Drug Potency Prediction of SARS-CoV-2 Main Protease Inhibitors Based on a Graph Generative Model

The prediction of a ligand potency to inhibit SARS-CoV-2 main protease (M-pro) would be a highly helpful addition to a virtual screening process. The most potent compounds might then be the focus of further efforts to experimentally validate their potency and improve them. A computational method to predict drug potency, which is based on three main steps, is defined: (1) defining the drug and protein in only one 3D structure; (2) applying graph autoencoder techniques with the aim of generating a latent vector; and (3) using a classical fitting model to the latent vector to predict the potency of the drug. Experiments in a database of 160 drug-M-pro pairs, from which the pIC50 is known, show the ability of our method to predict their drug potency with high accuracy. Moreover, the time spent to compute the pIC50 of the whole database is only some seconds, using a current personal computer. Thus, it can be concluded that a computational tool that predicts, with high reliability, the pIC50 in a cheap and fast way is achieved. This tool, which can be used to prioritize which virtual screening hits, will be further examined in vitro.

Automated summary

Predicting the potency of a drug in inhibiting the SARS-CoV-2 main protease (M-pro) would greatly aid the virtual screening process. The most promising compounds could be further investigated and improved. Our computational method, based on a three-step process, accurately predicts drug potency by defining the drug and protein in a 3D structure, employing graph autoencoder techniques to generate a latent vector, and using a classical fitting model to predict potency. Experimental results on a database of 160 drug-M-pro pairs confirmed the high accuracy of our method in predicting drug potency, with the pIC50 computation taking only a few seconds on a personal computer. Therefore, we have successfully developed a cost-effective and rapid computational tool for predicting pIC50, which can prioritize virtual screening hits and will be further validated in vitro.