Subgraph-Oriented Heterogeneous Drug-Target Interaction Identification

Drug-target interaction (DTI) is an important task in drug discovery and drug repurposing. Currently, most methods utilizing drug-based and protein-based similarity values to predict DTIs achieve promising results. However, calculating similarities for each pair of nodes is time-consuming, especially for relatively large datasets. In this research, we propose a novel subgraph-oriented heterogeneous DTI identification method that transforms the DTI task from a link prediction task to a subgraph classification task. For each link, a local subgraph around this link is extracted. Then, a subgraph labeling process distinguishes different topologies of subgraphs. A random walk-based node representation generation is also integrated with the model. Finally, we apply a graph neural network for the subgraph classification. Our method avoids incorporating human-made similarity values by extracting more meaningful local subgraph topological information. Experimental studies for known DTI predictions on two DTI datasets show promising results for DTI prediction. Empirical results for new DTI predictions on two external public databases show the generalization ability of the proposed method.