V-SYNTHES2—the next generation tool for structure-based virtual screening of giga-scale chemical spaces

On-demand chemical spaces of drug-like compounds open new horizons in the discovery of ligands and drug candidates for clinically relevant targets, but also expose the scalability of computational screening as a key bottleneck. Recently, we introduced the V-SYNTHES modular screening approach, showing >1000-fold acceleration relative to direct brute-force docking of fully enumerated ultra-large chemical libraries. Initially, the method was based on the early version of Enamine REAL space (11 billion compounds) and validated on two relatively well-characterized targets. Here we present an upgraded V-SYNTHES2 workflow with improved automation features and scalability, expanding to REAL Space of 36 billion readily available compounds, and assessing its performance on new, more challenging targets. V-SYNTHES2 introduces a new geometry-based CapSelect tool that fully automates fragment selection based on docking scores and binding poses of the Minimal Enumeration Library (MEL). The method shows excellent enrichment and binding pose reproducibility in computational benchmarks, including targets with shallow pockets, RNA-binding sites, GPCRs, and phospholipid-binding enzymes. Experimental validation shows the utility of this workflow in prospective screening campaigns for two novel targets. The fully automated V-SYNTHES2 workflow can be deployed on computing clusters or clouds, offering a powerful tool for effective screening of giga-scale chemical spaces.