The abstract is read at the publisher; the summary is JClub's.
Screening 1,758 AI-designed protein binders against BCMA, CD19, and CD22 identified sequence and structural determinants that retain on-target CAR activation while mitigating tonic signalling, occluded epitope engagement, and off-target activity.
- Why it matters: De novo binders have been well characterized biochemically but are not yet reliably evaluated as candidate CAR therapeutics, limiting translation to T-cell efficacy.
- What they did: The study synthesized generative protein design workflows and tested 1,758 binders in scalable protein-binding, T-cell activation, and in vivo killing assays, then used computational and experimental heuristics plus sequence-variant screens of parental structures.
- The result: The resulting framework accelerates preclinical screening of AI-designed proteins for cellular therapies by addressing key CAR-specific liabilities linked to signalling, epitope accessibility, and off-target activity.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.