Current Insights on Skin Permeability Data and Quantitative Structure-Property Relationship Modeling

Area of Science:

• Pharmacokinetics and Drug Delivery
• Computational Chemistry and Cheminformatics
• Toxicology and Occupational Safety

Background:

• Skin permeability is crucial for product development and safety assessments.
• Experimental measurement of skin permeability coefficients (K_p) is laborious and costly.
• Computational prediction models are needed to streamline research and development.

Purpose of the Study:

• To develop and validate a quantitative structure-property relationship (QSPR) model for predicting skin permeability.
• To utilize the SkinPiX dataset and HuskinDB database for model development.
• To provide a freely accessible tool for researchers and industry professionals.

Main Methods:

• Development of a QSPR model using curated compound data from SkinPiX and HuskinDB.
• Inclusion of 209 compounds with experimentally determined K_p values and metadata.
• Validation of the model against three new experimental data points.

Main Results:

• A robust QSPR model was successfully developed for predicting skin permeability coefficients.
• The model demonstrates reliable performance on new experimental data.
• The developed datasets and predictive models are made publicly available.

Conclusions:

• The QSPR model offers an efficient and cost-effective method for estimating skin permeability.
• This tool can significantly aid in the development of safer pharmaceuticals, cosmetics, and in occupational safety evaluations.
• The free availability of datasets and models promotes wider adoption and accelerates innovation.