Bioinformatics Analysis Combined with Machine Learning Algorithms to Predict Biomarkers and Their Related Mechanisms in Sjögren's Syndrome

Research Methods Three sets of pSjD-related gene expression data were obtained from the Gene Expression Omnibus (GEO) database, and differentially expressed genes (DEGs) were identified and acquired using R software. pSjD patients were randomly divided into training and validation groups in a 7:3 ratio, and the least absolute shrinkage and selection operator (LASSO) and Support Vector Machine (SVM) were employed to select the optimal differential immune genes. The ROC curve was used for visualization, followed by rigorous evaluation and validation; further exploration of the potential mechanisms of these differential genes in pSjD was conducted.Research Results A total of 1,085 differentially expressed genes (DEGs), including 87 downregulated and 998 upregulated genes, were detected in pSjD patients through bioinformatics methods. Functional enrichment analysis via GO and KEGG revealed that these genes play significant roles in immune and inflammatory responses. Using the LASSO algorithm, 10 optimal differential immune genes (KIR3DX1, XAF1, CD180, CCR5, IFI27, TRIM69, SNORA71C, NC00691, FAM90A4P, and HMGB1P35) were screened. Subsequent SVM machine learning algorithm identified 50 key differential immune genes. After intersection analysis via Venn diagrams for both algorithms, ROC analysis of the key differential immune genes ultimately selected two genes (CCR5 and CD180) with high sensitivity and specificity. Immune infiltration analysis demonstrated that the high expression of CCR5 and CD180 is closely associated with functional alterations in T cells and macrophages.Conclusion CCR5 and CD180, as key immune genes, play important roles in immune disorders of pSjD and may become potential biomarkers for the disease. Based on their good diagnostic value, CCR5 and CD180 provide new ideas for early diagnosis and targeted therapy of pSjD.Research Objectives and Significance : This study aims to systematically screen and analyze the differentially expressed gene profiles and immune characteristics of patients with primary Sjögren's syndrome (pSjD) by combining gene chip technology with machine learning algorithms, providing key data foundations and bioinformatics support for in-depth exploration of the disease's pathogenesis and novel biomarkers.