Predicting diagnostic gene biomarkers in patients with diabetic kidney disease based on weighted gene co expression network analysis and machine learning algorithms

Abstract

The present study was designed to identify potential diagnostic markers for diabetic kidney disease (DKD). Two publicly available gene expression profiles (GSE142153 and GSE30528 datasets) from human DKD and control samples were downloaded from the GEO database. Differentially expressed genes (DEGs) were screened between 23 DKD and 10 control samples using the gene data from GSE142153. Weighted gene co expression network analysis was used to find the modules related to DKD. The overlapping genes of DEGs and Turquoise modules were narrowed down and using the least absolute shrinkage and selection operator regression model and support vector machine-recursive feature elimination analysis to identify candidate biomarkers. The area under the receiver operating characteristic curve value was obtained and used to evaluate discriminatory ability using the gene data from GSE30528. A total of 110 DEGs were obtained: 64 genes were significantly upregulated and 46 genes were significantly downregulated. Weighted gene co expression network analysis found that the turquoise module had the strongest correlation with DKD (R = -0.58, P = 4 × 10-4). Thirty-eight overlapping genes of DEGs and turquoise modules were extracted. The identified DEGs were mainly involved in p53 signaling pathway, HIF-1 signaling pathway, JAK - STAT signaling pathway and FoxO signaling pathway between and the control. C-X-C motif chemokine ligand 3 was identified as diagnostic markers of DKD with an area under the receiver operating characteristic curve of 0.735 (95% CI 0.487-0.932). C-X-C motif chemokine ligand 3 was identified as diagnostic biomarkers of DKD and can provide new insights for future studies on the occurrence and the molecular mechanisms of DKD.