Prediction of In Vivo Pharmacokinetic Parameters and Time–Exposure Curves in Rats Using Machine Learning from the Chemical Structure

• Published in: Molecular pharmaceutics Vol. 19; no. 5; pp. 1488 - 1504
• Main Authors: Obrezanova, Olga, Martinsson, Anton, Whitehead, Tom, Mahmoud, Samar, Bender, Andreas, Miljković, Filip, Grabowski, Piotr, Irwin, Ben, Oprisiu, Ioana, Conduit, Gareth, Segall, Matthew, Smith, Graham F, Williamson, Beth, Winiwarter, Susanne, Greene, Nigel
• Format: Journal Article
• Language: English
• Published: United States American Chemical Society 02.05.2022
• Subjects: Animals; Biological Availability; Drug Discovery; Machine Learning; Metabolic Clearance Rate; Models, Biological; Pharmaceutical Preparations; Pharmacokinetics; Rats; data imputation; QSPR; graph convolutions; bioavailability; neural networks; clearance; machine learning; compound design; concentration−time pharmacokinetic profiles; rat pharmacokinetics
• ISSN: 1543-8384; 1543-8392
• DOI: 10.1021/acs.molpharmaceut.2c00027

Animal pharmacokinetic (PK) data as well as human and animal in vitro systems are utilized in drug discovery to define the rate and route of drug elimination. Accurate prediction and mechanistic understanding of drug clearance and disposition in animals provide a degree of confidence for extrapolation to humans. In addition, prediction of in vivo properties can be used to improve design during drug discovery, help select compounds with better properties, and reduce the number of in vivo experiments. In this study, we generated machine learning models able to predict rat in vivo PK parameters and concentration–time PK profiles based on the molecular chemical structure and either measured or predicted in vitro parameters. The models were trained on internal in vivo rat PK data for over 3000 diverse compounds from multiple projects and therapeutic areas, and the predicted endpoints include clearance and oral bioavailability. We compared the performance of various traditional machine learning algorithms and deep learning approaches, including graph convolutional neural networks. The best models for PK parameters achieved R 2 = 0.63 [root mean squared error (RMSE) = 0.26] for clearance and R 2 = 0.55 (RMSE = 0.46) for bioavailability. The models provide a fast and cost-efficient way to guide the design of molecules with optimal PK profiles, to enable the prediction of virtual compounds at the point of design, and to drive prioritization of compounds for in vivo assays.