Sequence and structural determinants of efficacious de novo chimaeric antigen receptors
- 1Computational and Systems Biology Program, Memorial Sloan Kettering Cancer Center, New York, NY, USA
- 2Computational and Systems Biology Program, Memorial Sloan Kettering Cancer Center, New York, NY, USA. [email protected]
Abstract
Advances in generative protein design using artificial intelligence (AI) have enabled the rapid development of binders against heterogeneous targets, including tumour-associated antigens. Despite extensive biochemical characterization, these novel protein binders have had limited evaluation in candidate therapeutics, including chimaeric antigen receptor (CAR) T cells. Here we synthesize generative protein design workflows to screen 1,758 newly designed protein binders targeting BCMA, CD19 and CD22 for efficacy in scalable protein-binding, T-cell activation and in vivo killing assays. We characterize three main challenges that hinder the utility of de novo protein binders as CARs, including tonic signalling, occluded epitope engagement and off-target activity. We develop computational and experimental heuristics to overcome these limitations, including screens of sequence variants of individual parental structures, that retain on-target CAR activation while mitigating liabilities. Together, our framework accelerates the development of AI-designed proteins for future preclinical therapeutic screening, helping enable a new generation of cellular therapies.
Related
- Decoding the Sequence Determinants of DNA Cleavage in Histidine-Containing Copper(II) Metallopeptides
- mRNA-based tuberculosis vaccines BNT164a1 and BNT164b1 are immunogenic, well tolerated and efficacious in rodent models
- From Structural Blindness to Structural Perception: Theorizing LUMEN, a Multisensory Pedagogy for the Structural Determinants of Health in Nursing Education.
- Beyond Iron Supplementation: A Narrative Review of the Structural Determinants of Anaemia in Pregnancy in India.
- Lifestyle interventions on Alzheimer's disease and related dementias: Social and structural determinants of implementation effectiveness and sustainability.
BibTeX
@article{chow2026sequence,
title = {{Sequence and structural determinants of efficacious de novo chimaeric antigen receptors}},
author = {Arthur Chow and Hoyin Chu and Ruofan Li and Benan N. Nalbant and Abdul Vehab Dozic and Laura C. Kida and Zeyu Tang and Joseph R. Palmeri and Caleb A. Lareau},
journal = {Nature Biomedical Engineering},
year = {2026},
month = sep,
doi = {10.1038/s41551-026-01790-9},
url = {https://doi.org/10.1038/s41551-026-01790-9},
note = {CC BY},
}
RIS
TY - JOUR
TI - Sequence and structural determinants of efficacious de novo chimaeric antigen receptors
AU - Arthur Chow
AU - Hoyin Chu
AU - Ruofan Li
AU - Benan N. Nalbant
AU - Abdul Vehab Dozic
AU - Laura C. Kida
AU - Zeyu Tang
AU - Joseph R. Palmeri
AU - Caleb A. Lareau
PY - 2026
DA - 2026/09/09
JO - Nature Biomedical Engineering
DO - 10.1038/s41551-026-01790-9
UR - https://doi.org/10.1038/s41551-026-01790-9
AB - Advances in generative protein design using artificial intelligence (AI) have enabled the rapid development of binders against heterogeneous targets, including tumour-associated antigens. Despite extensive biochemical characterization, these novel protein binders have had limited evaluation in candidate therapeutics, including chimaeric antigen receptor (CAR) T cells. Here we synthesize generative protein design workflows to screen 1,758 newly designed protein binders targeting BCMA, CD19 and CD22 for efficacy in scalable protein-binding, T-cell activation and in vivo killing assays. We characterize three main challenges that hinder the utility of de novo protein binders as CARs, including tonic signalling, occluded epitope engagement and off-target activity. We develop computational and experimental heuristics to overcome these limitations, including screens of sequence variants of individual parental structures, that retain on-target CAR activation while mitigating liabilities. Together, our framework accelerates the development of AI-designed proteins for future preclinical therapeutic screening, helping enable a new generation of cellular therapies.
SN - 2157-846X
ER -