MSHGCL: Multi-Scale Hierarchical Graph Contrastive Learning for Drug-Drug Interactions

Drug-drug interactions (DDIs) refer to the change in efficacy when two or more drugs taken at the same time. Reasonable DDI can enhance efficacy or reduce adverse drug reactions; otherwise, it may lead to adverse events. The recent DDI prediction methods, which use different graph neural networks to extract the drug substructures, convert the DDI prediction into the prediction of the relationship between the two drug substructures, and achieve good performance. However, these methods do not pay attention to the relationship between drug substructures extracted from the same drug. Therefore, we propose MSHGCL to constrain the relationship between drug substructures by multi-scale hierarchical graph contrastive learning module. Specifically, the intra-layer contrastive learning module constrains the relationship between drug substructures of the same scale, and the inter-layer contrastive learning module further constrains the relationship between drug substructures of adjacent layers. We evaluate MSHGCL on two real-world datasets. Experimental results show that the proposed MSHGCL method outperforms the most advanced DDI prediction method.