Year: 2026
Type: article
Abstract: Immune checkpoint inhibitors are standard across cancers, yet most patients do not respond and existing biomarkers generalize poorly across tumor types, drugs and clinical settings. We present C ompass , a pan-cancer foundation model that predicts immunotherapy response from bulk tumor transcriptomes using a concept-bottleneck transformer. C ompass encodes gene expression through 44 biologically grounded immune concepts representing immune cell states, tumor-microenvironment interactions, and signaling pathways. Trained on 10,184 tumors across 33 cancer types, C ompass outperforms 22 baseline methods in 16 independent clinical cohorts spanning seven cancers and six immune checkpoint inhibitors, increasing accuracy by 8.5% and area under the precision-recall curve by 15.7%, with minimal additional training. The model generalizes to unseen cancer types and treatments, supporting indication selection and patient stratification in early-phase clinical trials. In survival analyses, C ompass -stratified responders have longer overall survival (hazard ratio = 4.7, p < 0.0001). Personalized response maps connect gene expression to immune concepts, revealing mechanisms of response and resistance; in immune-inflamed non-responders, C ompass highlights programs including TGF- β signaling, endothelial exclusion, CD4+ T cell dysfunction, and B cell deficiency. By combining interpretability with transfer learning, C ompass enables robust prediction and mechanistic insight to inform trial design and translational studies.
Source: Nature Medicine
Authors: Wanxiang Shen, Intae Moon, Thinh H. Nguyen, Michelle M. Li, Yepeng Huang, Nitya Nair, Daniel Marbach, Marinka Zitnik
Language: English
Subfield: Oncology
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
Estimated APC paid: $12,690
Funders: National Science Foundation, Bill and Melinda Gates Foundation, Pfizer, AstraZeneca, GlaxoSmithKline, Sanofi, Harvard University, Zhejiang University, Clalit Health Services, National Institutes of Health, Harvard Data Science Initiative, Harvard University, National Institute of Allergy and Infectious Diseases, Eunice Kennedy Shriver National Institute of Child Health and Human Development
Awards: CAREER: Geometric Deep Learning to Facilitate Algorithmic and Scientific Advances in Therapeutics, G4950536974, G6671297155, Harvard University - To leverage knowledge graph AI to enhance evidence-based decision making for global health., Measuring Neonatal Regionalization, Molecular Basis of Allergic and Immunologic Disease
OpenAlex ID: W4410090477