[Paper Review] Biomedical Knowledge Graph: A Survey of Domains, Tasks, and Real-World Applications

Yuxing Lu, Sin Yee Goi+2 more|ArXiv.org|Jan 20, 2025

Biomedical Text Mining and Ontologies4 citations

TL;DR

This survey provides a unified framework for Biomedical Knowledge Graphs (BKGs) by examining their domain coverage, core tasks, and real-world applications in precision medicine, drug discovery, and scientific research.

ABSTRACT

Biomedical knowledge graphs (BKGs) have emerged as powerful tools for organizing and leveraging the vast and complex data found across the biomedical field. Yet, current reviews of BKGs often limit their scope to specific domains or methods, overlooking the broader landscape and the rapid technological progress reshaping it. In this survey, we address this gap by offering a systematic review of BKGs from three core perspectives: domains, tasks, and applications. We begin by examining how BKGs are constructed from diverse data sources, including molecular interactions, pharmacological datasets, and clinical records. Next, we discuss the essential tasks enabled by BKGs, focusing on knowledge management, retrieval, reasoning, and interpretation. Finally, we highlight real-world applications in precision medicine, drug discovery, and scientific research, illustrating the translational impact of BKGs across multiple sectors. By synthesizing these perspectives into a unified framework, this survey not only clarifies the current state of BKG research but also establishes a foundation for future exploration, enabling both innovative methodological advances and practical implementations.

Motivation & Objective

• Clarify how BKGs are constructed from diverse data sources such as molecular interactions, pharmacological datasets, and clinical records.
• Identify the essential tasks enabled by BKGs including knowledge management, retrieval, reasoning, and interpretation.
• Highlight real-world translational applications of BKGs in precision medicine, drug discovery, and scientific research.

Proposed method

• Systematic review of BKGs across domains, tasks, and applications.
• Synthesis into a unified framework to clarify current state and guide future work.
• Discussion of data sources and integration strategies for constructing BKGs.

Experimental results

Research questions

• RQ1 What domains do Biomedical Knowledge Graphs cover and how are they constructed from diverse data sources?
• RQ2 What core tasks do BKGs enable (knowledge management, retrieval, reasoning, interpretation) and how are they realized?
• RQ3 What real-world applications demonstrate the translational impact of BKGs in medicine and science?

Key findings

• BKGs aggregate data from molecular interactions, pharmacological datasets, and clinical records.
• BKGs support knowledge management, retrieval, reasoning, and interpretation tasks.
• Real-world applications highlighted include precision medicine, drug discovery, and scientific research.