{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Li C"],"funding":["Shenzhen Medical Research Fund","National Natural Science Foundation of China","Shanghai Sailing Program"],"pagination":["btag057"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12944826"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["42(2)"],"pubmed_abstract":["Motivation
Heterogeneity is a hallmark of both macroscopic complex diseases and microscopic single-cell distribution. Gaussian graphical models (GGMs)-based heterogeneity analysis highlights its important role in capturing the essential characteristics of biological regulatory networks, but faces instability with scarce samples from rare subgroups. Transfer learning offers promise by leveraging auxiliary data, yet existing approaches rely on unrealistic overall similarity between domains, requiring the same subgroup number and similar parameters. Numerous biological problems call for local similarities, where only some subgroups share statistical structures.Results
In this article, we propose LtransHeteroGGM, a novel local transfer learning framework for GGM-based heterogen"],"journal":["Bioinformatics (Oxford, England)"],"pubmed_title":["LtransHeteroGGM: local transfer learning for Gaussian graphical model-based heterogeneity analysis."],"pmcid":["PMC12944826"],"funding_grant_id":["E250200621","E250200620","12501373","24YF2721900","82202367"],"pubmed_authors":["Li C","Ma H","Ren M"],"additional_accession":[]},"is_claimable":false,"name":"LtransHeteroGGM: local transfer learning for Gaussian graphical model-based heterogeneity analysis.","description":"Motivation
Heterogeneity is a hallmark of both macroscopic complex diseases and microscopic single-cell distribution. Gaussian graphical models (GGMs)-based heterogeneity analysis highlights its important role in capturing the essential characteristics of biological regulatory networks, but faces instability with scarce samples from rare subgroups. Transfer learning offers promise by leveraging auxiliary data, yet existing approaches rely on unrealistic overall similarity between domains, requiring the same subgroup number and similar parameters. Numerous biological problems call for local similarities, where only some subgroups share statistical structures.Results
In this article, we propose LtransHeteroGGM, a novel local transfer learning framework for GGM-based heterogen","dates":{"release":"2026-01-01T00:00:00Z","publication":"2026 Feb","modification":"2026-07-16T21:55:30.04Z","creation":"2026-07-10T03:15:36.003Z"},"accession":"S-EPMC12944826","cross_references":{"pubmed":["41638991"],"doi":["10.1093/bioinformatics/btag057"]}}