Prediction of skin penetration using machine learning methods

Yi Sun; Gary Moss; M. Prapopoulou; Roderick Adams; Marc Brown; N. Davey

doi:10.1109/ICDM.2008.97

Prediction of skin penetration using machine learning methods

Yi Sun, Gary Moss, M. Prapopoulou, Roderick Adams, Marc Brown, N. Davey

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

173 Downloads (Pure)

Abstract

Improving predictions of the skin permeability coefficient is a difficult problem. It is also an important issue with the increasing use of skin patches as a means of drug delivery. In this work, we applyK-nearest-neighbour regression, single
layer networks, mixture of experts and Gaussian processes to predict the permeability coefficient. We obtain a considerable improvement over the quantitative structureactivity relationship (QSARs) predictors. We show that using
five features, which are molecular weight, solubility parameter, lipophilicity, the number of hydrogen bonding acceptor and donor groups, can produce better predictions than the one using only lipophilicity and the molecular weight. The Gaussian process regression with five compound features gives the best performance in this work.

Original language	English
Title of host publication	Procs of the 8th IEEE International Conference on Data Mining
Subtitle of host publication	(ICDM'08)
Editors	D Gunopulos, F Turini, C Zaniolo, N Ramakrishnan, XD Wu
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1049-1054
Number of pages	6
ISBN (Print)	978-0-7695-3502-9
DOIs	https://doi.org/10.1109/ICDM.2008.97
Publication status	Published - 2008
Event	8th IEEE International Conference on Data Mining - Pisa Duration: 15 Dec 2008 → 19 Dec 2008

Conference

Conference	8th IEEE International Conference on Data Mining
City	Pisa
Period	15/12/08 → 19/12/08

Keywords

STRUCTURE-PERMEABILITY RELATIONSHIPS
PERCUTANEOUS-ABSORPTION

Access to Document

10.1109/ICDM.2008.97

903274Submitted manuscript, 256 KB

Cite this

Sun, Y., Moss, G., Prapopoulou, M., Adams, R., Brown, M., & Davey, N. (2008). Prediction of skin penetration using machine learning methods. In D. Gunopulos, F. Turini, C. Zaniolo, N. Ramakrishnan, & XD. Wu (Eds.), Procs of the 8th IEEE International Conference on Data Mining: (ICDM'08) (pp. 1049-1054). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICDM.2008.97

@inproceedings{c9a91f535600425e9727df8c9cfb8cd7,

title = "Prediction of skin penetration using machine learning methods",

abstract = "Improving predictions of the skin permeability coefficient is a difficult problem. It is also an important issue with the increasing use of skin patches as a means of drug delivery. In this work, we applyK-nearest-neighbour regression, single layer networks, mixture of experts and Gaussian processes to predict the permeability coefficient. We obtain a considerable improvement over the quantitative structureactivity relationship (QSARs) predictors. We show that using five features, which are molecular weight, solubility parameter, lipophilicity, the number of hydrogen bonding acceptor and donor groups, can produce better predictions than the one using only lipophilicity and the molecular weight. The Gaussian process regression with five compound features gives the best performance in this work.",

keywords = "STRUCTURE-PERMEABILITY RELATIONSHIPS, PERCUTANEOUS-ABSORPTION",

author = "Yi Sun and Gary Moss and M. Prapopoulou and Roderick Adams and Marc Brown and N. Davey",

year = "2008",

doi = "10.1109/ICDM.2008.97",

language = "English",

isbn = "978-0-7695-3502-9",

pages = "1049--1054",

editor = "D Gunopulos and F Turini and C Zaniolo and N Ramakrishnan and XD Wu",

booktitle = "Procs of the 8th IEEE International Conference on Data Mining",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "8th IEEE International Conference on Data Mining ; Conference date: 15-12-2008 Through 19-12-2008",

}

Sun, Y, Moss, G, Prapopoulou, M, Adams, R, Brown, M & Davey, N 2008, Prediction of skin penetration using machine learning methods. in D Gunopulos, F Turini, C Zaniolo, N Ramakrishnan & XD Wu (eds), Procs of the 8th IEEE International Conference on Data Mining: (ICDM'08). Institute of Electrical and Electronics Engineers (IEEE), pp. 1049-1054, 8th IEEE International Conference on Data Mining, Pisa, 15/12/08. https://doi.org/10.1109/ICDM.2008.97

Prediction of skin penetration using machine learning methods. / Sun, Yi; Moss, Gary; Prapopoulou, M. et al.
Procs of the 8th IEEE International Conference on Data Mining: (ICDM'08). ed. / D Gunopulos; F Turini; C Zaniolo; N Ramakrishnan; XD Wu. Institute of Electrical and Electronics Engineers (IEEE), 2008. p. 1049-1054.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Prediction of skin penetration using machine learning methods

AU - Sun, Yi

AU - Moss, Gary

AU - Prapopoulou, M.

AU - Adams, Roderick

AU - Brown, Marc

AU - Davey, N.

PY - 2008

Y1 - 2008

N2 - Improving predictions of the skin permeability coefficient is a difficult problem. It is also an important issue with the increasing use of skin patches as a means of drug delivery. In this work, we applyK-nearest-neighbour regression, single layer networks, mixture of experts and Gaussian processes to predict the permeability coefficient. We obtain a considerable improvement over the quantitative structureactivity relationship (QSARs) predictors. We show that using five features, which are molecular weight, solubility parameter, lipophilicity, the number of hydrogen bonding acceptor and donor groups, can produce better predictions than the one using only lipophilicity and the molecular weight. The Gaussian process regression with five compound features gives the best performance in this work.

AB - Improving predictions of the skin permeability coefficient is a difficult problem. It is also an important issue with the increasing use of skin patches as a means of drug delivery. In this work, we applyK-nearest-neighbour regression, single layer networks, mixture of experts and Gaussian processes to predict the permeability coefficient. We obtain a considerable improvement over the quantitative structureactivity relationship (QSARs) predictors. We show that using five features, which are molecular weight, solubility parameter, lipophilicity, the number of hydrogen bonding acceptor and donor groups, can produce better predictions than the one using only lipophilicity and the molecular weight. The Gaussian process regression with five compound features gives the best performance in this work.

KW - STRUCTURE-PERMEABILITY RELATIONSHIPS

KW - PERCUTANEOUS-ABSORPTION

UR - http://www.scopus.com/inward/record.url?scp=67049097965&partnerID=8YFLogxK

U2 - 10.1109/ICDM.2008.97

DO - 10.1109/ICDM.2008.97

M3 - Conference contribution

AN - SCOPUS:67049097965

SN - 978-0-7695-3502-9

SP - 1049

EP - 1054

BT - Procs of the 8th IEEE International Conference on Data Mining

A2 - Gunopulos, D

A2 - Turini, F

A2 - Zaniolo, C

A2 - Ramakrishnan, N

A2 - Wu, XD

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 8th IEEE International Conference on Data Mining

Y2 - 15 December 2008 through 19 December 2008

ER -

Prediction of skin penetration using machine learning methods

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this