Support vector regression to estimate the permeability enhancement of potential transdermal enhancers

Alpa Shah; Yi Sun; Roderick Adams; Neil Davey; Simon Charles Wilkinson; Gary Patrick Joseph Moss

doi:10.1111/jphp.12508

Support vector regression to estimate the permeability enhancement of potential transdermal enhancers

Alpa Shah, Yi Sun, Roderick Adams, Neil Davey, Simon Charles Wilkinson, Gary Patrick Joseph Moss

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

122 Downloads (Pure)

Abstract

Objectives

Searching for chemicals that will safely enhance transdermal drug delivery is a significant challenge. This study applies support vector regression (SVR) for the first time to estimating the optimal formulation design of transdermal hydrocortisone formulations.

Methods

The aim of this study was to apply SVR methods with two different kernels in order to estimate the enhancement ratio of chemical enhancers of permeability.
Key findings

A statistically significant regression SVR model was developed. It was found that SVR with a nonlinear kernel provided the best estimate of the enhancement ratio for a chemical enhancer.

Conclusions

Support vector regression is a viable method to develop predictive models of biological processes, demonstrating improvements over other methods. In addition, the results of this study suggest that a global approach to modelling a biological process may not necessarily be the best method and that a ‘mixed-methods’ approach may be best in optimising predictive models.

Original language	English
Pages (from-to)	170-184
Number of pages	15
Journal	Journal of Pharmacy and Pharmacology
Volume	68
Issue number	2
Early online date	11 Jan 2016
DOIs	https://doi.org/10.1111/jphp.12508
Publication status	Published - 16 Feb 2016

Keywords

Gaussian processes
hydrocortisone
support vector machine
support vector regression
transdermal enhancer

Access to Document

10.1111/jphp.12508

Accepted ManuscriptAccepted author manuscript, 1.43 MB

Cite this

@article{700fde45aa004f5fa6a19cc8abfab4b3,

title = "Support vector regression to estimate the permeability enhancement of potential transdermal enhancers",

abstract = "ObjectivesSearching for chemicals that will safely enhance transdermal drug delivery is a significant challenge. This study applies support vector regression (SVR) for the first time to estimating the optimal formulation design of transdermal hydrocortisone formulations.MethodsThe aim of this study was to apply SVR methods with two different kernels in order to estimate the enhancement ratio of chemical enhancers of permeability.Key findingsA statistically significant regression SVR model was developed. It was found that SVR with a nonlinear kernel provided the best estimate of the enhancement ratio for a chemical enhancer.ConclusionsSupport vector regression is a viable method to develop predictive models of biological processes, demonstrating improvements over other methods. In addition, the results of this study suggest that a global approach to modelling a biological process may not necessarily be the best method and that a {\textquoteleft}mixed-methods{\textquoteright} approach may be best in optimising predictive models.",

keywords = "Gaussian processes, hydrocortisone, support vector machine, support vector regression, transdermal enhancer",

author = "Alpa Shah and Yi Sun and Roderick Adams and Neil Davey and Wilkinson, {Simon Charles} and Moss, {Gary Patrick Joseph}",

note = "This is the peer reviewed version of the following article: Shah, A., Sun, Y., Adams, R. G., Davey, N., Wilkinson, S. C. and Moss, G. P. (2016), Support vector regression to estimate the permeability enhancement of potential transdermal enhancers', Journal of Pharmacy and Pharmacology, Vol. 68 (2): 170–184, which has been published in final form at doi:10.1111/jphp.12508. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving. {\textcopyright} 2016 Royal Pharmaceutical Society.",

year = "2016",

month = feb,

day = "16",

doi = "10.1111/jphp.12508",

language = "English",

volume = "68",

pages = "170--184",

journal = "Journal of Pharmacy and Pharmacology",

issn = "0022-3573",

publisher = "Oxford University Press (OUP)",

number = "2",

}

TY - JOUR

T1 - Support vector regression to estimate the permeability enhancement of potential transdermal enhancers

AU - Shah, Alpa

AU - Sun, Yi

AU - Adams, Roderick

AU - Davey, Neil

AU - Wilkinson, Simon Charles

AU - Moss, Gary Patrick Joseph

N1 - This is the peer reviewed version of the following article: Shah, A., Sun, Y., Adams, R. G., Davey, N., Wilkinson, S. C. and Moss, G. P. (2016), Support vector regression to estimate the permeability enhancement of potential transdermal enhancers', Journal of Pharmacy and Pharmacology, Vol. 68 (2): 170–184, which has been published in final form at doi:10.1111/jphp.12508. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving. © 2016 Royal Pharmaceutical Society.

PY - 2016/2/16

Y1 - 2016/2/16

N2 - ObjectivesSearching for chemicals that will safely enhance transdermal drug delivery is a significant challenge. This study applies support vector regression (SVR) for the first time to estimating the optimal formulation design of transdermal hydrocortisone formulations.MethodsThe aim of this study was to apply SVR methods with two different kernels in order to estimate the enhancement ratio of chemical enhancers of permeability.Key findingsA statistically significant regression SVR model was developed. It was found that SVR with a nonlinear kernel provided the best estimate of the enhancement ratio for a chemical enhancer.ConclusionsSupport vector regression is a viable method to develop predictive models of biological processes, demonstrating improvements over other methods. In addition, the results of this study suggest that a global approach to modelling a biological process may not necessarily be the best method and that a ‘mixed-methods’ approach may be best in optimising predictive models.

AB - ObjectivesSearching for chemicals that will safely enhance transdermal drug delivery is a significant challenge. This study applies support vector regression (SVR) for the first time to estimating the optimal formulation design of transdermal hydrocortisone formulations.MethodsThe aim of this study was to apply SVR methods with two different kernels in order to estimate the enhancement ratio of chemical enhancers of permeability.Key findingsA statistically significant regression SVR model was developed. It was found that SVR with a nonlinear kernel provided the best estimate of the enhancement ratio for a chemical enhancer.ConclusionsSupport vector regression is a viable method to develop predictive models of biological processes, demonstrating improvements over other methods. In addition, the results of this study suggest that a global approach to modelling a biological process may not necessarily be the best method and that a ‘mixed-methods’ approach may be best in optimising predictive models.

KW - Gaussian processes

KW - hydrocortisone

KW - support vector machine

KW - support vector regression

KW - transdermal enhancer

U2 - 10.1111/jphp.12508

DO - 10.1111/jphp.12508

M3 - Article

SN - 0022-3573

VL - 68

SP - 170

EP - 184

JO - Journal of Pharmacy and Pharmacology

JF - Journal of Pharmacy and Pharmacology

IS - 2

ER -

Support vector regression to estimate the permeability enhancement of potential transdermal enhancers

Abstract

Keywords

Access to Document

Fingerprint

Cite this