GraphCF: Drug–target interaction prediction via multi-feature fusion with contrastive graph neural network

Abstract

Drug–target interaction (DTI) is paramount in drug discovery and repurposing, which involves screening for effective candidate drugs by targeting specific proteins. Existing methods often focus on one or two representations of drugs or targets, and little has been explored regarding 3D structures. Moreover, how to capture interactions between multi-modal features comprehensively is also a key issue. A multi-modal interaction fusion method called GraphCF is proposed to overcome these limitations. Specifically, GraphCF uses a MixHop aggregator to gather higher-order neighborhood information between nodes in the DTI topological network and incorporate graph contrastive learning to capture more discriminative 2D representations of drugs and targets. Additionally, GraphCF utilizes convolutional neural networks and graph neural networks to extract the sequence and 3D structural features of drugs and targets, respectively. Then, GraphCF employs a cross-attention-based multi-feature fusion module to facilitate information interaction and fusion among multi-modal feature representations. GraphCF is evaluated and compared with some advanced methods on four public datasets, and the results demonstrate the competitive performance of GraphCF in DTI prediction.