Multi-Knowledge Graph and Multi-View Entity Feature Learning for Predicting Drug-Related Side Effects

Computational prediction of potential drug side effects plays a crucial role in reducing health risks for clinical patients and accelerating drug development. Recent methods have constructed heterogeneous graphs that represent drugs and their side effects, utilizing graph learning strategies such as graph convolutional networks to predict associations between them. However, existing approaches fail to fully exploit the diverse topologies and semantics present in multiple knowledge graphs. We propose MVDSA, a novel multi-view drug-side effect association prediction model. Our approach integrates multiple relationship semantics, local topologies of knowledge graphs, and multi-view features of drug-side effect entity pairs. First, we constructed two knowledge graphs based on drug functional and structural similarity, side effect similarity, and drug-side effect associations. These knowledge graphs capture the topological and semantic connections between drug and side effect entities from diverse perspectives. Second, considering the diverse similarities and associations between entities, we designed a space-sensitive learning strategy where a relation-gated semantic encoder is constructed for each type of relationship. This encoder adaptively adjusts the contribution of each entity feature to the relational semantic representation, facilitating the learning of entity-specific semantic features within each relational space. Third, for the two knowledge graphs, given the multiple types of connections between head and tail entities, we propose a connection-sensitive tail entity attention mechanism to integrate these diverse semantic relationships. To capture the contribution of different knowledge graphs to entity feature learning, we designed a knowledge graph-level attention mechanism to adaptively fuse the enhanced features from multiple knowledge graphs. Finally, we propose a multi-view enhanced multi-layer perceptron (MLP) strategy to encode the features of drug-side effect pairs from three perspectives and capture the potential associations between entities. Extensive experiments demonstrate that MVDSA outperforms 10 state-of-the-art methods in predicting drug-side effect associations. Ablation studies validate the contributions of the proposed innovations to improved prediction performance. Additionally, case studies on candidate side effects for five drugs highlight MVDSA's capability to discover potential drug-side effect associations.