Chemical space docking enables large-scale structure-based virtual screening to discover ROCK1 kinase inhibitors

Abstract

With the ever-increasing number of synthesis-on-demand compounds for drug lead discovery, there is a great need for efficient search technologies. We present the successful application of a virtual screening method that combines two advances: (1) it avoids full library enumeration (2) products are evaluated by molecular docking, leveraging protein structural information. Crucially, these advances enable a structure-based technique that can efficiently explore libraries with billions of molecules and beyond. We apply this method to identify inhibitors of ROCK1 from almost one billion commercially available compounds. Out of 69 purchased compounds, 27 (39%) have Ki values < 10 µM. X-ray structures of two leads confirm their docked poses. This approach to docking scales roughly with the number of reagents that span a chemical space and is therefore multiple orders of magnitude faster than traditional docking.

Evaluating scalable supervised learning for synthesize-on-demand chemical libraries

“…32 Machine learning and virtual screening tools are now being applied to score and prioritize millions to billions of compounds more routinely. 14,[33][34][35] There are examples of experimentally evaluating those predictions, [11][12][13][23][24][25][26][36][37][38][39][40][41] but they primarily employ structure-based virtual screening workflows.…”

“…GPUs to score 1.37 billion compounds in less than 24 hours. 35 However, active learning 44 and fragment-based 13,40 docking strategies are emerging to avoid exhaustively docking entire on-demand libraries.…”

Machine Learning-Boosted Docking Enables the Efficient Structure-Based Virtual Screening of Giga-Scale Enumerated Chemical Libraries

“…One strategy is to grow compounds from fragments instead of docking full-size molecules and thus avoiding the enumeration of large numbers of compounds. 7,8 Alternatively, several strategies that recently gained traction for boosting docking-based screening rely on iterative approaches utilizing machine learning (ML). [9][10][11] The idea is simple, yet powerful:…”

Chemical Space Virtual Screening against Hard-to-Drug RNA Methyltransferases DNMT2 and NSUN6

“…Alternatively, taking advantage of target knowledge can be a promising route to design its own focused chemical spaces, as demonstrated in an exclusive series of tetrahydropyridines as potential serotonin (5-hydroxytryptamine, 5-HT) receptor ligands [ 45 ]. Another approach is based on fragment-based drug design (FBDD), either physically by generating a chemical space upon crystallographically known fragment substructures and corresponding building blocks [ 46 , 47 ] or starting with pure fragment docking [ 48 , 49 ]. While both strategies rely on the placement of initial virtual ‘synthons’, a crystallographic fragment screening as a first step can support the docking process using the experimental binding mode for template docking, whereas the latter is defined by general limitations of fragment docking.…”

“…While both strategies rely on the placement of initial virtual ‘synthons’, a crystallographic fragment screening as a first step can support the docking process using the experimental binding mode for template docking, whereas the latter is defined by general limitations of fragment docking. The limitation that probably requires the most attention in this regard is that scoring functions might be unable to distinguish the correct binding mode from incorrect ones due to the intrinsically low number of interactions of fragments requiring proper additional re-scoring methods or pharmacophore constraints [ 47 , 49 , 50 , 51 ].…”