RxBERT: 提高药物标签 通过人工智能语言建模来进行文本挖掘和分析
Leihong Wu1, Magnus Gray1, Oanh Dang2
1Division of Bioinformatics and Biostatistics, FDA National Center for Toxicological Research, Jefferson, AR 72079, USA.
Experimental biology and medicine (Maywood, N.J.)
|January 3, 2024
概括
研究人员开发了RxBERT,这是一种专门的AI模型,用于分析美国药物标签文件. 这种先进的自然语言处理工具通过改进从复杂文本中提取信息来增强药物安全性审查和监管决策.
科学领域:
- 计算语言学计算语言学
- 监管科学是一种监管科学.
- 医学中的人工智能
背景情况:
- 美国药物标签文件对于评估药物的有效性和安全性至关重要,但由于其体积和自由文本性质,对传统的文本挖掘构成挑战.
- 人工智能 (AI) 和自然语言处理 (NLP) 的进步为从这些复杂的监管文件中提取关键信息提供了新的方法.
- 现有的NLP模型可能无法针对FDA药物标签数据的特定细微差别和结构进行最佳调整.
研究的目的:
- 开发和评估RxBERT,一种基于变压器的NLP模型,专门经过FDA人类处方药标签文件的预训练.
- 加强药品标签信息的处理和利用,用于研究和监管审查目的.
- 展示定制大型语言模型 (LLM) 对敏感监管文件分析的潜力.
主要方法:
- 开发了RxBERT,一种来自变压器的双向编码器表示 (BERT) 模型,通过进一步预训练BioBERT在FDA人类处方药标签文件上.
- 在多个监管数据集上评估RxBERT,包括NIST TAC数据集,FDA ADE Eval数据集和美国药物标签数据集用于文本分类.
- 与BERT和BioBERT等既有NLP模型相比,比较了RxBERT的表现.
主要成果:
- 与其他NLP方法相比,RxBERT实现了竞争性或优异的性能.
- 在NIST TAC和FDA ADE Eval分类任务中获得了86.5个F1分.
- 在美国药品标签数据集上达到87%的预测准确度,用于将文本分类为标签部分.
结论:
- 适用于药物标签的变压器模型RxBERT表现出比原始BERT模型更高的性能.
- RxBERT显示出有很大的潜力,可以帮助研究人员和FDA审查人员处理药物标签信息,从而提高药物的有效性和公共卫生安全.
- 该研究验证了为专门的,敏感的监管数据创建定制的LLM的途径.
相关概念视频
Drug Discovery: Overview
7.9K
Drug discovery is a multifaceted process involving extensive screening, testing, and optimization of lead compounds to identify potential new drugs for therapeutic use. It combines several approaches, including screening large numbers of natural products, chemical modification of known active molecules, identification of new drug targets, and rational design based on biological mechanisms and drug-receptor structure. These approaches are carried out in both academic research laboratories and...
7.9K
Drug Biotransformation: Overview
2.4K
Pharmaceutical substances known as xenobiotics are predominantly lipophilic and nonionized. This enables them to permeate lipid bilayers, such as cell membranes, and interact with intracellular target receptors. Lipophilic drugs have an advantage in crossing biological barriers and reaching their intended sites of action. However, lipophilic drugs often have a restricted capacity for renal expulsion or elimination from the body. When these drugs enter the kidneys and undergo glomerular...
2.4K
Drug Nomenclature
1.8K
During the development of a new pharmaceutical, the manufacturer initially assigns a code name to the drug. Once approved, the drug receives a United States Adopted Name (USAN)—a generic, nonproprietary designation. Upon being listed in the United States Pharmacopeia, this nonproprietary name becomes the drug's official name. Additionally, the manufacturer assigns a proprietary name or trademark, which serves as the brand name under which the drug is marketed. It is worth noting that...
1.8K
Targets for Drug Action: Overview
6.3K
Drugs target macromolecules to modify ongoing cellular processes. Primary drug targets include receptors, ion channels, transporters, and enzymes.
Receptors are either membrane-spanning or intracellular proteins, which upon binding a ligand, get activated and transmit the signal downstream to elicit a response. Drugs bind receptors, either mimicking the action of endogenous ligands or blocking the receptor activity to bring about a modified response. Nearly 35% of approved drugs target the G...
Receptors are either membrane-spanning or intracellular proteins, which upon binding a ligand, get activated and transmit the signal downstream to elicit a response. Drugs bind receptors, either mimicking the action of endogenous ligands or blocking the receptor activity to bring about a modified response. Nearly 35% of approved drugs target the G...
6.3K
Factors Affecting Drug Response: Overview
2.0K
When it comes to infants and young children, they are typically administered smaller doses of medication in comparison to adults. This is primarily because their organ functions still need to fully develop, meaning their bodies are not as efficient at metabolizing or eliminating drugs. Additionally, their blood-brain barrier is more permeable than in adults. As a result, high concentrations of drugs can easily penetrate the central nervous system (CNS), potentially leading to neurological...
2.0K
Structure-Activity Relationships and Drug Design
726
Drug design is a dynamic field that involves discovering and developing new medications based on specific biological targets. This process heavily relies on structure-activity relationships (SAR) and quantitative structure-activity relationships (QSAR) to guide the design and optimization of efficient drugs.
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...
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...
726


