Cianna N. Calia

The paper validates and analyzes 12,000 AI-designed CAR-T binders from a global competition, identifying successful designs and factors improving their performance.

This study uses deep learning to redesign an antifreeze protein, identifying variants with improved properties but not surpassing wild-type activity.

The paper investigates how beta-solenoid scaffolds affect threonine ladder structure and ice-binding properties, suggesting scaffold-specific effects on antifreeze protein design.

The paper analyzes a crowdsourced protein design competition, showing participants designed EGFR binders with varying affinities and highlighting challenges in benchmarking and experimental design.