2D binary QSAR modeling of LPA3 receptor antagonism

James I. Fells, Ryoko Tsukahara, Jianxiong Liu, Gabor Tigyi, Abby L. Parrill

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

A structurally diverse dataset of 119 compounds was used to develop and validate a 2D binary QSAR model for the LPA3 receptor. The binary QSAR model was generated using an activity threshold of greater than 15% inhibition at 10 μM. The overall accuracy of the model on the training set was 82%. It had accuracies of 55% for active and 91% for inactive compounds, respectively. The model was validated using an external test set of 10 compounds. The accuracy on the external test set was 60% overall, identifying three out of seven actives and all three inactive compounds. This model was combined with similarity searching to rapidly screen libraries and select 14 candidate LPA3 antagonists. Experimental assays confirmed 13 of these (93%) met the 15% inhibition threshold defining actives. The successful application of the model to select candidates for screening demonstrates the power of this binary QSAR model to prioritize compound selection for experimental consideration.

Original languageEnglish (US)
Pages (from-to)828-833
Number of pages6
JournalJournal of Molecular Graphics and Modelling
Volume28
Issue number8
DOIs
StatePublished - Jun 1 2010

Fingerprint

Lysophosphatidic Acid Receptors
thresholds
Assays
Screening
education
screening

All Science Journal Classification (ASJC) codes

  • Physical and Theoretical Chemistry
  • Spectroscopy
  • Computer Graphics and Computer-Aided Design
  • Materials Chemistry

Cite this

2D binary QSAR modeling of LPA3 receptor antagonism. / Fells, James I.; Tsukahara, Ryoko; Liu, Jianxiong; Tigyi, Gabor; Parrill, Abby L.

In: Journal of Molecular Graphics and Modelling, Vol. 28, No. 8, 01.06.2010, p. 828-833.

Research output: Contribution to journalArticle

Fells, James I. ; Tsukahara, Ryoko ; Liu, Jianxiong ; Tigyi, Gabor ; Parrill, Abby L. / 2D binary QSAR modeling of LPA3 receptor antagonism. In: Journal of Molecular Graphics and Modelling. 2010 ; Vol. 28, No. 8. pp. 828-833.
@article{7021e7417cd74dcf8bac338270bd4066,
title = "2D binary QSAR modeling of LPA3 receptor antagonism",
abstract = "A structurally diverse dataset of 119 compounds was used to develop and validate a 2D binary QSAR model for the LPA3 receptor. The binary QSAR model was generated using an activity threshold of greater than 15{\%} inhibition at 10 μM. The overall accuracy of the model on the training set was 82{\%}. It had accuracies of 55{\%} for active and 91{\%} for inactive compounds, respectively. The model was validated using an external test set of 10 compounds. The accuracy on the external test set was 60{\%} overall, identifying three out of seven actives and all three inactive compounds. This model was combined with similarity searching to rapidly screen libraries and select 14 candidate LPA3 antagonists. Experimental assays confirmed 13 of these (93{\%}) met the 15{\%} inhibition threshold defining actives. The successful application of the model to select candidates for screening demonstrates the power of this binary QSAR model to prioritize compound selection for experimental consideration.",
author = "Fells, {James I.} and Ryoko Tsukahara and Jianxiong Liu and Gabor Tigyi and Parrill, {Abby L.}",
year = "2010",
month = "6",
day = "1",
doi = "10.1016/j.jmgm.2010.03.002",
language = "English (US)",
volume = "28",
pages = "828--833",
journal = "Journal of Molecular Graphics and Modelling",
issn = "1093-3263",
publisher = "Elsevier Inc.",
number = "8",

}

TY - JOUR

T1 - 2D binary QSAR modeling of LPA3 receptor antagonism

AU - Fells, James I.

AU - Tsukahara, Ryoko

AU - Liu, Jianxiong

AU - Tigyi, Gabor

AU - Parrill, Abby L.

PY - 2010/6/1

Y1 - 2010/6/1

N2 - A structurally diverse dataset of 119 compounds was used to develop and validate a 2D binary QSAR model for the LPA3 receptor. The binary QSAR model was generated using an activity threshold of greater than 15% inhibition at 10 μM. The overall accuracy of the model on the training set was 82%. It had accuracies of 55% for active and 91% for inactive compounds, respectively. The model was validated using an external test set of 10 compounds. The accuracy on the external test set was 60% overall, identifying three out of seven actives and all three inactive compounds. This model was combined with similarity searching to rapidly screen libraries and select 14 candidate LPA3 antagonists. Experimental assays confirmed 13 of these (93%) met the 15% inhibition threshold defining actives. The successful application of the model to select candidates for screening demonstrates the power of this binary QSAR model to prioritize compound selection for experimental consideration.

AB - A structurally diverse dataset of 119 compounds was used to develop and validate a 2D binary QSAR model for the LPA3 receptor. The binary QSAR model was generated using an activity threshold of greater than 15% inhibition at 10 μM. The overall accuracy of the model on the training set was 82%. It had accuracies of 55% for active and 91% for inactive compounds, respectively. The model was validated using an external test set of 10 compounds. The accuracy on the external test set was 60% overall, identifying three out of seven actives and all three inactive compounds. This model was combined with similarity searching to rapidly screen libraries and select 14 candidate LPA3 antagonists. Experimental assays confirmed 13 of these (93%) met the 15% inhibition threshold defining actives. The successful application of the model to select candidates for screening demonstrates the power of this binary QSAR model to prioritize compound selection for experimental consideration.

UR - http://www.scopus.com/inward/record.url?scp=77951974258&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951974258&partnerID=8YFLogxK

U2 - 10.1016/j.jmgm.2010.03.002

DO - 10.1016/j.jmgm.2010.03.002

M3 - Article

VL - 28

SP - 828

EP - 833

JO - Journal of Molecular Graphics and Modelling

JF - Journal of Molecular Graphics and Modelling

SN - 1093-3263

IS - 8

ER -