HistoAtlas: A Pan-Cancer Morphology Atlas Linking Histomics to Molecular Programs and Clinical Outcomes
This work addresses the problem of biomarker discovery from routine histology for cancer researchers and clinicians, enabling large-scale analysis without specialized methods, though it is incremental in applying computational techniques to existing data.
The researchers tackled the challenge of linking histology images to molecular and clinical data by creating HistoAtlas, a pan-cancer atlas that extracts 38 interpretable features from 6,745 H&E slides across 21 cancer types, systematically associating them with survival, gene expression, mutations, and immune subtypes, while uncovering new morphological subtypes with divergent outcomes.
We present HistoAtlas, a pan-cancer computational atlas that extracts 38 interpretable histomic features from 6,745 diagnostic H&E slides across 21 TCGA cancer types and systematically links every feature to survival, gene expression, somatic mutations, and immune subtypes. All associations are covariate-adjusted, multiple-testing corrected, and classified into evidence-strength tiers. The atlas recovers known biology, from immune infiltration and prognosis to proliferation and kinase signaling, while uncovering compartment-specific immune signals and morphological subtypes with divergent outcomes. Every result is spatially traceable to tissue compartments and individual cells, statistically calibrated, and openly queryable. HistoAtlas enables systematic, large-scale biomarker discovery from routine H&E without specialized staining or sequencing. Data and an interactive web atlas are freely available at https://histoatlas.com .