机器学习联合加权基因共表达网络分析揭示原发性干燥综合征新型生物标志物OA

Objective Primary Sjögren Syndrome(pSS)has complex etiology and pathogenesis,and there is currently a lack of efficient and specific diagnostic biomarkers.Methods This study integrated multiple machine learning algorithms with weighted gene co-expression network analysis to systematically identify poten-tial diagnostic biomarkers for pSS.Results The Endosome/lysosome-associated apoptosis and autophagy regu-lator 1(KIAA1324)was significantly downregulated in the pSS group.Pathway enrichment analysis indicated its primary involvement in the Epstein-Barr virus infection,Hepatitis B,and Janus Kinase-Signal Transducer and Activator of Transcription signaling pathway.Diagnostic efficacy evaluation confirmed that KIAA1324 exhib-its favorable accuracy and sensitivity in the diagnosis of pSS.Furthermore,the expression of KIAA1324 was closely correlated with the level of immune cell infiltration,showing a significant association with the infiltration of activated dendritic cells in particular.Conclusions The KIAA1324 is a potential biomarker for pSS.Its signifi-cant association with the infiltration of activated dendritic cells suggests that it may play a role in the regulation of the pSS immune microenvironment,providing new clues for elucidating its immunopathological mechanisms.