Predictive modeling of skin permeability for molecules: Investigating FDA-approved drug permeability with various AI algorithms

The transdermal route of drug administration has gained popularity for its convenience and bypassing the first-pass metabolism. Accurate skin permeability prediction is crucial for successful transdermal drug delivery (TDD). In this study, we address this critical need to enhance TDD. A dataset comprising 441 records for 140 molecules with diverse LogKp values was characterized. The descriptor calculation yielded 145 relevant descriptors. Machine learning models, including MLR, RF, XGBoost, CatBoost, LGBM, and ANN, were employed for regression analysis. Notably, LGBM, XGBoost, and gradient boosting models outperformed others, demonstrating superior predictive accuracy. Key descriptors influencing skin permeability, such as hydrophobicity, hydrogen bond donors, hydrogen bond acceptors, and topological polar surface area, were identified and visualized. Cluster analysis applied to the FDA-approved drug dataset (2326 compounds) revealed four distinct clusters with significant differences in molecular characteristics. Predicted LogKp values for these clusters offered insights into the permeability variations among FDA-approved drugs. Furthermore, an investigation into skin permeability patterns across 83 classes of FDA-approved drugs based on the ATC code showcased significant differences, providing valuable information for drug development strategies. The study underscores the importance of accurate skin permeability prediction for TDD, emphasizing the superior performance of nonlinear machine learning models. The identified key descriptors and clusters contribute to a nuanced understanding of permeability characteristics among FDA-approved drugs. These findings offer actionable insights for drug design, formulation, and prioritization of molecules with optimum properties, potentially reducing reliance on costly experimental testing. Future research directions include offering promising applications in pharmaceutical research and formulation within the burgeoning field of computer-aided drug design.Author summary: Our study delves into the exciting realm of transdermal drug delivery, a growing preference for patients due to its convenience. Recognizing the challenge posed by the skin’s natural barrier to drug permeation, we employed advanced machine learning models to predict skin permeability solely based on descriptors computationally calculated from the chemical structure of the molecule. Key descriptors, including partition coefficient, hydrogen bond donors, hydrogen bond acceptors, and topological polar surface area, emerged as influential factors in skin permeability prediction. Hydrophobicity, polarity, and adherence to Lipinski rules were identified as crucial considerations. Analyzing FDA-approved drugs and their predicted permeability revealed distinct clusters with varied permeability characteristics, shedding light on the potential applications of different compounds in transdermal drug delivery. Our research provides valuable tools for early-stage drug discovery, facilitating the selection of compounds with optimal skin permeability. While acknowledging certain limitations, particularly in representing high molecular weight drugs, our models offer a promising avenue for efficient drug design and formulation. By making these findings accessible, we aim to contribute to the broader understanding of transdermal drug delivery and inspire further research in this dynamic field.