Predicting drug-target interaction using 3D structure-embedded graph representations from graph neural networks

TL;DR

This paper introduces a graph neural network model that directly uses 3D structural data of protein-ligand complexes to predict drug-target interactions, outperforming existing methods in virtual screening and pose prediction.

Contribution

It presents a novel GNN approach with distance-aware attention and gate augmentation that effectively incorporates 3D structural information for DTI prediction.

Findings

Outperforms docking and other deep learning methods in virtual screening

Accurately predicts binding poses of drug-target complexes

Reproduces natural distribution of active and inactive molecules

Abstract

Accurate prediction of drug-target interaction (DTI) is essential for in silico drug design. For the purpose, we propose a novel approach for predicting DTI using a GNN that directly incorporates the 3D structure of a protein-ligand complex. We also apply a distance-aware graph attention algorithm with gate augmentation to increase the performance of our model. As a result, our model shows better performance than docking and other deep learning methods for both virtual screening and pose prediction. In addition, our model can reproduce the natural population distribution of active molecules and inactive molecules.