Quantitative structure-antibacterial activity relationship modeling using a combination of piecewise linear regression-discriminant analysis (I): Quantum chemical, topographic, and topological descriptors

E. Estrada, Enrique Molina, Delvin Nodarse, Luis A. Torres, Humberto Gonzalez, Eugenio Uriarte

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Time-dependent antibacterial activity of 2-furylethylenes using quantum chemical, topographic, and topological indices is described as inhibition of respiration in E. coli. A QSAR strategy based on the combination of the linear piecewise regression and the discriminant analysis is used to predict the biological activity values of strong and moderates antibacterial furylethylenes. The breakpoint in the values of the biological activity was detected. The biological activities of the compounds are described by two linear regression equations. A discriminant analysis is carried out to classify the compounds in one of the biological activity two groups. The results showed using different kind of descriptors were compared. In all cases the piecewise linear regression - discriminant analysis (PLR-DA) method produced significantly better QSAR models than the linear regression analysis. The QSAR models were validated using an external validation previously extracted from the original data. A prediction of reported antibacterial activity analysis was carried out showing dependence between the probability of a good classification and the experimental antibacterial activity. Statistical parameters showed the quality of quantum-chemical descriptors based models prediction in LDA having an accuracy of 0.9 and a C of 0.9. The best PLR-DA model explains more than 92% of the variance of experimental activity. Models with best prediction results were those based on quantum-chemical descriptors. An interpretation of quantum-chemical descriptors entered in models was carried out
LanguageEnglish
Pages1856-1871
Number of pages15
JournalInternational Journal of Quantum Chemistry
Volume108
Issue number10
DOIs
Publication statusPublished - 2008

Fingerprint

Discriminant analysis
Linear regression
regression analysis
activity (biology)
Bioactivity
predictions
respiration
Regression analysis
Escherichia coli

Keywords

  • QSAR
  • LMR
  • piecewise regression
  • LDA
  • topological indices
  • topographic indices
  • quantum chemical descriptors
  • antibacterial activity

Cite this

@article{5f4b2683ba8c44fc9585a03e583d7e31,
title = "Quantitative structure-antibacterial activity relationship modeling using a combination of piecewise linear regression-discriminant analysis (I): Quantum chemical, topographic, and topological descriptors",
abstract = "Time-dependent antibacterial activity of 2-furylethylenes using quantum chemical, topographic, and topological indices is described as inhibition of respiration in E. coli. A QSAR strategy based on the combination of the linear piecewise regression and the discriminant analysis is used to predict the biological activity values of strong and moderates antibacterial furylethylenes. The breakpoint in the values of the biological activity was detected. The biological activities of the compounds are described by two linear regression equations. A discriminant analysis is carried out to classify the compounds in one of the biological activity two groups. The results showed using different kind of descriptors were compared. In all cases the piecewise linear regression - discriminant analysis (PLR-DA) method produced significantly better QSAR models than the linear regression analysis. The QSAR models were validated using an external validation previously extracted from the original data. A prediction of reported antibacterial activity analysis was carried out showing dependence between the probability of a good classification and the experimental antibacterial activity. Statistical parameters showed the quality of quantum-chemical descriptors based models prediction in LDA having an accuracy of 0.9 and a C of 0.9. The best PLR-DA model explains more than 92{\%} of the variance of experimental activity. Models with best prediction results were those based on quantum-chemical descriptors. An interpretation of quantum-chemical descriptors entered in models was carried out",
keywords = "QSAR, LMR, piecewise regression, LDA, topological indices, topographic indices, quantum chemical descriptors, antibacterial activity",
author = "E. Estrada and Enrique Molina and Delvin Nodarse and Torres, {Luis A.} and Humberto Gonzalez and Eugenio Uriarte",
year = "2008",
doi = "10.1002/qua.21702",
language = "English",
volume = "108",
pages = "1856--1871",
journal = "International Journal of Quantum Chemistry",
issn = "0020-7608",
number = "10",

}

Quantitative structure-antibacterial activity relationship modeling using a combination of piecewise linear regression-discriminant analysis (I): Quantum chemical, topographic, and topological descriptors. / Estrada, E.; Molina, Enrique; Nodarse, Delvin; Torres, Luis A.; Gonzalez, Humberto; Uriarte, Eugenio.

In: International Journal of Quantum Chemistry, Vol. 108, No. 10, 2008, p. 1856-1871.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Quantitative structure-antibacterial activity relationship modeling using a combination of piecewise linear regression-discriminant analysis (I): Quantum chemical, topographic, and topological descriptors

AU - Estrada, E.

AU - Molina, Enrique

AU - Nodarse, Delvin

AU - Torres, Luis A.

AU - Gonzalez, Humberto

AU - Uriarte, Eugenio

PY - 2008

Y1 - 2008

N2 - Time-dependent antibacterial activity of 2-furylethylenes using quantum chemical, topographic, and topological indices is described as inhibition of respiration in E. coli. A QSAR strategy based on the combination of the linear piecewise regression and the discriminant analysis is used to predict the biological activity values of strong and moderates antibacterial furylethylenes. The breakpoint in the values of the biological activity was detected. The biological activities of the compounds are described by two linear regression equations. A discriminant analysis is carried out to classify the compounds in one of the biological activity two groups. The results showed using different kind of descriptors were compared. In all cases the piecewise linear regression - discriminant analysis (PLR-DA) method produced significantly better QSAR models than the linear regression analysis. The QSAR models were validated using an external validation previously extracted from the original data. A prediction of reported antibacterial activity analysis was carried out showing dependence between the probability of a good classification and the experimental antibacterial activity. Statistical parameters showed the quality of quantum-chemical descriptors based models prediction in LDA having an accuracy of 0.9 and a C of 0.9. The best PLR-DA model explains more than 92% of the variance of experimental activity. Models with best prediction results were those based on quantum-chemical descriptors. An interpretation of quantum-chemical descriptors entered in models was carried out

AB - Time-dependent antibacterial activity of 2-furylethylenes using quantum chemical, topographic, and topological indices is described as inhibition of respiration in E. coli. A QSAR strategy based on the combination of the linear piecewise regression and the discriminant analysis is used to predict the biological activity values of strong and moderates antibacterial furylethylenes. The breakpoint in the values of the biological activity was detected. The biological activities of the compounds are described by two linear regression equations. A discriminant analysis is carried out to classify the compounds in one of the biological activity two groups. The results showed using different kind of descriptors were compared. In all cases the piecewise linear regression - discriminant analysis (PLR-DA) method produced significantly better QSAR models than the linear regression analysis. The QSAR models were validated using an external validation previously extracted from the original data. A prediction of reported antibacterial activity analysis was carried out showing dependence between the probability of a good classification and the experimental antibacterial activity. Statistical parameters showed the quality of quantum-chemical descriptors based models prediction in LDA having an accuracy of 0.9 and a C of 0.9. The best PLR-DA model explains more than 92% of the variance of experimental activity. Models with best prediction results were those based on quantum-chemical descriptors. An interpretation of quantum-chemical descriptors entered in models was carried out

KW - QSAR

KW - LMR

KW - piecewise regression

KW - LDA

KW - topological indices

KW - topographic indices

KW - quantum chemical descriptors

KW - antibacterial activity

UR - http://www3.interscience.wiley.com/journal/29830/home

UR - http://dx.doi.org/10.1002/qua.21702

U2 - 10.1002/qua.21702

DO - 10.1002/qua.21702

M3 - Article

VL - 108

SP - 1856

EP - 1871

JO - International Journal of Quantum Chemistry

T2 - International Journal of Quantum Chemistry

JF - International Journal of Quantum Chemistry

SN - 0020-7608

IS - 10

ER -