This article is a collaboration with Intellegens, the University of Cambridge and AstraZeneca. It provides a proof-of-concept study in which Cerella is used to predict rat in vivo pharmacokinetic (PK) parameters and concentration–time PK profiles.

This graphical abstract depicts the process used to predict rat in vivo pharmacokinetic parameters. Using descriptors and limited experimental input to train our AI methods, the researchers were able to identify compounds most likely to be successful in this project and improve their DMTA cycle


To uncover the rate and route of a potential drug’s elimination from the body, scientists assess and predict both in vivo animal pharmacokinetic (PK) data as well as human and animal in vitro systems. Computational prediction of in vivo properties can also 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, the researchers generated new machine learning models. These were able to predict rat in vivo PK parameters and concentration–time PK profiles based on a compound’s molecular structure and either measured or predicted in vitro parameters. They trained the models on internal in vivo rat PK data for over 3000 diverse compounds, with predicted endpoints including clearance and oral bioavailability, and compared various traditional machine learning algorithms and deep learning approaches for performance.

They found that the models provide a fast and cost-efficient way to guide the design of molecules with optimal PK profiles. This enables the prediction of virtual compounds at the point of design, and drives the prioritization of compounds for in vivo assays.

Citation details

O. Obrezanova, A. Martinsson, T. Whitehead, S. Mahmoud, A. Bender, F. Miljković, P. Grabowski, B. Irwin, I. Oprisiu, G. Conduit, M. Segall, G. F. Smith, B. Williamson, S. Winiwarter, and N. Greene, Mol. Pharmaceutics, 2022, 19, 5, 1488–1504.

DOI: 10.1021/acs.molpharmaceut.2c00027

Find out more about predicting in vivo properties

For further detail on how Cerella can be used to predict PK parameters and curves, watch our webinar. It features three of the authors of this paper, Matt Segall (Optibrium), Tom Whitehead (Intellegens), Nigel Greene (AstraZeneca), discussing their work around Cerella and its applications.