Predicting Distant Drug-Target Interactions via a Random Walk Guided Graph Neural Network

Recently, the prediction of drug-target interactions (DTIs) is improved by graph neural networks (GNNs). There exists some DTIs that are far away from other DTIs, which plays fundamental role in drug development. However, conventional GNNs encode long-range topological correlations with latent embeddings, restricting their performances in inferring distant DTIs. Inspired by random walk methods that directly encode the connectivity between nodes by transition probabilities, a random walk guided graph neural network (RWGNN) method is proposed, in which random walk profiles are passed through a GNN to enable it to learn distance-aware node embeddings. For an unknown DTI, enclosing subnetworks are firstly extracted. Node-level, interaction-level and network-level transition probabilities of random walks (i.e., random walk profile) are calculated on these subnetworks. Then, each graph convolutional layer aggregates node embeddings from multi-hop neighbors according to attentional weights calculated from random walk profiles. Finally, the DTI’s drug embedding, protein embedding and random walk profile are aggregated to calculate an interaction score for it. The performance in inferring distant DTIs (≥ 3 hops away from known DTIs) has been improved by RWGNN (AUC=0.957) significantly, compared with GCN (AUC=0.582) and GIN (AUC=0.724). Besides, RWGNN is powerful in inferring DTIs for cold-start drugs and target proteins. Top-10 scored DTIs of RWGNN can be verified in literatures.