Ligand-induced protein dynamics differences correlate with protein-ligand binding affinities: An unsupervised deep learning approach
arXiv:2109.01339 · doi:10.1038/s42003-022-03416-7
Abstract
Prediction of protein-ligand binding affinity is a major goal in drug discovery. Generally, free energy gap is calculated between two states (e.g., ligand binding and unbinding). The energy gap implicitly includes the effects of changes in protein dynamics induced by the binding ligand. However, the relationship between protein dynamics and binding affinity remains unclear. Here, we propose a novel method that represents protein behavioral change upon ligand binding with a simple feature that can be used to predict protein-ligand affinity. From unbiased molecular simulation data, an unsupervised deep learning method measures the differences in protein dynamics at a ligand-binding site depending on the bound ligands. A dimension-reduction method extracts a dynamic feature that is strongly correlated to the binding affinities. Moreover, the residues that play important roles in protein-ligand interactions are specified based on their contribution to the differences. These results indicate the potential for dynamics-based drug discovery.
References in corpus (8)
- Canonical sampling through velocity-rescaling
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- DeepDTA: Deep Drug-Target Binding Affinity Prediction
- Machine learning for molecular simulation
- DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks
- Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening
- Universal relation between instantaneous diffusivity and radius of gyration of proteins in aqueous solution
- Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials