与全球模型预测性能相比,探索适应性,本地机器学习的潜力:来自拜耳Caco-2透性数据库的案例研究
Frank Filip Steinbauer1,2, Thorsten Lehr2, Andreas Reichel1
1Preclinical Modeling and Simulation, Preclinical Development, Bayer AG, Muellerstr. 178, 13353 Berlin, Germany.
Journal of chemical information and modeling
|November 20, 2024
概括
机器学习模型可以预测Caco-2的透性,用于药物发现. 具有RDKit描述符的全球LightGBM模型有效地预测透性,优于自适应的本地模型.
科学领域:
- 计算化学是一种计算化学.
- 药品化学 药品化学 是一个
- 药物发现 药物发现
背景情况:
- 机器学习 (ML) 模型预测药物设计的分子性质在扩展和超越五 (eRo5, bRo5) 化学空间的规则.
- 准确预测Caco-2的透性,特别是对于eRo5/bRo5空间中的较大分子,对于全球ML模型来说仍然具有挑战性.
研究的目的:
- 确定一个最佳的ML算法和描述器组合来预测Caco-2的透性.
- 将全球ML模型的性能与适应性局部模型进行对比,以预测Caco-2的透性.
主要方法:
- 使用了LightGBM算法与RDKit分子属性描述器.
- 开发了一种基于所有可用的数据进行训练的全球模型.
- 开发了一个自适应的本地模型,使用Tanimoto指纹相似性来选择训练数据.
主要成果:
- 全球模型证明了高效和准确的Caco-2透性的预测.
- 与全球模型相比,自适应的本地模型只显示了边际性能改进.
- 无法确定局部模型参数化的一般规则,这表明预先选择训练数据是不有利的.
结论:
- 使用LightGBM和RDKit描述符的全球ML模型对于Caco-2透性预测非常有效.
- 适应性本地建模方法在这个特定任务中并不总是优于全球模型.
- 进一步的研究可能将重点放在数据效率模型创建上,而不是复杂的数据选择策略.
相关概念视频
Pharmacokinetic Models: Comparison and Selection Criterion
43
Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
43
Two-Compartment Open Model: Extravascular Administration
156
The two-compartment model for extravascular administration represents a drug's absorption and distribution process. It features a central compartment, where the drug is first absorbed, and a peripheral compartment, which illustrates the drug's distribution throughout the body. The rate of change in drug concentration in the central compartment is calculated by three exponents: absorption, distribution, and elimination.
The absorption exponent (ka) indicates the speed at which the drug...
The absorption exponent (ka) indicates the speed at which the drug...
156


