Agenus Inc. (NASDAQ: AGEN) announced retrospective data showing that artificial intelligence analysis of routine tumor images identified patients more likely to respond to its experimental cancer treatment combination.

The analysis used Noetik's TARIO-2 platform to examine standard pathology images from 113 patients treated with botensilimab plus balstilimab in a Phase 1b trial. The AI system analyzed spatial tumor microenvironment patterns from hematoxylin and eosin stained tissue samples taken before treatment.

In patients with microsatellite stable metastatic colorectal cancer without active liver metastases, the AI-identified subgroup showed a 64% response rate compared to 9% in the remaining patients. The AI-identified group also demonstrated significantly improved overall survival, with median survival not yet reached and a hazard ratio of 0.18 versus other patients.

The data will be presented at the American Society of Clinical Oncology Annual Meeting on May 30, 2026. The analysis included patients with colorectal cancer, ovarian cancer and sarcomas from the C-800-01 trial.

"These data suggest that AI-based analysis of pretreatment H&E images may help identify spatial tumor microenvironment patterns associated with clinical benefit from BOT+BAL," said Ryan Dalton, Senior Computational Scientist at Noetik.

Botensilimab is an Fc-enhanced anti-CTLA-4 antibody designed to enhance immune responses against tumors. Balstilimab is an anti-PD-1 antibody. The combination has been evaluated in approximately 1,300 patients across multiple tumor types.

The companies stated the findings support prospective validation of the AI model as a biomarker strategy for the treatment combination. Agenus is conducting a global Phase 3 trial evaluating the combination in metastatic colorectal cancer.