AI-HistoPS: decoding proteomic heterogeneity with subtype resolution from histopathology in liver metastases

Liver metastasis is a lethal manifestation of diverse malignancies, but its molecular heterogeneity is not readily captured by routine histopathology. Proteomic profiling has identified functional states of metastatic lesions, although their histomorphological and tumor microenvironmental correlates remain incompletely understood. Here, we developed AI-HistoPS, a computational pathology framework for inferring proteomics-informed states from H&E-stained whole slide images. AI-HistoPS integrates pathology foundation model representations with agent-mediated multiple instance learning to capture subtype-associated morphological patterns. Using multicentre cohorts of liver metastases from multiple primary tumor types, we evaluated associations between histomorphology and three proteomic liver metastasis subtypes (LMS1-3). These states were associated with differences in tumor architecture, stromal composition, and immune cell distribution. AI-HistoPS showed subtype discrimination in the discovery cohort and was evaluated across external cohorts, demonstrating the feasibility of histology-derived representations for proteomics-informed stratification across heterogeneous clinical settings. Attention-guided analyses identified tissue regions associated with subtype-related morphological and microenvironmental features. Multiplex immunohistochemistry supported spatial associations between histological patterns and subtype-related protein markers. These findings suggest that routine histopathology may provide a lower-cost approach for approximating proteomics-informed stratification of liver metastases. Further validation in larger, more diverse, prospectively collected cohorts is required before clinical implementation or use in prognostic or treatment-related decision-making.