Role of physicochemical properties in the estimation of skin permeability: in vitro data assessment by Partial Least-Squares Regression.

Skin provides passage for the delivery of drugs. The in vitro and in vivo testing of chemicals for estimation of dermal absorption is very time consuming, costly and has many ethical difficulties related to human and animal testing. The solution to the problem is Quantitative structure-permeability relationships. This method relates dermal penetration properties of a range of chemical compounds to their physicochemical parameters. In the present study, an effort has been made to develop models for the accurate prediction of skin permeability using a large, diverse dataset through the combination of various regression methods coupled with the Genetic Algorithm (GA)/Interval Partial Least-Squares Algorithm (iPLS). The descriptors were calculated using e-DRAGON and ADME Pharma Algorithms-Abrahams descriptors. The original dataset was divided into a training set and a testing set using the Kennard-Stone Algorithm. The selection of descriptors was made by the GA and iPLS. The model applicability domain was determined. The results showed that a three-parameter model built through Partial Least-squares Regression was most accurate with r(2) of 0.936.