A Heterogeneous Network-based Contrastive Learning Approach for Predicting Drug-Target Interaction

TL;DR

This paper introduces HNCL-DTI, a novel contrastive learning approach using heterogeneous graph attention networks that effectively predicts drug-target interactions by incorporating edge features, outperforming existing methods.

Contribution

The paper presents a new contrastive learning framework with heterogeneous graph attention networks that explicitly models edge features for improved DTI prediction.

Findings

HNCL-DTI outperforms baseline methods on benchmark datasets.

The approach demonstrates strong predictive accuracy and practical utility.

Incorporates edge features into heterogeneous graph neural networks.

Abstract

Drug-target interaction (DTI) prediction is crucial for drug development and repositioning. Methods using heterogeneous graph neural networks (HGNNs) for DTI prediction have become a promising approach, with attention-based models often achieving excellent performance. However, these methods typically overlook edge features when dealing with heterogeneous biomedical networks. We propose a heterogeneous network-based contrastive learning method called HNCL-DTI, which designs a heterogeneous graph attention network to predict potential/novel DTIs. Specifically, our HNCL-DTI utilizes contrastive learning to collaboratively learn node representations from the perspective of both node-based and edge-based attention within the heterogeneous structure of biomedical networks. Experimental results show that HNCL-DTI outperforms existing advanced baseline methods on benchmark datasets, demonstrating strong predictive ability and practical effectiveness. The data and source code are available at https://github.com/Zaiwen/HNCL-DTI.