Machine learning reveals targets of

Background: Rheumatoid arthritis (RA) is an autoimmune disease characterized by chronic inflammation and gut microbiota dysbiosis. Methods and results: In this study, we employed an integrated strategy combining machine learning (ML), molecular docking, and molecular dynamics simulations to identify active compounds within GHTFs. The therapeutic mechanisms of these compounds were further investigated using LPS-stimulated RAW264.7 macrophages and a collagen-induced arthritis mouse model. Differential expression analysis identified 2,676 RA-associated genes. A glmBoost + LDA model demonstrated robust diagnostic performance (AUC_train = 0.959; AUC_val ≥ 0.837) and prioritized five key genes (POLB, EGFR, MMP13, VEGFA, and KMT2D). Molecular docking and dynamics simulations confirmed the stable binding of amentoflavone (AF), a primary constituent of GHTFs, to core targets MMP9, MMP13, TOP2A, and ALOX5. Conclusions: Collectively, our findings identify GHTFs as a promising therapeutic candidate for RA, ameliorating disease progression through modulation of inflammatory responses and microbiota-mediated immune regulation.