|
Physiologically based pharmacokinetic (PBPK) modeling provides a mechanistic framework for describing the absorption, distribution, metabolism, and excretion (ADME) of drugs by integrating drug-specific properties with physiological and anatomical information. However, reliable PBPK modeling often requires the estimation of drug-specific parameters that are difficult or expensive to obtain experimentally.
This research explores the use of machine learning, cheminformatics, and explainable artificial intelligence to predict such parameters from molecular structure and other experimentally accessible information. A particular focus is placed on developing reliable and interpretable models for ADME properties with rigorous evaluation of model uncertainty.
|
|
|
PUBLICATION
Rajdeep Mondal, Rajith K. R. Rajoli, Andrew Owen and Soumitra Samanta,
Reliable Apparent Permeability Prediction Through Benchmarking, Stability, Uncertainty Quantification, and Explainable Machine Learning, CPT: Pharmacometrics & Systems Pharmacology, 15(8), 2026,
[pdf]
[bibtex]
[demo]
|
|
