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 LogK_p 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 LogK_p 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.

Glioma, a highly aggressive form of brain cancer, continues to pose significant therapeutic challenges in the field of medicine. Its invasive nature and resistance to traditional treatments make it particularly difficult to combat. This review examines the potential of metformin, a commonly prescribed antidiabetic medication, as a promising new treatment option for glioma. The potential of metformin to target crucial metabolic pathways in cancer cells presents an encouraging approach to improve therapeutic outcomes. The review explores the complexities of metabolic reprogramming in glioma and metformin's role in inhibiting these metabolic pathways. Preclinical studies demonstrate metformin's efficacy in reducing tumor growth and enhancing the sensitivity of glioma cells to chemotherapy and radiotherapy. Furthermore, clinical studies highlight metformin's potential in improving progression-free survival and overall survival rates in glioma patients. The review also addresses the synergistic effects of combining metformin with other therapeutic agents, such as temozolomide and radiotherapy, to overcome drug resistance and improve treatment efficacy. Despite the promising findings, the review acknowledges the need for further clinical trials to establish optimal dosing regimens, understand the molecular mechanisms underlying metformin's antitumor effects, and identify patient populations that would benefit the most from metformin-based therapies. Additionally, the potential side effects and the long-term impact of metformin on Glioma patients require careful evaluation. In conclusion, this review underscores the potential of metformin as a repurposed drug in glioma treatment, emphasizing its multifaceted role in targeting metabolic dysregulation. Metformin holds promise as part of a combination therapy approach to improve the therapeutic landscape of glioma and offers hope for better patient outcomes.