Fuzzy modeling of skin permeability coefficients

Angela K. Pannier, Rhonda M. Brand, David D. Jones

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Purpose. The purpose of this work was to determine whether a new modeling methodology using fuzzy logic can predict skin permeability coefficients that are given compound descriptors that have been proven to affect percutaneous penetration. Methods. Three fuzzy inference models were developed using subtractive clustering to define natural structures within the data and assign subsequent rules. The numeric parameters describing the rules were refined through the use of an Adaptive Neural Fuzzy Inference System implemented in MatLab. Each model was evaluated using the entire data set. Then predicted outputs were compared to the published experimental data. Results. All databases produced fuzzy inference models that successfully predicted skin permeability coefficients, with correlation coefficients ranging from 0.83 to 0.97. The lowest correlation coefficient resulted from a model using log octanol/water partition coefficient and molecular weight as inputs with two input membership functions evaluated by two fuzzy rules. The correlation coefficient of 0.97 occurred when log octanol/water partition coefficient and hydrogen bond donor activity were used as inputs with three input membership functions evaluated by three fuzzy rules. Conclusions. Fuzzy rule-based models are a realistic and promising tool that can be used to successfully model and predict skin permeability coefficients as well as or better than previous algorithms with fewer inputs.

Original languageEnglish (US)
Pages (from-to)143-148
Number of pages6
JournalPharmaceutical Research
Volume20
Issue number2
DOIs
StatePublished - Feb 1 2003

Fingerprint

Hydraulic conductivity
Octanols
Permeability
Skin
Fuzzy inference
Fuzzy rules
Fuzzy Logic
Water
Membership functions
Cluster Analysis
Hydrogen
Molecular Weight
Databases
Fuzzy logic
Hydrogen bonds
Molecular weight

Keywords

  • Adaptive neural fuzzy inference system
  • Clustering
  • Fuzzy logic
  • Percutaneous absorption
  • Skin permeability

ASJC Scopus subject areas

  • Biotechnology
  • Molecular Medicine
  • Pharmacology
  • Pharmaceutical Science
  • Organic Chemistry
  • Pharmacology (medical)

Cite this

Fuzzy modeling of skin permeability coefficients. / Pannier, Angela K.; Brand, Rhonda M.; Jones, David D.

In: Pharmaceutical Research, Vol. 20, No. 2, 01.02.2003, p. 143-148.

Research output: Contribution to journalArticle

Pannier, Angela K. ; Brand, Rhonda M. ; Jones, David D. / Fuzzy modeling of skin permeability coefficients. In: Pharmaceutical Research. 2003 ; Vol. 20, No. 2. pp. 143-148.
@article{527afa17a5824b929d91567fe1bbc4a5,
title = "Fuzzy modeling of skin permeability coefficients",
abstract = "Purpose. The purpose of this work was to determine whether a new modeling methodology using fuzzy logic can predict skin permeability coefficients that are given compound descriptors that have been proven to affect percutaneous penetration. Methods. Three fuzzy inference models were developed using subtractive clustering to define natural structures within the data and assign subsequent rules. The numeric parameters describing the rules were refined through the use of an Adaptive Neural Fuzzy Inference System implemented in MatLab. Each model was evaluated using the entire data set. Then predicted outputs were compared to the published experimental data. Results. All databases produced fuzzy inference models that successfully predicted skin permeability coefficients, with correlation coefficients ranging from 0.83 to 0.97. The lowest correlation coefficient resulted from a model using log octanol/water partition coefficient and molecular weight as inputs with two input membership functions evaluated by two fuzzy rules. The correlation coefficient of 0.97 occurred when log octanol/water partition coefficient and hydrogen bond donor activity were used as inputs with three input membership functions evaluated by three fuzzy rules. Conclusions. Fuzzy rule-based models are a realistic and promising tool that can be used to successfully model and predict skin permeability coefficients as well as or better than previous algorithms with fewer inputs.",
keywords = "Adaptive neural fuzzy inference system, Clustering, Fuzzy logic, Percutaneous absorption, Skin permeability",
author = "Pannier, {Angela K.} and Brand, {Rhonda M.} and Jones, {David D.}",
year = "2003",
month = "2",
day = "1",
doi = "10.1023/A:1022273115847",
language = "English (US)",
volume = "20",
pages = "143--148",
journal = "Pharmaceutical Research",
issn = "0724-8741",
publisher = "Springer New York",
number = "2",

}

TY - JOUR

T1 - Fuzzy modeling of skin permeability coefficients

AU - Pannier, Angela K.

AU - Brand, Rhonda M.

AU - Jones, David D.

PY - 2003/2/1

Y1 - 2003/2/1

N2 - Purpose. The purpose of this work was to determine whether a new modeling methodology using fuzzy logic can predict skin permeability coefficients that are given compound descriptors that have been proven to affect percutaneous penetration. Methods. Three fuzzy inference models were developed using subtractive clustering to define natural structures within the data and assign subsequent rules. The numeric parameters describing the rules were refined through the use of an Adaptive Neural Fuzzy Inference System implemented in MatLab. Each model was evaluated using the entire data set. Then predicted outputs were compared to the published experimental data. Results. All databases produced fuzzy inference models that successfully predicted skin permeability coefficients, with correlation coefficients ranging from 0.83 to 0.97. The lowest correlation coefficient resulted from a model using log octanol/water partition coefficient and molecular weight as inputs with two input membership functions evaluated by two fuzzy rules. The correlation coefficient of 0.97 occurred when log octanol/water partition coefficient and hydrogen bond donor activity were used as inputs with three input membership functions evaluated by three fuzzy rules. Conclusions. Fuzzy rule-based models are a realistic and promising tool that can be used to successfully model and predict skin permeability coefficients as well as or better than previous algorithms with fewer inputs.

AB - Purpose. The purpose of this work was to determine whether a new modeling methodology using fuzzy logic can predict skin permeability coefficients that are given compound descriptors that have been proven to affect percutaneous penetration. Methods. Three fuzzy inference models were developed using subtractive clustering to define natural structures within the data and assign subsequent rules. The numeric parameters describing the rules were refined through the use of an Adaptive Neural Fuzzy Inference System implemented in MatLab. Each model was evaluated using the entire data set. Then predicted outputs were compared to the published experimental data. Results. All databases produced fuzzy inference models that successfully predicted skin permeability coefficients, with correlation coefficients ranging from 0.83 to 0.97. The lowest correlation coefficient resulted from a model using log octanol/water partition coefficient and molecular weight as inputs with two input membership functions evaluated by two fuzzy rules. The correlation coefficient of 0.97 occurred when log octanol/water partition coefficient and hydrogen bond donor activity were used as inputs with three input membership functions evaluated by three fuzzy rules. Conclusions. Fuzzy rule-based models are a realistic and promising tool that can be used to successfully model and predict skin permeability coefficients as well as or better than previous algorithms with fewer inputs.

KW - Adaptive neural fuzzy inference system

KW - Clustering

KW - Fuzzy logic

KW - Percutaneous absorption

KW - Skin permeability

UR - http://www.scopus.com/inward/record.url?scp=0037331609&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037331609&partnerID=8YFLogxK

U2 - 10.1023/A:1022273115847

DO - 10.1023/A:1022273115847

M3 - Article

C2 - 12636150

AN - SCOPUS:0037331609

VL - 20

SP - 143

EP - 148

JO - Pharmaceutical Research

JF - Pharmaceutical Research

SN - 0724-8741

IS - 2

ER -