Yichun Feng, Lu Zhou, Chao Ma, Yikai Zheng, Ruikun He, Yixue Li
{"title":"Knowledge graph-based thought: a knowledge graph-enhanced LLM framework for pan-cancer question answering.","authors":"Yichun Feng, Lu Zhou, Chao Ma, Yikai Zheng, Ruikun He, Yixue Li","doi":"10.1093/gigascience/giae082","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>In recent years, large language models (LLMs) have shown promise in various domains, notably in biomedical sciences. However, their real-world application is often limited by issues like erroneous outputs and hallucinatory responses.</p><p><strong>Results: </strong>We developed the knowledge graph-based thought (KGT) framework, an innovative solution that integrates LLMs with knowledge graphs (KGs) to improve their initial responses by utilizing verifiable information from KGs, thus significantly reducing factual errors in reasoning. The KGT framework demonstrates strong adaptability and performs well across various open-source LLMs. Notably, KGT can facilitate the discovery of new uses for existing drugs through potential drug-cancer associations and can assist in predicting resistance by analyzing relevant biomarkers and genetic mechanisms. To evaluate the knowledge graph question answering task within biomedicine, we utilize a pan-cancer knowledge graph to develop a pan-cancer question answering benchmark, named pan-cancer question answering.</p><p><strong>Conclusions: </strong>The KGT framework substantially improves the accuracy and utility of LLMs in the biomedical field. This study serves as a proof of concept, demonstrating its exceptional performance in biomedical question answering.</p>","PeriodicalId":12581,"journal":{"name":"GigaScience","volume":"14 ","pages":""},"PeriodicalIF":11.8000,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11702363/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"GigaScience","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1093/gigascience/giae082","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Background: In recent years, large language models (LLMs) have shown promise in various domains, notably in biomedical sciences. However, their real-world application is often limited by issues like erroneous outputs and hallucinatory responses.
Results: We developed the knowledge graph-based thought (KGT) framework, an innovative solution that integrates LLMs with knowledge graphs (KGs) to improve their initial responses by utilizing verifiable information from KGs, thus significantly reducing factual errors in reasoning. The KGT framework demonstrates strong adaptability and performs well across various open-source LLMs. Notably, KGT can facilitate the discovery of new uses for existing drugs through potential drug-cancer associations and can assist in predicting resistance by analyzing relevant biomarkers and genetic mechanisms. To evaluate the knowledge graph question answering task within biomedicine, we utilize a pan-cancer knowledge graph to develop a pan-cancer question answering benchmark, named pan-cancer question answering.
Conclusions: The KGT framework substantially improves the accuracy and utility of LLMs in the biomedical field. This study serves as a proof of concept, demonstrating its exceptional performance in biomedical question answering.
期刊介绍:
GigaScience seeks to transform data dissemination and utilization in the life and biomedical sciences. As an online open-access open-data journal, it specializes in publishing "big-data" studies encompassing various fields. Its scope includes not only "omic" type data and the fields of high-throughput biology currently serviced by large public repositories, but also the growing range of more difficult-to-access data, such as imaging, neuroscience, ecology, cohort data, systems biology and other new types of large-scale shareable data.