Abstract B103: Optim.AI 2.0™: An immune-integrated functional precision platform for predicting combinatorial immunotherapy response

Abstract Background: Immunotherapies have improved the management of various cancers, with response rates observed in approximately 20-40% of patients. However, the variable response and lack of reliable biomarkers pose challenges in predicting responses to immunotherapy, thus limiting its efficacy. Optim.AI™ is a combinatorial functional precision medicine platform that has previously demonstrated clinical utility in predicting effective combination therapies for hematological cancers and sarcoma. While these studies have successfully guided chemo- and targeted-based therapies, the absence of immune cells limited the types of drugs that can be evaluated. This study introduces Optim.AI™ 2.0, which incorporates high-content imaging of tumor-immune co-culture models to also evaluate ex vivo immunotherapy response. We aim to evaluate its potential to functionally predict responses to immunotherapy combinations across both solid and hematological cancers. Methods: Peripheral blood mononuclear cells (PBMCs) and tumor cells (diffuse large B-cell lymphoma (DLBCL) and breast cancer (BC)) were fluorescently labeled to facilitate multicellular tracking for high-content analysis. Combinatorial drug treatment was carried out on the co-culture models with indication-specific 12-drug panels, including immunotherapies such as monoclonal antibodies, antibody-drug conjugates and bispecific antibodies. High-content imaging analysis of tumor-specific cell death was evaluated and used as dataset for Optim.AI™ 2.0 analysis, ranking all possible combinatorial therapies. Results: Leveraging Optim.AI™ 2.0 platform, optimized effector-to-target ratios were established across indications to effectively quantify immune-mediated tumor killing, including antibody-dependent cellular cytotoxicity (ADCC), following drug treatment. High-content imaging enabled endpoint-based phenotypic assessment of tumor-specific killing and visualization of key immune-tumor dynamics, such as immune cell migration and tumor cell infiltration. The platform demonstrated feasibility and specificity across indications by capturing antigen-dependent responses and identifying distinct, context-specific antibody-based combinations in both hematological and solid tumor models. Conclusion: We have developed a high-throughput, high-content antibody-based platform that enables immunotherapy-focused drug sets to be evaluated in a physiologically relevant tumor-immune cell co-culture system. With further validation in other indications, this integrated platform could help guide clinicians in identifying effective immunotherapy-based therapies across both solid and hematological cancers. Citation Format: Edward Kai-Hua. Chow, Sharon Chan, Jhin Jieh Lim, Masturah Mohd Abdul Rashid. Optim.AI 2.0™: An immune-integrated functional precision platform for predicting combinatorial immunotherapy response [abstract]. In: Proceedings of the AACR-NCI-EORTC International Conference on Molecular Targets and Cancer Therapeutics; 2025 Oct 22-26; Boston, MA. Philadelphia (PA): AACR; Mol Cancer Ther 2025;24(10 Suppl):Abstract nr B103.