Generalizable AI predicts immunotherapy outcomes across cancers and treatments

Immune checkpoint inhibitors have become standard care across many cancers, but most patients do not respond. Predicting response remains challenging due to complex tumorimmune interactions and the poor generalizability of current biomarkers and models. Predictors such as tumor mutational burden, PD-L1 expression, and transcriptomic signatures often fail across cancer types, therapies, and clinical settings. There is a clear need for a robust, interpretable model that captures shared immune response principles and adapts to diverse clinical contexts. We present CO_SCPLOWOMPASSC_SCPLOW, a foundation model for predicting immunotherapy response from pan-cancer transcriptomic data using a concept bottleneck architecture. CO_SCPLOWOMPASSC_SCPLOWencodes tumor 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, CO_SCPLOWOMPASSC_SCPLOWoutperforms 22 baseline methods in 16 independent clinical cohorts spanning seven cancers and six immune checkpoint inhibitors, increasing precision by 8.5%, Matthews correlation coefficient by 12.3%, and area under the precision-recall curve by 15.7%, with minimal or no additional training. The model generalizes to unseen cancer types and treatments, supporting indication selection and patient stratification in early-phase clinical trials. Survival analysis shows that CO_SCPLOWOMPASSC_SCPLOW-stratified responders have significantly longer overall survival (hazard ratio = 4.7, p < 0.0001). Personalized response maps link gene expression to immune concepts, revealing distinct mechanisms of response and resistance. For example, among immune-inflamed non-responders, CO_SCPLOWOMPASSC_SCPLOWidentifies distinct resistance programs involving TGF-{beta} signaling, endothelial exclusion, CD4+ T cell dysfunction, and B cell deficiency. By combining mechanistic interpretability with transfer learning, CO_SCPLOWOMPASSC_SCPLOWprovides mechanistic insights into treatment response variability, supports clinical decision-making, and informs trial design.