Identification of key immune‐related genes and immune infiltration in diabetic nephropathy based on machine learning algorithms

Abstract

Abstract Background Diabetic nephropathy (DN) is a complication of diabetes. This study aimed to identify potential diagnostic markers of DN and explore the significance of immune cell infiltration in this pathology. Methods The GSE30528, GSE96804, and GSE1009 datasets were downloaded from the Gene Expression Omnibus database. Differentially expressed genes (DEGs) were identified by merging the GSE30528 and GSE96804 datasets. Enrichment analyses of the DEGs were performed. A LASSO regression model, support vector machine recursive feature elimination analysis and random forest analysis methods were performed to identify candidate biomarkers. The CIBERSORT algorithm was utilised to compare immune infiltration between DN and normal controls. Results In total, 115 DEGs were obtained. The enrichment analysis showed that the DEGs were prominent in immune and inflammatory responses. The DEGs were closely related to kidney disease, urinary system disease, kidney cancer etc. CXCR2, DUSP1, and LPL were recognised as diagnostic markers of DN. The immune cell infiltration analysis indicated that DN patients contained a higher ratio of memory B cells, gamma delta T cells, M1 macrophages, M2 macrophages etc. cells than normal people. Conclusion Immune cell infiltration is important for the occurrence of DN. CXCR2, DUSP1, and LPL may become novel diagnostic markers of DN.

Keywords

• biomarker
• CIBERSORT
• diabetic nephropathy
• immune infiltration