Simple Summary The coronavirus disease 2019 (COVID-19) pandemic caused more than 6.7 million deaths worldwide. Certain groups of individuals are still at a high risk of severe illness. The availability of drugs to treat COVID-19 symptoms will save many lives. The main protease (M-pro) of SARS-CoV2, the causal agent of COVID-19, is a promising target for drug discovery. Natural products have been used for thousands of years to treat diseases and represent valuable resources for drug discovery. While the process of experimentally screening chemicals for drug discovery has often been very long and expensive, recent advances in virtual screening have made it possible to screen millions of potential chemicals in a very short time using computers. In this research, around 400,000 natural products were virtually screened within a month and narrowed down to 20 products that could potentially bind to the SARS-CoV2 M-pro. In vitro experimental testing of seven natural products demonstrated that the virtual screening approach used in this study had a significantly high rate of accuracy since more than 50% of the experimentally tested natural products (four out of seven) were able to inhibit the function of the M-pro in real-life consistent with the computer predictions. Our results show that with further research, beta-carboline, N-alkyl indole, and Benzoic acid ester types of natural products could be used in treating COVID-19 in the future. The rapid spread of the coronavirus disease 2019 (COVID-19) resulted in serious health, social, and economic consequences. While the development of effective vaccines substantially reduced the severity of symptoms and the associated deaths, we still urgently need effective drugs to further reduce the number of casualties associated with SARS-CoV-2 infections. Machine learning methods both improved and sped up all the different stages of the drug discovery processes by performing complex analyses with enormous datasets. Natural products (NPs) have been used for treating diseases and infections for thousands of years and represent a valuable resource for drug discovery when combined with the current computation advancements. Here, a dataset of 406,747 unique NPs was screened against the SARS-CoV-2 main protease (M-pro) crystal structure (6lu7) using a combination of ligand- and structural-based virtual screening. Based on 1) the predicted binding affinities of the NPs to the M-pro, 2) the types and number of interactions with the M-pro amino acids that are critical for its function, and 3) the desirable pharmacokinetic properties of the NPs, we identified the top 20 candidates that could potentially inhibit the M-pro protease function. A total of 7 of the 20 top candidates were subjected to in vitro protease inhibition assay and 4 of them (4/7; 57%), including two beta carbolines, one N-alkyl indole, and one Benzoic acid ester, had significant inhibitory activity against M-pro protease. These four NPs could be developed further for the treatment of COVID-19 symptoms.
