Predicting drug-protein interactions by preserving the graph information of multi source data

Abstract

Examining potential drug-target interactions (DTIs) is a pivotal component of drug discovery and repurposing. Recently, there has been a significant rise in the use of computational techniques to predict DTIs. Nevertheless, previous investigations have predominantly concentrated on assessing either the connections between nodes or the consistency of the network's topological structure in isolation. Such one-sided approaches could severely hinder the accuracy of DTI predictions. In this study, we propose a novel method called TTGCN, which combines heterogeneous graph convolutional neural networks (GCN) and graph attention networks (GAT) to address the task of DTI prediction. TTGCN employs a two-tiered feature learning strategy, utilizing GAT and residual GCN (R-GCN) to extract drug and target embeddings from the diverse network, respectively. These drug and target embeddings are then fused through a mean-pooling layer. Finally, we employ an inductive matrix completion technique to forecast DTIs while preserving the network's node connectivity and topological structure. Our approach demonstrates superior performance in terms of area under the curve and area under the precision-recall curve in experimental comparisons, highlighting its significant advantages in predicting DTIs. Furthermore, case studies provide additional evidence of its ability to identify potential DTIs.

Keywords: Drug–target interactions; Graph attention networks; Residual graph convolutional neural networks.

Fig. 1

The framework of TTGCN

Fig. 2

An illustration of a heterogeneous information network for DTIs

Fig. 3

a Evaluation of ROC and PR for TTGCN in comparison to four state-of-the-art DTI prediction methods. b Assessment of ROC curves and PR curves in the context of the ablation experiment

Fig. 4

Evaluation of MCC for TTGCN in comparison to four state-of-the-art DTI prediction methods

Fig. 5

Loss function graph

Fig. 6

The mean recall rates for various top-k thresholds

Fig. 7

The mean coverage for each approach