Docking-generated multiple ligand poses for bootstrapping bioactivity classifying Machine Learning: Repurposing covalent inhibitors for COVID-19-related TMPRSS2 as case study
Authors:
Open Access
- 1 January 2021
- journal article
- research article
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 19, 4790-4824
Abstract
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.Keywords
Funding Information
- University of Jordan
- Hashemite University
This publication has 157 references indexed in Scilit:
- The pharmacological landscape and therapeutic potential of serine hydrolasesNature Reviews Drug Discovery, 2012
- Recent advances in computer-aided drug designBriefings in Bioinformatics, 2009
- Synthetic and structural studies on syringolin A and B reveal critical determinants of selectivity and potency of proteasome inhibitionProceedings of the National Academy of Sciences, 2009
- Efficient Drug Lead Discovery and OptimizationAccounts of Chemical Research, 2009
- Active site conformational changes of prostasin provide a new mechanism of protease regulation by divalent cationsProtein Science, 2009
- Serine proteasesIUBMB Life, 2009
- Validation of Molecular Docking Programs for Virtual Screening against Dihydropteroate SynthaseJournal of Chemical Information and Modeling, 2009
- Structure of Human Prostasin, a Target for the Regulation of HypertensionJournal of Biological Chemistry, 2008
- Classifier performance estimation under the constraint of a finite sample size: Resampling schemes applied to neural network classifiersNeural Networks, 2008
- Irreversible Inhibitors of Serine, Cysteine, and Threonine ProteasesChemical Reviews, 2002