Identification of mitochondria-related feature genes for predicting type 2 diabetes mellitus using machine learning methods DOI Creative Commons

Xiuping Xuan,

Mingjin Sun,

Donghui Hu

et al.

Frontiers in Endocrinology, Journal Year: 2025, Volume and Issue: 16

Published: March 27, 2025

Purpose We aimed to identify the mitochondria-related feature genes associated with type 2 diabetes mellitus and explore their potential roles in immune cell infiltration. Methods Datasets from GSE41762, GSE38642, GSE25724, GSE20966 were obtained Gene Expression Omnibus database. Weighted Co-expression Network Analysis was performed achieve hub genes. Random Forest, Least Absolute Shrinkage Selection Operator, Support Vector Machines-Recursive Feature Elimination algorithms used screen Receiver Operating Characteristic analysis applied evaluate accuracy of Pearson’s correlation calculate correlations between The prediction candidate drugs targeting predicted using DGIdb qRT-PCR access mRNA expressions Results Five (SLC2A2, ENTPD3, ARG2, CHL1, RASGRP1) identified for prediction. They possessed high predictive accuracies area under curve values >0.8. All five showed strongest positive regulatory T cells negative neutrophils. Additionally, revealed 2(S)-amino-6-boronohexanoic acid, difluoromethylornithine, compound 9 could target while metformin a drug SCL2A2. Finally, all confirmed be decreased MIN6 treated glucose palmitic acid. Conclusion SLC2A2, RASGRP1 as predict therapeutic targets.

Language: Английский

Mechanistic Insights into Carbon Black-Activated AKT/TMEM175 Cascade Impairing Macrophage-Epithelial Cross-Talk and Airway Epithelial Proliferation DOI

Yawen Feng,

Xiaowen Tang,

Hongying Fu

et al.

Environmental Pollution, Journal Year: 2025, Volume and Issue: unknown, P. 126076 - 126076

Published: March 1, 2025

Language: Английский

Citations

0
Identification of mitochondria-related feature genes for predicting type 2 diabetes mellitus using machine learning methods DOI Creative Commons

Xiuping Xuan,

Mingjin Sun,

Donghui Hu

et al.

Frontiers in Endocrinology, Journal Year: 2025, Volume and Issue: 16

Published: March 27, 2025

Purpose We aimed to identify the mitochondria-related feature genes associated with type 2 diabetes mellitus and explore their potential roles in immune cell infiltration. Methods Datasets from GSE41762, GSE38642, GSE25724, GSE20966 were obtained Gene Expression Omnibus database. Weighted Co-expression Network Analysis was performed achieve hub genes. Random Forest, Least Absolute Shrinkage Selection Operator, Support Vector Machines-Recursive Feature Elimination algorithms used screen Receiver Operating Characteristic analysis applied evaluate accuracy of Pearson’s correlation calculate correlations between The prediction candidate drugs targeting predicted using DGIdb qRT-PCR access mRNA expressions Results Five (SLC2A2, ENTPD3, ARG2, CHL1, RASGRP1) identified for prediction. They possessed high predictive accuracies area under curve values >0.8. All five showed strongest positive regulatory T cells negative neutrophils. Additionally, revealed 2(S)-amino-6-boronohexanoic acid, difluoromethylornithine, compound 9 could target while metformin a drug SCL2A2. Finally, all confirmed be decreased MIN6 treated glucose palmitic acid. Conclusion SLC2A2, RASGRP1 as predict therapeutic targets.

Language: Английский

Citations

0