{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["49(1)"],"submitter":["Hayes SMS"],"pubmed_abstract":["Network inference is a valuable approach for gaining mechanistic insight from high-dimensional biological data. Existing methods for network inference focus on ranking all possible relations (edges) among all measured quantities such as genes, proteins, metabolites (features) observed, which yields a dense network that is challenging to interpret. Identifying a sparse, interpretable network using these methods thus requires an error-prone thresholding step which compromises their performance. In this article we propose a new method, DEKER-NET, that addresses this limitation by directly identifying a sparse, interpretable network without thresholding, improving real-world performance. DEKER-NET uses a novel machine learning method for feature selection in an iterative framework for network "],"journal":["Journal of pharmacokinetics and pharmacodynamics"],"pagination":["81-99"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC8837529"],"repository":["biostudies-literature"],"pubmed_title":["From complex data to biological insight: 'DEKER' feature selection and network inference."],"pmcid":["PMC8837529"],"pubmed_authors":["Sachs JR","Cho CR","Hayes SMS"],"additional_accession":[]},"is_claimable":false,"name":"From complex data to biological insight: 'DEKER' feature selection and network inference.","description":"Network inference is a valuable approach for gaining mechanistic insight from high-dimensional biological data. Existing methods for network inference focus on ranking all possible relations (edges) among all measured quantities such as genes, proteins, metabolites (features) observed, which yields a dense network that is challenging to interpret. Identifying a sparse, interpretable network using these methods thus requires an error-prone thresholding step which compromises their performance. In this article we propose a new method, DEKER-NET, that addresses this limitation by directly identifying a sparse, interpretable network without thresholding, improving real-world performance. DEKER-NET uses a novel machine learning method for feature selection in an iterative framework for network ","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022 Feb","modification":"2025-04-04T08:58:30.235Z","creation":"2025-04-04T08:58:30.235Z"},"accession":"S-EPMC8837529","cross_references":{"pubmed":["34791577"],"doi":["10.1007/s10928-021-09792-7"]}}