Identification and Verification of Diagnostic Biomarkers for Glomerular Injury in Diabetic Nephropathy Based on Machine Learning Algorithms

Abstract

Diabetic nephropathy (DN) is regarded as the leading cause of end-stage renal disease worldwide and lacks novel therapeutic targets. To screen and verify special biomarkers for glomerular injury in patients with DN, fifteen datasets were retrieved from the Gene Expression Omnibus (GEO) database, correspondingly divided into training and testing cohorts and then merged. Using the limma package, 140 differentially expressed genes (DEGs) were screened out between 81 glomerular DN samples and 41 normal ones from the training cohort. With the help of the ConsensusClusterPlus and WGCNA packages, the 81 glomerular DN samples were distinctly divided into two subclusters, and two highly associated modules were identified. By using machine learning algorithms (LASSO, RF, and SVM-RFE) and the Venn diagram, two overlapping genes (PRKAR2B and TGFBI) were finally determined as potential biomarkers, which were further validated in external testing datasets and the HFD/STZ-induced mouse models. Based on the biomarkers, the diagnostic model was developed with reliable predictive ability for diabetic glomerular injury. Enrichment analyses indicated the apparent abnormal immune status in patients with DN, and the two biomarkers played an important role in the immune microenvironment. The identified biomarkers demonstrated a meaningful correlation between the immune cells' infiltration and renal function. In conclusion, two robust genes were identified as diagnostic biomarkers and may serve as potential targets for therapeutics of DN, which were closely associated with multiple immune cells.

Keywords: biomarker; diabetic nephropathy; diagnostic model; glomerular injury; machine learning algorithm.