A machine learning regression model for the screening and design of potential SARS-CoV-2 protease inhibitors

The widespread infection caused by the 2019 novel corona virus (SARS-CoV-2) has initiated global efforts to search for antiviral agents. Drug discovery is the first step in the development of commercially viable pharmaceutical products to deal with novel diseases. In an effort to accelerate the screening and drug discovery workflow for potential SARS-CoV-2 protease inhibitors, a machine learning model that can predict the binding free energies of compounds to the SARS-CoV-2 main protease is presented. The optimized multiple linear regression model, which was trained and tested on 226 natural compounds demonstrates reliable prediction performance (r(2) test = 0.81, RMSE test = 0.43), while only requiring five topological descriptors. The externally validated model can help conserve and maximize available resources by limiting biological assays to compounds that yielded favorable outcomes from the model. The emergence of highly infectious diseases will always be a threat to human health and development, which is why the development of computational tools for rapid response is very important.

Automated summary

A machine learning model has been proposed to predict potential SARS-CoV-2 protease inhibitors' binding free energies, demonstrating reliable predictive performance with only five topological descriptors from training and testing data of 226 natural compounds. The externally validated model helps conserve resources, mitigate the threat of highly infectious diseases, and expedite new drug development.