Identification of three-gene signature to diagnose rheumatoid arthritis through WGCNA and machine learning methods

Background Rheumatoid arthritis(RA)is a systemic immune-related disease characterized by synovial inflammation and destruction of joint cartilage.The pathogenesis of RA remains unclear,and there is an urgent need to discover new diagnostic markers with high sensitivity and specificity.The aim of this study was to identify new potential biomarkers in the synovium for diagnosing rheumatoid arthritis and to investigate their association with immune infiltration. Method We downloaded four datasets containing 51 RA and 36 healthy synovium samples from the Gene Expression Omnibus(GEO)database.Differentially expressed genes(DEGs)were identified with the help of R program.Then various enrichment analysis were conducted.Subsequently,WGCNA,random forest(RF),support vector machine-recursive feature elimination(SVM-RFE),least absolute shrinkage and selection operator(LASSO)were used to identify the hub genes for RA diagnosis.Receiver operating characteristic curves(ROC)and nomogram models were used to validate the specificity and sensitivity of hub genes.Additionally,we analyzed the infiltration levels of 28 immune cells in the expression profile and their relationship with hub genes using single-sample gene set enrichment analysis (ssGSEA). Results Three hub genes(RRM2,DLGAP5 and KIF11)were identified through WGCNA,Lasso,SVM-RFE and RF algorithms.These hub genes showed the strong correlation with T cells,Natural killer cells and Macrophage cells indicated by the analysis of immune cell infiltration. Conclusion A nomogram model for the diagnosis of RA based on RRM2,DLGAP5 and KIF11 has been established,providing diagnosis and treatment targets of RA.