Prediction of Human Skin Permeability Using a Combination of Molecular Orbital Calculations and Artificial Neural Network.

Lim, Chee Wooi; Fujiwara, Sayaka; Yamashita, Fumiyoshi; Hashida, Mitsuru

doi:10.1248/bpb.25.361

Cited by 55 publications

(27 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However in a later study [36] this clear trend with molecular width was only obtained for one of the NF membranes used and not for the other 3 membranes. Molecular [58], b [34], c [183], d [184], e [113], f [78], g [185], h [186], i [41], j [95], k [59], l [187], m [188], n [189], o [190], p [52], q [191], r [169], s [192].…”

Section: Micropollutant Characteristics: the Group Of Estrogensmentioning

confidence: 99%

Micropollutant sorption to membrane polymers: A review of mechanisms for estrogens

Schäfer

Akanyeti

Semiao

2011

Advances in Colloid and Interface Science

249

140

View full text Add to dashboard Cite

Organic micropollutants such as estrogens occur in water in increasing quantities from predominantly anthropogenic sources. In water such micropollutants partition not only to surfaces such as membrane polymers but also to any other natural or treatment related surfaces. Such interactions are often observed as sorption in treatment processes and this phenomenon is exploited in activated carbon filtration, for example. Sorption is important for polymeric materials and this is used for the concentration of such micropollutants for analytical purposes in solid phase extraction. In membrane filtration the mechanism of micropollutant sorption is a relatively new discovery that was facilitated through new analytical techniques. This sorption plays an important role in micropollutant retention by membranes although mechanisms of interaction are to date not understood. This review is focused on sorption of estrogens on polymeric surfaces, specifically membrane polymers. Such sorption has been observed to a large extent with values of up to 1.2 ng/cm(2) measured. Sorption is dependent on the type of polymer, micropollutant characteristics, solution chemistry, membrane operating conditions as well as membrane morphology. Likely contributors to sorption are the surface roughness as well as the microporosity of such polymers. While retention-and/or reflection coefficient as well as solute to effective pore size ratio-controls the access of such micropollutants to the inner surface, pore size, porosity and thickness as well as morphology or shape of inner voids determines the available area for sorption. The interaction mechanisms are governed, most likely, by hydrophobic as well as solvation effects and interplay of molecular and supramolecular interactions such as hydrogen bonding, π-cation/anion interactions, π-π stacking, ion-dipole and dipole-dipole interactions, the extent of which is naturally dependent on micropollutant and polymer characteristics. Systematic investigations are required to identify and quantify both relative contributions and strength of such interactions and develop suitable surface characterisation tools. This is a difficult endeavour given the complexity of systems, the possibility of several interactions taking place simultaneously and the generally weaker forces involved.

show abstract

Section: Micropollutant Characteristics: the Group Of Estrogensmentioning

confidence: 99%

Micropollutant sorption to membrane polymers: A review of mechanisms for estrogens

Schäfer

Akanyeti

Semiao

2011

Advances in Colloid and Interface Science

249

140

View full text Add to dashboard Cite

show abstract

“…We adopted log P c and MW c , which are simple, widely used molecular descriptors that were employed by Potts and Guy (1992) to predict skin permeability of a large number of structurally diverse compounds. These descriptors are straightforward and have clear physical significance in comparison with the complex descriptors used in other studies; for example, Lim et al (2002) used molecular orbital calculation, Ghafourian et al (2010) used rather complicated physicochemical properties, Pugh et al (2000) used H-bonding and electronic charge, Naegel et al (2008) used a geometric mathematical modeling, and Rim et al (2009) used molecular dynamics simulations of diffusion.…”

Section: Discussionmentioning

confidence: 99%

“…Saini et al (2010) developed a method for predicting the skin permeability of chemicals by artificial neural network (ANN) analysis of log K p and Abraham descriptors. Lim et al (2002) predicted the skin permeability of chemicals from their three-dimensional molecular structure using a combination of molecular orbital calculation and ANN analysis. Chen et al (2007) also developed a method for predicting skin permeability of chemicals by using a combination of Abraham descriptors and ANN analysis.…”

Section: Introductionmentioning

confidence: 99%

Artificial neural network analysis for predicting human percutaneous absorption taking account of vehicle properties

et al. 2015

Self Cite

View full text Add to dashboard Cite

-An in silico method for predicting percutaneous absorption of cosmetic ingredients was developed by using artificial neural network (ANN) analysis to predict the human skin permeability coefficient (log K p ), taking account of the physicochemical properties of the vehicle, and the apparent diffusion coefficient (log D). Molecular weight and octanol-water partition coefficient (log P) of chemicals, and log P of the vehicles, were used as molecular descriptors for predicting log K p and log D of 359 samples, for which literature values of either or both of log K p and log D were available. Adaptivity of the ANN model was evaluated in comparison with a multiple linear regression model (MLR) by calculating the root-mean-square (RMS) errors. Accuracy and robustness were confirmed by 10-fold cross-validation. The predictive RMS errors of the ANN model were smaller than those of the MLR model (log K p ; 0.675 vs 0.887, log D; 0.553 vs 0.658), indicating superior performance. The predictive RMS errors for log K p and log D with the ANN model after 10-fold cross-validation analysis were 0.723 and 0.606, respectively. Moreover, we estimated the cumulative amounts of chemicals permeated into the skin during 24 hr (Q24hr) from the values of log K p and log D by applying Fick's law of diffusion. Our results suggest that this newly established ANN analysis method, taking account of the property of the vehicle, could contribute to non-animal risk assessment of cosmetic ingredients by providing a tool for calculating Q24hr, which is required for evaluating the margin of safety.

show abstract

“…Further, a cross-validation technique such as a ''leaveone-out (LOO) method'' may be applied to ensure the optimality of an ANN structure [22][23][24]. One data pair is systematically removed from the training data set, and the ANN is then trained by using the reduced data set.…”

Section: Artificial Neural Network Modelingmentioning

confidence: 99%

Artificial Neural Network in Drug Delivery and Pharmaceutical Research

Sutariya¹,

Groshev²,

Sadana³

et al. 2013

TOBIOIJ

View full text Add to dashboard Cite

Artificial neural networks (ANNs) technology models the pattern recognition capabilities of the neural networks of the brain. Similarly to a single neuron in the brain, artificial neuron unit receives inputs from many external sources, processes them, and makes decisions. Interestingly, ANN simulates the biological nervous system and draws on analogues of adaptive biological neurons. ANNs do not require rigidly structured experimental designs and can map functions using historical or incomplete data, which makes them a powerful tool for simulation of various non-linear systems.ANNs have many applications in various fields, including engineering, psychology, medicinal chemistry and pharmaceutical research. Because of their capacity for making predictions, pattern recognition, and modeling, ANNs have been very useful in many aspects of pharmaceutical research including modeling of the brain neural network, analytical data analysis, drug modeling, protein structure and function, dosage optimization and manufacturing, pharmacokinetics and pharmacodynamics modeling, and in vitro in vivo correlations. This review discusses the applications of ANNs in drug delivery and pharmacological research.

show abstract

Prediction of Human Skin Permeability Using a Combination of Molecular Orbital Calculations and Artificial Neural Network.

Cited by 55 publications

References 23 publications

Micropollutant sorption to membrane polymers: A review of mechanisms for estrogens

Micropollutant sorption to membrane polymers: A review of mechanisms for estrogens

Artificial neural network analysis for predicting human percutaneous absorption taking account of vehicle properties

Artificial Neural Network in Drug Delivery and Pharmaceutical Research

Contact Info

Product

Resources

About