Linear and nonlinear quantitative structure-activity relationship modeling of the HIV-1 reverse transcriptase inhibiting activities of thiocarbamates

Mohammad Goodarzi, Matheus P. Freitas, Yvan Vander Heyden

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

For a series of thiocarbamates, non-nucleoside HIV-1 reverse transcriptase inhibitors, few descriptors have been selected from a large pool of theoretical molecular descriptors by means of the ant colony optimization (ACO) feature selection method. The selected descriptors were correlated with the bioactivities of the molecules using the well known multiple linear regression (MLR) and partial least squares (PLS) regression techniques, and, to account for nonlinearity, also PLS coupled to radial basis function (RBF) on the one hand and radial basis function neural network (RBFNN) on the other. In this case study, the RBF/PLS results were better than those from the other modeling techniques applied. The prediction ability of the ACO/RBF/PLS-based quantitative structure-activity relationship (QSAR) model was found to be significantly superior to comparative molecular field analysis (CoMFA) and comparative molecular similarity index analysis (CoMSIA) models previously established for this series of compounds. It was also demonstrated that RBF as a nonlinear approach is useful in deriving simple and predictive QSAR models, without the need to recourse to expeditious 3D methodologies.

Original languageEnglish (US)
Pages (from-to)166-173
Number of pages8
JournalAnalytica Chimica Acta
Volume705
Issue number1-2
DOIs
StatePublished - Oct 31 2011

Fingerprint

Thiocarbamates
Quantitative Structure-Activity Relationship
human immunodeficiency virus
Least-Squares Analysis
ant
Ants
Ant colony optimization
modeling
bioactivity
similarity index
nonlinearity
Reverse Transcriptase Inhibitors
inhibitor
Linear Models
Bioactivity
Linear regression
methodology
Feature extraction
prediction
Human immunodeficiency virus 1 reverse transcriptase

Keywords

  • Ant colony optimization
  • HIV-1 reverse transcriptase
  • Partial least squares
  • Radial basis function
  • Thiocarbamates

ASJC Scopus subject areas

  • Analytical Chemistry
  • Biochemistry
  • Environmental Chemistry
  • Spectroscopy

Cite this

Linear and nonlinear quantitative structure-activity relationship modeling of the HIV-1 reverse transcriptase inhibiting activities of thiocarbamates. / Goodarzi, Mohammad; Freitas, Matheus P.; Heyden, Yvan Vander.

In: Analytica Chimica Acta, Vol. 705, No. 1-2, 31.10.2011, p. 166-173.

Research output: Contribution to journalArticle

@article{ca0e3f87249b44998f73ad15283d204d,
title = "Linear and nonlinear quantitative structure-activity relationship modeling of the HIV-1 reverse transcriptase inhibiting activities of thiocarbamates",
abstract = "For a series of thiocarbamates, non-nucleoside HIV-1 reverse transcriptase inhibitors, few descriptors have been selected from a large pool of theoretical molecular descriptors by means of the ant colony optimization (ACO) feature selection method. The selected descriptors were correlated with the bioactivities of the molecules using the well known multiple linear regression (MLR) and partial least squares (PLS) regression techniques, and, to account for nonlinearity, also PLS coupled to radial basis function (RBF) on the one hand and radial basis function neural network (RBFNN) on the other. In this case study, the RBF/PLS results were better than those from the other modeling techniques applied. The prediction ability of the ACO/RBF/PLS-based quantitative structure-activity relationship (QSAR) model was found to be significantly superior to comparative molecular field analysis (CoMFA) and comparative molecular similarity index analysis (CoMSIA) models previously established for this series of compounds. It was also demonstrated that RBF as a nonlinear approach is useful in deriving simple and predictive QSAR models, without the need to recourse to expeditious 3D methodologies.",
keywords = "Ant colony optimization, HIV-1 reverse transcriptase, Partial least squares, Radial basis function, Thiocarbamates",
author = "Mohammad Goodarzi and Freitas, {Matheus P.} and Heyden, {Yvan Vander}",
year = "2011",
month = "10",
day = "31",
doi = "10.1016/j.aca.2011.04.046",
language = "English (US)",
volume = "705",
pages = "166--173",
journal = "Analytica Chimica Acta",
issn = "0003-2670",
publisher = "Elsevier",
number = "1-2",

}

TY - JOUR

T1 - Linear and nonlinear quantitative structure-activity relationship modeling of the HIV-1 reverse transcriptase inhibiting activities of thiocarbamates

AU - Goodarzi, Mohammad

AU - Freitas, Matheus P.

AU - Heyden, Yvan Vander

PY - 2011/10/31

Y1 - 2011/10/31

N2 - For a series of thiocarbamates, non-nucleoside HIV-1 reverse transcriptase inhibitors, few descriptors have been selected from a large pool of theoretical molecular descriptors by means of the ant colony optimization (ACO) feature selection method. The selected descriptors were correlated with the bioactivities of the molecules using the well known multiple linear regression (MLR) and partial least squares (PLS) regression techniques, and, to account for nonlinearity, also PLS coupled to radial basis function (RBF) on the one hand and radial basis function neural network (RBFNN) on the other. In this case study, the RBF/PLS results were better than those from the other modeling techniques applied. The prediction ability of the ACO/RBF/PLS-based quantitative structure-activity relationship (QSAR) model was found to be significantly superior to comparative molecular field analysis (CoMFA) and comparative molecular similarity index analysis (CoMSIA) models previously established for this series of compounds. It was also demonstrated that RBF as a nonlinear approach is useful in deriving simple and predictive QSAR models, without the need to recourse to expeditious 3D methodologies.

AB - For a series of thiocarbamates, non-nucleoside HIV-1 reverse transcriptase inhibitors, few descriptors have been selected from a large pool of theoretical molecular descriptors by means of the ant colony optimization (ACO) feature selection method. The selected descriptors were correlated with the bioactivities of the molecules using the well known multiple linear regression (MLR) and partial least squares (PLS) regression techniques, and, to account for nonlinearity, also PLS coupled to radial basis function (RBF) on the one hand and radial basis function neural network (RBFNN) on the other. In this case study, the RBF/PLS results were better than those from the other modeling techniques applied. The prediction ability of the ACO/RBF/PLS-based quantitative structure-activity relationship (QSAR) model was found to be significantly superior to comparative molecular field analysis (CoMFA) and comparative molecular similarity index analysis (CoMSIA) models previously established for this series of compounds. It was also demonstrated that RBF as a nonlinear approach is useful in deriving simple and predictive QSAR models, without the need to recourse to expeditious 3D methodologies.

KW - Ant colony optimization

KW - HIV-1 reverse transcriptase

KW - Partial least squares

KW - Radial basis function

KW - Thiocarbamates

UR - http://www.scopus.com/inward/record.url?scp=80053383769&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053383769&partnerID=8YFLogxK

U2 - 10.1016/j.aca.2011.04.046

DO - 10.1016/j.aca.2011.04.046

M3 - Article

C2 - 21962359

AN - SCOPUS:80053383769

VL - 705

SP - 166

EP - 173

JO - Analytica Chimica Acta

JF - Analytica Chimica Acta

SN - 0003-2670

IS - 1-2

ER -