Single-cell sequencing and machine learning-based prediction of spliceosome-associated factor 2 may represent potential targets for osteoarthritis.

Background: Osteoarthritis has become a global health challenge due to its complex pathologic mechanisms. Spliceosome-associated factor 2 (SYF2) has been reported in tumors and neurological diseases, but not in studies of osteoarthritis. We employed single-cell sequencing and machine learning techniques to predict SYF2 as a potential therapeutic target for osteoarthritis and the underlying mechanisms involved. Methods: Single-cell dataset (GSE220243), cartilage tissue gene expression profiles (GSE169077, GSE117999, GSE53857) and blood sample expression profile (GSE48556) were obtained. We combined single-cell sequencing analysis and machine learning to sort candidate targets for osteoarthritis. We used GSEA analysis to predict the mechanisms of core target for osteoarthritis, and ultimately established osteoarthritis animal models to validate the screened targets. Results: Bioinformatics screening revealed a negative association between SYF2 and osteoarthritis. GSEA analysis showed that SYF2 negatively correlated with apoptosis. After establishing an osteoarthritis animal model, relative mRNA and protein expression levels were measured, consistent with the bioinformatics prediction results. Conclusions: Our research identified a previously unreported potential target for osteoarthritis, SYF2, through single-cell sequencing and machine learning. This target is likely to be related to cell apoptosis.