Ultrahigh-throughput virtual screening (uHTVS) is an emerging field linking together classical docking techniques with high-throughput AI methods. We outline mechanistic docking models' goals and successes. We present different AI accelerated workflows for uHTVS, mainly through surrogate docking models. We showcase a novel feature representation technique, molecular depictions (images), as a surrogate model for docking. Along with a discussion on analyzing screens using regression enrichment surfaces at the tens of billion scale, we outline a future for uHTVS screening pipelines with deep learning.
Keywords: Chemical screening; Deep learning; Drug discovery; Graph convolution; Protein–ligand docking; Virtual screening.
© 2022. The Author(s), under exclusive license to Springer Science+Business Media, LLC, part of Springer Nature.