HIt Discovery using docking ENriched by GEnerative Modeling (HIDDEN GEM): A novel computational workflow for accelerated virtual screening of ultra‐large chemical libraries

Abstract

Recent rapid expansion of make‐on‐demand, purchasable, chemical libraries comprising dozens of billions or even trillions of molecules has challenged the efficient application of traditional structure‐based virtual screening methods that rely on molecular docking. We present a novel computational methodology termed HIDDEN GEM ( <b>HI</b>t Discovery using <b>D</b>ocking <b>EN</b>riched by <b>GE</b>nerative <b>M</b>odeling) that greatly accelerates virtual screening. This workflow uniquely integrates machine learning, generative chemistry, massive chemical similarity searching and molecular docking of small, selected libraries in the beginning and the end of the workflow. For each target, HIDDEN GEM nominates a small number of top‐scoring virtual hits prioritized from ultra‐large chemical libraries. We have benchmarked HIDDEN GEM by conducting virtual screening campaigns for 16 diverse protein targets using Enamine REAL Space library comprising 37 billion molecules. We show that HIDDEN GEM yields the highest enrichment factors as compared to state of the art accelerated virtual screening methods, while requiring the least computational resources. HIDDEN GEM can be executed with any docking software and employed by users with limited computational resources.

STOPLIGHT: A Hit Scoring Calculator

“…STOPLIGHT can be used at the end of a virtual screen to help rank which compounds follow up on with experiments. STOPLIGHT was used on three virtual screening sets, two taken from a virtual docking campaign and one from a quantitative structure activity (QSAR) modeling campaign. Each set is composed of 5,000 initial virtual hits.…”

Correlation of protein binding pocket properties with hits’ chemistries used in generation of ultra-large virtual libraries

“…The surge in utilization of computational approaches has been stimulated by improvements in binding energy calculations, the growth of computational resources, advances in protein structures determination and availability of large and diverse virtual libraries of compounds [3][4][5][6][7][8][9][10][11][12][13][14][15]. However, our ability to access the vast druggable chemical space is still limited and will be impacted by the limits of computing resources for the foreseeable future [16][17][18][19]. We have the potential of generating trillions or more of virtual synthesizable molecules, but enumerating these chemical spaces, and thus converting them into screenable files is impractical if not impossible in practice.…”