Given the urgent need to find an alternative drug to vaccines used to treat the SARS-CoV-2 epidemic, we performed two-dimensional quantitative structure–activity relationship (QSAR) models to predict the therapeutic activity of 78 analogues of PF-07321332 (nitrile -containing antiviral compounds): Multiple Linear Regression (MLR), Multilayer Perceptron network (MLP) and Feed forward Neural Network using Particle Swarm Optimization (FNN-PSO).

Given the urgent need to find an alternative drug to vaccines used to treat the SARS-CoV-2 epidemic, we performed two-dimensional quantitative structure–activity relationship (QSAR) models to predict the therapeutic activity of 78 analogues of PF-07321332 (nitrile -containing antiviral compounds): Multiple Linear Regression (MLR), Multilayer Perceptron network (MLP) and Feed forward Neural Network using Particle Swarm Optimization (FNN-PSO). Five desсrіptors were selected using genetic algorithms, whereas, internal and external validation of the models was performed according to all available validation strategies. It was shown that 3CLpro enzyme inhibitory activity is mainly governed by polarizability, the structure of the molecule, and the hydrogen bonds. The best results were obtained with the MLP model. The results obtained may assist in the design of new 3CLpro enzyme inhibitors.