适应性AI框架用于使用GAT,变压器和AutoML的药理动力学
R Satheeskumar1, P Devabalan2, C H V Satyanarayana3
1Narasaraopeta Engineering College, Narasaraopet, Andhra Pradesh, India. satheesme@gmail.com.
这项研究引入了一个动态的人工智能框架,用于实时预测药物药理动力学参数. 这种先进的模型提高了预测准确度,并加速了基于数据的药物开发决策.
科学领域:
- 药理动力学 药理动力学
- 人工智能在药物发现中的作用
- 计算化学计算化学
背景情况:
- 准确预测药物动力学参数 (吸收,分布,新陈代谢,分泌) 在药物发现中至关重要,但具有挑战性.
- 传统的实验方法耗时且昂贵,阻碍了快速决策.
- 现有的计算模型往往是静态的,并且需要使用新数据进行广泛的再培训.
研究的目的:
- 开发和验证实时人工智能 (AI) 框架,用于预测药理动力学参数.
- 为了使动态模型重新校准使用新可用的数据,而不是完全重新训练.
- 提高药物开发中的药理动力学建模的可扩展性,响应性和预测准确性.
主要方法:
- 集成图表注意力网络,变压器模型和自动机器学习.
- 开发一个动态框架,定期纳入新的数据,按给药途径分层 (例如静脉注射,口服).
- 实施模型重新校准而不需要完全重新训练以适应新的化合物数据,包括单点测量.
主要成果:
- 对于药物动力学参数预测,达到0.93的平均确定系数 (R2).
- 达到0.059的平均绝对误差 (MAE),表明预测准确度高.
- 在动态预测场景中,与传统批量学习技术相比,表现优越.
结论:
- 拟议的AI框架为实时,准确的药理动力学参数预测提供了一个有希望的解决方案.
- 动态重新校准方法提高了灵活性,并允许高效地集成新化合物.
- 这一框架有可能在整个药物开发过程中显著加速数据驱动的决策.
更多相关视频
08:49Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
Published on: June 20, 2025
07:23Author Spotlight: Developing a Simple and Robust Hepatic Model for Pharmacological and Toxicological Applications
Published on: October 20, 2023
相关概念视频
Model Approaches for Pharmacokinetic Data: 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...
Pharmacokinetic Models: Overview
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal...
Analysis of Population Pharmacokinetic Data
Model Approaches for Pharmacokinetic Data: Compartment Models
Two primary types of compartment models are recognized: mammillary and catenary. The more...
Model-Independent Approaches for Pharmacokinetic Data: Noncompartmental Analysis
One important characteristic of noncompartmental analyses is that drug exposure increases proportionally with increasing doses. This...
Model Approaches for Pharmacokinetic Data: Physiological Models
