Identification and validation of immune and oxidative stress-related diagnostic markers for diabetic nephropathy by WGCNA and machine learning

Abstract

Background: Diabetic nephropathy (DN) is the primary cause of end-stage renal disease, but existing therapeutics are limited. Therefore, novel molecular pathways that contribute to DN therapy and diagnostics are urgently needed.

Methods: Based on the Gene Expression Omnibus (GEO) database and Limma R package, we identified differentially expressed genes of DN and downloaded oxidative stress-related genes based on the Genecard database. Then, immune and oxidative stress-related hub genes were screened by combined WGCNA, machine learning, and protein-protein interaction (PPI) networks and validated by external validation sets. We conducted ROC analysis to assess the diagnostic efficacy of hub genes. The correlation of hub genes with clinical characteristics was analyzed by the Nephroseq v5 database. To understand the cellular clustering of hub genes in DN, we performed single nucleus RNA sequencing through the KIT database.

Results: Ultimately, we screened three hub genes, namely CD36, ITGB2, and SLC1A3, which were all up-regulated. According to ROC analysis, all three demonstrated excellent diagnostic efficacy. Correlation analysis revealed that the expression of hub genes was significantly correlated with the deterioration of renal function, and the results of single nucleus RNA sequencing showed that hub genes were mainly clustered in endothelial cells and leukocyte clusters.

Conclusion: By combining three machine learning algorithms with WGCNA analysis, this research identified three hub genes that could serve as novel targets for the diagnosis and therapy of DN.

Keywords: WGCNA; bioinformatic analysis; biomarker; diabetic nephropathy; machine learning.