AUTHOR=Zhong Ming , Zhu Enyi , Li Na , Gong Lian , Xu Hai , Zhong Yong , Gong Kai , Jiang Shan , Wang Xiaohua , Fei Lingyan , Tang Chun , Lei Yan , Wang Zhongli , Zheng Zhihua TITLE=Identification of diagnostic markers related to oxidative stress and inflammatory response in diabetic kidney disease by machine learning algorithms: Evidence from human transcriptomic data and mouse experiments JOURNAL=Frontiers in Endocrinology VOLUME=Volume 14 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2023.1134325 DOI=10.3389/fendo.2023.1134325 ISSN=1664-2392 ABSTRACT=Diabetic kidney disease (DKD) is a long-term complication of diabetes and causes renal microvascular disease. It is also one of the main causes of end-stage renal disease (ESRD), which has a complex pathophysiological process. Timely prevention and treatment are of great significance for delaying DKD. This study aimed to use bioinformatics analysis to find key diagnostic markers that could be possible therapeutic targets for DKD.We downloaded DKD datasets from seven different experimental platforms in the Gene Expression Omnibus (GEO) database after which we removed batch effects and integrated them. Biological processes, such as immune activation, T-cell activation, and cell adhesion were found to be enriched in DKD using an Over-Representation Analysis (ORA) enrichment analysis. Based on differentially expressed oxidative stress and inflammatory response-related genes (DEOIGs), we divided diabetic kidney disease patients into C1 and C2 subtypes based on consensus clustering. Four potential diagnostic markers for DKD, including tenascin C, peroxidasin, tissue inhibitor metalloproteinases 1, and tropomyosin (TNC, PXDN, TIMP1, and TPM1, respectively) were identified using multiple bioinformatics analyses such as WGCNA, LASSO, RF, and SVM_RFE. The reliability of these diagnostic markers was verified in an external dataset. To facilitate clinical application, we constructed a diagnostic model containing four diagnostic markers. The reliability and practicability of the model were confirmed by constructing a calibration curve, the receiver operating characteristic (ROC) curve and a Decision Curve Analysis (DCA) curve. To further explore the biological processes involved in the four diagnostic markers, we found that they were closely related to a variety of immune cells based on Gene Set Enrichment Analysis (GSEA) and correlation analysis and played a vital role in the immune microenvironment of DKD. Finally, we constructed a mouse model of DKD and DM, and we further verified the reliability of the four diagnostic markers through various experiments. In conclusion, we identified four reliable and potential diagnostic markers through a comprehensive and systematic bioinformatics analysis and experimental validation, which could serve as potential therapeutic targets for DKD. We performed a preliminary examination of the biological processes involved in DKD pathogenesis and provide a novel idea for DKD diagnosis and treatment.