PKSmart: an open-source computational model to predict intravenous pharmacokinetics of small molecules

← Back to publications

Published: 2025-09-26

Formatted citation

Seal S, Trapotsi MA, Mahale M, Subramanian V, Greene N, Spjuth O, and Bender A.. PKSmart: an open-source computational model to predict intravenous pharmacokinetics of small molecules.
Journal of Cheminformatics. 17, 147 (2025). DOI: 10.1186/s13321-025-01066-5

Abstract

Drug exposure, a key determinant of drug safety and efficacy, is governed by pharmacokinetic (PK) parameters such as volume of distribution (VDss), clearance (CL), half-life (t½), fraction unbound in plasma (fu), and mean residence time (MRT). In this study, we developed machine learning models to predict human PK parameters for 1,283 unique compounds using molecular structure, physicochemical properties, and predicted animal PK data. Our approach involved a two-stage modeling pipeline. First, we trained models to predict rat, dog, and monkey PK parameters (VDss, CL, fu) from chemical structure and properties for 371 compounds. These models were used to predict animal PK values for 1,283 unique compounds with human PK data. These animal PK predictions were then integrated with molecular descriptors and fingerprints to build Random Forest models for human PK parameters. The models demonstrated consistent performance across nested cross-validation and external validation sets, with predictive accuracy for VDss comparable to proprietary models developed by AstraZeneca. Notably, human VDss and CL predictions achieved external R2 values of 0.39 and 0.46, respectively. To support broad accessibility and integration into early drug discovery workflows such as Design-Make-Test-Analyze (DMTA), we developed PKSmart (https://broad.io/PKSmart), a freely available web application. All code and models are also open source, enabling local deployment. To our knowledge, this represents the first public suite of PK prediction models with performance on par with industry standard models.