Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Feb 22:14:1084531.
doi: 10.3389/fimmu.2023.1084531. eCollection 2023.

Identification and validation of immune and oxidative stress-related diagnostic markers for diabetic nephropathy by WGCNA and machine learning

Mingming Xu  1 , Hang Zhou  1 , Ping Hu  2 , Yang Pan  1 , Shangren Wang  1 , Li Liu  1 , Xiaoqiang Liu  1
Affiliations

Identification and validation of immune and oxidative stress-related diagnostic markers for diabetic nephropathy by WGCNA and machine learning

Mingming Xu et al. Front Immunol. .

Abstract

Background: Diabetic nephropathy (DN) is the primary cause of end-stage renal disease, but existing therapeutics are limited. Therefore, novel molecular pathways that contribute to DN therapy and diagnostics are urgently needed.

Methods: Based on the Gene Expression Omnibus (GEO) database and Limma R package, we identified differentially expressed genes of DN and downloaded oxidative stress-related genes based on the Genecard database. Then, immune and oxidative stress-related hub genes were screened by combined WGCNA, machine learning, and protein-protein interaction (PPI) networks and validated by external validation sets. We conducted ROC analysis to assess the diagnostic efficacy of hub genes. The correlation of hub genes with clinical characteristics was analyzed by the Nephroseq v5 database. To understand the cellular clustering of hub genes in DN, we performed single nucleus RNA sequencing through the KIT database.

Results: Ultimately, we screened three hub genes, namely CD36, ITGB2, and SLC1A3, which were all up-regulated. According to ROC analysis, all three demonstrated excellent diagnostic efficacy. Correlation analysis revealed that the expression of hub genes was significantly correlated with the deterioration of renal function, and the results of single nucleus RNA sequencing showed that hub genes were mainly clustered in endothelial cells and leukocyte clusters.

Conclusion: By combining three machine learning algorithms with WGCNA analysis, this research identified three hub genes that could serve as novel targets for the diagnosis and therapy of DN.

Keywords: WGCNA; bioinformatic analysis; biomarker; diabetic nephropathy; machine learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Flowchart for research.
Figure 2
Figure 2
Screening for DEGs. (A) Volcano plot of DEGs in GSE30528. (B) Heatmap of DEGs in GSE30528. (C) Venn diagrams of DEOSGs. DEGs, differentially expressed genes; DEOSGs, differentially expressed genes related to oxidative stress.
Figure 3
Figure 3
Immune infiltration analysis and construction of weighted gene co-expression networks. (A) 22 immune cells in samples with normal and diabetic nephropathy in GSE30528. (B) Choosing the best soft-threshold power. (C) 11 modules revealed by the WGCNA. WGCNA, weighted gene co-expression network analysis.
Figure 4
Figure 4
Acquisition and functional enrichment analysis of DEIOSGs. (A) Venn diagrams of DEIOSGs. (B) The GO outcomes are displayed with a bubble plot. (C) A bubble plot was constructed to illustrate the KEGG outcomes. (D) Results of KEGG are depicted on circle charts. DEIOSGs, differentially expressed immune-related oxidative stress genes; GO, Gene Ontology; KEGG, Kyoto Encyclopedia of Genes and Genomes; BP, biological process; CC, cellular component; MF, molecular function.
Figure 5
Figure 5
Screening hub genes by machine learning. (A) LASSO regression algorithm. (B) SVM-RFE algorithm. (C) RF algorithm. (D) Venn diagrams for three algorithms. LASSO, Least Absolute Shrinkage and Selection Operator; SVM-RFE, Support Vector Machine-Recursive Feature Elimination; RF, Random Forest.
Figure 6
Figure 6
Screening hub genes by PPI network. (A) PPI network. (B) Venn diagrams for 12 algorithms in cytoHubba plugin. PPI, protein-protein interaction.
Figure 7
Figure 7
Expression of hub genes and validation of external datasets. (A-C) Expression of hub genes in the GSE30528 dataset. (D-F) Expression of hub genes in the GSE104948 dataset. * p<0.05; ** p<0.01; *** p<0.001; **** p<0.0001.
Figure 8
Figure 8
ROC curve analysis. (A–C) Hub genes in the GSE30528 dataset were analyzed using ROC curves. (D–F) Hub genes in the GSE104948 dataset were analyzed using ROC curves.
Figure 9
Figure 9
(A-C) GSEA analysis of hub genes.
Figure 10
Figure 10
Correlation analysis. (A, B) Correlation analysis of CD36 with GFR and serum creatinine. (C, D) Correlation analysis of ITGB2 with GFR and serum creatinine. GFR, glomerular filtration rate.
Figure 11
Figure 11
Regulatory network. (A) Interaction network of TFs and genes for the hub genes. (B) Network of interactions between miRNAs and the hub genes. TF, transcription factors; miRNA, microRNA.
Figure 12
Figure 12
Single Nucleus RNA Sequencing. (A) The distribution of hub genes in 12 cell groups. (B) CD36. (C) ITGB2. (D) SLC1A3. PCT, proximal convoluted tubule; CD, collecting duct; ICA, Type A intercalated cells; ICB, Type B intercalated cells; PEC, parietal epithelial cells; PC, principal cell; DCT, distal convoluted tubule; CT, connecting tubule; LOH, loop of Henle; PODO, podocyte; ENDO, endothelium; MES, mesangial cell; LEUK, leukocyte.
See this image and copyright information in PMC

References

    1. Flyvbjerg A. The role of the complement system in diabetic nephropathy. Nat Rev Nephrol (2017) 13:311–8. doi: 10.1038/nrneph.2017.31 - DOI - PubMed
    1. Umanath K, Lewis JB. Update on diabetic nephropathy: Core curriculum 2018. Am J Kidney Dis: Off J Natl Kidney Foundation (2018) 71:884–95. doi: 10.1053/j.ajkd.2017.10.026 - DOI - PubMed
    1. Thomas B. The global burden of diabetic kidney disease: Time trends and gender gaps. Curr Diabetes Rep (2019) 19:18. doi: 10.1007/s11892-019-1133-6 - DOI - PubMed
    1. Tuttle KR, Agarwal R, Alpers CE, Bakris GL, Brosius FC, Kolkhof P, et al. Molecular mechanisms and therapeutic targets for diabetic kidney disease. Kidney Int (2022) 102:248–60. doi: 10.1016/j.kint.2022.05.012 - DOI - PubMed
    1. Alicic R, Nicholas SB. Diabetic kidney disease back in focus: Management field guide for health care professionals in the 21st century. Mayo Clin Proc (2022) 97:1904–19. doi: 10.1016/j.mayocp.2022.05.003 - DOI - PubMed

Publication types