Steffens, Alicia

ABSTRACT Meningiomas are the most common primary brain tumors and, despite their benign reputation, often behave aggressively. Meningiomas are morphologically heterogeneous, yet the full significance of their histologic diversity is unclear. This is in large part because many features are not readily quantifiable by traditional observer-based light microscopy. Molecular testing improves prognostic stratification, but is not universally accessible. We therefore sought to determine whether an artificial intelligence (AI)-trained program could predict specific genomic and epigenomic patterns in meningiomas, and whether it could extract more prognostic information out of standard hematoxylin and eosin (H&E) histopathology than the current WHO classification. To do this, we developed Morphologic Set Enrichment (MSE), an interpretable computational pathology framework that quantifies statistical enrichment of morphologic patterns, cells, and tissue architecture from H&E whole-slide images. The MSE meningioma histology program was able to accurately predict DNA methylation subtypes and concurrent chromosome 1p/22q losses, in the process identifying specific morphologic patterns associated with key genomic and epigenomic alterations. It also added prognostic value independent of standard clinical and pathological variables. These results demonstrate that AI-based quantitative morphologic profiling can capture clinically and biologically relevant information that redefines risk stratification for meningiomas, incorporating histological information not included in existing grading schemes.

IDH1/2 mutations (IDH mut ) increase methylation of DNA and histones in gliomas. IDH mut inhibitors are effective against low-grade IDH mut gliomas, but new strategies against high-grade IDH mut gliomas are needed. Although histone deacetylase inhibitors (HDACi) are ineffective against IDH wt glioblastoma (GBM), their potential in IDH mut gliomas has not been extensively studied. We previously established that IDH mut gliomas are more sensitive to HDACi than IDH wt GBM. Here we show that IDH mut is associated with greater sensitivity to HDACi only in glioma, not in IDH mut chondrosarcoma or cholangiocarcinoma. While HDACi induced more histone acetylation and gene regulation in IDH mut glioma than in IDH wt GBM, such acetylation was mostly within gene deserts, whereas IDH mut glioma promoters paradoxically lost histone acetylation. Two mediators of HDACi resistance, YAP and TAZ, were methylated and suppressed in IDH mut gliomas but not in other IDH mut cancers. Inducing YAP or TAZ expression in IDH mut gliomas conferred resistance to HDACi. Finally, belinostat extended in vivo survival only in IDH mut glioma models, not in IDH mut GBM models. Our findings provide a mechanistic rationale for further studies of HDACi in patients with IDH mut glioma, as well as the potential use of YAP/TAZ as a biomarker of HDACi sensitivity in cancers.