Consensus features of CP-MLR and GA in modeling HIV-1 RT inhibitory activity of 4-benzyl/benzoylpyridin-2-one analogues

Shreekant Deshpande, Rinki Singh, Mohammad Goodarzi, Seturam B. Katti, Yenamandra S. Prabhakar

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The HIV-1 reverse transcriptase (RT) inhibitory activity of benzyl/benzoylpyridinones is modeled with molecular features identified in combinatorial protocol in multiple linear regression (CP-MLR) and genetic algorithm (GA). Among the features, nDB and LogP are found to be the most influential descriptors to modulate the activity. Although the coefficient of nDB suggested in favor of benzylpyridinones skeleton, the coefficient of LogP suggested the favorability of hydrophilic nature in compounds for better activity. The partial least squares analysis of the descriptors common to CP-MLR and GA has displayed their predictivity over the total descriptors identified in both the approaches. The back-propagation artificial neural networks model from the five most significant common descriptors (nDB, T(O.O), MATS8e, LogP, and BELp4) has explained 93.2% variance in the HIV-1 RT activity of the training set compounds and showed a test set r 2 of 0.89. The results suggest that the descriptors have the ability to identify the patterns in the compounds to predict potential analogues.

Original languageEnglish (US)
Pages (from-to)696-705
Number of pages10
JournalJournal of Enzyme Inhibition and Medicinal Chemistry
Volume26
Issue number5
DOIs
StatePublished - Oct 1 2011

Fingerprint

Linear Models
Neural Networks (Computer)
Least-Squares Analysis
Skeleton
Teaching
Human immunodeficiency virus 1 reverse transcriptase

Keywords

  • ANN
  • Benzyl/benzoylpyridinones
  • CPMLR
  • GA
  • HIV-1 RT inhibitors
  • QSAR

ASJC Scopus subject areas

  • Pharmacology
  • Drug Discovery

Cite this

Consensus features of CP-MLR and GA in modeling HIV-1 RT inhibitory activity of 4-benzyl/benzoylpyridin-2-one analogues. / Deshpande, Shreekant; Singh, Rinki; Goodarzi, Mohammad; Katti, Seturam B.; Prabhakar, Yenamandra S.

In: Journal of Enzyme Inhibition and Medicinal Chemistry, Vol. 26, No. 5, 01.10.2011, p. 696-705.

Research output: Contribution to journalArticle

Deshpande, Shreekant ; Singh, Rinki ; Goodarzi, Mohammad ; Katti, Seturam B. ; Prabhakar, Yenamandra S. / Consensus features of CP-MLR and GA in modeling HIV-1 RT inhibitory activity of 4-benzyl/benzoylpyridin-2-one analogues. In: Journal of Enzyme Inhibition and Medicinal Chemistry. 2011 ; Vol. 26, No. 5. pp. 696-705.
@article{d364444f36724396817ee55e2f0f6174,
title = "Consensus features of CP-MLR and GA in modeling HIV-1 RT inhibitory activity of 4-benzyl/benzoylpyridin-2-one analogues",
abstract = "The HIV-1 reverse transcriptase (RT) inhibitory activity of benzyl/benzoylpyridinones is modeled with molecular features identified in combinatorial protocol in multiple linear regression (CP-MLR) and genetic algorithm (GA). Among the features, nDB and LogP are found to be the most influential descriptors to modulate the activity. Although the coefficient of nDB suggested in favor of benzylpyridinones skeleton, the coefficient of LogP suggested the favorability of hydrophilic nature in compounds for better activity. The partial least squares analysis of the descriptors common to CP-MLR and GA has displayed their predictivity over the total descriptors identified in both the approaches. The back-propagation artificial neural networks model from the five most significant common descriptors (nDB, T(O.O), MATS8e, LogP, and BELp4) has explained 93.2{\%} variance in the HIV-1 RT activity of the training set compounds and showed a test set r 2 of 0.89. The results suggest that the descriptors have the ability to identify the patterns in the compounds to predict potential analogues.",
keywords = "ANN, Benzyl/benzoylpyridinones, CPMLR, GA, HIV-1 RT inhibitors, QSAR",
author = "Shreekant Deshpande and Rinki Singh and Mohammad Goodarzi and Katti, {Seturam B.} and Prabhakar, {Yenamandra S.}",
year = "2011",
month = "10",
day = "1",
doi = "10.3109/14756366.2010.548328",
language = "English (US)",
volume = "26",
pages = "696--705",
journal = "Journal of Enzyme Inhibition and Medicinal Chemistry",
issn = "1475-6366",
publisher = "Informa Healthcare",
number = "5",

}

TY - JOUR

T1 - Consensus features of CP-MLR and GA in modeling HIV-1 RT inhibitory activity of 4-benzyl/benzoylpyridin-2-one analogues

AU - Deshpande, Shreekant

AU - Singh, Rinki

AU - Goodarzi, Mohammad

AU - Katti, Seturam B.

AU - Prabhakar, Yenamandra S.

PY - 2011/10/1

Y1 - 2011/10/1

N2 - The HIV-1 reverse transcriptase (RT) inhibitory activity of benzyl/benzoylpyridinones is modeled with molecular features identified in combinatorial protocol in multiple linear regression (CP-MLR) and genetic algorithm (GA). Among the features, nDB and LogP are found to be the most influential descriptors to modulate the activity. Although the coefficient of nDB suggested in favor of benzylpyridinones skeleton, the coefficient of LogP suggested the favorability of hydrophilic nature in compounds for better activity. The partial least squares analysis of the descriptors common to CP-MLR and GA has displayed their predictivity over the total descriptors identified in both the approaches. The back-propagation artificial neural networks model from the five most significant common descriptors (nDB, T(O.O), MATS8e, LogP, and BELp4) has explained 93.2% variance in the HIV-1 RT activity of the training set compounds and showed a test set r 2 of 0.89. The results suggest that the descriptors have the ability to identify the patterns in the compounds to predict potential analogues.

AB - The HIV-1 reverse transcriptase (RT) inhibitory activity of benzyl/benzoylpyridinones is modeled with molecular features identified in combinatorial protocol in multiple linear regression (CP-MLR) and genetic algorithm (GA). Among the features, nDB and LogP are found to be the most influential descriptors to modulate the activity. Although the coefficient of nDB suggested in favor of benzylpyridinones skeleton, the coefficient of LogP suggested the favorability of hydrophilic nature in compounds for better activity. The partial least squares analysis of the descriptors common to CP-MLR and GA has displayed their predictivity over the total descriptors identified in both the approaches. The back-propagation artificial neural networks model from the five most significant common descriptors (nDB, T(O.O), MATS8e, LogP, and BELp4) has explained 93.2% variance in the HIV-1 RT activity of the training set compounds and showed a test set r 2 of 0.89. The results suggest that the descriptors have the ability to identify the patterns in the compounds to predict potential analogues.

KW - ANN

KW - Benzyl/benzoylpyridinones

KW - CPMLR

KW - GA

KW - HIV-1 RT inhibitors

KW - QSAR

UR - http://www.scopus.com/inward/record.url?scp=80052854752&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052854752&partnerID=8YFLogxK

U2 - 10.3109/14756366.2010.548328

DO - 10.3109/14756366.2010.548328

M3 - Article

C2 - 21284408

AN - SCOPUS:80052854752

VL - 26

SP - 696

EP - 705

JO - Journal of Enzyme Inhibition and Medicinal Chemistry

JF - Journal of Enzyme Inhibition and Medicinal Chemistry

SN - 1475-6366

IS - 5

ER -