Physiologically Informed Deep Learning: A Multi-Scale Framework for Next-Generation PBPK Modeling

TL;DR

This paper introduces a multi-scale deep learning framework for PBPK modeling that combines mechanistic and data-driven methods, improving simulation speed, accuracy, and biological plausibility in drug pharmacokinetics.

Contribution

It presents three novel models: PBPK Transformers, Physically Constrained Diffusion Models, and Neural Allometry, integrating physics and machine learning for advanced PBPK analysis.

Findings

Reduced physiological violation rates from 2.00% to 0.50%.

Enhanced simulation speed and biological compliance.

Demonstrated effectiveness on synthetic datasets.

Abstract

Physiologically Based Pharmacokinetic (PBPK) modeling is a cornerstone of model-informed drug development (MIDD), providing a mechanistic framework to predict drug absorption, distribution, metabolism, and excretion (ADME). Despite its utility, adoption is hindered by high computational costs for large-scale simulations, difficulty in parameter identification for complex biological systems, and uncertainty in interspecies extrapolation. In this work, we propose a unified Scientific Machine Learning (SciML) framework that bridges mechanistic rigor and data-driven flexibility. We introduce three contributions: (1) Foundation PBPK Transformers, which treat pharmacokinetic forecasting as a sequence modeling task; (2) Physiologically Constrained Diffusion Models (PCDM), a generative approach that uses a physics-informed loss to synthesize biologically compliant virtual patient populations; and (3) Neural Allometry, a hybrid architecture combining Graph Neural Networks (GNNs) with Neural ODEs to learn continuous cross-species scaling laws. Experiments on synthetic datasets show that the framework reduces physiological violation rates from 2.00% to 0.50% under constraints while offering a path to faster simulation.