reguloGPT: Harnessing GPT for Knowledge Graph Construction of Molecular Regulatory Pathways

作者：Xidong Wu, Yiming Zeng, Arun Das, Sumin Jo, Tinghe Zhang, Parth Patel, Jianqiu Zhang, Shou‐Jiang Gao, Dexter Pratt, Yu‐Chiao Chiu, Yufei Huang · 发表于：bioRxiv (Cold Spring Harbor Laboratory) · 年份：2024 · DOI：10.1101/2024.01.27.577521 · 被引用次数：11 · 研究领域：Biomedical Text Mining and Ontologies、Bioinformatics and Genomic Networks、Advanced Graph Neural Networks

Abstract Motivation Molecular Regulatory Pathways (MRPs) are crucial for understanding biological functions. Knowledge Graphs (KGs) have become vital in organizing and analyzing MRPs, providing structured representations of complex biological interactions. Current tools for mining KGs from biomedical literature are inadequate in capturing complex, hierarchical relationships and contextual information about MRPs. Large Language Models (LLMs) like GPT-4 offer a promising solution, with advanced capabilities to decipher the intricate nuances of language. However, their potential for end-to-end KG construction, particularly for MRPs, remains largely unexplored. Results We present reguloGPT, a novel GPT-4 based in-context learning prompt, designed for the end-to-end joint name entity recognition, N-ary relationship extraction, and context predictions from a sentence that describes regulatory interactions with MRPs. Our reguloGPT approach introduces a context-aware relational graph that effectively embodies the hierarchical structure of MRPs and resolves semantic inconsistencies by embedding context directly within relational edges. We created a benchmark dataset including 400 annotated PubMed titles on N6-methyladenosine (m 6 A) regulations. Rigorous evaluation of reguloGPT on the benchmark dataset demonstrated marked improvement over existing algorithms. We further developed a novel G-Eval scheme, leveraging GPT-4 for annotation-free performance evaluation and demonstrated its ag...