ADPO:自动区分辅助的参数优化
Rong Chen1, Mark Sale2, Alex Mazur2
1Data Sciences Software Division, Certara Inc., 4 Radnor Corporate Center, Suite 350, Radnor, 19087, PA, USA. rong.chen@certara.com.
自动分化 (AD) 现在在城NLME 8.6中,显著加快了药理动力学/药理动力学 (PK/PD) 模型分析. 这种新方法,即自动区分辅助参数优化 (ADPO),与传统方法相比,可减少20-50%的计算时间.
科学领域:
- 制药指标 (Pharmacometrics) 是一个指标.
- 计算科学 计算科学
- 机器学习 机器学习
背景情况:
- 准确的导数计算对于非线性混合效应建模至关重要.
- 像有限差的传统方法可以是计算密集的.
- 尼克斯NLME是用于药理动力学/药理动力学 (PK/PD) 分析的广泛使用的软件.
研究的目的:
- 在Phoenix NLME中引入自动差异化 (AD) 进行增强的参数优化.
- 与传统的有限差异方法相比,评估基于AD的方法的性能和效率.
- 评估AD对各种人口PK/PD建模算法的影响.
主要方法:
- 在Phoenix NLME 8.6.6中实现了AD作为"自动区分辅助参数优化" (ADPO).
- 应用ADPO到一阶条件估计扩展最小方程 (FOCE ELS),拉普拉斯和自适应高斯方程 (AGQ) 算法.
- 使用四种PK/PD模型和各种ODE解决器对有限差异 (FD) 方法进行基准ADPO.
主要成果:
- ADPO和传统的FOCE ELS (使用FD) 证明了可比的准确性和稳定性.
- 在所有测试的ODE解决方案中,ADPO显著减少了计算时间,一般为20%至50%.
- 一个使用voriconazole模型的具体案例显示,使用ADPO和"自动检测"ODE解决器,运行时间减少了95%.
结论:
- 在城NLME中,ADPO为PK/PD建模提供了相当大的计算优势.
- 支持ADPO的"快速优化"选项为传统梯度计算方法提供了更有效的替代方案.
- 应用AD代表了加速复杂的药理动力学和药理动力学分析的重大进展.
更多相关视频
10:36Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption
Published on: November 3, 2023
06:45Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
Published on: October 28, 2022
相关概念视频
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Statistical Methods to Analyze Parametric Data: ANOVA
One-way ANOVA is applied when a single independent variable or factor is scrutinized. It compares...
Implicit Differentiation: Problem Solving
Implicit Differentiation
Statistical Inference Techniques in Hypothesis Testing: Parametric Versus Nonparametric Data
Parametric statistics, as the name suggests, assumes that data follow a specific distribution, often a normal distribution. This assumption enables robust hypothesis testing and estimation. Parametric methods, like the Student's t-test or Goodness-of-fit test, are frequently employed in biostatistics due to their robustness. For instance,...
PD Controller: Design
Designing a continuous-data controller requires selecting and linking components like adders and integrators, which are fundamental in Proportional,...
