CONFIRMATION OF EIGHT ENDOTYPES OF LUPUS BASED ON WHOLE BLOOD RNA PROFILES

PV180 / #508 Poster Topic: AS20 - Precision Medicine Background/Purpose We previously described a classification system of persons with SLE based on whole blood (WB) mRNA profiles and a random forest (RF) algorithm to predict individual patient endotypes.[1] Here, we apply this algorithm prospectively in an independent set of patients to validate its use as a staging biomarker. Methods WB from 101 patients participating in 3 clinical trials meeting ACR or SLICC criteria for SLE classification was obtained at baseline, and RNA isolated and sequenced. Gene expression values were used as input to Gene Set Variation Analysis (GSVA) and the RF algorithm was applied using GSVA enrichment scores of 32 informative gene sets as input. Composite scores summarizing gene expression perturbations were assigned to each patient using a ridge logistic regression algorithm. Binary classifiers characterizing patients in the prospective cohort into each endotype were additionally constructed and Shapley Additive Explanations (SHAP) analysis was employed to explain the contribution of molecular features to the RF algorithmic decision. Results Eight SLE endotypes were identified by the algorithm (Figure 1). Patterns of gene enrichment in the identified endotypes mirrored those found in the previously reported endotypes.[1] Differences in clinical characteristics, including serum complement levels, autoantibody positivity, and the presence of nephritis, were observed between patients in various endotypes. Patients with active, contemporaneous nephritis were disproportionately assigned to the more molecularly perturbed endotypes. Composite scores were significantly, but modestly, inversely correlated with complement but not SLEDAI or anti-dsDNA titer. SHAP analysis revealed specific important features and patterns of features per endotype and per patient contributing to the RF models’ classification decision. Figure 1. Identification of Eight Endotypes Among 101 SLE Patients GSVA enrichment scores of 26 immune/inflammatory modules show the molecular profiles for each of the 101 SLE patients according to endotype membership, which was identified by a random forest algorithm using the enrichment scores. Clinical metadata for each patient (x-axis) was annotated as shown. Heatmap constructed in R v 4.3.3 using the ComplexHeatmap package v. 2.18.0. LN=lupus nephritis; ISN_RPS=International Society of Nephrology/Renal Pathology Society. Conclusions The identification of 8 molecular endotypes of lupus based on WB gene expression was validated in an independent dataset of diverse patients. Endotyping SLE patients based on transcriptional profiles can provide important status (presence of nephritis) information and provide novel molecular insights in support of personalized management.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.