Generalizable AI predicts immunotherapy outcomes across cancers and treatments
Open Access
- 3 July 2026
- journal article
- research article
- Published by Springer Nature in Nature Medicine
- Vol. 32 (8) , 1-13
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 TGFβ 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.Keywords
This publication has 55 references indexed in Scilit:
- Atezolizumab as first-line treatment in cisplatin-ineligible patients with locally advanced and metastatic urothelial carcinoma: a single-arm, multicentre, phase 2 trialThe Lancet, 2017
- Immunomodulatory Activity of Nivolumab in Metastatic Renal Cell CarcinomaClinical Cancer Research, 2016
- Atezolizumab in patients with locally advanced and metastatic urothelial carcinoma who have progressed following treatment with platinum-based chemotherapy: a single-arm, multicentre, phase 2 trialThe Lancet, 2016
- Mechanism-driven biomarkers to guide immune checkpoint blockade in cancer therapyNature Reviews Cancer, 2016
- Atezolizumab versus docetaxel for patients with previously treated non-small-cell lung cancer (POPLAR): a multicentre, open-label, phase 2 randomised controlled trialThe Lancet, 2016
- Genomic and Transcriptomic Features of Response to Anti-PD-1 Therapy in Metastatic MelanomaCell, 2016
- Genomic correlates of response to CTLA-4 blockade in metastatic melanomaScience, 2015
- T cell exclusion, immune privilege, and the tumor microenvironmentScience, 2015
- Molecular and Genetic Properties of Tumors Associated with Local Immune Cytolytic ActivityCell, 2015
- 12-Chemokine Gene Signature Identifies Lymph Node-like Structures in Melanoma: Potential for Patient Selection for Immunotherapy?Scientific Reports, 2012