Deep Learning-based Modeling Enhances Efficacy of Natural Ligand CAR Binders Targeting CD70
- 1University of California, San Francisco
Abstract
CD70 is well-recognized as a promising "pan-cancer: chimeric antigen receptor (CAR) T-cell target. 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. Yet while antibody-based CARs are routinely optimized by affinity maturation of their scFv, whether the binding sequence of an NL CAR can be engineered to improve its function remains unexplored. Here, we combined deep learning with physics-based modeling to redesign residues at the CD27:CD70 interface, identifying a CD27 variant, "N88A", which enhances the 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. Our work presents CD27N88A CAR T-cells as a promising new therapeutic option and proposes that computational modeling could be applied to enhance efficacy of other NL-based immunotherapies.
Related
- 914 Dual-antigen targeting via a PMPC-engineered bispecific ADC overcomes tumor heterogeneity and enhances anti-tumor efficacy in advanced ovarian cancer
- Antibody-drug conjugate combination therapy targeting LGR5 and MET with different payloads enhances efficacy in preclinical colorectal cancer models
- Antibody Targeting Soluble NKG2D Ligand MIC Enhances Adoptive T-Cell Therapy in an NK Cell-Dependent Mechanism
- Structural engineering of dual-targeting antisense oligonucleotides enhances exon 44 skipping for treating Duchenne muscular dystrophy
- 837 Targeting a CD36-dependent macrophage immunometabolic program enhances PARP inhibitor response in BRCA-associated TNBC
BibTeX
@misc{kang2026deep,
title = {{Deep Learning-based Modeling Enhances Efficacy of Natural Ligand CAR Binders Targeting CD70}},
author = {A. S. Kang and R. Dalal and M. Li and A. A. Ojha and S. Walunj and C. E. Cornell and R. Rahnama and A. Barpanda and S. Prudhvi and T. Patel and M. Aspinall-O'Dea and B. Walker and C. Adams and V. Steri and P. Phojanakong and J. A. Camara Serrano and H. Li and J. Rivera and D. A. Fletcher and B. J. Huang and S. M. Hanson and P. Cossio and T. Kortemme and J. Eyquem and A. P. Wiita},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.06.749651},
url = {https://www.biorxiv.org/content/10.64898/2026.09.06.749651v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Deep Learning-based Modeling Enhances Efficacy of Natural Ligand CAR Binders Targeting CD70
AU - A. S. Kang
AU - R. Dalal
AU - M. Li
AU - A. A. Ojha
AU - S. Walunj
AU - C. E. Cornell
AU - R. Rahnama
AU - A. Barpanda
AU - S. Prudhvi
AU - T. Patel
AU - M. Aspinall-O'Dea
AU - B. Walker
AU - C. Adams
AU - V. Steri
AU - P. Phojanakong
AU - J. A. Camara Serrano
AU - H. Li
AU - J. Rivera
AU - D. A. Fletcher
AU - B. J. Huang
AU - S. M. Hanson
AU - P. Cossio
AU - T. Kortemme
AU - J. Eyquem
AU - A. P. Wiita
PY - 2026
DA - 2026/09/06
PB - bioRxiv
DO - 10.64898/2026.09.06.749651
UR - https://www.biorxiv.org/content/10.64898/2026.09.06.749651v1
AB - CD70 is well-recognized as a promising "pan-cancer: chimeric antigen receptor (CAR) T-cell target. 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. Yet while antibody-based CARs are routinely optimized by affinity maturation of their scFv, whether the binding sequence of an NL CAR can be engineered to improve its function remains unexplored. Here, we combined deep learning with physics-based modeling to redesign residues at the CD27:CD70 interface, identifying a CD27 variant, "N88A", which enhances the 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. Our work presents CD27N88A CAR T-cells as a promising new therapeutic option and proposes that computational modeling could be applied to enhance efficacy of other NL-based immunotherapies.
ER -