Modeling Chimeric Antigen Receptor Response at the Single-Cell Level with Conditional Optimal Transport

Chimeric Antigen Receptor (CAR) T-cell therapy is a promising cancer immunotherapy, yet several challenges hamper its clinical efficacy. While new computational models are attempting to explore the vast combinatorial design space of CAR components and suggest new designs, there remain challenges in capturing cellular heterogeneity as well as generalizing to novel CAR variants. Here, we introduce an Optimal Transport (OT)-based framework designed to predict response to CAR expression at the single-cell level, including variants that have not been experimentally tested. Our model accurately captures gene expression changes across diverse CAR variants, significantly outperforming the baseline for in-distribution CARs while reflecting biological characteristics. By embedding CARs via protein language models, we extend our framework to a conditional OT-based model, successfully generalizing our predictions to out-of-distribution CAR designs. Our findings highlight the utility of OT-based modeling in elucidating CAR design-function relationships, enabling the rational design of novel CARs with therapeutic potential.