Date of this Version
The skin is a major exposure route for many potentially toxic chemicals. It is, therefore, important to be able to predict the permeability of compounds through skin under a variety of conditions. Available skin permeability databases are often limited in scope and not conducive to developing effective models. This sparseness and ambiguity of available data prompted the use of fuzzy set theory to model and predict skin permeability. Using a previously published database containing 140 compounds, a rule-based Takagi–Sugeno fuzzy model is shown to predict skin permeability of compounds using octanol-water partition coefficient, molecular weight, and temperature as inputs. Model performance was estimated using a cross-validation approach. In addition, 10 data points were removed prior to model development for additional testing with new data. The fuzzy model is compared to a regression model for the same inputs using both R2 and root mean square error measures. The quality of the fuzzy model is also compared with previously published models. The statistical analysis demonstrates that the fuzzy model performs better than the regression model with identical data and validation protocols. The prediction quality for this model is similar to others that were published. The fuzzy model provides insights on the relationships between lipophilicity, molecular weight, and temperature on percutaneous penetration. This model can be used as a tool for rapid determination of initial estimates of skin permeability.