Multiple linear regression analysis and optimal descriptors

Predicting the cholesteryl ester transfer protein inhibition activity

Bakhtiyor F. Rasulev, Andrey A. Toropov, Ashton T. Hamme, Jerzy Leszczynski

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Quantitative structure - activity relationships have been developed for a set of 40 halogenated substituted N-benzyl-N-phenyl aminoalcohol compounds. IC50 values for Cholesteryl Ester Transfer Protein (CETP) inhibition activity for these compounds expressed in log units have been modeled by Multiple Linear Regression Analysis (MLRA) based on descriptors generated by DRAGON software and optimal descriptors approach. Forty benzene derivatives have been divided into training (n=20) and test (n=20) sets. In the case of the MLRA, the three-variable model has the best predictive potential. Comparison of the quality of MLRA and optimal descriptor models shows that the predictive potential of the one-variable model, based on the optimal descriptor, provides a low correlation coefficient in the training set. However, this one-variable model performs better for the test set when compared to the two- and three-variable MLRA models.

Original languageEnglish
Pages (from-to)595-606
Number of pages12
JournalQSAR and Combinatorial Science
Volume27
Issue number5
DOIs
Publication statusPublished - May 2008

Fingerprint

Cholesterol Ester Transfer Proteins
Linear regression
Regression analysis
Linear Models
Esters
Regression Analysis
Proteins
Benzene Derivatives
Quantitative Structure-Activity Relationship
Inhibitory Concentration 50
Software
Benzene
Derivatives

Keywords

  • Cholesteryl ester transfer protein
  • Inhibitors
  • MLRA
  • Optimal descriptors
  • QSAR

ASJC Scopus subject areas

  • Drug Discovery
  • Organic Chemistry
  • Computer Science Applications

Cite this

Multiple linear regression analysis and optimal descriptors : Predicting the cholesteryl ester transfer protein inhibition activity. / Rasulev, Bakhtiyor F.; Toropov, Andrey A.; Hamme, Ashton T.; Leszczynski, Jerzy.

In: QSAR and Combinatorial Science, Vol. 27, No. 5, 05.2008, p. 595-606.

Research output: Contribution to journalArticle

Rasulev, Bakhtiyor F. ; Toropov, Andrey A. ; Hamme, Ashton T. ; Leszczynski, Jerzy. / Multiple linear regression analysis and optimal descriptors : Predicting the cholesteryl ester transfer protein inhibition activity. In: QSAR and Combinatorial Science. 2008 ; Vol. 27, No. 5. pp. 595-606.
@article{2d3921ce7e874c9ba1a73ff7d8833efc,
title = "Multiple linear regression analysis and optimal descriptors: Predicting the cholesteryl ester transfer protein inhibition activity",
abstract = "Quantitative structure - activity relationships have been developed for a set of 40 halogenated substituted N-benzyl-N-phenyl aminoalcohol compounds. IC50 values for Cholesteryl Ester Transfer Protein (CETP) inhibition activity for these compounds expressed in log units have been modeled by Multiple Linear Regression Analysis (MLRA) based on descriptors generated by DRAGON software and optimal descriptors approach. Forty benzene derivatives have been divided into training (n=20) and test (n=20) sets. In the case of the MLRA, the three-variable model has the best predictive potential. Comparison of the quality of MLRA and optimal descriptor models shows that the predictive potential of the one-variable model, based on the optimal descriptor, provides a low correlation coefficient in the training set. However, this one-variable model performs better for the test set when compared to the two- and three-variable MLRA models.",
keywords = "Cholesteryl ester transfer protein, Inhibitors, MLRA, Optimal descriptors, QSAR",
author = "Rasulev, {Bakhtiyor F.} and Toropov, {Andrey A.} and Hamme, {Ashton T.} and Jerzy Leszczynski",
year = "2008",
month = "5",
doi = "10.1002/qsar.200710006",
language = "English",
volume = "27",
pages = "595--606",
journal = "QSAR and Combinatorial Science",
issn = "1611-020X",
publisher = "Wiley - VCH Verlag GmbH & CO. KGaA",
number = "5",

}

TY - JOUR

T1 - Multiple linear regression analysis and optimal descriptors

T2 - Predicting the cholesteryl ester transfer protein inhibition activity

AU - Rasulev, Bakhtiyor F.

AU - Toropov, Andrey A.

AU - Hamme, Ashton T.

AU - Leszczynski, Jerzy

PY - 2008/5

Y1 - 2008/5

N2 - Quantitative structure - activity relationships have been developed for a set of 40 halogenated substituted N-benzyl-N-phenyl aminoalcohol compounds. IC50 values for Cholesteryl Ester Transfer Protein (CETP) inhibition activity for these compounds expressed in log units have been modeled by Multiple Linear Regression Analysis (MLRA) based on descriptors generated by DRAGON software and optimal descriptors approach. Forty benzene derivatives have been divided into training (n=20) and test (n=20) sets. In the case of the MLRA, the three-variable model has the best predictive potential. Comparison of the quality of MLRA and optimal descriptor models shows that the predictive potential of the one-variable model, based on the optimal descriptor, provides a low correlation coefficient in the training set. However, this one-variable model performs better for the test set when compared to the two- and three-variable MLRA models.

AB - Quantitative structure - activity relationships have been developed for a set of 40 halogenated substituted N-benzyl-N-phenyl aminoalcohol compounds. IC50 values for Cholesteryl Ester Transfer Protein (CETP) inhibition activity for these compounds expressed in log units have been modeled by Multiple Linear Regression Analysis (MLRA) based on descriptors generated by DRAGON software and optimal descriptors approach. Forty benzene derivatives have been divided into training (n=20) and test (n=20) sets. In the case of the MLRA, the three-variable model has the best predictive potential. Comparison of the quality of MLRA and optimal descriptor models shows that the predictive potential of the one-variable model, based on the optimal descriptor, provides a low correlation coefficient in the training set. However, this one-variable model performs better for the test set when compared to the two- and three-variable MLRA models.

KW - Cholesteryl ester transfer protein

KW - Inhibitors

KW - MLRA

KW - Optimal descriptors

KW - QSAR

UR - http://www.scopus.com/inward/record.url?scp=54949113678&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=54949113678&partnerID=8YFLogxK

U2 - 10.1002/qsar.200710006

DO - 10.1002/qsar.200710006

M3 - Article

VL - 27

SP - 595

EP - 606

JO - QSAR and Combinatorial Science

JF - QSAR and Combinatorial Science

SN - 1611-020X

IS - 5

ER -