Tweet
The IFM team is glad to announce that their recent investigation on the impact of AI-driven technologies on virtual screening is out. Our work suggests a new role for co-folding methods like Boltz2 in the drug discovery pipeline with potentially increased enrichments. It will be exciting to see how this will help conceiving new pharmaceuticals. The results have appeared in the Journal of Chemical Information and Modelling (JCIM).
Abstract
AI foundational models for predicting protein-ligand interactions and binding affinities have started to emerge. We challenged Boltz-2 on a difficult dataset constructed on ten ultra-large virtual screening hit lists of pharmacologically relevant targets with in vitro binding assays. We show that Boltz-2 is the best classifier, with a success rate twice that of any other rescoring strategy. Ligand classifications by Boltz-2 are straightforward, accurate, efficient and robust, opening to million-compound accurate rankings on commodity resources.
Reference
Rise of AI Technologies in Virtual Screening
Marco Cecchini and Hryhory Sinenka
Journal of Chemical Information and Modeling, Published April 16 (2026), DOI: https://pubs.acs.org/doi/full/10.1021/acs.jcim.6c00877
