In Silico Prediction of Skin Permeability Using a Two-QSAR Approach

Abstract

Topical and transdermal drug delivery is an effective, safe, and preferred route of drug administration. As such, skin permeability is one of the critical parameters that should be taken into consideration in the process of drug discovery and development. The ex vivo human skin model is considered as the best surrogate to evaluate in vivo skin permeability. This investigation adopted a novel two-QSAR scheme by collectively incorporating machine learning-based hierarchical support vector regression (HSVR) and classical partial least square (PLS) to predict the skin permeability coefficient and to uncover the intrinsic permeation mechanism, respectively, based on ex vivo excised human skin permeability data compiled from the literature. The derived HSVR model functioned better than PLS as represented by the predictive performance in the training set, test set, and outlier set in addition to various statistical estimations. HSVR also delivered consistent performance upon the application of a mock test, which purposely mimicked the real challenges. PLS, contrarily, uncovered the interpretable relevance between selected descriptors and skin permeability. Thus, the synergy between interpretable PLS and predictive HSVR models can be of great use for facilitating drug discovery and development by predicting skin permeability.

Activity Prediction of Various Herbicides against Honey Bee, Avian, and Multiple Human Leukemia, CNS, Ovarian, Prostate Cancer Cell Lines

“…As it is known, in Silico modeling provides non-ethical economical methodology of natural, synthesized, and hypothetical compound(s) with limited time-consuming steps. Permeation of any chemical can be occurred by diffusion, trans-or inter-cellular route according to its molecular polarity character and other physicochemical properties [24,25].…”

Development of a method for evaluating skin dullness: A mathematical model explaining dullness by the color, optical properties, and microtopography of the skin

“…R 2 > 0.5 represents a high level of confidence in the prediction whereas 0.3 < R 2 < 0.5 indicates acceptable prediction accuracy. PLS analysis is adopted in a wide range of research fields, including skin sensory evaluation and drug efficacy evaluation 10–15 . In the present study, we applied PLS analysis to explain the sensory evaluation of skin dullness using skin parameters and proposed that the perception of dullness is age dependent among Japanese women.…”

“…PLS analysis is adopted in a wide range of research fields, including skin sensory evaluation and drug efficacy evaluation. [10][11][12][13][14][15] In the present study, we applied PLS analysis to explain the sensory evaluation of skin dullness using skin parameters and proposed that the perception of dullness is age dependent among Japanese women. Such methodology and this paper's insights into physiological changes can be applied to define the perception of dullness on a global scale in the future.…”

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

“…In silico QSPR (Quantitative Structure-Property Relationship) models, which correlate numerical descriptors of molecular structure with specific properties, have been extensively used to predict skin permeability [ 8 ]. Multiple linear regression (MLR) and principal component analysis (PCA) models have traditionally been employed in QSPR studies of skin permeability [ 9 , 10 ].…”

“…However, due to the complex and diverse nature of the chemicals involved, nonlinear regression methods such as support vector machine (SVM), random forest (RF), and artificial neural networks (ANN) have gained popularity over linear methods. These nonlinear methods are more effective at identifying patterns and capturing nonlinear relationships within complex datasets [ 7 , 8 ].…”