Prediction of toxicity and data exploratory analysis of estrogen-active endocrine disruptors using counter-propagation artificial neural networks
Samo za registrovane korisnike
2010
Članak u časopisu (Objavljena verzija)
![](/themes/MirageREDUN//images/creativecommons/arr.png)
Metapodaci
Prikaz svih podataka o dokumentuApstrakt
In this work, a novel algorithm for optimization of counter-propagation artificial neural networks has been used for development of quantitative structure-activity relationships model for prediction of the estrogenic activity of endocrine-disrupting chemicals. The search for the best model was performed using genetic algorithms. Genetic algorithms were used not only for selection of the most suitable descriptors for modeling, but also for automatic adjustment of their relative importance. Using our recently developed algorithm for automatic adjustment of the relative importance of the input variables, we have developed simple models with very good generalization performances using only few interpretable descriptors. One of the developed models is in details discussed in this article. The simplicity of the chosen descriptors and their relative importance for this model helped us in performing a detailed data exploratory analysis which gave us an insight in the structural features requir...ed for the activity of the estrogenic endocrine-disrupting chemicals.
Ključne reči:
SAR / QSAR / Estrogenic activity prediction / Endocrine disruptors toxicity / Data exploratory analysis / Counter-propagation artificial neural networksIzvor:
Journal of Molecular Graphics & Modelling, 2010, 29, 3, 450-460Izdavač:
- ELSEVIER SCIENCE INC, NEW YORK
DOI: 10.1016/j.jmgm.2010.09.001
ISSN: 1093-3263
PubMed: 20952233
WoS: 000285402500017
Scopus: 2-s2.0-78649522324
Institucija/grupa
Fakultet za studije bezbednostiTY - JOUR AU - Stojić, Nataša AU - Erić, Slavica AU - Kuzmanovski, Igor PY - 2010 UR - https://redun.educons.edu.rs/handle/123456789/64 AB - In this work, a novel algorithm for optimization of counter-propagation artificial neural networks has been used for development of quantitative structure-activity relationships model for prediction of the estrogenic activity of endocrine-disrupting chemicals. The search for the best model was performed using genetic algorithms. Genetic algorithms were used not only for selection of the most suitable descriptors for modeling, but also for automatic adjustment of their relative importance. Using our recently developed algorithm for automatic adjustment of the relative importance of the input variables, we have developed simple models with very good generalization performances using only few interpretable descriptors. One of the developed models is in details discussed in this article. The simplicity of the chosen descriptors and their relative importance for this model helped us in performing a detailed data exploratory analysis which gave us an insight in the structural features required for the activity of the estrogenic endocrine-disrupting chemicals. PB - ELSEVIER SCIENCE INC, NEW YORK T2 - Journal of Molecular Graphics & Modelling T1 - Prediction of toxicity and data exploratory analysis of estrogen-active endocrine disruptors using counter-propagation artificial neural networks EP - 460 IS - 3 SP - 450 VL - 29 DO - 10.1016/j.jmgm.2010.09.001 UR - conv_718 ER -
@article{ author = "Stojić, Nataša and Erić, Slavica and Kuzmanovski, Igor", year = "2010", abstract = "In this work, a novel algorithm for optimization of counter-propagation artificial neural networks has been used for development of quantitative structure-activity relationships model for prediction of the estrogenic activity of endocrine-disrupting chemicals. The search for the best model was performed using genetic algorithms. Genetic algorithms were used not only for selection of the most suitable descriptors for modeling, but also for automatic adjustment of their relative importance. Using our recently developed algorithm for automatic adjustment of the relative importance of the input variables, we have developed simple models with very good generalization performances using only few interpretable descriptors. One of the developed models is in details discussed in this article. The simplicity of the chosen descriptors and their relative importance for this model helped us in performing a detailed data exploratory analysis which gave us an insight in the structural features required for the activity of the estrogenic endocrine-disrupting chemicals.", publisher = "ELSEVIER SCIENCE INC, NEW YORK", journal = "Journal of Molecular Graphics & Modelling", title = "Prediction of toxicity and data exploratory analysis of estrogen-active endocrine disruptors using counter-propagation artificial neural networks", pages = "460-450", number = "3", volume = "29", doi = "10.1016/j.jmgm.2010.09.001", url = "conv_718" }
Stojić, N., Erić, S.,& Kuzmanovski, I.. (2010). Prediction of toxicity and data exploratory analysis of estrogen-active endocrine disruptors using counter-propagation artificial neural networks. in Journal of Molecular Graphics & Modelling ELSEVIER SCIENCE INC, NEW YORK., 29(3), 450-460. https://doi.org/10.1016/j.jmgm.2010.09.001 conv_718
Stojić N, Erić S, Kuzmanovski I. Prediction of toxicity and data exploratory analysis of estrogen-active endocrine disruptors using counter-propagation artificial neural networks. in Journal of Molecular Graphics & Modelling. 2010;29(3):450-460. doi:10.1016/j.jmgm.2010.09.001 conv_718 .
Stojić, Nataša, Erić, Slavica, Kuzmanovski, Igor, "Prediction of toxicity and data exploratory analysis of estrogen-active endocrine disruptors using counter-propagation artificial neural networks" in Journal of Molecular Graphics & Modelling, 29, no. 3 (2010):450-460, https://doi.org/10.1016/j.jmgm.2010.09.001 ., conv_718 .