Machine learning to identify immune-related biomarkers of rheumatoid arthritis based on WGCNA network

Objectives This study was designed to identify the potential diagnostic biomarkers of rheumatoid arthritis (RA) and to explore the potential pathological relevance of immune cell infiltration in this disease. Methods Three previously published datasets containing gene expression data from 35 RA patients and 29 controls (GSE55235, GSE55457, and GSE12021) were downloaded from the GEO database, after which a weighted correlation network analysis (WGCNA) approach was utilized to clarify differentially abundant genes. Candidate biomarkers of RA were then identified via the use of a LASSO regression model and support vector machine recursive feature elimination (SVM-RFE) analyses. Data were validated based upon the area under the receiver operating characteristic curve (AUC) values, with hub genes being identified as those with an AUC > 85% and a P value < 0.05. Lastly, the CIBERSORT algorithm was used to assess immune cell infiltration of RA tissues, and correlations between immune cell infiltration and disease-related diagnostic biomarkers were assessed. Results The green-yellow module containing 87 genes was found to be highly correlated with RA positivity. FADD, CXCL2, and CXCL8 were identified as potential RA diagnostic biomarkers (AUC > 0.85), and these results were validated using the GSE77298 dataset. Immune cell infiltration analyses revealed the expression of hub genes to be correlated with mast cells, monocytes, activated NK cells, CD8 T cells, resting dendritic cells, and plasma cells. Conclusion These data indicate that FADD, CXCL2, and CXCL8 are valuable diagnostic biomarkers of RA, offering new insight that can guide future studies of RA incidence and progression.