From Static to Dynamic Structures: Improving Binding Affinity Prediction with Graph‐Based Deep Learning
Open Access
- 29 August 2024
- journal article
- research article
- Published by Wiley in Advanced Science
- Vol. 11 (40) , e2405404
Abstract
Accurate prediction of protein‐ligand binding affinities is an essential challenge in structure‐based drug design. Despite recent advances in data‐driven methods for affinity prediction, their accuracy is still limited, partially because they only take advantage of static crystal structures while the actual binding affinities are generally determined by the thermodynamic ensembles between proteins and ligands. One effective way to approximate such a thermodynamic ensemble is to use molecular dynamics (MD) simulation. Here, an MD dataset containing 3,218 different protein‐ligand complexes is curated, and Dynaformer, a graph‐based deep learning model is further developed to predict the binding affinities by learning the geometric characteristics of the protein‐ligand interactions from the MD trajectories. In silico experiments demonstrated that the model exhibits state‐of‐the‐art scoring and ranking power on the CASF‐2016 benchmark dataset, outperforming the methods hitherto reported. Moreover, in a virtual screening on heat shock protein 90 (HSP90) using Dynaformer, 20 candidates are identified and their binding affinities are further experimentally validated. Dynaformer displayed promising results in virtual drug screening, revealing 12 hit compounds (two are in the submicromolar range), including several novel scaffolds. Overall, these results demonstrated that the approach offer a promising avenue for accelerating the early drug discovery process.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (T2125007, 32270640)
- National Key Research and Development Program of China (2021YFF1201300)
This publication has 75 references indexed in Scilit:
- GB‐score: Minimally designed machine learning scoring function based on distance‐weighted interatomic contact featuresMolecular Informatics, 2023
- Pre‐Training of Equivariant Graph Matching Networks with Conformation Flexibility for Drug BindingAdvanced Science, 2022
- Deep Learning Unravels a Dynamic Hierarchy While Empowering Molecular Dynamics SimulationsAnnalen der Physik, 2020
- Improving scoring-docking-screening powers of protein-ligand scoring functions using random forestJournal of Computational Chemistry, 2016
- MDAnalysis: A toolkit for the analysis of molecular dynamics simulationsJournal of Computational Chemistry, 2011
- Basic ingredients of free energy calculations: A reviewJournal of Computational Chemistry, 2009
- How to obtain statistically converged MM/GBSA resultsJournal of Computational Chemistry, 2009
- AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreadingJournal of Computational Chemistry, 2009
- CHARMM‐GUI: A web‐based graphical user interface for CHARMMJournal of Computational Chemistry, 2008
- A kinematic view of loop closureJournal of Computational Chemistry, 2004