Abstract 1292: Multimodal modeling of detailed cancer subtypes and molecular features from 60,000 patients with co-registered H&E images and clinical tumor sequencing.

Abstract Background: Optimal oncology treatment depends upon detailed cancer subtyping and molecular characterization. However, due to small datasets, prior digital pathology work often grouped detailed histologic subtypes by anatomy. Furthermore, the role of digital pathology as a complement to DNA sequencing rather than a surrogate remains underexplored. This study develops machine learning for H0.05, corrected Fisher’s p0.05). For biomarker inference (single nucleotide variants, pathway-level alterations, and higher-order features), Paladin achieved AUROC ≥0.80 for 165 (5%) of 3,541, improving on benchmarks. Importantly, the model also identified phenotype associations for functional states of KEAP1 variants of unknown significance (VUS) in lung adenocarcinoma; VUS cases with H log-rank p0.01). For STK11, discordant H Mann-Whitney U (MWU) p0.01) and STK11 RNA abundance (MWU p0.01). This phenocopying had prognostic consequences: wildtype (WT) cases with STK11-mutant phenotype on H60,000 patients with co-registered H Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 1292.