PXR ligand classification model with SFED-weighted WHIM and CoMMA descriptors

S. L. Ma, J. Y. Joung, S. Lee, K. H. Cho, K. T. No

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Understanding which type of endogenous and exogenous compounds serve as agonists for the nuclear pregnane X receptor (PXR) would be valuable for drug discovery and development, because PXR regulates a large number of genes related to xenobiotic metabolism. Although several models have been proposed to classify human PXR activators and non-activators, models with better predictability are necessary for practical purposes in drug discovery. Grid-weighted holistic invariant molecular (G-WHIM) and comparative molecular moment analysis (G-CoMMA) type 3D descriptors that contain information about the solvation free energy of target molecules were developed. With these descriptors, prediction models built using decision tree (DT)-, support vector machine (SVM)-, and Kohonen neural network (KNN)-based models exhibited better predictability than previously proposed models. Solvation free energy density-weighted G-WHIM and G-CoMMA descriptors reveal new insights into PXR ligand classification, and incorporation with machine learning methods (DT, SVM, KNN) exhibits promising results, especially SVM and KNN. SVM- and KNN-based models exhibit accuracy around 0.90, and DT-based models exhibit accuracy around 0.8 for both the training and test sets.

Original languageEnglish
Pages (from-to)485-504
Number of pages20
JournalSAR and QSAR in Environmental Research
Volume23
Issue number5-6
DOIs
Publication statusPublished - 2012 Jul 1

Fingerprint

Decision Trees
Ligands
Neural Networks (Computer)
Drug Discovery
Support vector machines
Decision trees
Neural networks
Solvation
Xenobiotics
Free energy
pregnane X receptor
Support Vector Machine
Metabolism
Learning systems
Genes
Molecules

All Science Journal Classification (ASJC) codes

  • Bioengineering
  • Molecular Medicine
  • Drug Discovery

Cite this

Ma, S. L. ; Joung, J. Y. ; Lee, S. ; Cho, K. H. ; No, K. T. / PXR ligand classification model with SFED-weighted WHIM and CoMMA descriptors. In: SAR and QSAR in Environmental Research. 2012 ; Vol. 23, No. 5-6. pp. 485-504.
@article{5177b67755e94cd79938dd9a3b4912cb,
title = "PXR ligand classification model with SFED-weighted WHIM and CoMMA descriptors",
abstract = "Understanding which type of endogenous and exogenous compounds serve as agonists for the nuclear pregnane X receptor (PXR) would be valuable for drug discovery and development, because PXR regulates a large number of genes related to xenobiotic metabolism. Although several models have been proposed to classify human PXR activators and non-activators, models with better predictability are necessary for practical purposes in drug discovery. Grid-weighted holistic invariant molecular (G-WHIM) and comparative molecular moment analysis (G-CoMMA) type 3D descriptors that contain information about the solvation free energy of target molecules were developed. With these descriptors, prediction models built using decision tree (DT)-, support vector machine (SVM)-, and Kohonen neural network (KNN)-based models exhibited better predictability than previously proposed models. Solvation free energy density-weighted G-WHIM and G-CoMMA descriptors reveal new insights into PXR ligand classification, and incorporation with machine learning methods (DT, SVM, KNN) exhibits promising results, especially SVM and KNN. SVM- and KNN-based models exhibit accuracy around 0.90, and DT-based models exhibit accuracy around 0.8 for both the training and test sets.",
author = "Ma, {S. L.} and Joung, {J. Y.} and S. Lee and Cho, {K. H.} and No, {K. T.}",
year = "2012",
month = "7",
day = "1",
doi = "10.1080/1062936X.2012.665385",
language = "English",
volume = "23",
pages = "485--504",
journal = "SAR and QSAR in Environmental Research",
issn = "1062-936X",
publisher = "Taylor and Francis Ltd.",
number = "5-6",

}

PXR ligand classification model with SFED-weighted WHIM and CoMMA descriptors. / Ma, S. L.; Joung, J. Y.; Lee, S.; Cho, K. H.; No, K. T.

In: SAR and QSAR in Environmental Research, Vol. 23, No. 5-6, 01.07.2012, p. 485-504.

Research output: Contribution to journalArticle

TY - JOUR

T1 - PXR ligand classification model with SFED-weighted WHIM and CoMMA descriptors

AU - Ma, S. L.

AU - Joung, J. Y.

AU - Lee, S.

AU - Cho, K. H.

AU - No, K. T.

PY - 2012/7/1

Y1 - 2012/7/1

N2 - Understanding which type of endogenous and exogenous compounds serve as agonists for the nuclear pregnane X receptor (PXR) would be valuable for drug discovery and development, because PXR regulates a large number of genes related to xenobiotic metabolism. Although several models have been proposed to classify human PXR activators and non-activators, models with better predictability are necessary for practical purposes in drug discovery. Grid-weighted holistic invariant molecular (G-WHIM) and comparative molecular moment analysis (G-CoMMA) type 3D descriptors that contain information about the solvation free energy of target molecules were developed. With these descriptors, prediction models built using decision tree (DT)-, support vector machine (SVM)-, and Kohonen neural network (KNN)-based models exhibited better predictability than previously proposed models. Solvation free energy density-weighted G-WHIM and G-CoMMA descriptors reveal new insights into PXR ligand classification, and incorporation with machine learning methods (DT, SVM, KNN) exhibits promising results, especially SVM and KNN. SVM- and KNN-based models exhibit accuracy around 0.90, and DT-based models exhibit accuracy around 0.8 for both the training and test sets.

AB - Understanding which type of endogenous and exogenous compounds serve as agonists for the nuclear pregnane X receptor (PXR) would be valuable for drug discovery and development, because PXR regulates a large number of genes related to xenobiotic metabolism. Although several models have been proposed to classify human PXR activators and non-activators, models with better predictability are necessary for practical purposes in drug discovery. Grid-weighted holistic invariant molecular (G-WHIM) and comparative molecular moment analysis (G-CoMMA) type 3D descriptors that contain information about the solvation free energy of target molecules were developed. With these descriptors, prediction models built using decision tree (DT)-, support vector machine (SVM)-, and Kohonen neural network (KNN)-based models exhibited better predictability than previously proposed models. Solvation free energy density-weighted G-WHIM and G-CoMMA descriptors reveal new insights into PXR ligand classification, and incorporation with machine learning methods (DT, SVM, KNN) exhibits promising results, especially SVM and KNN. SVM- and KNN-based models exhibit accuracy around 0.90, and DT-based models exhibit accuracy around 0.8 for both the training and test sets.

UR - http://www.scopus.com/inward/record.url?scp=84864659881&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864659881&partnerID=8YFLogxK

U2 - 10.1080/1062936X.2012.665385

DO - 10.1080/1062936X.2012.665385

M3 - Article

C2 - 22591167

AN - SCOPUS:84864659881

VL - 23

SP - 485

EP - 504

JO - SAR and QSAR in Environmental Research

JF - SAR and QSAR in Environmental Research

SN - 1062-936X

IS - 5-6

ER -