Machine learning approach to discovery of small molecules with potential inhibitory action against vasoactive metalloproteases
Date
Authors
Cañizares-Carmenate, Yudith
Mena-Ulecia, Karel
MacLeod-Carey, Desmond
Perera-Sardiña, Yunier
Hernández-Rodríguez, Erix Wiliam
Marrero-Ponce, Yovani
Torres Pérez, Francisco
Castillo-Garit, Juan A.
Mena-Ulecia, Karel
MacLeod-Carey, Desmond
Perera-Sardiña, Yunier
Hernández-Rodríguez, Erix Wiliam
Marrero-Ponce, Yovani
Torres Pérez, Francisco
Castillo-Garit, Juan A.
Authors
URI
Date
Datos de publicación:
10.1007/s11030-021-10260-0
Keywords
Angiotensin-converting Enzyme - Artificial Intelligence - Docking - Machine Learning - Neutral Endopeptidase - Thermolysin - Virtual Screening - Estradiol - Metalloproteinase - Thermolysin - Yohimbine - Zinc Ion - Metalloproteases - Antihypertensive Agent - Carboxylic Acid - Db 00783 Inhibitor - Db 02177 Inhibitor - Db 03444 Inhibitor - Estradiol - Estrogen - Hydroxamic Acid - Metalloproteinase - Phosphinate - Small Molecule Transport Agent - Thermolysin - Unclassified Drug - Vasoactive Agent - Vasoactive Metalloprotease - Yohimbine - Zinc Ion - Accuracy - Algorithm - Analytical Parameters - Article - Artificial Intelligence - Artificial Neural Network - Bayesian Learning - Bayesian Network - Binding Energy - Cardiovascular Disease - Cluster Analysis - Combinatorial Chemistry - Computer Model - Connectivity Indices - Crystal Structure - Data Base - Drug Bioavailability - Drug Repositioning - Drugbank Database - Enzyme Binding Site - Enzyme Substrate Complex - Human - Hydrogen Bond - Hypertension - Lipinskis Rule - Machine Learning - Matthews Correlation Coefficient - Metabolic Fingerprinting - Molecular Docking - Molecular Library - Molecular Property - Multilayer Perceptron - Network Training Algorithm - Peptide Bond - Pharmacodynamics - Phylogenetic Tree - Piecewise Regression Method - Prediction - Probability - Protein Data Bank - Quantitative Structure Activity Relation - Receiver Operating Characteristic - Sensitivity And Specificity - Symmetry - Topological Distance - Training - X Ray Crystallography - Bayes Theorem - Artificial Intelligence - Bayes Theorem - Drug Repositioning - Humans - Machine Learning - Metalloproteases - Molecular Docking Simulation - Quantitative Structure-activity Relationship
Collections
Abstract
Abstract: With the advancement of combinatorial chemistry and big data, drug repositioning has boomed. In this sense, machine learning and artificial intelligence techniques offer a priori information to identify the most promising candidates. In this study, we combine QSAR and docking methodologies to identify compounds with potential inhibitory activity of vasoactive metalloproteases for the treatment of cardiovascular diseases. To develop this study, we used a database of 191 thermolysin inhibitor compounds, which is the largest as far as we know. First, we use Dragon's molecular descriptors (0-3D) to develop classification models using Bayesian networks (Naive Bayes) and artificial neural networks (Multilayer Perceptron). The obtained models are used for virtual screening of small molecules in the international DrugBank database. Second, docking experiments are carried out for all three enzymes using the Autodock Vina program, to identify possible interactions with the active site of human metalloproteases. As a result, high-performance artificial intelligence QSAR models are obtained for training and prediction sets. These allowed the identification of 18 compounds with potential inhibitory activity and an adequate oral bioavailability profile, which were evaluated using docking. Four of them showed high binding energies for the three enzymes, and we propose them as potential dual ACE/NEP inhibitors for the control of blood pressure. In summary, the in silico strategies used here constitute an important tool for the early identification of new antihypertensive drug candidates, with substantial savings in time and money. Graphic abstract: [Figure not available: see fulltext.]. © 2022 Elsevier B.V., All rights reserved.
Description
Keywords
Angiotensin-converting Enzyme , Artificial Intelligence , Docking , Machine Learning , Neutral Endopeptidase , Thermolysin , Virtual Screening , Estradiol , Metalloproteinase , Thermolysin , Yohimbine , Zinc Ion , Metalloproteases , Antihypertensive Agent , Carboxylic Acid , Db 00783 Inhibitor , Db 02177 Inhibitor , Db 03444 Inhibitor , Estradiol , Estrogen , Hydroxamic Acid , Metalloproteinase , Phosphinate , Small Molecule Transport Agent , Thermolysin , Unclassified Drug , Vasoactive Agent , Vasoactive Metalloprotease , Yohimbine , Zinc Ion , Accuracy , Algorithm , Analytical Parameters , Article , Artificial Intelligence , Artificial Neural Network , Bayesian Learning , Bayesian Network , Binding Energy , Cardiovascular Disease , Cluster Analysis , Combinatorial Chemistry , Computer Model , Connectivity Indices , Crystal Structure , Data Base , Drug Bioavailability , Drug Repositioning , Drugbank Database , Enzyme Binding Site , Enzyme Substrate Complex , Human , Hydrogen Bond , Hypertension , Lipinskis Rule , Machine Learning , Matthews Correlation Coefficient , Metabolic Fingerprinting , Molecular Docking , Molecular Library , Molecular Property , Multilayer Perceptron , Network Training Algorithm , Peptide Bond , Pharmacodynamics , Phylogenetic Tree , Piecewise Regression Method , Prediction , Probability , Protein Data Bank , Quantitative Structure Activity Relation , Receiver Operating Characteristic , Sensitivity And Specificity , Symmetry , Topological Distance , Training , X Ray Crystallography , Bayes Theorem , Artificial Intelligence , Bayes Theorem , Drug Repositioning , Humans , Machine Learning , Metalloproteases , Molecular Docking Simulation , Quantitative Structure-activity Relationship
Citation
10.1007/s11030-021-10260-0