Relevance of 3D Rotationally Equivariant Neural Networks for Predicting Protein-Ligand Binding Affinities
- 14 August 2025
- journal article
- Published by Springer Nature in Interdisciplinary Sciences: Computational Life Sciences
- Vol. 18 (2) , 392-418
Abstract
Proteins are fundamental to biological processes, mediating critical functions through precise molecular interactions. The rotational dynamics between ligand atoms and protein binding sites can significantly influence interaction efficacy by modifying spatial relationships. In our research, we present the PLAe (three-dimensional (3D) rotationally equivariant neural networks for predicting protein-ligand binding affinities) methodology. This novel model synergizes radial basis functions with e3nn networks to encapsulate the radial and angular dimensions of molecular features. Radial basis functions effectively measure interatomic distances, while e3nn-an advanced neural network utilizing spherical harmonics-maintains invariance under rotational and translational transformations. The Clebsch-Gordan coefficients are employed to integrate angular and atomic properties seamlessly. By merging radial basis and spherical harmonic elements with Clebsch-Gordan representations, our approach adeptly captures molecular rotational symmetries and interatomic interactions. The inclusion of an attention mechanism further refines the affinity predictions, ensuring a high level of precision. This integrative and sophisticated model sets a new benchmark to accurately predict protein-ligand binding affinities, leveraging intricate molecular details to enhance predictive performance.Keywords
Funding Information
- Natural Science Foundation of Gansu Province (Grant No. 20JR10RA613)
This publication has 82 references indexed in Scilit:
- KDEEP: Protein–Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural NetworksJournal of Chemical Information and Modeling, 2018
- Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural NetworksACS Central Science, 2017
- Structural and Sequence Similarity Makes a Significant Impact on Machine-Learning-Based Scoring Functions for Protein–Ligand InteractionsJournal of Chemical Information and Modeling, 2017
- Forging the Basis for Developing Protein–Ligand Interaction Scoring FunctionsAccounts of Chemical Research, 2017
- Beware of Machine Learning-Based Scoring Functions—On the Danger of Developing Black BoxesJournal of Chemical Information and Modeling, 2014
- Comparative Assessment of Scoring Functions on an Updated Benchmark: 1. Compilation of the Test SetJournal of Chemical Information and Modeling, 2014
- Binding Affinity Prediction for Protein–Ligand Complexes Based onβContacts and B FactorJournal of Chemical Information and Modeling, 2013
- Comments on “Leave-Cluster-Out Cross-Validation Is Appropriate for Scoring Functions Derived from Diverse Protein Data Sets”: Significance for the Validation of Scoring FunctionsJournal of Chemical Information and Modeling, 2011
- Leave-Cluster-Out Cross-Validation Is Appropriate for Scoring Functions Derived from Diverse Protein Data SetsJournal of Chemical Information and Modeling, 2010
- AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreadingJournal of Computational Chemistry, 2009