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

Abstract

ObjectiveDiabetic kidney disease (DKD) is the leading cause of chronic kidney disease and end-stage renal disease worldwide. Early diagnosis is critical to prevent its progression. The aim of this study was to identify potential diagnostic biomarkers for DKD, illustrate the biological processes related to the biomarkers and investigate the relationship between them and immune cell infiltration.Materials and methodsGene expression profiles (GSE30528, GSE96804, and GSE99339) for samples obtained from DKD and controls were downloaded from the Gene Expression Omnibus database as a training set, and the gene expression profiles (GSE47185 and GSE30122) were 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, and immunohistochemical (IHC) staining for biomarkers was performed in the DKD and control kidney tissues. In addition, the CIBERSORT, XCELL and TIMER algorithms were employed to assess the infiltration of immune cells in DKD, and the relationships between the biomarkers and infiltrating immune cells were also investigated.ResultsA total of 95 DEGs were identified. Using three machine learning algorithms, DUSP1 and PRKAR2B were identified as potential biomarker genes 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 (0.789 and 0.709, respectively). IHC staining suggested that the expression levels of DUSP1 and PRKAR2B were significantly lower in DKD patients compared to normal. Immune cell infiltration analysis showed that B memory cells, gamma delta T cells, macrophages, and neutrophils may be involved in the development of DKD. Furthermore, both of the candidate genes are associated with these immune cell subtypes to varying extents.ConclusionDUSP1 and PRKAR2B are potential diagnostic markers of DKD, and they are closely associated with immune cell infiltration.

Transcriptomic and machine learning analyses identify hub genes of metabolism and host immune response that are associated with the progression of breast capsular contracture

“…PRKAR2B was also discovered to enhance prostate cancer metastasis by activating the Wnt/β-catenin signaling pathway. 26 Some studies suggested that PRKAR2B can serve as a potential biological marker for diabetic kidney disease 27 , 28 , 29 , 30 and squamous cell carcinoma. 31 PRKAR2B has been found to be related to various other diseases.…”

Identification of biomarkers for the diagnosis of chronic kidney disease (CKD) with non-alcoholic fatty liver disease (NAFLD) by bioinformatics analysis and machine learning

“…There are limitations to our study. First, CKD is an umbrella term with significant heterogeneity, and we were not able to analyze specific types of CKD; Second, we focus on the pathogenesis and diagnostic markers of CKD in the context of NAFLD, and it is important to note that CKD has the opposite effect on NAFLD, which is beyond the scope of our discussion; Third, our findings were required to validate in vivo and in vitro to better guide clinical practice, although the decreased expression of DUSPI and ZFP36 in CKD has been confirmed by related studies (36,53).…”

The Role of Immune Cells in DKD: Mechanisms and Targeted Therapies

“…Juan Jin et al 73 identified biomarkers, including CTLA-4, CXCR3, CCR4, CD39, PD-1, and HLA-DR, via mass cytometry (CyTOF) analysis, which are associated with significantly altered monocyte, T cell, and B cell subpopulations in early-stage DKD; however, further validation in other cohorts is necessary. Shaojie Fu et al 121 used three different algorithms, including least absolute shrinkage and selection operator (LASSO), support vector machine-recursive feature elimination (SVM-RFE), and random forest (RF), to identify DUSP1 and PRKAR2B as possible biomarkers. Further, immunohistochemical staining indicated that DUSP1 and PRKAR2B expression levels were significantly decreased in patients with DKD.…”