{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T21:41:06Z","timestamp":1792359666520,"version":"4.4.0"},"reference-count":0,"publisher":"Canadian Science Publishing","license":[{"start":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T00:00:00Z","timestamp":1792281600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.nrcresearchpress.com\/page\/about\/CorporateTextAndDataMining"}],"content-domain":{"domain":["cdnsciencepub.com"],"crossmark-restriction":false},"short-container-title":["Genome"],"abstract":"<jats:p>High-throughput multi-omics technologies generate high-dimensional, heterogeneous and noisy datasets, making robust biomarker discovery and disease modelling challenging. This review critically examines dimensionality reduction and representation strategies for multi-omics analysis while distinguishing three related but different goals: feature selection, feature extraction\/representation learning, and multi-omics integration. We use sparse canonical correlation analysis (sCCA), variational autoencoders (VAEs), and graph convolutional networks (GCNs) as representative case studies spanning sparse linear, probabilistic deep-learning, and graph-based approaches. Rather than treating these methods as interchangeable, we compare their data requirements, assumptions, interpretability, ability to accommodate non-linearity and missing modalities, computational demands, and validation needs. Applications across cancer, cardiovascular and neurodegenerative disease, and across bulk, single-cell, spatial and imaging multi-omics are summarized in comparative tables. We conclude with practical guidance for matching method families to biological questions and emphasize that robust biomarker claims require leakage-free model development, stability assessment and independent validation.<\/jats:p>","DOI":"10.1139\/gen-2026-0094","type":"journal-article","created":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T21:37:11Z","timestamp":1792359431000},"update-policy":"https:\/\/doi.org\/10.1139\/csp-crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Feature selection and dimensionality reduction in multi-omics"],"prefix":"10.1139","author":[{"given":"Sweta","family":"Rai","sequence":"first","affiliation":[{"name":"University of Lethbridge, Department of Biological Sciences, Lethbridge, Canada;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Igor","family":"Kovalchuk","sequence":"additional","affiliation":[{"name":"University of Lethbridge, Biology, Lethbridge, Alberta, Canada;"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"155","published-online":{"date-parts":[[2026,10,18]]},"container-title":["Genome"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdnsciencepub.com\/doi\/pdf\/10.1139\/gen-2026-0094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T21:37:12Z","timestamp":1792359432000},"score":1,"resource":{"primary":{"URL":"https:\/\/cdnsciencepub.com\/doi\/10.1139\/gen-2026-0094"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,18]]},"references-count":0,"alternative-id":["10.1139\/gen-2026-0094"],"URL":"https:\/\/doi.org\/10.1139\/gen-2026-0094","relation":{},"ISSN":["0831-2796","1480-3321"],"issn-type":[{"value":"0831-2796","type":"print"},{"value":"1480-3321","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,18]]},"assertion":[{"value":"2026-06-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"gen-2026-0094"}}