Integrating Logical Rules Into Neural Multi-Hop Reasoning for Drug Repurposing

TL;DR

This paper introduces a novel method that integrates logical rules into neural multi-hop reasoning with reinforcement learning to improve drug repurposing by capturing long-range dependencies in biomedical data.

Contribution

The paper presents a new approach combining logical rules with neural reasoning for biomedical knowledge graphs, enhancing drug repurposing performance.

Findings

Outperforms baseline methods on Hetionet

Effectively captures long-range dependencies in biomedical data

Improves link prediction accuracy for drug repurposing

Abstract

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.