Back

State-of-the-art covalent virtual screening with AlphaFold3

London, N.; Shamir, Y.

2025-03-19 biochemistry
10.1101/2025.03.19.642201 bioRxiv
Show abstract

Covalent inhibitors are a prominent modality for research and therapeutic tools. However, a scarcity of computational methods for their discovery slows progress in this field. AI models such as AlphaFold3 (AF3) have shown accuracy in ligand pose prediction, but their applicability for virtual screening campaigns was not assessed. We show that AF3 co-folding predictions and an associated predicted confidence metric ranks true covalent binders with near-optimal classification over property-matched decoys, significantly outperforming state-of-the-art covalent docking tools for a set of protein kinases. In a prospective virtual screening campaign against the model kinase BTK, we discovered a chemically distinct, novel, covalent small molecule that displays potent inhibition in vitro and in cells while maintaining marked kinome and proteomic selectivity. Co-crystallography validated the sub-angstrom accuracy of the predicted AF3 binding mode. These results demonstrate that AF3 can be practically used to discover novel chemical matter for kinases, one of the most prolific families of drug targets.

Published in Journal of the American Chemical Society (predicted rank #5) · training set

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.