COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation

TL;DR

This paper introduces COVID-KG, a comprehensive multimedia knowledge graph framework that extracts detailed biomedical knowledge from literature to facilitate drug repurposing and report generation for COVID-19.

Contribution

The paper presents a novel framework for constructing multimedia knowledge graphs from scientific literature, enabling improved question answering and drug repurposing for COVID-19.

Findings

Effective extraction of entities, relations, and visual structures from literature.

Knowledge graphs support accurate question answering and report generation.

Case study demonstrates potential for drug repurposing insights.

Abstract

To combat COVID-19, both clinicians and scientists need to digest vast amounts of relevant biomedical knowledge in scientific literature to understand the disease mechanism and related biological functions. We have developed a novel and comprehensive knowledge discovery framework, COVID-KG to extract fine-grained multimedia knowledge elements (entities and their visual chemical structures, relations, and events) from scientific literature. We then exploit the constructed multimedia knowledge graphs (KGs) for question answering and report generation, using drug repurposing as a case study. Our framework also provides detailed contextual sentences, subfigures, and knowledge subgraphs as evidence.