Encoding Protein-Ligand Interactions: Binding Affinity Prediction with Multigraph-based Modeling and Graph Convolutional Network
Preprint
- 17 December 2023
- preprint
- Published by American Chemical Society (ACS) in ChemRxiv
Abstract
Machine learning models are employed to enhance the speed and provide novel insights in drug discovery due to their demonstrated effectiveness in predicting properties of small molecules like pKa, solubility, and binding affinity. These approaches accelerate drug discovery by helping researchers efficiently identify, prioritize, and optimize compounds. Nonetheless, when investigating properties that depend on the interaction between a ligand and its corresponding protein, a compelling need arises to incorporate the protein counterpart information within the models. Recently, graph neural networks (GNNs) have been developed to incorporate 3D structural information to improve our understanding of the underlying protein-ligand interactions. However, incorporating 3D information into GNNs is not always straightforward. To address the challenge, we introduce a model called InterGraph, which models the protein-ligand interaction as topological multigraphs. By leveraging a topological representation, InterGraph offers a comprehensive approach to a graph representation of the intricate spatial organization and connectivity patterns within protein-ligand systems. We introduce interaction spheres that assign varying edge densities, capturing the proximity-based influence of interactions. This approach enables us to capture the characteristics of the interaction network, filtering out the ones that are beyond 9 Å from the ligand since they are not considered relevant or established. Finally, we trained the model using a ligand binding dataset from PDBbind and tested it on a hold-out test set, achieving an RMSE value of 1.34. Our findings have demonstrated the power of the multigraph to encode the importance of close interactions, a factor that is relevant in the context of binding affinity. On average, our model accurately predicts binding affinity values for several protein-ligand complexes and exhibits higher accuracy for hydrolase, lyase, and families of proteins involved in mediating protein-protein interactions. Additionally, the Intergraph method displayed sensitivity to the binding mode when compared to a set of complexes that had undergone redocking calculationsKeywords
All Related Versions
This publication has 26 references indexed in Scilit:
- PLANET: A Multi-objective Graph Neural Network Model for Protein–Ligand Binding Affinity PredictionJournal of Chemical Information and Modeling, 2023
- Are Deep Learning Structural Models Sufficiently Accurate for Virtual Screening? Application of Docking Algorithms to AlphaFold2 Predicted StructuresJournal of Chemical Information and Modeling, 2023
- Graph neural network approaches for drug-target interactionsCurrent Opinion in Structural Biology, 2022
- Synergy and Complementarity between Focused Machine Learning and Physics-Based Simulation in Affinity PredictionJournal of Chemical Information and Modeling, 2021
- InteractionGraphNet: A Novel and Efficient Deep Graph Representation Learning Framework for Accurate Protein–Ligand Interaction PredictionsJournal of Medicinal Chemistry, 2021
- AutoDock Vina 1.2.0: New Docking Methods, Expanded Force Field, and Python BindingsJournal of Chemical Information and Modeling, 2021
- Accurate Prediction of GPCR Ligand Binding Affinity with Free Energy PerturbationJournal of Chemical Information and Modeling, 2020
- Binding Affinity Prediction by Pairwise Function Based on Neural NetworkJournal of Chemical Information and Modeling, 2020
- Comparative Assessment of Scoring Functions: The CASF-2016 UpdateJournal of Chemical Information and Modeling, 2018
- AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreadingJournal of Computational Chemistry, 2009