Machine Learning augmented docking studies of aminothioureas at the SARS-CoV-2—ACE2 interface

Abstract

The current pandemic outbreak clearly indicated the urgent need for tools allowing fast predictions of bioactivity of a large number of compounds, either available or at least synthesizable. In the computational chemistry toolbox, several such tools are available, with the main ones being docking and structure-activity relationship modeling either by classical linear QSAR or Machine Learning techniques. In this contribution, we focus on the comparison of the results obtained using different docking protocols on the example of the search for bioactivity of compounds containing N-N-C(S)-N scaffold at the S-protein of SARS-CoV-2 virus with ACE2 human receptor interface. Based on over 1800 structures in the training set we have predicted binding properties of the complete set of nearly 600000 structures from the same class using the Machine Learning Random Forest Regressor approach.

Methodology-Centered Review of Molecular Modeling, Simulation, and Prediction of SARS-CoV-2

“…In addition, an RF classifier was applied to the analysis of multiple isotype-specific responses to identify infected individuals . Rola et al studied different docking protocols and applied structures from 2D and 3D at the molecular mechanics level as features for the random forest for docking studies of the SARS-CoV-2 S protein binding to ACE2. RF models were also applied to identify SARS-CoV-2 drug inhibitors and antibodies for SARS-CoV-2 S protein and N protein. , …”