相关实验视频
Updated: May 11, 2026

Diagonal Method to Measure Synergy Among Any Number of Drugs
Published on: June 21, 2018
药物标评估:使用基于BERT的多级分类模型对标调制和相关健康影响进行分类
Jennifer Venhorst1, Gino Kalkman1
1Biomedical and Digital Health, The Netherlands Organization for Applied Scientific Research (TNO), Utrecht 3584 CB, The Netherlands.
大型语言模型从文献中系统地分析药物向健康影响. 这种人工智能方法通过提供有效性和安全性的机制性见解来加速药物发现,优于手工方法.
科学领域:
- 生物医学信息学 生物医学信息学
- 计算生物学 计算生物学
- 药物发现 药物发现 药物发现
背景情况:
- 药物标选择对于成功的药物开发至关重要.
- 手动风险/收益分析耗时且容易产生偏见.
- 大型语言模型 (LLM) 为文学策划提供了一个系统和高效的替代方案.
研究的目的:
- 开发和评估基于BERT的LLMs来分类药物标与健康影响的关系.
- 提供对目标调制对健康和疾病影响的机制性见解.
- 创建一个人工智能辅助的工具,用于有效的药物标识别和评估.
主要方法:
- 开发了BERT模型,用于PubMed索引关系的多层次分类.
- 基于因果关系,目标调制和健康影响方向的分类关系.
- 已验证的模型性能,F1得分从0.86到0.92.9不等.
主要成果:
- 取得了竞争性表现,F1得分为0.86-0.92.2.
- 通过案例研究证明了适用性 (ADAM33,OSM).
- 开发的管道是第一个提供这些关系的详细分类的管道.
结论:
- 该LLMs提供了对药物目标健康影响的机制性见解.
- 这种人工智能驱动的方法提高了药物标识别和评估效率.
- 目标Tri平台为人工智能辅助的药物发现提供了一个新的资源.
更多相关视频
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
13:18Network Pharmacology Prediction and Experimental Validation of Trichosanthes-Fritillaria thunbergii Action Mechanism Against Lung Adenocarcinoma
Published on: March 3, 2023
相关概念视频
Targets for Drug Action: Overview
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...
Therapeutic Drug Monitoring: Overview and Classification
Pharmacogenetics of Drug Targets: β₂-Adrenergic Receptors, Apo E, Thymidylate Synthase
Pharmacogenomics: Identification of New Drug Targets
Pharmacodynamic Models: Direct Effect Model and Indirect Response Model
Modified-Release Drug Delivery Systems: Site-Targeted