Large-scale QSAR study of aromatase inhibitors using SMILES-based descriptors

Apilak Worachartcheewan, Prasit Mandi, Virapong Prachayasittikul, Alla P. Toropova, Andrey A. Toropov, Chanin Nantasenamat

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

Aromatase inhibitors (AIs) represent a promising therapeutic class of anticancer agents against estrogen receptor-positive breast cancer. Bioactivity data on pIC50 of 973 AIs were employed in the construction of quantitative structure-activity relationship (QSAR) models using COR relation And Logic (CORAL) software (http://www.insilico.eu/coral) in which molecular structures are represented by the simplified molecular input line entry system (SMILES) notation. Symbols inherently present in SMILES nomenclatures describe the presence of molecular fragments and therefore represent a facile approach that essentially eliminate the need to geometrically optimize molecular structures or the hassle of computing and selecting molecular descriptors. Predictive models were built in accordance with the OECD principles. Monte Carlo optimization of correlation weights of such molecular fragments provides pertinent information on structural constituents for correlating with the aromatase inhibitory activity. Results from different splits and data sub-sets indicated reliable models for predicting and interpreting the origins of aromatase inhibitory activities with the correlation coefficient (R2) and cross-validated correlation coefficient (Q2) in ranges of 0.6271-0.7083 and 0.6218-0.7024, respectively. Insights gained from constructed models could aid in the future design of aromatase inhibitors.

Original languageEnglish
Pages (from-to)120-126
Number of pages7
JournalChemometrics and Intelligent Laboratory Systems
Volume138
DOIs
Publication statusPublished - Nov 15 2014

Fingerprint

Aromatase Inhibitors
Aromatase
Molecular structure
Bioactivity
Estrogen Receptors
Antineoplastic Agents

Keywords

  • Aromatase inhibitors
  • Breast cancer
  • CORAL software
  • Data mining
  • QSAR
  • SMILES

ASJC Scopus subject areas

  • Analytical Chemistry
  • Computer Science Applications
  • Software
  • Process Chemistry and Technology
  • Spectroscopy

Cite this

Worachartcheewan, A., Mandi, P., Prachayasittikul, V., Toropova, A. P., Toropov, A. A., & Nantasenamat, C. (2014). Large-scale QSAR study of aromatase inhibitors using SMILES-based descriptors. Chemometrics and Intelligent Laboratory Systems, 138, 120-126. https://doi.org/10.1016/j.chemolab.2014.07.017

Large-scale QSAR study of aromatase inhibitors using SMILES-based descriptors. / Worachartcheewan, Apilak; Mandi, Prasit; Prachayasittikul, Virapong; Toropova, Alla P.; Toropov, Andrey A.; Nantasenamat, Chanin.

In: Chemometrics and Intelligent Laboratory Systems, Vol. 138, 15.11.2014, p. 120-126.

Research output: Contribution to journalArticle

Worachartcheewan, A, Mandi, P, Prachayasittikul, V, Toropova, AP, Toropov, AA & Nantasenamat, C 2014, 'Large-scale QSAR study of aromatase inhibitors using SMILES-based descriptors', Chemometrics and Intelligent Laboratory Systems, vol. 138, pp. 120-126. https://doi.org/10.1016/j.chemolab.2014.07.017
Worachartcheewan A, Mandi P, Prachayasittikul V, Toropova AP, Toropov AA, Nantasenamat C. Large-scale QSAR study of aromatase inhibitors using SMILES-based descriptors. Chemometrics and Intelligent Laboratory Systems. 2014 Nov 15;138:120-126. https://doi.org/10.1016/j.chemolab.2014.07.017
Worachartcheewan, Apilak ; Mandi, Prasit ; Prachayasittikul, Virapong ; Toropova, Alla P. ; Toropov, Andrey A. ; Nantasenamat, Chanin. / Large-scale QSAR study of aromatase inhibitors using SMILES-based descriptors. In: Chemometrics and Intelligent Laboratory Systems. 2014 ; Vol. 138. pp. 120-126.
@article{33152c3fed7b40b9a4cf8fe057ec90c6,
title = "Large-scale QSAR study of aromatase inhibitors using SMILES-based descriptors",
abstract = "Aromatase inhibitors (AIs) represent a promising therapeutic class of anticancer agents against estrogen receptor-positive breast cancer. Bioactivity data on pIC50 of 973 AIs were employed in the construction of quantitative structure-activity relationship (QSAR) models using COR relation And Logic (CORAL) software (http://www.insilico.eu/coral) in which molecular structures are represented by the simplified molecular input line entry system (SMILES) notation. Symbols inherently present in SMILES nomenclatures describe the presence of molecular fragments and therefore represent a facile approach that essentially eliminate the need to geometrically optimize molecular structures or the hassle of computing and selecting molecular descriptors. Predictive models were built in accordance with the OECD principles. Monte Carlo optimization of correlation weights of such molecular fragments provides pertinent information on structural constituents for correlating with the aromatase inhibitory activity. Results from different splits and data sub-sets indicated reliable models for predicting and interpreting the origins of aromatase inhibitory activities with the correlation coefficient (R2) and cross-validated correlation coefficient (Q2) in ranges of 0.6271-0.7083 and 0.6218-0.7024, respectively. Insights gained from constructed models could aid in the future design of aromatase inhibitors.",
keywords = "Aromatase inhibitors, Breast cancer, CORAL software, Data mining, QSAR, SMILES",
author = "Apilak Worachartcheewan and Prasit Mandi and Virapong Prachayasittikul and Toropova, {Alla P.} and Toropov, {Andrey A.} and Chanin Nantasenamat",
year = "2014",
month = "11",
day = "15",
doi = "10.1016/j.chemolab.2014.07.017",
language = "English",
volume = "138",
pages = "120--126",
journal = "Chemometrics and Intelligent Laboratory Systems",
issn = "0169-7439",
publisher = "Elsevier",

}

TY - JOUR

T1 - Large-scale QSAR study of aromatase inhibitors using SMILES-based descriptors

AU - Worachartcheewan, Apilak

AU - Mandi, Prasit

AU - Prachayasittikul, Virapong

AU - Toropova, Alla P.

AU - Toropov, Andrey A.

AU - Nantasenamat, Chanin

PY - 2014/11/15

Y1 - 2014/11/15

N2 - Aromatase inhibitors (AIs) represent a promising therapeutic class of anticancer agents against estrogen receptor-positive breast cancer. Bioactivity data on pIC50 of 973 AIs were employed in the construction of quantitative structure-activity relationship (QSAR) models using COR relation And Logic (CORAL) software (http://www.insilico.eu/coral) in which molecular structures are represented by the simplified molecular input line entry system (SMILES) notation. Symbols inherently present in SMILES nomenclatures describe the presence of molecular fragments and therefore represent a facile approach that essentially eliminate the need to geometrically optimize molecular structures or the hassle of computing and selecting molecular descriptors. Predictive models were built in accordance with the OECD principles. Monte Carlo optimization of correlation weights of such molecular fragments provides pertinent information on structural constituents for correlating with the aromatase inhibitory activity. Results from different splits and data sub-sets indicated reliable models for predicting and interpreting the origins of aromatase inhibitory activities with the correlation coefficient (R2) and cross-validated correlation coefficient (Q2) in ranges of 0.6271-0.7083 and 0.6218-0.7024, respectively. Insights gained from constructed models could aid in the future design of aromatase inhibitors.

AB - Aromatase inhibitors (AIs) represent a promising therapeutic class of anticancer agents against estrogen receptor-positive breast cancer. Bioactivity data on pIC50 of 973 AIs were employed in the construction of quantitative structure-activity relationship (QSAR) models using COR relation And Logic (CORAL) software (http://www.insilico.eu/coral) in which molecular structures are represented by the simplified molecular input line entry system (SMILES) notation. Symbols inherently present in SMILES nomenclatures describe the presence of molecular fragments and therefore represent a facile approach that essentially eliminate the need to geometrically optimize molecular structures or the hassle of computing and selecting molecular descriptors. Predictive models were built in accordance with the OECD principles. Monte Carlo optimization of correlation weights of such molecular fragments provides pertinent information on structural constituents for correlating with the aromatase inhibitory activity. Results from different splits and data sub-sets indicated reliable models for predicting and interpreting the origins of aromatase inhibitory activities with the correlation coefficient (R2) and cross-validated correlation coefficient (Q2) in ranges of 0.6271-0.7083 and 0.6218-0.7024, respectively. Insights gained from constructed models could aid in the future design of aromatase inhibitors.

KW - Aromatase inhibitors

KW - Breast cancer

KW - CORAL software

KW - Data mining

KW - QSAR

KW - SMILES

UR - http://www.scopus.com/inward/record.url?scp=84906044145&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906044145&partnerID=8YFLogxK

U2 - 10.1016/j.chemolab.2014.07.017

DO - 10.1016/j.chemolab.2014.07.017

M3 - Article

AN - SCOPUS:84906044145

VL - 138

SP - 120

EP - 126

JO - Chemometrics and Intelligent Laboratory Systems

JF - Chemometrics and Intelligent Laboratory Systems

SN - 0169-7439

ER -