» Articles » PMID: 36355434

Machine-learning Classification Identifies Patients with Early Systemic Sclerosis As Abatacept Responders Via CD28 Pathway Modulation

Abstract

Here, the efficacy of abatacept in patients with early diffuse systemic sclerosis (dcSSc) was analyzed to test the hypothesis that patients in the inflammatory intrinsic subset would show the most significant clinical improvement. Eighty-four participants with dcSSc were randomized to receive abatacept or placebo for 12 months. RNA-Seq was performed on 233 skin paired biopsies at baseline and at 3 and 6 months. Improvement was defined as a 5-point or more than 20% change in modified Rodnan skin score (mRSS) between baseline and 12 months. Samples were assigned to intrinsic gene expression subsets (inflammatory, fibroproliferative, or normal-like subsets). In the abatacept arm, change in mRSS was most pronounced for the inflammatory and normal-like subsets relative to the placebo subset. Gene expression for participants on placebo remained in the original molecular subset, whereas inflammatory participants treated with abatacept had gene expression that moved toward the normal-like subset. The Costimulation of the CD28 Family Reactome Pathway decreased in patients who improved on abatacept and was specific to the inflammatory subset. Patients in the inflammatory subset had elevation of the Costimulation of the CD28 Family pathway at baseline relative to that of participants in the fibroproliferative and normal-like subsets. There was a correlation between improved ΔmRSS and baseline expression of the Costimulation of the CD28 Family pathway. This study provides an example of precision medicine in systemic sclerosis clinical trials.

Citing Articles

An international perspective on the future of systemic sclerosis research.

Abraham D, Black C, Denton C, Distler J, Domsic R, Feghali-Bostwick C Nat Rev Rheumatol. 2025; 21(3):174-187.

PMID: 39953141 DOI: 10.1038/s41584-024-01217-2.


Can machine learning assist in systemic sclerosis diagnosis and management? A scoping review.

McMullen E, Grewal R, Storm K, Mbuagbaw L, Maretzki M, Larche M J Scleroderma Relat Disord. 2024; 9(3):171-177.

PMID: 39493733 PMC: 11528611. DOI: 10.1177/23971983241253718.


Scleromyositis: A distinct novel entity within the systemic sclerosis and autoimmune myositis spectrum. Implications for care and pathogenesis.

Giannini M, Ellezam B, Leclair V, Lefebvre F, Troyanov Y, Hudson M Front Immunol. 2023; 13:974078.

PMID: 36776390 PMC: 9910219. DOI: 10.3389/fimmu.2022.974078.

References
1.
Yang M, Goh V, Lee J, Espinoza M, Yuan Y, Carns M . Clinical Phenotypes of Patients With Systemic Sclerosis With Distinct Molecular Signatures in Skin. Arthritis Care Res (Hoboken). 2022; 75(7):1469-1480. PMC: 9947190. DOI: 10.1002/acr.24998. View

2.
Taroni J, Martyanov V, Mahoney J, Whitfield M . A Functional Genomic Meta-Analysis of Clinical Trials in Systemic Sclerosis: Toward Precision Medicine and Combination Therapy. J Invest Dermatol. 2016; 137(5):1033-1041. PMC: 8190797. DOI: 10.1016/j.jid.2016.12.007. View

3.
Reich M, Liefeld T, Gould J, Lerner J, Tamayo P, Mesirov J . GenePattern 2.0. Nat Genet. 2006; 38(5):500-1. DOI: 10.1038/ng0506-500. View

4.
Liberzon A, Subramanian A, Pinchback R, Thorvaldsdottir H, Tamayo P, Mesirov J . Molecular signatures database (MSigDB) 3.0. Bioinformatics. 2011; 27(12):1739-40. PMC: 3106198. DOI: 10.1093/bioinformatics/btr260. View

5.
Denton C, Khanna D . Systemic sclerosis. Lancet. 2017; 390(10103):1685-1699. DOI: 10.1016/S0140-6736(17)30933-9. View