Modeling of structure-mutagenicity relationships: Counter propagation neural network approach using calculated structural descriptors

I. Valkova; M. Vračko; S. C. Basak

doi:10.1016/j.aca.2003.12.035

Modeling of structure-mutagenicity relationships: Counter propagation neural network approach using calculated structural descriptors

I. Valkova
, M. Vračko
, S. C. Basak

Research output: Contribution to journal › Article › peer-review

35 Scopus citations

Abstract

Counter propagation artificial neural network was applied for modeling the mutagenicity of 95 aromatic and heteroaromatic amines collected from the literature. Molecules were represented by topostructural, topochemical, geometrical and quantum chemical descriptors. A sphere exclusion algorithm was used for rational division of the dataset into training and test sets. The initial training set was improved by a step-wise inclusion of two outliers from the test set. Recall ability of the final model is good (R²=0.986) as well as prediction ability in respect to the test set (R²=0.816). Validity of the best model obtained in the study was confirmed by randomization test and test with exchanged training and test sets. Study demonstrated the capabilities of CP ANN in analyzing the similarities between compounds and identifying of outliers. It was shown that CP ANN is a powerful tool for modeling the structure-mutagenicity relationships of the compounds considered.

Original language	English (US)
Pages (from-to)	179-186
Number of pages	8
Journal	Analytica Chimica Acta
Volume	509
Issue number	2
DOIs	https://doi.org/10.1016/j.aca.2003.12.035
State	Published - May 3 2004
Externally published	Yes

Bibliographical note

Funding Information:
MV acknowledges the Ministry of Education, Science and Sport of R Slovenia for the financial support under contracts 034 0507 and 034 0508. IV acknowledges The European Union IMAGETOX Research Training Network (HPRN-CT-1999-00015). This is Contribution Number 355 from the Center for Water and the Environment of the Natural Resources Research Institute. Research reported in this paper was supported in part by Grant F49620-02-1-0138 from the United States Air Force and Cooperative Agreement Number 572112 from the Agency for Toxic Substances and Disease Registry.

Keywords

Aromatic amines
Counter propagation artificial neural network
Mutagenicity
QSAR

Publisher link

10.1016/j.aca.2003.12.035

Find It

Find It at U of M Libraries

Cite this

@article{61318e337f374595984be20d1be73dd5,

title = "Modeling of structure-mutagenicity relationships: Counter propagation neural network approach using calculated structural descriptors",

abstract = "Counter propagation artificial neural network was applied for modeling the mutagenicity of 95 aromatic and heteroaromatic amines collected from the literature. Molecules were represented by topostructural, topochemical, geometrical and quantum chemical descriptors. A sphere exclusion algorithm was used for rational division of the dataset into training and test sets. The initial training set was improved by a step-wise inclusion of two outliers from the test set. Recall ability of the final model is good (R2=0.986) as well as prediction ability in respect to the test set (R2=0.816). Validity of the best model obtained in the study was confirmed by randomization test and test with exchanged training and test sets. Study demonstrated the capabilities of CP ANN in analyzing the similarities between compounds and identifying of outliers. It was shown that CP ANN is a powerful tool for modeling the structure-mutagenicity relationships of the compounds considered.",

keywords = "Aromatic amines, Counter propagation artificial neural network, Mutagenicity, QSAR",

author = "I. Valkova and M. Vra{\v c}ko and Basak, \{S. C.\}",

note = "Funding Information: MV acknowledges the Ministry of Education, Science and Sport of R Slovenia for the financial support under contracts 034 0507 and 034 0508. IV acknowledges The European Union IMAGETOX Research Training Network (HPRN-CT-1999-00015). This is Contribution Number 355 from the Center for Water and the Environment of the Natural Resources Research Institute. Research reported in this paper was supported in part by Grant F49620-02-1-0138 from the United States Air Force and Cooperative Agreement Number 572112 from the Agency for Toxic Substances and Disease Registry.",

year = "2004",

month = may,

day = "3",

doi = "10.1016/j.aca.2003.12.035",

language = "English (US)",

volume = "509",

pages = "179--186",

journal = "Analytica Chimica Acta",

issn = "0003-2670",

publisher = "Elsevier B.V.",

number = "2",

}

TY - JOUR

T1 - Modeling of structure-mutagenicity relationships

T2 - Counter propagation neural network approach using calculated structural descriptors

AU - Valkova, I.

AU - Vračko, M.

AU - Basak, S. C.

N1 - Funding Information: MV acknowledges the Ministry of Education, Science and Sport of R Slovenia for the financial support under contracts 034 0507 and 034 0508. IV acknowledges The European Union IMAGETOX Research Training Network (HPRN-CT-1999-00015). This is Contribution Number 355 from the Center for Water and the Environment of the Natural Resources Research Institute. Research reported in this paper was supported in part by Grant F49620-02-1-0138 from the United States Air Force and Cooperative Agreement Number 572112 from the Agency for Toxic Substances and Disease Registry.

PY - 2004/5/3

Y1 - 2004/5/3

N2 - Counter propagation artificial neural network was applied for modeling the mutagenicity of 95 aromatic and heteroaromatic amines collected from the literature. Molecules were represented by topostructural, topochemical, geometrical and quantum chemical descriptors. A sphere exclusion algorithm was used for rational division of the dataset into training and test sets. The initial training set was improved by a step-wise inclusion of two outliers from the test set. Recall ability of the final model is good (R2=0.986) as well as prediction ability in respect to the test set (R2=0.816). Validity of the best model obtained in the study was confirmed by randomization test and test with exchanged training and test sets. Study demonstrated the capabilities of CP ANN in analyzing the similarities between compounds and identifying of outliers. It was shown that CP ANN is a powerful tool for modeling the structure-mutagenicity relationships of the compounds considered.

AB - Counter propagation artificial neural network was applied for modeling the mutagenicity of 95 aromatic and heteroaromatic amines collected from the literature. Molecules were represented by topostructural, topochemical, geometrical and quantum chemical descriptors. A sphere exclusion algorithm was used for rational division of the dataset into training and test sets. The initial training set was improved by a step-wise inclusion of two outliers from the test set. Recall ability of the final model is good (R2=0.986) as well as prediction ability in respect to the test set (R2=0.816). Validity of the best model obtained in the study was confirmed by randomization test and test with exchanged training and test sets. Study demonstrated the capabilities of CP ANN in analyzing the similarities between compounds and identifying of outliers. It was shown that CP ANN is a powerful tool for modeling the structure-mutagenicity relationships of the compounds considered.

KW - Aromatic amines

KW - Counter propagation artificial neural network

KW - Mutagenicity

KW - QSAR

UR - https://www.scopus.com/pages/publications/1542509348

UR - https://www.scopus.com/pages/publications/1542509348#tab=citedBy

U2 - 10.1016/j.aca.2003.12.035

DO - 10.1016/j.aca.2003.12.035

M3 - Article

AN - SCOPUS:1542509348

SN - 0003-2670

VL - 509

SP - 179

EP - 186

JO - Analytica Chimica Acta

JF - Analytica Chimica Acta

IS - 2

ER -

Modeling of structure-mutagenicity relationships: Counter propagation neural network approach using calculated structural descriptors

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this