用动态图神经网络预测药物在器官间的浓度变化，更准且更稳定。
Dynamic Graph Neural Networks for Physiological Based Pharmacokinetic Modeling: A Novel Data Driven Approach to Drug Concentration Prediction
- 基于生理结构图，用动态消息传递建模器官间相互作用。
- MAPE仅15.7%，R²达0.9342，误差更稳定。
- 适合药物研发中需要高精度预测的场景。
生理药代动力学（PBPK）建模是药物开发中预测药物在各器官中浓度动态的关键工具。传统方法依赖常微分方程并做简化假设，难以捕捉非线性及系统级生理交互。本文探索基于数据驱动的PBPK建模，实现两种基线架构——多层感知机（MLP）与长短期记忆网络（LSTM），并提出一种动态图神经网络（Dynamic GNN），通过在生理图上进行循环消息传递，显式建模器官间交互。在多器官药代动力学数据集上的实验表明，Dynamic GNN在所有模型中达到最低平均绝对百分比误差（MAPE）15.7%，相对精度更高，尽管绝对误差略高于MLP基线。该模型取得R²为0.9342，误差行为更稳定，且更好地捕捉了器官间的药代动力学关系。结果表明，结构感知建模对PBPK应用至关重要，所提出的Dynamic GNN为数据驱动药代预测提供了一种可扩展、无需方程的替代方案。
原文摘要 · Abstract (English)
Physiologically Based Pharmacokinetic (PBPK) modeling is a key tool in drug development for predicting drug concentration dynamics across organs. Traditional PBPK approaches rely on ordinary differential equations with simplifying assumptions that limit their ability to capture nonlinear and system-level physiological interactions. In this work, we investigate data-driven PBPK modeling using deep learning. We implement two baseline architectures -- a multilayer perceptron (MLP) and a long short-term memory (LSTM) network -- and propose a Dynamic Graph Neural Network (Dynamic GNN) that explicitly models inter-organ interactions through recurrent message passing on a physiological graph. Experiments on a multi-organ pharmacokinetic dataset show that the Dynamic GNN achieves the lowest mean absolute percentage error (MAPE) of 15.7% among all models, demonstrating improved relative accuracy despite slightly higher absolute error compared to the MLP baseline. The model attains an R2 of 0.9342 with more stable error behavior and better captures inter-organ pharmacokinetic relationships. These results highlight the importance of structure-aware modeling for PBPK applications and demonstrate that the proposed Dynamic GNN offers a scalable, equation-free alternative for data-driven pharmacokinetic prediction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。