Identifying biomarkers for methotrexate efficacy in rheumatoid arthritis: a machine learning approach to whole-blood transcriptomic analysis
Abstract Objectives Methotrexate (MTX) is the first-line treatment for rheumatoid arthritis (RA), yet inadequate response is reported in 30-40% of patients. Predicting MTX response early could enable more personalised and effective treatment. This study aimed to identify biomarkers predictive of MTX response at 6 months through whole-blood transcriptomic signatures using machine learning. Methods RNA-sequencing data were generated in whole-blood samples taken from 100 MTX-naïve RA patients at baseline (pre-treatment) and following 4-weeks post treatment with MTX. Machine learning models were trained to classify MTX response following 6-months of treatment using gradient boosted trees and interpreted using SHAP values to identify predictive genes. Results Machine learning models trained on baseline and 4-weeks data achieved AUCs of 0.89 and 0.90 respectively. Stability of SHAP values showed that the baseline model was generally more stable, and therefore potentially more generalisable. Key predictive genes at baseline, which were downregulated in responders, included CAV1, LCN12, and GLB1L. Conclusion Blood-based gene expression profiling at baseline and after 4-weeks of MTX treatment can predict treatment response with high confidence revealing relevant gene pathways and candidate gene targets but requires independent validation. These findings highlight the potential for transcriptomic biomarkers to inform early treatment decision in RA, supporting precision medicine approaches.
Authors
- Nisha Nair (ORCID: https://orcid.org/0000-0001-9829-792X)
- Darren Plant (ORCID: https://orcid.org/0000-0003-1395-9344)
- María Rivas-Torrubia (ORCID: https://orcid.org/0009-0006-6515-2947)
- Brian Quilty
- Suzanne M. M. Verstappen (ORCID: https://orcid.org/0000-0001-6181-0646)
- Anne C Barton (ORCID: https://orcid.org/0000-0003-3316-2527)
- Guillermo Barturen (ORCID: https://orcid.org/0000-0003-2103-1028)
- Hider Samantha
- Robertson Lindsay
- Roy Dipak
- Atheer Al-Ansari
- Sanjeet Kamath
- Chuan Fu Yap (ORCID: https://orcid.org/0000-0001-5256-5642)
- Mathews Catherine
- Sanders Paul
- Symmons Deborah
- Galloway James
- Marta Ortova Gut (ORCID: https://orcid.org/0000-0002-4063-7159)
- DasGupta Bhaskar
- Green Michael
- Ivo Gut (ORCID: https://orcid.org/0000-0001-7219-632X)
- Scott David
- Lane Suzanne
- Richard Smith
- Kimme Hyrich
- Louise Pollard
- Marwan Bukhari
- Hyrich Kimme
- Macphie Lizzy
- RAMS co-investigators
- Callan Margaret
- Chinoy Hector
- Cooper Annie
- Teh Lee-Suan
- Marta E Alarcón Riquelme
- Ahmed Khalid
- Knight Susan
- Hassan Waji
- Marshall Tarnya
- Lee Martin
- Adebajo Ade
- Viner Nick
- Marguerie Christopher
- Gough Andrew
- Naz Sophia
- Smith Gillian
- Hamilton Jennifer
- Amarasena Roshan
- McKenna Frank
- Gullick Nicola
- Saravanan Vadivelu
- Perry Mark
- Levy Sarah
- Davis Martin
- G Chelliah Easwaradhas
Institutions
- Universidad de Granada (ES)
- Karolinska Institutet (SE)
- University of Manchester (GB)
- Pfizer-University of Granada-Junta de Andalucía Centre for Genomics and Oncological Research (ES)
- Centro Nacional de Análisis Genómico (ES)
- Parque Tecnológico de la Salud (ES)
- NIHR Manchester Biomedical Research Centre (GB)
- Centre for Epidemiology Versus Arthritis (GB)
- Universitat de Barcelona (ES)
Publication Details
- Journal
- Lara D. Veeken
- Published
- 2026-10-08
- DOI
- https://doi.org/10.1093/rheumatology/keag560
- Primary Topic
- Rheumatoid Arthritis Research and Therapies
- Type
- article
- Field-Weighted Citation Impact
- 0.00