综合工业吸收,分布,新陈代谢和排泄数据集的多任务深度学习模型,以改善泛化
Joseph A Napoli1, Michael Reutlinger2, Patricia Brandl2
1Drug Metabolism & Pharmacokinetics (DMPK), Genentech, Inc., 1 DNA Way, South San Francisco, California 94080, United States.
Molecular pharmaceutics
|March 7, 2025
概括
来自多个来源的吸收,分布,新陈代谢和排泄 (ADME) 数据的结合增强了机器学习模型的概括性. 跨站点模型改善了对各种化学空间的预测,有助于药物发现.
科学领域:
- 药物的发现和开发.
- 计算化学是一种计算化学.
- 药理动力学 药理动力学
背景情况:
- 优化吸收,分布,新陈代谢和分泌 (ADME) 概况对于成功的药物发现至关重要.
- 机器学习 (ML) 模型对于优先考虑复合设计至关重要,但它们的有效性取决于多样化,高质量的实验数据.
- 扩大ML模型探索的化学空间对于识别新药候选药物至关重要.
研究的目的:
- 为了评估扩大化学空间对ML模型性能对ADME分析的影响.
- 评估结合来自不同来源的大规模历史ADME数据集的实用性.
- 研究跨不同数据源的多任务 (MT) 神经网络的泛化能力.
主要方法:
- 来自Genentech和Roche的联合ADME数据集,包括11个终点的100多万次测量.
- 利用多任务 (MT) 神经网络架构,同时对多个ADME端点进行建模.
- 训练并比较单个站点,单个任务的基线模型与跨站点MT模型,将不同站点的数据视为单独的任务.
- 评估基于集群,时间和外部测试集的模型性能,以评估概括性.
主要成果:
- 与单个站点模型相比,跨站点MT模型显示出更高的概括能力.
- 对于远程测试集 (外部和时间) 的性能改进更为显著,这表明应用范围扩大了.
- 该研究验证了利用来自多个来源的ADME数据的价值,没有直接聚合,即使使用不同的实验方法.
结论:
- 结合来自多个来源的ADME数据,提高了ML模型的预测能力和概括性.
- 跨站点多任务学习有效地扩大了ADME模型的应用领域.
- 这种方法通过从不同的化学空间中学习,在药物发现中促进了更强大的化合物优先级.
相关概念视频
Multicompartment Models: Overview
78
Multicompartment models are mathematical constructs that depict how drugs are distributed and eliminated within the body. They segment the body into several compartments, symbolizing various physiological or anatomical areas connected through drug transfer processes such as absorption, metabolism, distribution, and elimination.
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
78
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
54
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
54
Three-Compartment Open Model
120
The three-compartment open model is a pharmacokinetic model used to describe the distribution and elimination of drugs following extravascular administration. It comprises a central compartment representing the plasma and two peripheral compartments. The highly perfused peripheral compartment represents organs and tissues with a rich blood supply, such as the liver, kidneys, and lungs. The scarcely perfused peripheral compartment represents tissues with lower blood supply, such as adipose...
120
Two-Compartment Open Model: Overview
85
Multicompartmental models are crucial tools in pharmacokinetics, providing a framework to understand how drugs move within the body. The two-compartment model is a crucial subtype, segmenting the body into central and peripheral compartments. The central compartment represents areas with high blood flow, such as plasma and highly perfused organs like the kidneys and liver, while the peripheral compartment signifies tissues with lower blood flow, like adipose tissue and muscle tissue.
The...
The...
85
Two-Compartment Open Model: Extravascular Administration
130
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...
130
Pharmacokinetic Models: Comparison and Selection Criterion
35
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.
35


