Machine learning analysis of FOSL2 and RHoBTB1 as central immunological regulators in knee osteoarthritis synovium.

BackgroundKnee osteoarthritis is a debilitating disease with a complex pathogenesis. Synovitis, which refers to inflammation of the synovial membrane surrounding the joint, is believed to play an important role in the development and progression of knee osteoarthritis. To better understand the molecular mechanisms underlying knee osteoarthritis, we conducted a comprehensive analysis of gene expression in knee osteoarthritis synovium using machine learning.MethodsDifferentially expressed genes between knee osteoarthritis and control synovial tissues were analyzed using the GSE55235 dataset. We employed several machine learning algorithms, including least absolute shrinkage and selection operator and support vector machine-recursive feature elimination, to screen for key genes. Then, we validated the key genes using an external dataset (GSE51588) and an in vitro knee osteoarthritis animal model. CIBERSORT was used to compare immune cell infiltration levels between knee osteoarthritis and control synovial tissues and determine their relationship with the key genes. Finally, we performed a Connectivity Map analysis to screen for potential small-molecule compounds. Moreover, we conducted single-cell RNA sequencing analysis using knee joint tissues to annotate different subtypes of cells.ResultsA total of 930 differentially expressed genes were identified. Least absolute shrinkage and selection operator regression and support vector machine-recursive feature elimination identified