Deep learning-accelerated docking coupled with computational hit selection strategies enable the identification of inhibitors for the SARS-CoV-2 main protease from a chemical library of 40 billion small molecules.

The current COVID-19 pandemic has elicited extensive repurposing efforts (both small and large scale) to rapidly identify COVID-19 treatments among approved drugs. Herein, we provide a literature review of large-scale SARS-CoV-2 antiviral drug repurposing efforts and highlight a marked lack of consistent potency reporting. This variability indicates the importance of standardizing best practices—including the use of relevant cell lines, viral isolates, and validated screening protocols. We further surveyed available biochemical and virtual screening studies against SARS-CoV-2 targets (Spike, ACE2, RdRp, PL pro , and M pro ) and discuss repurposing candidates exhibiting consistent activity across diverse, triaging assays and predictive models. Moreover, we examine repurposed drugs and their efficacy against COVID-19 and the outcomes of representative repurposed drugs in clinical trials. Finally, we propose a drug repurposing pipeline to encourage the implementation of standard methods to fast-track the discovery of candidates and to ensure reproducible results.

Computational prediction of ligand–target interactions is a crucial part of modern drug discovery as it helps to bypass high costs and labor demands of in vitro and in vivo screening. As the wealth of bioactivity data accumulates, it provides opportunities for the development of deep learning (DL) models with increasing predictive powers. Conventionally, such models were either limited to the use of very simplified representations of proteins or ineffective voxelization of their 3D structures. Herein, we present the development of the PSG-BAR (Protein Structure Graph-Binding Affinity Regression) approach that utilizes 3D structural information of the proteins along with 2D graph representations of ligands. The method also introduces attention scores to selectively weight protein regions that are most important for ligand binding. Results: The developed approach demonstrates the state-of-the-art performance on several binding affinity benchmarking datasets. The attention-based pooling of protein graphs enables identification of surface residues as critical residues for protein–ligand binding. Finally, we validate our model predictions against an experimental assay on a viral main protease (Mpro)—the hallmark target of SARS-CoV-2 coronavirus.

MotivationComputational prediction of ligand-target interactions is a crucial part of modern drug discovery as it helps to bypass high costs and labor demands of in vitro and in vivo screening. As the wealth of bioactivity data accumulates, it provides opportunities for the development of deep learning (DL) models with increasing predictive powers. Conventionally, such models were either limited to the use of very simplified representations of proteins or ineffective voxelization of their 3D structures. Herein, we present the development of the PSG-BAR (Protein Structure Graph –Binding Affinity Regression) approach that utilizes 3D structural information of the proteins along with 2D graph representations of ligands. The method also introduces attention scores to selectively weight protein regions that are most important for ligand binding.ResultsThe developed approach demonstrates the state-of-the-art performance on several binding affinity benchmarking datasets. The attention-based pooling of protein graphs enables identification of surface residues as critical residues for protein-ligand binding. Finally, we validate our model predictions against an experimental assay on a viral main protease (Mpro)– the hallmark target of SARS-CoV-2 coronavirus.AvailabilityThe code for PSG-BAR is made available at https://github.com/diamondspark/PSG-BARContactacherkasov@prostatecentre.com

No abstract