Deep Learning-based Modeling Enhances Efficacy of Natural Ligand CAR Binders Targeting CD70

Prior work has shown that a “natural ligand” (NL)-based CAR targeting CD70, employing its physiological interaction partner CD27, may have therapeutic advantages over antibody-based CARs. However, in contrast to antibody-based CARs, it is largely unknown whether sequence modification of NL CARs can further improve activity.

To address this question, here we used deep learning and physics-based modeling to alter energetically-relevant amino acids at the CD27:CD70 interface. We identify a CD27 variant “N88A” which enhanced efficacy of CD70-targeting CAR T-cells across models of acute myeloid leukemia, multiple myeloma, and renal cell carcinoma. Biophysical approaches, including molecular dynamics simulations, support a mechanism of increased binder conformational freedom underlying potency enhancement.