Exploring qsars for inhibitory activity of non-peptide hiv-1 protease inhibitors by ga-pls and GA-SVM

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

The support vector machine (SVM) and partial least square (PLS) methods were used to develop quantitative structure activity relationship (QSAR) models to predict the inhibitory activity of non-peptide HIV-1 protease inhibitors. Genetic algorithm (GA) was employed to select variables that lead to the best-fitted models. A comparison between the obtained results using SVM with those of PLS revealed that the SVM model is much better than that of PLS. The root mean square errors of the training set and the test set for SVM model were calculated to be 0.2027, 0.2751, and the coefficients of determination (R 2) are 0.9800, 0.9355 respectively. Furthermore, the obtained statistical parameter of leave-one-out cross-validation test (Q2) on SVM model was 0.9672, which proves the reliability of this model. The results suggest that TE2, Ui, GATS5e, Mor13e, ATS7m, Ss, Mor27e, and RDF035e are the main independent factors contributing to the inhibitory activities of the studied compounds.

Original languageEnglish (US)
Pages (from-to)506-514
Number of pages9
JournalChemical Biology and Drug Design
Volume75
Issue number5
DOIs
StatePublished - May 1 2010

Fingerprint

Protease Inhibitors
Support vector machines
Genetic algorithms
Least-Squares Analysis
HIV Protease Inhibitors
Quantitative Structure-Activity Relationship
Mean square error
Support Vector Machine

Keywords

  • Genetic algorithms
  • HIV-1 protease inhibitors
  • Inhibitory activity
  • Partial least square
  • Quantitative structure activity relationship
  • Support vector machine

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Medicine

Cite this

Exploring qsars for inhibitory activity of non-peptide hiv-1 protease inhibitors by ga-pls and GA-SVM. / Deeb, Omar; Goodarzi, Mohammad.

In: Chemical Biology and Drug Design, Vol. 75, No. 5, 01.05.2010, p. 506-514.

Research output: Contribution to journalArticle

@article{35a54115718f49288505d855e1e58120,
title = "Exploring qsars for inhibitory activity of non-peptide hiv-1 protease inhibitors by ga-pls and GA-SVM",
abstract = "The support vector machine (SVM) and partial least square (PLS) methods were used to develop quantitative structure activity relationship (QSAR) models to predict the inhibitory activity of non-peptide HIV-1 protease inhibitors. Genetic algorithm (GA) was employed to select variables that lead to the best-fitted models. A comparison between the obtained results using SVM with those of PLS revealed that the SVM model is much better than that of PLS. The root mean square errors of the training set and the test set for SVM model were calculated to be 0.2027, 0.2751, and the coefficients of determination (R 2) are 0.9800, 0.9355 respectively. Furthermore, the obtained statistical parameter of leave-one-out cross-validation test (Q2) on SVM model was 0.9672, which proves the reliability of this model. The results suggest that TE2, Ui, GATS5e, Mor13e, ATS7m, Ss, Mor27e, and RDF035e are the main independent factors contributing to the inhibitory activities of the studied compounds.",
keywords = "Genetic algorithms, HIV-1 protease inhibitors, Inhibitory activity, Partial least square, Quantitative structure activity relationship, Support vector machine",
author = "Omar Deeb and Mohammad Goodarzi",
year = "2010",
month = "5",
day = "1",
doi = "10.1111/j.1747-0285.2010.00953.x",
language = "English (US)",
volume = "75",
pages = "506--514",
journal = "Chemical Biology and Drug Design",
issn = "1747-0277",
publisher = "Blackwell",
number = "5",

}

TY - JOUR

T1 - Exploring qsars for inhibitory activity of non-peptide hiv-1 protease inhibitors by ga-pls and GA-SVM

AU - Deeb, Omar

AU - Goodarzi, Mohammad

PY - 2010/5/1

Y1 - 2010/5/1

N2 - The support vector machine (SVM) and partial least square (PLS) methods were used to develop quantitative structure activity relationship (QSAR) models to predict the inhibitory activity of non-peptide HIV-1 protease inhibitors. Genetic algorithm (GA) was employed to select variables that lead to the best-fitted models. A comparison between the obtained results using SVM with those of PLS revealed that the SVM model is much better than that of PLS. The root mean square errors of the training set and the test set for SVM model were calculated to be 0.2027, 0.2751, and the coefficients of determination (R 2) are 0.9800, 0.9355 respectively. Furthermore, the obtained statistical parameter of leave-one-out cross-validation test (Q2) on SVM model was 0.9672, which proves the reliability of this model. The results suggest that TE2, Ui, GATS5e, Mor13e, ATS7m, Ss, Mor27e, and RDF035e are the main independent factors contributing to the inhibitory activities of the studied compounds.

AB - The support vector machine (SVM) and partial least square (PLS) methods were used to develop quantitative structure activity relationship (QSAR) models to predict the inhibitory activity of non-peptide HIV-1 protease inhibitors. Genetic algorithm (GA) was employed to select variables that lead to the best-fitted models. A comparison between the obtained results using SVM with those of PLS revealed that the SVM model is much better than that of PLS. The root mean square errors of the training set and the test set for SVM model were calculated to be 0.2027, 0.2751, and the coefficients of determination (R 2) are 0.9800, 0.9355 respectively. Furthermore, the obtained statistical parameter of leave-one-out cross-validation test (Q2) on SVM model was 0.9672, which proves the reliability of this model. The results suggest that TE2, Ui, GATS5e, Mor13e, ATS7m, Ss, Mor27e, and RDF035e are the main independent factors contributing to the inhibitory activities of the studied compounds.

KW - Genetic algorithms

KW - HIV-1 protease inhibitors

KW - Inhibitory activity

KW - Partial least square

KW - Quantitative structure activity relationship

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=77949929296&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949929296&partnerID=8YFLogxK

U2 - 10.1111/j.1747-0285.2010.00953.x

DO - 10.1111/j.1747-0285.2010.00953.x

M3 - Article

C2 - 20486937

AN - SCOPUS:77949929296

VL - 75

SP - 506

EP - 514

JO - Chemical Biology and Drug Design

JF - Chemical Biology and Drug Design

SN - 1747-0277

IS - 5

ER -