{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"submitter":["Christensen NJ"],"pubmed_abstract":["<h4>Motivation</h4>The identification of predictive biomarker signatures from omics and multi-omics data for clinical applications is an active area of research. Recent developments in assay technologies and machine learning (ML) methods have led to significant improvements in predictive performance. However, most high-performing ML methods suffer from complex architectures and lack interpretability.<h4>Results</h4>We present the application of a novel symbolic-regression-based algorithm, the QLattice, on a selection of clinical omics datasets. This approach generates parsimonious high-performing models that can both predict disease outcomes and reveal putative disease mechanisms, demonstrating the importance of selecting maximally relevant and minimally redundant features in omics-based m"],"journal":["Bioinformatics (Oxford, England)"],"pagination":["btac405"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9344843"],"repository":["biostudies-literature"],"pubmed_title":["Identifying interactions in omics data for clinical biomarker discovery using symbolic regression."],"pmcid":["PMC9344843"],"pubmed_authors":["Stentoft-Hansen V","Christensen NJ","Pedersen L","Iglesias MT","Salvatore M","Demharter S","Machado M"],"additional_accession":[]},"is_claimable":false,"name":"Identifying interactions in omics data for clinical biomarker discovery using symbolic regression.","description":"<h4>Motivation</h4>The identification of predictive biomarker signatures from omics and multi-omics data for clinical applications is an active area of research. Recent developments in assay technologies and machine learning (ML) methods have led to significant improvements in predictive performance. However, most high-performing ML methods suffer from complex architectures and lack interpretability.<h4>Results</h4>We present the application of a novel symbolic-regression-based algorithm, the QLattice, on a selection of clinical omics datasets. This approach generates parsimonious high-performing models that can both predict disease outcomes and reveal putative disease mechanisms, demonstrating the importance of selecting maximally relevant and minimally redundant features in omics-based m","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022 Jun","modification":"2025-04-18T13:16:01.019Z","creation":"2025-02-19T05:06:11.722Z"},"accession":"S-EPMC9344843","cross_references":{"pubmed":["35731214"],"doi":["10.1093/bioinformatics/btac405"]}}