Diabetic nephropathy (DN) is a common microvascular complication that easily leads to end-stage renal disease. It is important to explore the key biomarkers and molecular mechanisms relevant to diabetic nephropathy (DN). We used highthroughput RNA sequencing to obtain the genes related to DN glomerular tissues and healthy glomerular tissues of mice.Then we used LIMMA to analyze differentially expressed genes (DEGs) between DN and non-diabetic glomerular samples. And we performed KEGG, gene ontology functional (GO) enrichment, and gene set enrichment analysis to reveal the signaling pathway of the disease. The CIBERSORT algorithm based on support vector machine was used to determine the immune infiltration score. Random forest algorithm and Cytoscape obtained hub genes. Finally, we applied co-staining, immunohistochemical staining, RT-qPCR and western blotting to validate the protein and mRNA expression of both hub genes. We obtained 913 DEGs mainly related to inflammatory factors and immunity. GSEA results showed that differential genes were mainly enriched in IL-17 signaling pathway, lipid and atherosclerosis, rheumatoid arthritis, TNF signaling pathway, neutrophil extracellular trap formation, Staphylococcus aureus infection and other pathways. The intersection of the random forest algorithm and Cytoscape revealed both hub genes of CD300A and CXCL1. Experiments have shown that the both key genes of CD300A and CXCL1 shown increased expression in glomerular podocytes, and are related to the inflammation of diabetic nephropathy. And immunohistochemical staining and RT-qPCR further confirmed that the protein and mRNA expression level of CD300A or CXCL1 in glomeruli tissue in DN mice were increased. The expression levels of CD300A and CXCL1 increased significantly under HG (high glucose) stimulation, further confirming that diabetes can lead to increased levels of CD300A and CXCL1 at the cellular level. Through bioinformatics analysis, machine learning algorithms, and experimental research, CD300A and CXCL1 are confirmed as both potential biomarkers in diabetic nephropathy. And we further revealed the main pathways of differential genes and the differentially distributed immune infiltrating cells in diabetic nephropathy.

Background: Diabetic nephropathy (DN) is the most common complication of type 2 diabetes mellitus and the main cause of end-stage renal disease worldwide. Diagnostic biomarkers may allow early diagnosis and treatment of DN to reduce the prevalence and delay the development of DN. Kidney biopsy is the gold standard for diagnosing DN; however, its invasive character is its primary limitation. The machine learning approach provides a non-invasive and specific criterion for diagnosing DN, although traditional machine learning algorithms need to be improved to enhance diagnostic performance. Methods: We applied high-throughput RNA sequencing to obtain the genes related to DN tubular tissues and normal tubular tissues of mice. Then machine learning algorithms, random forest, LASSO logistic regression, and principal component analysis were used to identify key genes (CES1G, CYP4A14, NDUFA4, ABCC4, ACE). Then, the genetic algorithm-optimized backpropagation neural network (GA-BPNN) was used to improve the DN diagnostic model. Results: The AUC value of the GA-BPNN model in the training dataset was 0.83, and the AUC value of the model in the validation dataset was 0.81, while the AUC values of the SVM model in the training dataset and external validation dataset were 0.756 and 0.650, respectively. Thus, this GA-BPNN gave better values than the traditional SVM model. This diagnosis model may aim for personalized diagnosis and treatment of patients with DN. Immunohistochemical staining further confirmed that the tissue and cell expression of NADH dehydrogenase (ubiquinone) 1 alpha subcomplex, 4-like 2 (NDUFA4L2) in tubular tissue in DN mice were decreased. Conclusion: The GA-BPNN model has better accuracy than the traditional SVM model and may provide an effective tool for diagnosing DN.