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.
@article{arxiv.1904.08144,
title = {Predicting drug-target interaction using 3D structure-embedded graph representations from graph neural networks},
author = {Jaechang Lim and Seongok Ryu and Kyubyong Park and Yo Joong Choe and Jiyeon Ham and Woo Youn Kim},
journal= {arXiv preprint arXiv:1904.08144},
year = {2019}
}