Computational investigation of drug bank compounds against 3C-like protease (3CL) of SARS-CoV-2 using deep learning and molecular dynamics simulation.

Blocking the main replicating enzyme, 3 Chymotrypsin-like protease (3CL) is the most promising drug development strategy against the SARS-CoV-2 virus, responsible for the current COVID-19 pandemic. In the present work, 9101 drugs obtained from the drug bank database were screened against SARS-CoV-2 3CL prosing deep learning, molecular docking, and molecular dynamics simulation techniques. In the initial stage, 500 drug-screened by deep learning regression model and subjected to molecular docking that resulted in 10 screened compounds with strong binding affinity. Further, five compounds were checked for their binding potential by analyzing molecular dynamics simulation for 100 ns at 300 K. In the final stage, two compounds {4-[(2s,4e)-2-(1,3-Benzothiazol-2-Yl)-2-(1h-1,2,3-Benzotriazol-1-Yl)-5-Phenylpent-4-Enyl]Phenyl}(Difluoro)Methylphosphonic Acid and 1-(3-(2,4-dimethylthiazol-5-yl)-4-oxo-2,4-dihydroindeno[1,2-c]pyrazol-5-yl)-3-(4-methylpiperazin-1-yl)urea were screened as potential hits by analyzing several parameters like RMSD, Rg, RMSF, MMPBSA, and SASA. Thus, our study suggests two potential drugs that can be tested in the experimental conditions to evaluate the efficacy against SARS-CoV-2. Further, such drugs could be modified to develop more potent drugs against COVID-19.