Integrating Logical Rules Into Neural Multi-Hop Reasoning for Drug Repurposing
This work addresses drug repurposing for biomedical applications, presenting an incremental improvement by combining existing techniques.
The authors tackled the problem of drug repurposing by integrating logical rules into a neural multi-hop reasoning approach, showing that their method outperforms baseline methods on the Hetionet biomedical knowledge graph.
The graph structure of biomedical data differs from those in typical knowledge graph benchmark tasks. A particular property of biomedical data is the presence of long-range dependencies, which can be captured by patterns described as logical rules. We propose a novel method that combines these rules with a neural multi-hop reasoning approach that uses reinforcement learning. We conduct an empirical study based on the real-world task of drug repurposing by formulating this task as a link prediction problem. We apply our method to the biomedical knowledge graph Hetionet and show that our approach outperforms several baseline methods.