Machine learning and molecular docking prediction of potential inhibitors against dengue virus - Original Research Article

Aug 5, 2026

Upload by Liam

Dengue fever remains a major global health threat driven by Aedes aegypti and Aedes albopictus. While vaccines and existing antivirals are available, resistance, diminished efficacy, and high costs create an ongoing need for new therapeutics. The study identifies potential dengue virus inhibitors through an integrative workflow combining machine learning screening with molecular docking, followed by interaction and computational stability assessments.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Introduction

Method

Dataset and model training

Molecular docking and follow-up analyses

Results

TYPE Original Research PUBLISHED 24 December 2024 DOI 10.3389/fchem.2024.1510029 OPEN ACCESS EDITED BY Simone Brogi, University of Pisa, Italy REVIEWED BY Nitin Sharma, Washington University in St. Louis, United States Jennifer Binning, Mofﬁtt Cancer Center, United States *CORRESPONDENCE George Hanson, [george.hanson417@gmail.com](george.hanson417@gmail.com)[ ](george.hanson417@gmail.com)Olaitan I. Awe, [laitanawe@gmail.com](laitanawe@gmail.com) RECEIVED 12 October 2024 ACCEPTED 09 December 2024 PUBLISHED 24 December 2024 CITATION Hanson G, Adams J, Kepgang DIB, Zondagh LS, Tem Bueh L, Asante A, Shirolkar SA, Kisaakye M, Bondarwad H and Awe OI (2024) Machine learning and molecular docking prediction of potential inhibitors against dengue virus. Front. Chem. 12:1510029 . doi: 10.3389/fchem.2024.1510029 COPYRIGHT © 2024 Hanson, Adams, Kepgang, Zondagh, Tem Bueh, Asante, Shirolkar, Kisaakye, Bondarwad and Awe. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Machine learning and molecular docking prediction of potential inhibitors against dengue virus George Hanson 􀀁 1*, Joseph Adams 􀀁 1, Daveson I. B. Kepgang 􀀁 2, Luke S. Zondagh 􀀁 3, Lewis Tem Bueh 􀀁 4, Andy Asante 􀀁 5, Soham A. Shirolkar 􀀁 6, Maureen Kisaakye 􀀁 7, Hem Bondarwad 􀀁 8 and Olaitan I. Awe 􀀁 9* 1Department of Parasitology, Noguchi Memorial Institute for Medical Research (NMIMR), College of Health Sciences (CHS), University of Ghana, Accra, Ghana, 2Department of Biochemistry, Faculty of Sciences, University of Douala, Douala, Cameroon, 3Pharmaceutical Chemistry, School of Pharmacy, University of Western Cape Town, Cape Town, South Africa, 4Department of Computer Engineering, Faculty of Engineering and Technology, University of Buea, Buea, Cameroon, 5Department of Immunology, Noguchi Memorial Institute for Medical Research (NMIMR), College of Health Sciences (CHS), University of Ghana, Accra, Ghana, 6College of Engineering, University of South Florida, Florida, United States, 7Department of Immunology and Molecular Biology, College of Health Sciences, Makerere University, Kampala, Uganda, 8Department of Biotechnology and Bioinformatics, Deogiri College, Dr. Babasaheb Ambedkar Marathwada University, Sambhajinagar, India, 9African Society for Bioinformatics and Computational Biology, Cape Town, South Africa Introduction: Dengue Fever continues to pose a global threat due to the widespread distribution of its vector mosquitoes, Aedes aegypti and Aedes albopictus. While the WHO-approved vaccine, Dengvaxia, and antiviral treatments like Balapiravir and Celgosivir are available, challenges such as drug resistance, reduced efﬁcacy, and high treatment costs persist. This study aims to identify novel potential inhibitors of the Dengue virus (DENV) using an integrative drug discovery approach encompassing machine learning and molecular docking techniques. Method: Utilizing a dataset of 21,250 bioactive compounds from PubChem (AID: 651640), alongside a total of 1,444 descriptors generated using PaDEL, we trained various models such as Support Vector Machine, Random Forest, k-nearest neighbors, Logistic Regression, and Gaussian Naïve Bayes. The top-performing model was used to predict active compounds, followed by molecular docking performed using AutoDock Vina. The detailed interactions, toxicity, stability, and Abbreviations: 3D, Three-dimensional; ADMET, chemical Absorption, Distribution, Metabolism, Excretion, and Toxicity; AI, Artiﬁcial Intelligence; AID, BioAssay Identiﬁcation number; ANPDB, African Natural Products Dat

FAQs

What is the main goal of this study on dengue virus inhibitors?

To identify novel potential inhibitors of dengue virus using an integrative drug discovery approach combining machine learning and molecular docking.

How were machine learning models trained and used to predict inhibitors?

The study used a dataset of 21,250 bioactive compounds from PubChem with 1,444 descriptors from PaDEL to train multiple models; the best-performing model then predicted active compounds.

What role does molecular docking and molecular dynamics play in evaluating candidates?

Docking was performed on the NS2B/NS3 protease to estimate binding affinity and interaction residues, and molecular dynamics with binding free energy calculations further assessed stability.

Aug 5, 2026

Upload by Liam