<HashMap><database>biostudies-literature</database><scores/><additional><omics_type>Unknown</omics_type><volume>16</volume><submitter>Xuan X</submitter><pubmed_abstract>&lt;h4>Purpose&lt;/h4>We aimed to identify the mitochondria-related feature genes associated with type 2 diabetes mellitus and explore their potential roles in immune cell infiltration.&lt;h4>Methods&lt;/h4>Datasets from GSE41762, GSE38642, GSE25724, and GSE20966 were obtained from the Gene Expression Omnibus database. Weighted Gene Co-expression Network Analysis was performed to achieve mitochondria-related hub genes. Random Forest, Least Absolute Shrinkage and Selection Operator, and Support Vector Machines-Recursive Feature Elimination algorithms were used to screen mitochondria-related feature genes. Receiver Operating Characteristic analysis was applied to evaluate the accuracy of the feature genes. Pearson's correlation analysis was used to calculate the correlations between feature genes and im</pubmed_abstract><journal>Frontiers in endocrinology</journal><pagination>1501159</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC11983445</full_dataset_link><repository>biostudies-literature</repository><pubmed_title>Identification of mitochondria-related feature genes for predicting type 2 diabetes mellitus using machine learning methods.</pubmed_title><pmcid>PMC11983445</pmcid><pubmed_authors>Sun M</pubmed_authors><pubmed_authors>Hu D</pubmed_authors><pubmed_authors>Lu C</pubmed_authors><pubmed_authors>Xuan X</pubmed_authors></additional><is_claimable>false</is_claimable><name>Identification of mitochondria-related feature genes for predicting type 2 diabetes mellitus using machine learning methods.</name><description>&lt;h4>Purpose&lt;/h4>We aimed to identify the mitochondria-related feature genes associated with type 2 diabetes mellitus and explore their potential roles in immune cell infiltration.&lt;h4>Methods&lt;/h4>Datasets from GSE41762, GSE38642, GSE25724, and GSE20966 were obtained from the Gene Expression Omnibus database. Weighted Gene Co-expression Network Analysis was performed to achieve mitochondria-related hub genes. Random Forest, Least Absolute Shrinkage and Selection Operator, and Support Vector Machines-Recursive Feature Elimination algorithms were used to screen mitochondria-related feature genes. Receiver Operating Characteristic analysis was applied to evaluate the accuracy of the feature genes. Pearson's correlation analysis was used to calculate the correlations between feature genes and im</description><dates><release>2025-01-01T00:00:00Z</release><publication>2025</publication><modification>2026-04-22T03:28:52.102Z</modification><creation>2026-04-22T03:12:52.054Z</creation></dates><accession>S-EPMC11983445</accession><cross_references><pubmed>40213100</pubmed><doi>10.3389/fendo.2025.1501159</doi></cross_references></HashMap>