Development and validation of a molecular classifier of meningiomas

Abstract

Background: Meningiomas exhibit considerable clinical and biological heterogeneity. We previously identified 4 distinct molecular groups (immunogenic, NF2-wildtype, hypermetabolic, and proliferative) that address much of this heterogeneity. Despite the utility of these groups, the stochasticity of clustering methods and the use of multi-omics data for discovery limits the potential for classifying prospective cases. We sought to address this with a dedicated classifier.

Methods: Using an international cohort of 1698 meningiomas, we constructed and rigorously validated a machine learning-based molecular classifier using only DNA methylation data as input. Original and newly predicted molecular groups were compared using DNA methylation, RNA sequencing, copy number profiles, whole-exome sequencing, and clinical outcomes.

Results: We show that group-specific outcomes in the validation cohort are nearly identical to those originally described, with median progression-free survival (PFS) of 7.4 (4.9-Inf) years in hypermetabolic tumors and 2.5 (2.3-5.3) years in proliferative tumors (not reached in the other groups). Tumors classified as NF2-wildtype had no NF2 mutations, and 51.4% had canonical mutations previously described in this group. RNA pathway analysis revealed upregulation of immune-related pathways in the immunogenic group, metabolic pathways in the hypermetabolic group, and cell cycle programs in the proliferative group. Bulk deconvolution similarly revealed the enrichment of macrophages in immunogenic tumors and neoplastic cells in hypermetabolic and proliferative tumors with similar proportions to those originally described.

Conclusions: Our DNA methylation-based classifier, which is publicly available for immediate clinical use, recapitulates the biology and outcomes of the original molecular groups as assessed using multiple metrics/platforms that were not used in its training.

Keywords: DNA methylation; meningioma | molecular classification | Neuro-Oncology | outcome prediction.

Figure 1.

Predicted molecular groups recapitulate the methylation signatures, inferred copy number profiles, and outcomes of the original molecular groups. (A) Model diagram, depicting information flow from model 1 to model 2 with additional CNA-based refinement. (B) Distribution of methylation model probability scores in both models based on final predictions (excluding cases that were reassigned based on CNV profile). (C) Barplots depicting the proportion of samples in each molecular group with canonical CNAs among the validation cohort (predicted, top) and the discovery cohort (original, bottom). (D) Group-specific Kaplan Meyer survival curves are plotted for the validation cohort (left), the prospective RTOG-0539 cohort (a subset of the validation cohort, middle), and the discovery cohort (right). Vertical lines represent median progression-free survival.

Figure 2.

Validation of predicted molecular groups using orthogonal genomic platforms. (A) Whole-exome sequencing reveals similar molecular group-specific patterns of mutations between cohorts, with benign NF2-intact (MG2) cases harboring the majority of canonical non-NF2 mutations TRAF7, KLF4, AKT1, and POLR2A, but comparatively few NF2 mutations in both cohorts. (B) Pathway analysis reveals expected transcriptomic signatures in each molecular group, with enrichment of immune pathways in immunogenic (MG1, and, to a lesser extent, hypermetabolic, MG3, cases), metabolic signaling pathways in hypermetabolic (MG3) cases, and cell cycle pathways in proliferative (MG4) cases. In this network, nodes represent pathways and edges represent shared genes between pathways. Nodes colored in red represent upregulated pathways and those colored in blue represent downregulated pathways. Boxplots below depict the expression of each group-specific gene signature identified on the discovery cohort (ANOVA P-values plotted for each). (C) Bulk deconvolution analysis demonstrates consistent MG-specific cell populations between discovery and validation cohorts. Notably, immunogenic tumors are associated with greater macrophage infiltration while hypermetabolic and proliferative tumors are associated with a higher proportion of neoplastic cells.