Descriptive Knowledge Graph in Biomedical Domain
This system addresses the challenge for biomedical researchers in efficiently accessing and navigating relational knowledge from large corpora, though it appears incremental by building on existing methods like ChatGPT and fine-tuning.
The authors tackled the problem of inefficient search in biomedical literature by developing a system that automatically extracts and generates descriptive sentences and organizes them into a relational graph, enabling researchers to explore connections like diseases treated by chemicals or potential drugs for diseases, with applications in COVID-19 research such as drug repurposing.
We present a novel system that automatically extracts and generates informative and descriptive sentences from the biomedical corpus and facilitates the efficient search for relational knowledge. Unlike previous search engines or exploration systems that retrieve unconnected passages, our system organizes descriptive sentences as a relational graph, enabling researchers to explore closely related biomedical entities (e.g., diseases treated by a chemical) or indirectly connected entities (e.g., potential drugs for treating a disease). Our system also uses ChatGPT and a fine-tuned relation synthesis model to generate concise and reliable descriptive sentences from retrieved information, reducing the need for extensive human reading effort. With our system, researchers can easily obtain both high-level knowledge and detailed references and interactively steer to the information of interest. We spotlight the application of our system in COVID-19 research, illustrating its utility in areas such as drug repurposing and literature curation.