Agenus Partners with Noetik to Develop AI-Powered Biomarkers for Precision Immunotherapy
核心洞察
Agenus and Noetik (搜索) announced a research collaboration to develop predictive biomarkers for the BOT/BAL immunotherapy combination using AI-powered virtual cell models.
The partnership leverages Noetik (搜索)'s OCTO foundation model, trained on data from nearly 200 million tumor and immune cells across thousands of patients with various cancer types.
The collaboration aims to identify which patients are most likely to respond to botensilimab and balstilimab treatment, potentially improving clinical trial outcomes and patient care.
Agenus Inc. and Noetik (搜索) have announced a research collaboration to develop predictive biomarkers for Agenus' lead immunotherapy combination using artificial intelligence-powered virtual cell models. The partnership aims to identify which patients are most likely to benefit from treatment with botensilimab (BOT) and balstilimab (BAL), potentially accelerating precision immunotherapy development.
AI-Powered Virtual Cell Models Drive Biomarker Discovery
Central to the collaboration is Noetik (搜索)'s OCTO virtual cell model, a 1.5 billion parameter foundation model trained on one of the largest proprietary multimodal spatial datasets in oncology. This comprehensive dataset integrates spatial proteomics, spatial transcriptomics, H&E pathology, DNA genotyping, and clinical metadata from nearly 200 million tumor and immune cells collected from thousands of patients with cancers including colorectal cancer (搜索), non-small cell lung cancer (搜索), ovarian cancers (搜索), and sarcomas (搜索).
"By integrating these diverse data types, Noetik (搜索)'s foundation models provide a systems-level view of the tumor microenvironment in real patients, unlocking novel insights into cancer biology that can drive more precise therapeutic discovery and development," according to the companies.
Extensive Clinical Experience with BOT/BAL Combination
Botensilimab, alone or in combination with balstilimab, has been evaluated in more than 1,200 patients across nine tumor types, including colorectal cancer (搜索), NSCLC, and sarcomas (搜索). The combination targets complementary immune pathways and has demonstrated deep and durable clinical responses, even in tumors considered immunotherapy "cold" or resistant to prior immunotherapy treatment.
The regimen has generated recognition within the medical community, supported by compelling data presented in both late-line and neoadjuvant settings, multiple peer-reviewed publications, and presentations at more than a dozen major medical congresses over the past three years. The collaboration builds on a landmark 2024 Cancer Discovery study that elucidated botensilimab's unique FcγR-mediated immune activation underlying activity in refractory tumors.
Exclusive Rights and Clinical Applications
The collaboration will use OCTO virtual cell models to simulate tumor behavior and analyze complex biological data from multiple cancer types. The goal is to identify patterns that can predict treatment outcomes and help classify patient groups who may benefit most from BOT/BAL therapy. Agenus will have exclusive rights to apply these insights in its drug development and commercialization efforts.
"Enhancing clinical efficacy is the most important problem in developing new medicines, and exactly what we've trained our foundation models to do," said Ron Alfa, M.D., Ph.D., CEO & Co-Founder of Noetik (搜索). "We are excited to deploy Noetik's virtual cell foundation models on Agenus' rich clinical data to uncover biomarkers that can enrich patient therapeutic response, improve trial outcomes, and ultimately deliver more precise therapies."
Advancing Precision Medicine in Oncology
Dr. Garo Armen, Chairman and CEO of Agenus, emphasized the potential impact of the collaboration: "By integrating Noetik (搜索)'s virtual cell models with our expansive BOT/BAL clinical dataset, we have the potential to accelerate the identification of predictive biomarkers, enhance the success of our pivotal trials, and ultimately improve outcomes for patients who currently have limited or no treatment options."
The collaboration reflects growing momentum in oncology toward model-driven trial design and AI-enabled precision medicine, an area increasingly prioritized by the FDA as central to advancing more equitable and effective cancer care. By applying these technologies to real patient data, the partnership aims to accelerate delivery of more personalized treatments and expand access to therapies for patients who need them most.
Novel Mechanism of Action
Botensilimab is a human Fc enhanced CTLA-4 (搜索) blocking antibody designed to boost both innate and adaptive anti-tumor immune responses. Its novel design leverages mechanisms of action to extend immunotherapy benefits to "cold" tumors which generally respond poorly to standard of care or are refractory to conventional PD-1 (搜索)/CTLA-4 therapies. The antibody augments immune responses across a wide range of tumor types by priming and activating T cells, downregulating intratumoral regulatory T cells, activating myeloid cells and inducing long-term memory responses.
Balstilimab is a fully human monoclonal immunoglobulin G4 (IgG4) designed to block PD-1 (搜索) from interacting with its ligands PD-L1 (搜索) and PD-L2 (搜索). It has been evaluated in more than 900 patients to date and has demonstrated clinical activity and a favorable tolerability profile in several tumor types. Approximately 1,100 patients have been treated across the botensilimab/balstilimab program in phase 1 and phase 2 clinical trials.