Modeling and Prediction of Solvent Effect on Human Skin Permeability using Support Vector Regression and Random Forest

Machine learning for skin permeability prediction: random forest and XG boost regression

Background: Machine learning algorithms that can quickly and easily estimate skin permeability (Kp) are increasingly being used in drug delivery research. The linear free energy relationship (LFER) developed by Abraham is a practical technique for predicting Kp. The permeability coefficients and Abraham solute descriptor values for 175 organic compounds have been documented in the scientific literature.Purpose: The purpose of this project was to use a publicly available dataset to make skin permeability predictions using the random forest and XBoost regression techniques.Methods: We employed Pandas-based methods in JupyterLab to predict permeability coefficient (Kp) from solute descriptors (excess molar refraction [E], combined dipolarity/polarizability [S], overall solute hydrogen bond acidity and basicity [A and B], and the McGowan's characteristic molecular volume [V]).Results: The random forest and XG Boost regression models established statistically significant association between the descriptors and the skin permeability coefficient.

Development of a 2D-QSAR Model for Tissue-to-Plasma Partition Coefficient Value with High Accuracy Using Machine Learning Method, Minimum Required Experimental Values, and Physicochemical Descriptors

BACKGROUND

The demand for physiologically based pharmacokinetic (PBPK) model is increasing currently. New drug application (NDA) of many compounds is submitted with PBPK models for efficient drug development. Tissue-to-plasma partition coefficient (K_p) is a key parameter for the PBPK model to describe differential equations. However, it is difficult to obtain the K_p value experimentally because the measurement of drug concentration in the tissue is much harder than that in plasma.

OBJECTIVE

Instead of experiments, many researchers have sought in silico methods. Today, most of the models for K_p prediction are using in vitro and in vivo parameters as explanatory variables. We thought of physicochemical descriptors that could improve the predictability. Therefore, we aimed to develop the two-dimensional quantitative structure-activity relationship (2D-QSAR) model for K_p using physicochemical descriptors instead of in vivo experimental data as explanatory variables.

METHODS

We compared our model with the conventional models using 20-fold cross-validation according to the published method (Yun et al. J Pharmacokinet Pharmacodyn 41:1-14, 2014). We used random forest algorithm, which is known to be one of the best predictors for the 2D-QSAR model. Finally, we combined minimum in vitro experimental values and physiochemical descriptors. Thus, the prediction method for K_p value using a few in vitro parameters and physicochemical descriptors was developed; this is a multimodal model.

RESULTS

Its accuracy was found to be superior to that of the conventional models. Results of this research suggest that multimodality is useful for the 2D-QSAR model [RMSE and % of two-fold error: 0.66 and 42.2% (Berezohkovsky), 0.52 and 52.2% (Rodgers), 0.65 and 34.6% (Schmitt), 0.44 and 61.1% (published model), 0.41 and 62.1% (traditional model), 0.39 and 64.5% (multimodal model)].

CONCLUSION

We could develop a 2D-QSAR model for K_p value with the highest accuracy using a few in vitro experimental data and physicochemical descriptors.

A Mathematical Approach Using Strat-M® to Predict the Percutaneous Absorption of Chemicals under Finite Dose Conditions

Estimation of the percutaneous absorption is essential for the safety assessment of cosmetic and dermopharmaceutical products. Currently, an artificial membrane, Strat-M^®, has been focused on as the tool which could obtain the permeation parameters close to the skin-derived values. Nevertheless, few practical methodologies using the permeation parameters for assessing percutaneous absorption under in-use conditions are available. In the present study, based on Fick's first law of diffusion, a novel mathematical model incorporating the permeation parameters as well as considering the water evaporation (T_eva) was constructed. Then, to evaluate the applicability domain of our model in the case where Strat-M^®-derived parameters were used, the permeation parameters were compared between the skin from edible porcine and Strat-M^®. Regarding chemicals (-0.2 ≤ Log K_ow ≤ 2.0), their permeation profiles were equivalent between Strat-M^® and porcine skin. Therefore, for these chemicals, the percutaneous absorption was calculated using our model with the permeation parameters obtained using Strat-M^® and the T_eva determined by measuring the solution weight. The calculated values revealed a good correlation to the values obtained using porcine skin in finite dose experiments, suggesting that our mathematical approach with Strat-M^® would be useful for the future safety assessment of cosmetic and dermopharmaceutical products.

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

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.

Application of machine learning to a material library for modeling of relationships between material properties and tablet properties

This study investigates the usefulness of machine learning for modeling complex relationships in a material library. We tested 81 types of active pharmaceutical ingredients (APIs) and their tablets to construct the library, which included the following variables: 20 types of API material properties, one type of process parameter (three levels of compression pressure), and two types of tablet properties (tensile strength (TS) and disintegration time (DT)). The machine learning algorithms boosted tree (BT) and random forest (RF) were applied to analysis of our material library to model the relationships between input variables (material properties and compression pressure) and output variables (TS and DT). The calculated BT and RF models achieved higher performance statistics compared with a conventional modeling method (i.e., partial least squares regression), and revealed the material properties that strongly influence TS and DT. For TS, true density, the tenth percentile of the cumulative percentage size distribution, loss on drying, and compression pressure were of high relative importance. For DT, total surface energy, water absorption rate, polar surface energy, and hygroscopicity had significant effects. Thus, we demonstrate that BT and RF can be used to model complex relationships and clarify important material properties in a material library.

High-Payload Nanosuspension of Centella asiatica Extract for Improved Skin Delivery with No Irritation

Background

The titrated extract of Centella asiatica (CA) has received much attention as a cosmeceutical ingredient owing to its anti-wrinkle effect. However, due to the low solubility and high molecular weight of pharmacologically active constituents, including asiatic acid (AA), madecassic acid (MA), and asiaticoside (AS), it is challenging to fabricate high-payload topical preparations of CA with satisfactory skin absorption profiles.

Purpose

This study aimed to design a high-payload topical preparation of CA using nanocrystallization technique and to evaluate its skin absorption profile and local tolerability.

Methods

High-payload nanocrystal suspensions (NSs) were prepared using lab-scale bead-milling technology, by adjusting the type and amount of suspending agent, CA content, type of vehicle, and milling speed. CA-loaded NSs were characterized in terms of morphology, particle size, crystallinity, and in vitro dissolution pattern. Skin absorption of CA nanocrystals was evaluated using a vertical Franz diffusion cell mounted with porcine skin. In vivo skin irritation following topical application of high-payload NS was assessed in normal rats.

Results

The optimized NS system, composed of 10% (w/v) CA, 0.5% polyvinylpyrrolidone (PVP) K30 as steric stabilizer, and 89.5% of distilled water, was characterized as follows: spherical or elliptical in shape, 200 nm in size, with low crystallinity. The in vitro dissolution of AA or MA from NSs was markedly faster compared to raw material, under sink condition. Penetration of AA, MA, and AS in the porcine skin was markedly elevated using the high-payload NS formula, providing 5-, 4-, and 4.5-fold higher accumulation in skin layer, compared to that of the marketed cream formula (CA 1%, Madeca cream). Moreover, topical application of high-payload NS was tolerable, showing neither erythema nor oedema in normal rats.

Conclusion

The novel NS system is expected to be a virtuous approach for offering a better skin absorption of CA, without using an excess quantity of solubilizers.

Use of QSAR Global Models and Molecular Docking for Developing New Inhibitors of c-src Tyrosine Kinase

A prototype of a family of at least nine members, cellular Src tyrosine kinase is a therapeutically interesting target because its inhibition might be of interest not only in a number of malignancies, but also in a diverse array of conditions, from neurodegenerative pathologies to certain viral infections. Computational methods in drug discovery are considerably cheaper than conventional methods and offer opportunities of screening very large numbers of compounds in conditions that would be simply impossible within the wet lab experimental settings. We explored the use of global quantitative structure-activity relationship (QSAR) models and molecular ligand docking in the discovery of new c-src tyrosine kinase inhibitors. Using a dataset of 1038 compounds from ChEMBL database, we developed over 350 QSAR classification models. A total of 49 models with reasonably good performance were selected and the models were assembled by stacking with a simple majority vote and used for the virtual screening of over 100,000 compounds. A total of 744 compounds were predicted by at least 50% of the QSAR models as active, 147 compounds were within the applicability domain and predicted by at least 75% of the models to be active. The latter 147 compounds were submitted to molecular ligand docking using AutoDock Vina and LeDock, and 89 were predicted to be active based on the energy of binding.

Exploiting machine learning for end-to-end drug discovery and development

A variety of machine learning methods such as naive Bayesian, support vector machines and more recently deep neural networks are demonstrating their utility for drug discovery and development. These leverage the generally bigger datasets created from high-throughput screening data and allow prediction of bioactivities for targets and molecular properties with increased levels of accuracy. We have only just begun to exploit the potential of these techniques but they may already be fundamentally changing the research process for identifying new molecules and/or repurposing old drugs. The integrated application of such machine learning models for end-to-end (E2E) application is broadly relevant and has considerable implications for developing future therapies and their targeting.

Predicting Skin Permeability by Means of Computational Approaches: Reliability and Caveats in Pharmaceutical Studies

The skin is the main barrier between the internal body environment and the external one. The characteristics of this barrier and its properties are able to modify and affect drug delivery and chemical toxicity parameters. Therefore, it is not surprising that permeability of many different compounds has been measured through several in vitro and in vivo techniques. Moreover, many different in silico approaches have been used to identify the correlation between the structure of the permeants and their permeability, to reproduce the skin behavior, and to predict the ability of specific chemicals to permeate this barrier. A significant number of issues, like interlaboratory variability, experimental conditions, data set building rationales, and skin site of origin and hydration, still prevent us from obtaining a definitive predictive skin permeability model. This review wants to show the main advances and the principal approaches in computational methods used to predict this property, to enlighten the main issues that have arisen, and to address the challenges to develop in future research.

Prediction of Skin Permeation of Flurbiprofen from Neat Ester Oils and Their O/W Emulsions

Although many in silico models were reported to predict the skin permeation of drugs from aqueous solutions, few studies were founded on the in silico estimation models for the skin permeation of drugs from neat oil formulations and o/w emulsions. In the present study, the cumulative amount of a model lipophilic drug, flurbiprofen (FP), that permeated through skin was determined from 12 different kinds of ester oils (Q_oil) and an in silico model was developed for predicting the skin permeation of FP from these ester oils. Thus, the obtained Q_oil values were well predicted with the FP solubility in the oils (S_oil), the amount of FP uptake into the stratum corneum (SC_oil) and molecular descriptors of dipolarity/polarizability (π₂^H) and molecular density. This model suggests that the thermodynamic activities of FP both in the formulations and skin are the key factors for predicting the skin permeation of FP from the ester oils. In addition, a high linear relationship was observed in the double-logarithm plots between the Q_oil and the cumulative amount of FP permeated through skin from 20% ester oil in water emulsion (Q_emul20%). Furthermore, the skin permeations of FP from 5 and 10% ester oil in water emulsions, Q_emul5% and Q_emul10%, respectively, were also predicted by the horizontal translation of the y-axis intercept of the liner equation for the relation between the Q_oil and Q_emul20%. These prediction methods must be helpful for designing topical oily and/or o/w emulsion formulations having suitable and high skin permeation rate of lipophilic drugs.

Investigation of dermal toxicity of ionic liquids in monolayer-cultured skin cells and 3D reconstructed human skin models

Ionic liquids have gained increasing attention in the chemical industry as potential green substitutes for traditional solvents. However, little is known about toxicity of ionic liquids on the skin, a major exposure portal to toxic substances. Here, we evaluated dermal toxicity of ionic liquids using human keratinocyte and fibroblast cell line, 3D reconstructed human epidermis, and full-thickness model to investigate underlying mechanisms. Cytotoxicity of ionic liquids was evaluated for representative anions, [TFSI], [PF₆], [BF₄], and [DCA], as well as for cations, [EMIM], [BMPY], [TBA] and [Zn], in human keratinocyte cell line, HaCaT, and human dermal fibroblasts. In our results, significant cytotoxicity was induced by ionic liquids with [TFSI] in both cell lines. Notably, cytotoxicity of [TFSI] containing ionic liquids was comparable to xylene, a toxic conventional organic solvent. Fluorescent and flow cytometric analysis revealed that [TFSI]-exposed cells underwent necrotic cell death. Reactive oxygen species (ROS) was increased while the amount of glutathione was decreased by [TFSI] in dose-dependent manner, which was reversed by antioxidant, N-acetylcysteine. In 3D reconstructed human epidermis and full-thickness model, a single application of [TFSI] induced toxicity although it was minimal and largely limited to epidermal layer. Collectively, these results demonstrated potential dermal toxicity of ionic liquids.

The Next Era: Deep Learning in Pharmaceutical Research

Over the past decade we have witnessed the increasing sophistication of machine learning algorithms applied in daily use from internet searches, voice recognition, social network software to machine vision software in cameras, phones, robots and self-driving cars. Pharmaceutical research has also seen its fair share of machine learning developments. For example, applying such methods to mine the growing datasets that are created in drug discovery not only enables us to learn from the past but to predict a molecule's properties and behavior in future. The latest machine learning algorithm garnering significant attention is deep learning, which is an artificial neural network with multiple hidden layers. Publications over the last 3 years suggest that this algorithm may have advantages over previous machine learning methods and offer a slight but discernable edge in predictive performance. The time has come for a balanced review of this technique but also to apply machine learning methods such as deep learning across a wider array of endpoints relevant to pharmaceutical research for which the datasets are growing such as physicochemical property prediction, formulation prediction, absorption, distribution, metabolism, excretion and toxicity (ADME/Tox), target prediction and skin permeation, etc. We also show that there are many potential applications of deep learning beyond cheminformatics. It will be important to perform prospective testing (which has been carried out rarely to date) in order to convince skeptics that there will be benefits from investing in this technique.