Medical Knowledge Graph QA for Drug-Drug Interaction Prediction based on Multi-hop Machine Reading Comprehension

TL;DR

This paper introduces MedKGQA, a knowledge graph question answering model that predicts drug-drug interactions by integrating external biomedical knowledge and machine reading comprehension, achieving improved accuracy over existing methods.

Contribution

The paper presents a novel approach combining knowledge graph construction and machine reading comprehension for drug interaction prediction, demonstrating enhanced accuracy and efficiency.

Findings

Achieved 4.5% higher prediction accuracy than previous models.

Effectively integrated external biomedical knowledge into MRC tasks.

Validated the feasibility of knowledge integration in drug interaction prediction.

Abstract

Drug-drug interaction prediction is a crucial issue in molecular biology. Traditional methods of observing drug-drug interactions through medical experiments require significant resources and labor. This paper presents a medical knowledge graph question answering model, dubbed MedKGQA, that predicts drug-drug interaction by employing machine reading comprehension from closed-domain literature and constructing a knowledge graph of drug-protein triplets from open-domain documents. The model vectorizes the drug-protein target attributes in the graph using entity embeddings and establishes directed connections between drug and protein entities based on the metabolic interaction pathways of protein targets in the human body. This aligns multiple external knowledge and applies it to learn the graph neural network. Without bells and whistles, the proposed model achieved a 4.5% improvement in terms of drug-drug interaction prediction accuracy compared to previous state-of-the-art models on the Qangaroo MedHop dataset. Experimental results demonstrate the efficiency and effectiveness of the model and verify the feasibility of integrating external knowledge in machine reading comprehension tasks.