Identification of podocyte molecular markers in diabetic kidney disease via single-cell RNA sequencing and machine learning

Diabetic kidney disease (DKD) is a major cause of end-stage renal disease globally, with podocytes being implicated in its pathogenesis. However, the underlying mechanisms of podocyte involvement remain unclear. The aim of the present study was to identify podocyte molecular markers associated with DKD using single-cell RNA sequencing (scRNA-seq) data from patients with early DKD. Through enrichment analysis, subcluster clustering, and ligand-receptor (LR) interaction analysis, we elucidated the role of podocytes in early DKD progression. Podocyte heterogeneity and functional differences in DKD were observed. Multiple machine-learning algorithms were used to screen and construct diagnostic models to identify hub differentially expressed podocyte marker genes (DE-podos), revealing ARHGEF26 as a significantly downregulated marker in DKD. Validation using external datasets, reverse transcription quantitative real-time PCR (RT-qPCR) and Western blot confirmed it as a potential diagnostic biomarker. Our findings elucidate podocyte function in DKD and provide viable therapeutic targets, potentially improving diagnostic accuracy and treatment outcomes.