In a new Science study, researchers introduce DrugCLIP, a contrastive learning framework that virtually screens small molecules and protein pockets, analyzing protein-ligand interactions 10 million times faster than most standard molecular docking approaches.
scim.ag/45FfSj2 
Deep contrastive learning enables genome-wide virtual screening
Recent breakthroughs in protein structure prediction have opened new avenues for genome-wide drug discovery, yet existing virtual screening methods remain computationally prohibitive. We present DrugC...
