Validated models for predicting skin penetration from different vehicles

The permeability of a penetrant though skin is controlled by the properties of the penetrants and the mixture components, which in turn relates to the molecular structures. Despite the well-investigated models for compound permeation through skin, the effect of vehicles and mixture components has not received much attention. The aim of this Quantitative Structure Activity Relationship (QSAR) study was to develop a statistically validated model for the prediction of skin permeability coefficients of compounds dissolved in different vehicles. Furthermore, the model can help with the elucidation of the mechanisms involved in the permeation process. With this goal in mind, the skin permeability of four different penetrants each blended in 24 different solvent mixtures were determined from diffusion cell studies using porcine skin. The resulting 96 kp values were combined with a previous dataset of 288 kp data for QSAR analysis. Stepwise regression analysis was used for the selection of the most significant molecular descriptors and development of several regression models. The selected QSAR employed two penetrant descriptors of Wiener topological index and total lipole moment, boiling point of the solvent and the difference between the melting point of the penetrant and the melting point of the solvent. The QSAR was validated internally, using a leave-many-out procedure, giving a mean absolute error of 0.454 for the log. kp value of the test set.