Stephen Buckley

This paper introduces an AI-based framework for designing responsive protein oligomers that assemble in response to chemical or phosphorylation triggers, validated through experimental testing.

This paper designs switchable cytokines that are activated by Venetoclax, showing tumor control comparable to native cytokines and enhancing therapeutic safety.

This paper designs phosphorylation-induced protein switches that control transcription in cells, demonstrating their functionality in synthetic signaling.

This paper designs proteins that target neosurfaces from protein-ligand complexes using a deep learning approach, validated experimentally against three drug-bound protein complexes.

Hallucinating binders by backpropagating through AlphaFold2 weights gave, across 12 targets, binders in 10-100% of the designs tested per target, mostly at nanomolar affinity.