AUTHOR=Fu Shaojie , Cheng Yanli , Wang Xueyao , Huang Jingda , Su Sensen , Wu Hao , Yu Jinyu , Xu Zhonggao 

TITLE=Identification of diagnostic gene biomarkers and immune infiltration in patients with diabetic kidney disease using machine learning strategies and bioinformatic analysis

JOURNAL=Frontiers in Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2022.918657

DOI=10.3389/fmed.2022.918657

ISSN=2296-858X

ABSTRACT=Objective: Diabetic kidney disease (DKD) is the leading cause of chronic kidney disease and end-stage renal disease worldwide. Thus, early diagnosis is critical to prevent the progression of DKD and the selection of an effective treatment strategy. The aim of the present study was to identify potential diagnostic biomarkers for DKD and determine the significance of immune cell infiltration for hits pathogenesis.Methods: Three gene expression profiles (GSE30528, GSE96804, and GSE99339) for samples obtained from patients with DKD and controls were downloaded from the Gene Expression Omnibus database as a training set, and the gene expression profile GSE47185 was downloaded as a validation set. Differentially expressed genes (DEGs) were identified using the training set, and functional correlation analyses were performed. The least absolute shrinkage and selection operator (LASSO), support vector machine-recursive feature elimination (SVM-RFE), and random forests (RF) were performed to identify potential diagnostic biomarkers. To evaluate the diagnostic efficacy of these potential biomarkers, receiver operating characteristic (ROC) curves were plotted separately for the training and validation sets. In addition, CIBERSORT bioinformatics algorithm was employed to assess the infiltration of immune cells in DKD and the relationships between the diagnostic biomarkers and infiltrating immune cells were characterized.Results: A total of 95 DEGs were identified that were mainly involved in extracellular matrix (ECM)-receptor interaction, the interleukin-17 signaling pathway, and the advanced glycation end-product (AGE)-receptor for AGE signaling pathway. Using three machine learning algorithms, DUSP1 and PRKAR2B were identified as biomarker genes that might be useful for the diagnosis of DKD. The diagnostic efficacy of DUSP1 and PRKAR2B was assessed using the areas under the curves in the ROC analysis of the training set (0.945 and 0.932, respectively) and validation set (0.945 and 0.958, respectively). Immune cell infiltration analysis showed that B memory cells, gamma delta T cells, macrophages, and resting mast cells may be involved in the development of DKD. Furthermore, both of the candidate genes are associated with these immune cell subtypes to varying extents.
Conclusion: DUSP1 and PRKAR2B are potential diagnostic markers of DKD, and immune cell infiltration plays an important role in the pathogenesis of this disease.