Active learning framework for high-throughput virtual screening — GIN surrogate model with MC-Dropout uncertainty, Thompson Sampling acquisition, and plug-in docking oracles (QED mock · AutoDock Vina · Glide). Recovers >95% of top-1% hits while docking only ~6% of the library. Based on Graff, Shakhnovich & Coley, Chem. Sci. 2021.
python machine-learning bioinformatics deep-learning cheminformatics pytorch computational-chemistry thompson-sampling drug-discovery screening rdkit active-learning virtual-screening molecular-docking mc-dropout graph-neural-networks pytorch-geometric gnn hit-discovery molecular-ml
-
Updated
Jun 25, 2026