The Application of Gaussian Processes in the Prediction of Percutaneous Absorption for Mammalian and Synthetic Membranes

Improving prediction of the skin permeability coefficient is a difficult problem, and an important issue with the increasing use of skin patches as a means of drug delivery. In this work, we apply Gaussian Processes (GPs) with five different covariance functions to predict the permeability coefficients of human, pig, rodent and silastic membranes. We obtain a considerable improvement over quantitative structure-activity relationship (QSARs) predictors. The GPs with Matérn and neural network covariance functions give the best performance in this work. We find that five compound features applied to human, pig and rodent membranes cannot represent the main characteristics of the silastic dataset.