Multi-Resolutional Collaborative Heterogeneous Graph Convolutional Auto-Encoder for Drug-Target Interaction Prediction

Identification of new interactions between drugs and target proteins (DTIs) plays a fundamental role in drug development. It is commonly recognized that the collaborative utilization of drug-drug interaction (DDI) networks and protein-protein interaction (PPI) networks contribute to more comprehensive prediction results. However, recent methods almost view the different types of nodes and edges in heterogeneous networks indiscriminately, thus neglecting the complementary information hidden across different types of interactions. Therefore, this work innovatively elaborates a Multi-Resolutional Collaborative Heterogeneous Graph Convolutional Auto-Encoder (MRCH-GCAE) for DTI prediction, which collaboratively aggregates the learned embeddings from different types of links in heterogeneous drugtarget networks, thus leading to more interpretable embeddings for each drug and target node. Experiments have demonstrated the outstanding effectiveness of it not only in the prediction accuracy but also the ability to predict DTIs for new drugs and new target proteins.