PIGNet: A physics-informed deep learning model toward generalized drug-target interaction predictions

TL;DR

PIGNet is a physics-informed deep learning model that improves drug-target interaction predictions by enhancing generalization, interpretability, and screening accuracy through physics-based features and data augmentation.

Contribution

The paper introduces a novel physics-informed neural network approach for DTI prediction that outperforms previous methods and offers interpretability of binding affinities.

Findings

Outperforms previous scoring functions in CASF 2016 benchmark

Provides interpretable affinity contributions via ligand substructure visualization

Achieves better generalization with data augmentation strategies

Abstract

Recently, deep neural network (DNN)-based drug-target interaction (DTI) models were highlighted for their high accuracy with affordable computational costs. Yet, the models' insufficient generalization remains a challenging problem in the practice of in-silico drug discovery. We propose two key strategies to enhance generalization in the DTI model. The first is to predict the atom-atom pairwise interactions via physics-informed equations parameterized with neural networks and provides the total binding affinity of a protein-ligand complex as their sum. We further improved the model generalization by augmenting a broader range of binding poses and ligands to training data. We validated our model, PIGNet, in the comparative assessment of scoring functions (CASF) 2016, demonstrating the outperforming docking and screening powers than previous methods. Our physics-informing strategy also enables the interpretation of predicted affinities by visualizing the contribution of ligand substructures, providing insights for further ligand optimization.