Phillip R. Woolley

This study evaluates zero-shot mutation prediction models in protein engineering, finding they struggle to identify optimal mutations and predict new functions due to limitations in capturing evolutionary constraints.

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 paper introduces a deep learning model that predicts biological function from chemical structure using scientific literature, identifying effective inhibitors of beta-lactamases.

The paper shows ATM deficiency leads to transcription-associated lesions, affecting cerebellum function and causing neurodegeneration through changes in transcription and PARylation.