Machine learning applied to whole-blood RNA-sequencing data uncovers distinct subsets of patients with systemic lupus erythematosus

Objectives: Systemic lupus erythematosus (SLE) is a heterogeneous autoimmune disease that is difficult to treat. There is currently no optimal stratification of patients with SLE, and thus, responses to available treatments are unpredictable. Here, we developed a new stratification scheme for patients with SLE, based on the computational analysis of patients’ whole-blood transcriptomes. Methods: We applied machine learning approaches to RNA-sequencing (RNA-seq) data sets to stratify patients with SLE into four distinct clusters based on their gene expression profiles. A meta-analysis on three recently published whole-blood RNA-seq data sets was carried out, and an additional similar data set of 30 patients with SLE and 29 healthy donors was incorporated in this study; a total of 161 patients with SLE and 57 healthy donors were analysed. Results: Examination of SLE clusters, as opposed to unstratified SLE patients, revealed underappreciated differences in the pattern of expression of disease-related genes relative to clinical presentation. Moreover, gene signatures correlated with flare activity were successfully identified. Conclusion: Given that SLE disease heterogeneity is a key challenge hindering the design of optimal clinical trials and the adequate management of patients, our approach opens a new possible avenue addressing this limitation via a greater understanding of SLE heterogeneity in humans. Stratification of patients based on gene expression signatures may be a valuable strategy allowing the identification of separate molecular mechanisms underpinning disease in SLE. Further, this approach may have a use in understanding the variability in responsiveness to therapeutics, thereby improving the design of clinical trials and advancing personalised therapy.