Matthew Asato
Research Mentor: Yongqun He
Mentor Department: Not Available, Medicine
Author(s): Matthew Asato, Feng-Yu (Leo) Yeh, Yongqun (Oliver) He
Session: Session 2 (10:00 AM – 10:50 AM)
Presentation Type:
Abstract
Large Language Models (LLMs) are increasingly used to extract structured knowledge from unstructured text. In this project, we develop a data-mining pipeline that leverages LLMs to extract vaccine-related information from biomedical research papers. The extracted data is stored in VaxKG, a graph database representing relationships among vaccines, pathogens, hosts, and other entities. The graph incorporates concepts from the Vaccine Ontology to ensure standardized biomedical representation. To make this knowledge accessible, we developed VaxChat, an agentic Retrieval-Augmented Generation (RAG) system that uses tools such as VaxKG to answer user questions about vaccines.
