Machine Learning Analysis of Whole-Blood Transcriptomics Data in Rheumatoid Arthritis Patients Treated with Adalimumab Identifies Predictive Biomarkers of Response.

OBJECTIVES Tumor necrosis factor inhibitors (TNFi) have significantly improved rheumatoid arthritis (RA) management, yet variability in patient response remains a substantial challenge, with approximately 40% of patients discontinuing TNFi due to non-response or adverse effects. This study aimed to identify biomarkers predictive of adalimumab treatment response using whole blood transcriptomics, leveraging machine learning models for data mining followed by targeted statistical analysis. METHODS A cohort of RA patients starting TNFi therapy (n=100) was assessed for treatment response at 6 months, with RNA sequencing performed on baseline (pre-treatment) and 3-month follow-up samples. Machine learning classifiers were built to identify predictive biomarkers for treatment outcomes. This was followed by a network analysis on the biomarkers to elucidate the most influential biomarker, which was subsequently confirmed through survival analysis. RESULTS Differential gene expression analysis in 97 samples passing QC identified 84 genes associated with treatment response. Random Forest classifiers achieved high predictive accuracy with AUCs up to 0.86, identifying genes contributing to treatment outcomes. Network analysis further elucidated gene interactions, highlighting MZB1 as a novel biomarker not captured by machine learning alone. MZB1's role in B cell development and antibody production was associated with anti-drug antibody formation, impacting treatment efficacy. CONCLUSION This study advances the understanding of transcriptomic alterations in RA treatment and enhancing our understanding of treatment response mechanisms. Whilst the gene signatures identified require independent replication, the study serves as a starting point to pave the way for personalized therapeutic strategies in patients commencing TNFi therapy in RA.