023154286600_ref10","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1038\/s43588-021-00086-z","article-title":"Undisclosed, unmet and neglected challenges in multi-omics studies","volume":"1","author":"Tarazona","year":"2021","journal-title":"Nat Comput Sci"},{"key":"2025123023154286600_ref11","doi-asserted-by":"publisher","first-page":"570255","DOI":"10.3389\/fgene.2020.570255","article-title":"A review of integrative imputation for multi-omics datasets","volume":"11","author":"Song","year":"2020","journal-title":"Front Genet"},{"key":"2025123023154286600_ref12","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: a review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"},{"key":"2025123023154286600_ref13","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1186\/s12967-024-05976-0","article-title":"Integration of graph neural networks and multi-omics analysis identify the predictive factor and key gene for immunotherapy response and prognosis of bladder cancer","volume":"22","author":"Ren","year":"2024","journal-title":"J Transl Med"},{"key":"2025123023154286600_ref14","doi-asserted-by":"publisher","first-page":"bbae184","DOI":"10.1093\/bib\/bbae184","article-title":"Prior knowledge-guided multilevel graph neural network for tumor risk prediction and interpretation via multi-omics data integration","volume":"25","author":"Yan","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025123023154286600_ref15","doi-asserted-by":"publisher","first-page":"3445","DOI":"10.1038\/s41467-021-23774-w","article-title":"MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification","volume":"12","author":"Wang","year":"2021","journal-title":"Nat Commun"},{"key":"2025123023154286600_ref16","doi-asserted-by":"publisher","first-page":"107322","DOI":"10.1016\/j.cmpb.2023.107322","article-title":"A multimodal attention-based deep learning network for multi-omics data integration","volume":"230","author":"Li","year":"2023","journal-title":"Comput Methods Programs Biomed"},{"key":"2025123023154286600_ref17","doi-asserted-by":"publisher","first-page":"e1013012","DOI":"10.1371\/journal.pcbi.1013012","article-title":"Multimodal CustOmics: a unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology","volume":"21","author":"Patel","year":"2025","journal-title":"PLoS Comput Biol"},{"key":"2025123023154286600_ref18","doi-asserted-by":"publisher","first-page":"bbae061","DOI":"10.1093\/bib\/bbae061","article-title":"Deeply integrating latent consistent representations in high-noise multi-omics data for cancer subtyping","volume":"25","author":"Li","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025123023154286600_ref19","doi-asserted-by":"publisher","first-page":"bbab600","DOI":"10.1093\/bib\/bbab600","article-title":"Deep latent space fusion for adaptive representation of heterogeneous multi-omics data","volume":"23","author":"Zhang","year":"2022","journal-title":"Brief Bioinform"},{"key":"2025123023154286600_ref20","doi-asserted-by":"publisher","first-page":"100781","DOI":"10.1016\/j.crmeth.2024.100781","article-title":"Subtype-WGME enables whole-genome-wide multi-omics cancer subtyping","volume":"4","author":"Xu","year":"2024","journal-title":"Cell Reports Methods"},{"key":"2025123023154286600_ref21","doi-asserted-by":"publisher","first-page":"e1012710","DOI":"10.1371\/journal.pcbi.1012710","article-title":"Cancer molecular subtyping using limited multi-omics data with missingness","volume":"20","author":"Bu","year":"2024","journal-title":"PLoS Comput Biol"},{"key":"2025123023154286600_ref22","doi-asserted-by":"publisher","first-page":"108058","DOI":"10.1016\/j.compbiomed.2024.108058","article-title":"CLCLSA: cross-omics linked embedding with contrastive learning and self attention for multi-omics integration with incomplete multi-omics data","volume":"170","author":"Zhao","year":"2024","journal-title":"Comput Biol Med"},{"key":"2025123023154286600_ref23","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae684","article-title":"MMOSurv: Meta-learning for few-shot survival analysis with multi-omics data","volume":"41","author":"Wen","year":"2024","journal-title":"Bioinformatics"},{"key":"2025123023154286600_ref24","doi-asserted-by":"publisher","first-page":"2287","DOI":"10.1093\/bioinformatics\/btac080","article-title":"MOMA: a multi-task attention learning algorithm for multi-omics data interpretation and classification","volume":"38","author":"Moon","year":"2022","journal-title":"Bioinformatics"},{"key":"2025123023154286600_ref25","doi-asserted-by":"publisher","first-page":"3047","DOI":"10.3390\/cancers13123047","article-title":"OmiEmbed: a unified multi-task deep learning framework for multi-omics data","volume":"13","author":"Zhang","year":"2021","journal-title":"Cancers (Basel)"},{"key":"2025123023154286600_ref26","first-page":"6212","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Wang","year":"2019"},{"key":"2025123023154286600_ref27","doi-asserted-by":"publisher","first-page":"W191","DOI":"10.1093\/nar\/gkz369","article-title":"G:profiler: a web server for functional enrichment analysis and conversions of gene lists (2019 update)","volume":"47","author":"Raudvere","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2025123023154286600_ref28","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1038\/cdd.2012.3","article-title":"HDAC5 is required for maintenance of pericentric heterochromatin, and controls cell-cycle progression and survival of human cancer cells","volume":"19","author":"Peixoto","year":"2012","journal-title":"Cell Death Differ"},{"key":"2025123023154286600_ref29","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1186\/s13046-021-02151-x","article-title":"The emerging role of ISWI chromatin remodeling complexes in cancer","volume":"40","author":"Li","year":"2021","journal-title":"J Exp Clin Cancer Res"},{"key":"2025123023154286600_ref30","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1007\/s10555-019-09811-7","article-title":"Cell surface-anchored serine proteases in cancer progression and metastasis","volume":"38","author":"Martin","year":"2019","journal-title":"Cancer Metastasis Rev"},{"key":"2025123023154286600_ref31","doi-asserted-by":"publisher","first-page":"832418","DOI":"10.3389\/fimmu.2022.832418","article-title":"Role of serine proteases at the tumor-stroma Interface","volume":"13","author":"Tagirasa","year":"2022","journal-title":"Front Immunol"},{"key":"2025123023154286600_ref32","doi-asserted-by":"publisher","first-page":"D941","DOI":"10.1093\/nar\/gky1015","article-title":"COSMIC: the catalogue of somatic mutations In cancer","volume":"47","author":"Tate","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2025123023154286600_ref33","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1038\/ng.518","article-title":"Somatic mutations altering EZH2 (Tyr641) in follicular and diffuse large B-cell lymphomas of germinal-center origin","volume":"42","author":"Morin","year":"2010","journal-title":"Nat Genet"},{"key":"2025123023154286600_ref34","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1126\/science.1102160","article-title":"Activating mutations of NOTCH1 in human T cell acute lymphoblastic leukemia","volume":"306","author":"Weng","year":"2004","journal-title":"Science."},{"key":"2025123023154286600_ref35","doi-asserted-by":"publisher","first-page":"5813","DOI":"10.1038\/s44318-024-00231-0","article-title":"TRPC5 controls the adrenaline-mediated counter regulation of hypoglycemia","volume":"43","author":"Br\u00f6ker-Lai","year":"2024","journal-title":"EMBO J"},{"key":"2025123023154286600_ref36","doi-asserted-by":"publisher","first-page":"e131","DOI":"10.1007\/BF03346721","article-title":"Somatostatin receptor expression in adrenocortical tumors and effect of a new somatostatin analog SOM230 on hormone secretion in vitro and in ex vivo adrenal cells","volume":"34","author":"Mariniello","year":"2011","journal-title":"J Endocrinol Invest"},{"key":"2025123023154286600_ref37"},{"key":"2025123023154286600_ref38"},{"key":"2025123023154286600_ref39","doi-asserted-by":"publisher","first-page":"S148","DOI":"10.1093\/ajcp\/aqaa161.323","article-title":"Genomic analysis identifies rare ALK positive cases In the TCGA database","volume":"154","author":"Patil","year":"2020","journal-title":"Am J Clin Pathol"},{"key":"2025123023154286600_ref40","doi-asserted-by":"publisher","first-page":"3886","DOI":"10.1210\/jc.2004-1267","article-title":"Peroxisome proliferator-activated receptor-\u03b3 agonists suppress adrenocortical tumour cell proliferation and induce differentiation","volume":"90","author":"Betz","year":"2005","journal-title":"J Clin Endocrinol Metab"},{"key":"2025123023154286600_ref41","doi-asserted-by":"publisher","first-page":"461","DOI":"10.3390\/cancers12020461","article-title":"Non-coding RNAs in adrenocortical cancer: from pathogenesis to diagnosis","volume":"12","author":"Decmann","year":"2020","journal-title":"Cancers"},{"key":"2025123023154286600_ref42","doi-asserted-by":"publisher","first-page":"5474","DOI":"10.1038\/s41598-017-05777-0","article-title":"Evaluation and diagnostic potential of circulating extracellular vesicle-associated microRNAs in adrenocortical tumors","volume":"7","author":"Perge","year":"2017","journal-title":"Sci Rep"},{"key":"2025123023154286600_ref43","doi-asserted-by":"publisher","first-page":"49191","DOI":"10.18632\/oncotarget.16788","article-title":"Next-generation sequencing reveals microRNA markers of adrenocortical tumors malignancy","volume":"8","author":"Koperski","year":"2017","journal-title":"Oncotarget"},{"key":"2025123023154286600_ref44"},{"key":"2025123023154286600_ref45","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1038\/s41416-019-0538-y","article-title":"EZH2 cooperates with E2F1 to stimulate expression of genes involved in adrenocortical carcinoma aggressiveness","volume":"121","author":"Tabbal","year":"2019","journal-title":"Br J Cancer"},{"key":"2025123023154286600_ref46","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1186\/s12894-022-01136-y","article-title":"CALN1 hypomethylation as a biomarker for high-risk bladder cancer","volume":"22","author":"Takagi","year":"2022","journal-title":"BMC Urol"},{"key":"2025123023154286600_ref47","doi-asserted-by":"publisher","first-page":"e70242","DOI":"10.1002\/cam4.70242","article-title":"PGK1 can affect the prognosis and development of bladder cancer","volume":"13","author":"Gao","year":"2024","journal-title":"Cancer Med"},{"key":"2025123023154286600_ref48","doi-asserted-by":"publisher","first-page":"24668","DOI":"10.18632\/oncotarget.14969","article-title":"MiR-21-5p in urinary extracellular vesicles is a novel biomarker of urothelial carcinoma","volume":"8","author":"Matsuzaki","year":"2017","journal-title":"Oncotarget"},{"key":"2025123023154286600_ref49","doi-asserted-by":"publisher","first-page":"13","DOI":"10.17776\/csj.1557751","article-title":"Isocitrate dehydrogenase: three subunits in different cancer types\u2014changes in gene expression, mutation status, and cancer progression","volume":"46","author":"Bulut Atalay","year":"2025","journal-title":"Cumhuriyet Sci J"},{"key":"2025123023154286600_ref50","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1038\/s41419-020-02801-6","article-title":"The miR-1224-5p\/TNS4\/EGFR axis inhibits tumour progression in oesophageal squamous cell carcinoma","volume":"11","author":"Shi","year":"2020","journal-title":"Cell Death Dis"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/6\/bbaf698\/66168518\/bbaf698.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/6\/bbaf698\/66168518\/bbaf698.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T04:15:47Z","timestamp":1767154547000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf698\/8407511"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"references-count":50,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf698","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,11]]},"published":{"date-parts":[[2025,11,1]]},"article-number":"bbaf698"}}