Docking-generated multiple ligand poses for bootstrapping bioactivity classifying Machine Learning: Repurposing covalent inhibitors for COVID-19-related TMPRSS2 as case study

In the present work we introduce the use of multiple docked poses for bootstrapping machine learning-based QSAR modelling. Ligand-receptor contact fingerprints are implemented as descriptor variables. We implemented this method for the discovery of potential inhibitors of the serine protease enzyme TMPRSS2 involved the infectivity of coronaviruses. Several machine learners were scanned, however, Xgboost, support vector machines (SVM) and random forests (RF) were the best with testing set accuracies reaching 90%. Three potential hits were identified upon using the method to scan known untested FDA approved drugs against TMPRSS2. Subsequent molecular dynamics simulation and covalent docking supported the results of the new computational approach. (C) 2021 The Author(s). Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology.

Automated summary

In this study, the use of multiple docked poses for machine learning-based QSAR modelling was introduced to discover potential inhibitors of the serine protease enzyme TMPRSS2. Xgboost, SVM, and RF were found to be the best machine learners with testing set accuracies reaching 90%. Three potential hits were identified by scanning known untested FDA approved drugs against TMPRSS2. Subsequent molecular dynamics simulation and covalent docking supported the new computational approach's results.