Vaginal administration is an important alternative to the oral route for both topical and systemic use. Therefore, the development of reliable in silico methods for the study of drugs permeability is becoming popular in order to avoid time-consuming and costly experiments. In the current study, Franz cells and appropriate HPLC or ESI-Q/MS analytical methods were used to experimentally measure the apparent permeability coefficient (P_app) of 108 compounds (drugs and non-drugs). P_app values were then correlate with 75 molecular descriptors (physicochemical, structural, and pharmacokinetic) by developing two Quantitative Structure Permeability Relationship (QSPR) models, a Partial Least Square (PLS) and a Support Vector Machine (SVM). Both were validated by internal, external and cross-validation. Based on the calculated statistical parameters (PLS model A: R² = 0.673 and Q² = 0.594, PLS model B: R² = 0.902 and Q² = 0.631, SVM: R² = 0.708 and Q² = 0.758). SVM presents higher predictability while PLS adequately interprets the theory of permeability. The most important parameters for vaginal permeability were found to be the relative PSA, logP, logD, water solubility and fraction unbound (FU). Respectively, the combination of both models could be a useful tool for understanding and predicting the vaginal permeability of drug candidates.

Vaginal administration is an important alternative to the oral route for both topical and systemic use. Therefore, the development of reliable in silico methods for the study of drugs permeability is becoming popular in order to avoid time-consuming and costly experiments. In the current study, Franz cells and appropriate HPLC or ESI-Q/MS analytical methods were used to experimentally measure the apparent permeability coefficient (P_app) of 108 compounds (drugs and non-drugs). P_app values were then correlate with 75 molecular descriptors (physicochemical, structural, and pharmacokinetic) by developing two Quantitative Structure Permeability Relationship (QSPR) models, a Partial Least Square (PLS) and a Support Vector Machine (SVM). Both were validated by internal, external and cross-validation. Based on the calculated statistical parameters (PLS model A: R² = 0.673 and Q² = 0.594, PLS model B: R² = 0.902 and Q² = 0.631, SVM: R² = 0.708 and Q² = 0.758). SVM presents higher predictability while PLS adequately interprets the theory of permeability. The most important parameters for vaginal permeability were found to be the relative PSA, logP, logD, water solubility and fraction unbound (FU). Respectively, the combination of both models could be a useful tool for understanding and predicting the vaginal permeability of drug candidates.