Keeping pace with the explosive growth of chemical libraries with structure‐based virtual screening

Abstract Recent efforts to synthetically expand drug‐like chemical libraries have led to the emergence of unprecedently large virtual databases. This surge of make‐on‐demand molecular datasets has been received enthusiastically across the drug discovery community as a new paradigm. In several recent studies, virtual screening (VS) of larger make‐on‐demand collections resulted in the identification of novel molecules with higher potency and specificity compared to more conventional VS campaigns relying on smaller in‐stock libraries. These results inspired ultra‐large VS against various clinically relevant targets, including key proteins of the SARS‐CoV‐2 virus. As library sizes rapidly surpassed the billion compounds mark, new computational screening strategies emerged, shifting from conventional docking to fragment‐based and machine learning‐accelerated methods. These approaches significantly reduce computational demands of ultra‐large screenings by lowering the number of molecules explicitly docked onto a target. Such strategies already demonstrated promise in evaluating libraries of tens of billions of molecules at relatively low computational cost. Herein, we review recent advancements in structure‐based methods for ultra‐large virtual screening that drug discovery practitioners have adopted to explore the ever‐expanding chemical universe. This article is categorized under: Data Science > Databases and Expert Systems Data Science > Artificial Intelligence/Machine Learning Molecular and Statistical Mechanics > Molecular Mechanics