{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["5"],"submitter":["Bauvin B"],"pubmed_abstract":["<h4>Introduction</h4>The complexity of COVID-19 requires approaches that extend beyond symptom-based descriptors. Multi-omic data, combining clinical, proteomic, and metabolomic information, offer a more detailed view of disease mechanisms and biomarker discovery.<h4>Methods</h4>As part of a large-scale Quebec initiative, we collected extensive datasets from COVID-19 positive and negative patient samples. Using a multi-view machine learning framework with ensemble methods, we integrated thousands of features across clinical, proteomic, and metabolomic domains to classify COVID-19 status. We further applied a novel feature relevance methodology to identify condensed signatures.<h4>Results</h4>Our models achieved a balanced accuracy of 89% ± 5% despite the high-dimensional nature of the data"],"journal":["Frontiers in bioinformatics"],"pagination":["1645785"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12497780"],"repository":["biostudies-literature"],"pubmed_title":["Extracting a COVID-19 signature from a multi-omic dataset."],"pmcid":["PMC12497780"],"pubmed_authors":["Quach C","Carpentier C","Huusaari R","Bauvin B","Godon T","Rousu J","Corbeil J","Deraspe M","Bachelot G"],"additional_accession":[]},"is_claimable":false,"name":"Extracting a COVID-19 signature from a multi-omic dataset.","description":"<h4>Introduction</h4>The complexity of COVID-19 requires approaches that extend beyond symptom-based descriptors. Multi-omic data, combining clinical, proteomic, and metabolomic information, offer a more detailed view of disease mechanisms and biomarker discovery.<h4>Methods</h4>As part of a large-scale Quebec initiative, we collected extensive datasets from COVID-19 positive and negative patient samples. Using a multi-view machine learning framework with ensemble methods, we integrated thousands of features across clinical, proteomic, and metabolomic domains to classify COVID-19 status. We further applied a novel feature relevance methodology to identify condensed signatures.<h4>Results</h4>Our models achieved a balanced accuracy of 89% ± 5% despite the high-dimensional nature of the data","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025","modification":"2026-06-04T06:56:33.59Z","creation":"2026-05-06T03:11:55.08Z"},"accession":"S-EPMC12497780","cross_references":{"pubmed":["41059484"],"doi":["10.3389/fbinf.2025.1645785"]}}