An evaluation of the potential of linear and nonlinear skin permeation models for the prediction of experimentally measured percutaneous drug absorption

Abstract

Objectives: The developments in combinatorial chemistry have led to a rapid increase in drug design and discovery and, ultimately, the production of many potential molecules that require evaluation. Hence, there has been much interest in the use of mathematical models to predict dermal absorption. Therefore, the aim of this study was to test the performance of both linear and nonlinear models to predict the skin permeation of a series of 11 compounds. Methods: The modelling in this study was carried out by the application of both quantitative structure permeability relationships and Gaussian process-based machine learning methods to predict the flux and permeability coefficient of the 11 compounds. The actual permeation of these compounds across human skin was measured using Franz cells and a standard protocol with high performance liquid chromatography analysis. Statistical comparison between the predicted and experimentally-derived values was performed using mean squared error and the Pearson sample correlation coefficient. Key findings: The findings of this study would suggest that the models failed to accurately predict permeation and in some cases were not within two-or threeorders of magnitude of the experimentally-derived values. However, with this set of compounds the models were able to effectively rank the permeants. Conclusions: Although not suitable for accurately predicting permeation the models may be suitable for determining a rank order of permeation, which may help to select candidate molecules for in-vitro screening. However, it is important to note that such predictions need to take into account actual relative drug candidate potencies.