Pre‐training strategy for antiviral drug screening with low‐data graph neural network: A case study in HIV‐1 K103N reverse transcriptase
- 22 October 2024
- journal article
- research article
- Published by Wiley in Journal of Computational Chemistry
- Vol. 46 (1)
Abstract
Graph neural networks (GNN) offer an alternative approach to boost the screening effectiveness in drug discovery. However, their efficacy is often hindered by limited datasets. To address this limitation, we introduced a robust GNN training framework, applied to various chemical databases to identify potent non‐nucleoside reverse transcriptase inhibitors (NNRTIs) against the challenging K103N‐mutated HIV‐1 RT. Leveraging self‐supervised learning (SSL) pre‐training to tackle data scarcity, we screened 1,824,367 compounds, using multi‐step approach that incorporated machine learning (ML)‐based screening, analysis of absorption, distribution, metabolism, and excretion (ADME) prediction, drug‐likeness properties, and molecular docking. Ultimately, 45 compounds were left as potential candidates with 17 of the compounds were previously identified as NNRTIs, exemplifying the model's efficacy. The remaining 28 compounds are anticipated to be repurposed for new uses. Molecular dynamics (MD) simulations on repurposed candidates unveiled two promising preclinical drugs: one designed against Plasmodium falciparum and the other serving as an antibacterial agent. Both have superior binding affinity compared to anti‐HIV drugs. This conceptual framework could be adapted for other disease‐specific therapeutics, facilitating the identification of potent compounds effective against both WT and mutants while revealing novel scaffolds for drug design and discovery.Keywords
This publication has 51 references indexed in Scilit:
- Machine learning‐guided design of potent darunavir analogs targeting HIV‐1 proteases: A computational approach for antiretroviral drug discoveryJournal of Computational Chemistry, 2024
- Enabling data-limited chemical bioactivity predictions through deep neural network transfer learningJournal of Computer-Aided Molecular Design, 2022
- Approved HIV reverse transcriptase inhibitors in the past decadeActa Pharmaceutica Sinica B, 2021
- Cyclic peptide natural products chart the frontier of oral bioavailability in the pursuit of undruggable targetsCurrent Opinion in Chemical Biology, 2017
- Oral Druggable Space beyond the Rule of 5: Insights from Drugs and Clinical CandidatesChemistry & Biology, 2014
- The Solvated Interaction Energy Method for Scoring Binding Affinities2011
- Molecular and structural aspects of clinically relevant mutations related to the approved non-nucleoside inhibitors of HIV-1 reverse transcriptaseDrug Resistance Updates, 2011
- Structure and Function of HIV-1 Reverse Transcriptase: Molecular Mechanisms of Polymerization and InhibitionJournal of Molecular Biology, 2009
- A Study of the Binding Energies of Efavirenz to Wild‐Type and K103N/Y181C HIV‐1 Reverse Transcriptase Based on the ONIOM MethodChemMedChem, 2008
- Development and validation of a genetic algorithm for flexible docking 1 1Edited by F. E. CohenJournal of Molecular Biology, 1997