QSAR and classification of murine and human soluble epoxide hydrolase inhibition by urea-like compounds

Nathan R. McElroy, Peter C. Jurs, Christophe Morisseau, Bruce D. Hammock

Research output: Contribution to journalArticle

61 Citations (Scopus)

Abstract

A data set of 348 urea-like compounds that inhibit the soluble epoxide hydrolase enzyme in mice and humans is examined. Compounds having IC50 values ranging from 0.06 to >500 μM (murine) and 0.10 to >500 μM (human) are categorized as active or inactive for classification, while quantitation is performed on smaller compound subsets ranging from 0.07 to 431 μM (murine) and 0.11 to 490 μM (human). Each compound is represented by calculated structural descriptors that encode topological, geometrical, electronic, and polar surface features. Multiple linear regression (MLR) and computational neural networks (CNNs) are employed for quantitative models. Three classification algorithms, k-nearest neighbor (kNN), linear discriminant analysis (LDA), and radial basis function neural networks (RBFNN), are used to categorize compounds as active or inactive based on selected data split points. Quantitative modeling of human enzyme inhibition results in a nonlinear, five-descriptor model with root- mean-square errors (log units of IC50 [μM]) of 0.616 (r2 = 0.66), 0.674 (r2 = 0.61), and 0.914 (r2 = 0.33) for training, cross-validation, and prediction sets, respectively. The best classification results for human and murine enzyme inhibition are found using kNN. Human classification rates using a seven-descriptor model for training and prediction sets are 89.1% and 91.4%, respectively. Murine classification rates using a five-descriptor model for training and prediction sets are 91.5% and 88.6%, respectively.

Original languageEnglish (US)
Pages (from-to)1066-1080
Number of pages15
JournalJournal of Medicinal Chemistry
Volume46
Issue number6
DOIs
StatePublished - Mar 13 2003

Fingerprint

Epoxide Hydrolases
Quantitative Structure-Activity Relationship
Urea
Enzyme inhibition
Inhibitory Concentration 50
Neural networks
Enzymes
Discriminant analysis
Linear regression
Mean square error
Discriminant Analysis
Linear Models

ASJC Scopus subject areas

  • Organic Chemistry

Cite this

QSAR and classification of murine and human soluble epoxide hydrolase inhibition by urea-like compounds. / McElroy, Nathan R.; Jurs, Peter C.; Morisseau, Christophe; Hammock, Bruce D.

In: Journal of Medicinal Chemistry, Vol. 46, No. 6, 13.03.2003, p. 1066-1080.

Research output: Contribution to journalArticle

McElroy, Nathan R. ; Jurs, Peter C. ; Morisseau, Christophe ; Hammock, Bruce D. / QSAR and classification of murine and human soluble epoxide hydrolase inhibition by urea-like compounds. In: Journal of Medicinal Chemistry. 2003 ; Vol. 46, No. 6. pp. 1066-1080.
@article{323d3d177e2646f4aefa6a17c679e575,
title = "QSAR and classification of murine and human soluble epoxide hydrolase inhibition by urea-like compounds",
abstract = "A data set of 348 urea-like compounds that inhibit the soluble epoxide hydrolase enzyme in mice and humans is examined. Compounds having IC50 values ranging from 0.06 to >500 μM (murine) and 0.10 to >500 μM (human) are categorized as active or inactive for classification, while quantitation is performed on smaller compound subsets ranging from 0.07 to 431 μM (murine) and 0.11 to 490 μM (human). Each compound is represented by calculated structural descriptors that encode topological, geometrical, electronic, and polar surface features. Multiple linear regression (MLR) and computational neural networks (CNNs) are employed for quantitative models. Three classification algorithms, k-nearest neighbor (kNN), linear discriminant analysis (LDA), and radial basis function neural networks (RBFNN), are used to categorize compounds as active or inactive based on selected data split points. Quantitative modeling of human enzyme inhibition results in a nonlinear, five-descriptor model with root- mean-square errors (log units of IC50 [μM]) of 0.616 (r2 = 0.66), 0.674 (r2 = 0.61), and 0.914 (r2 = 0.33) for training, cross-validation, and prediction sets, respectively. The best classification results for human and murine enzyme inhibition are found using kNN. Human classification rates using a seven-descriptor model for training and prediction sets are 89.1{\%} and 91.4{\%}, respectively. Murine classification rates using a five-descriptor model for training and prediction sets are 91.5{\%} and 88.6{\%}, respectively.",
author = "McElroy, {Nathan R.} and Jurs, {Peter C.} and Christophe Morisseau and Hammock, {Bruce D.}",
year = "2003",
month = "3",
day = "13",
doi = "10.1021/jm020269o",
language = "English (US)",
volume = "46",
pages = "1066--1080",
journal = "Journal of Medicinal Chemistry",
issn = "0022-2623",
publisher = "American Chemical Society",
number = "6",

}

TY - JOUR

T1 - QSAR and classification of murine and human soluble epoxide hydrolase inhibition by urea-like compounds

AU - McElroy, Nathan R.

AU - Jurs, Peter C.

AU - Morisseau, Christophe

AU - Hammock, Bruce D.

PY - 2003/3/13

Y1 - 2003/3/13

N2 - A data set of 348 urea-like compounds that inhibit the soluble epoxide hydrolase enzyme in mice and humans is examined. Compounds having IC50 values ranging from 0.06 to >500 μM (murine) and 0.10 to >500 μM (human) are categorized as active or inactive for classification, while quantitation is performed on smaller compound subsets ranging from 0.07 to 431 μM (murine) and 0.11 to 490 μM (human). Each compound is represented by calculated structural descriptors that encode topological, geometrical, electronic, and polar surface features. Multiple linear regression (MLR) and computational neural networks (CNNs) are employed for quantitative models. Three classification algorithms, k-nearest neighbor (kNN), linear discriminant analysis (LDA), and radial basis function neural networks (RBFNN), are used to categorize compounds as active or inactive based on selected data split points. Quantitative modeling of human enzyme inhibition results in a nonlinear, five-descriptor model with root- mean-square errors (log units of IC50 [μM]) of 0.616 (r2 = 0.66), 0.674 (r2 = 0.61), and 0.914 (r2 = 0.33) for training, cross-validation, and prediction sets, respectively. The best classification results for human and murine enzyme inhibition are found using kNN. Human classification rates using a seven-descriptor model for training and prediction sets are 89.1% and 91.4%, respectively. Murine classification rates using a five-descriptor model for training and prediction sets are 91.5% and 88.6%, respectively.

AB - A data set of 348 urea-like compounds that inhibit the soluble epoxide hydrolase enzyme in mice and humans is examined. Compounds having IC50 values ranging from 0.06 to >500 μM (murine) and 0.10 to >500 μM (human) are categorized as active or inactive for classification, while quantitation is performed on smaller compound subsets ranging from 0.07 to 431 μM (murine) and 0.11 to 490 μM (human). Each compound is represented by calculated structural descriptors that encode topological, geometrical, electronic, and polar surface features. Multiple linear regression (MLR) and computational neural networks (CNNs) are employed for quantitative models. Three classification algorithms, k-nearest neighbor (kNN), linear discriminant analysis (LDA), and radial basis function neural networks (RBFNN), are used to categorize compounds as active or inactive based on selected data split points. Quantitative modeling of human enzyme inhibition results in a nonlinear, five-descriptor model with root- mean-square errors (log units of IC50 [μM]) of 0.616 (r2 = 0.66), 0.674 (r2 = 0.61), and 0.914 (r2 = 0.33) for training, cross-validation, and prediction sets, respectively. The best classification results for human and murine enzyme inhibition are found using kNN. Human classification rates using a seven-descriptor model for training and prediction sets are 89.1% and 91.4%, respectively. Murine classification rates using a five-descriptor model for training and prediction sets are 91.5% and 88.6%, respectively.

UR - http://www.scopus.com/inward/record.url?scp=0037435071&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037435071&partnerID=8YFLogxK

U2 - 10.1021/jm020269o

DO - 10.1021/jm020269o

M3 - Article

C2 - 12620084

AN - SCOPUS:0037435071

VL - 46

SP - 1066

EP - 1080

JO - Journal of Medicinal Chemistry

JF - Journal of Medicinal Chemistry

SN - 0022-2623

IS - 6

ER -