Shen et al. developed COMPASS, an AI model that interprets pre-treatment tumor RNAseq data in the context of tumor-immune gene expression modules and maps them to predict ICB response. Trained on TCGA and cohort data, COMPASS was applicable across cohorts, indications, ICB drugs, and targets, with superior response prediction compared to established models or correlates (TMB, PD-L1). COMPASS also generated personalized “response maps” identifying potential resistance mechanisms; unexpected nonresponders (i.e. patients with an inflammatory TME) often had gene expression associated with angiogenesis, TGFβ, and B cell deficiency.
Contributed by Alex Najibi
ABSTRACT: Immune checkpoint inhibitors (ICIs) are a standard treatment across cancers, yet most patients do not respond, and existing biomarkers generalize poorly across tumor types and therapies. Here we present COMPASS, a pan-cancer foundation model that predicts immunotherapy response from bulk tumor transcriptomes using a concept bottleneck transformer. COMPASS encodes gene expression through 44 biologically grounded immune concepts representing immune cell states, tumor-microenvironment interaction and signaling pathways. Trained on 10,184 tumors across 33 cancer types, COMPASS achieves better average performance than 22 methods across 16 clinical cohorts spanning seven cancers and six ICIs, improving accuracy by 8.5% and area under the precision-recall curve by 15.7% on average across cohorts. COMPASS generalizes to cancer types and treatments not represented during fine-tuning and may inform indication selection and patient stratification. In survival analyses, patients classified by COMPASS as responders had longer overall survival (hazard ratio_=_4.7, P_<_0.0001). Personalized response maps connect gene expression to immune concepts, identifying programs associated with response and resistance; in immune-inflamed non-responders, COMPASS highlights programs including TGF_ signaling, endothelial exclusion, CD4(+) T cell dysfunction and B cell deficiency. COMPASS predicts immunotherapy response and provides hypothesis-generating mechanistic insight for trial design and translational studies.
