利用大型语言模型从生物医学文本中结构化提取P450物质相互作用
Mariam Alkarmouty1, Junya Ooka1, Fumiyoshi Yamashita1
1Department of Quantitative Pharmaceutics, Graduate School of Pharmaceutical Sciences, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan.
大型语言模型 (LLM) 现在可以准确地从生物医学文本中提取P450 (CYP) 和物质相互作用. 这种先进的框架大大改善了药物代谢研究的数据整合.
科学领域:
- 生物医学文本挖掘
- 药物基因组学
- 计算生物学
背景情况:
- 细胞P450 (CYP) 酶在药物代谢中起着至关重要的作用.
- 准确识别CYP与物质的相互作用对于药物开发和安全至关重要.
- 提取这些相互作用的先前方法在规模和精度上是有限的.
研究的目的:
- 使用大型语言模型 (LLM) 的最新进展,开发一个可扩展和高精度的框架来提取CYP物质相互作用.
- 改进 CYP 异型物质相互作用数据的系统整合.
- 克服以往对这些互动进行分类的局限性.
主要方法:
- 通过使用ChatGPT O3-mini大型语言模型.
- 使用结构化输出格式和嵌入式定义的快速工程.
- 使用精选的少量实例和批量处理,而不依赖于字典或特定领域的本体.
主要成果:
- 在所有CYP标中实现了0. 963的回忆率和0. 987的精度.
- 对于CYP3A4来说,回忆率为0. 923和精度为0. 993.
- 与以往的基于规则的方法相比,已经显著改进.
结论:
- 由LLM驱动的管道为CYP与物质相互作用的生物医学文本挖掘提供了重大进展.
- 开发的框架可以更系统,更全面地整合互动数据.
- 这种方法加速了药物代谢的研究,并支持开发更安全,更有效的治疗方法.
更多相关视频
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
07:34Large Scale Non-targeted Metabolomic Profiling of Serum by Ultra Performance Liquid Chromatography-Mass Spectrometry UPLC-MS
Published on: March 14, 2013
相关概念视频
Ligand Binding Sites
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
Protein-protein Interfaces
Drug Metabolism: Phase II Reactions
Quantitative Aspects of Drug-Receptor Interaction
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Structure-Activity Relationships and Drug Design
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
