Quantitative Structure-Activity Relationship study for pesticides by means of classification techniques

Autores
Cárdenas, Fernando; Tripaldi, Piercosimo; Rojas Villa, Cristian Xavier
Año de publicación
2014
Idioma
español castellano
Tipo de recurso
artículo
Estado
versión publicada
Descripción
The aim of this work was the comparison between k-Nearest Neighbors (k-NN) and Counterpropagation Artificial Neural network (CP-ANN) classification methods for modeling the toxicity of a set of 192 organochlorinated, organophosphates, carbamates, and pyrethroid pesticides measured as effective concentration (EC50). The EC50 values were divided into three classes, i.e. low, intermediate, and high toxicity. The 4885 molecular descriptors were calculated using the Dragon software, and then were simultaneously analyzed through k-NN classification analysis coupled with Genetic Algorithms - Variable Subset Selection (GA-VSS) technique. The models were properly validated through an external test set of compounds. The results clearly suggest that 3D-descriptors did not offer relevant information for modeling the classes. On the other hand, k-NN showed better results than CP-ANN.
El objetivo de este trabajo fue la comparación entre los métodos de clasificación del vecino más cercano (k-NN) y las redes neuronales artificiales de contrapropagación (CP-ANN) para modelar la toxicidad de un conjunto de 192 pesticidas organoclorados, organofosforados, carbamatos y piretroides, medidos como Concentración Efectiva (EC50) y que fueron divididos en tres clases, es decir, baja, intermedia y alta toxicidad. Se calcularon 4885 descriptores moleculares usando el programa DRAGON, los que fueron simultáneamente analizados mediante el método k-NN acoplado con la técnica de selección de variables de los Algoritmos Genéticos (GA-VSS). Los modelos fueron apropiadamente validados mediante un subconjunto de predicción. Los resultados claramente sugieren que los descriptores 3D no ofrecen información relevante para modelar las clases. Por otro lado, k-NN muestra mejores resultados que CP-ANN.
Instituto de Investigaciones Fisicoquímicas Teóricas y Aplicadas
Materia
Química
Pesticides
k-NN
CP-ANN
GA-VSS
QSAR Theory
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/4.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/112921
Acceder
id SEDICI_724d701f8340001f2fbe99350fc519d0
oai_identifier_str oai:sedici.unlp.edu.ar:10915/112921
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Quantitative Structure-Activity Relationship study for pesticides by means of classification techniquesEstudio de la Relación Cuantitativa Estructura-Actividad de pesticidas mediante técnicas de clasificaciónCárdenas, FernandoTripaldi, PiercosimoRojas Villa, Cristian XavierQuímicaPesticidesk-NNCP-ANNGA-VSSQSAR TheoryThe aim of this work was the comparison between k-Nearest Neighbors (k-NN) and Counterpropagation Artificial Neural network (CP-ANN) classification methods for modeling the toxicity of a set of 192 organochlorinated, organophosphates, carbamates, and pyrethroid pesticides measured as effective concentration (EC50). The EC50 values were divided into three classes, i.e. low, intermediate, and high toxicity. The 4885 molecular descriptors were calculated using the Dragon software, and then were simultaneously analyzed through k-NN classification analysis coupled with Genetic Algorithms - Variable Subset Selection (GA-VSS) technique. The models were properly validated through an external test set of compounds. The results clearly suggest that 3D-descriptors did not offer relevant information for modeling the classes. On the other hand, k-NN showed better results than CP-ANN.El objetivo de este trabajo fue la comparación entre los métodos de clasificación del vecino más cercano (k-NN) y las redes neuronales artificiales de contrapropagación (CP-ANN) para modelar la toxicidad de un conjunto de 192 pesticidas organoclorados, organofosforados, carbamatos y piretroides, medidos como Concentración Efectiva (EC50) y que fueron divididos en tres clases, es decir, baja, intermedia y alta toxicidad. Se calcularon 4885 descriptores moleculares usando el programa DRAGON, los que fueron simultáneamente analizados mediante el método k-NN acoplado con la técnica de selección de variables de los Algoritmos Genéticos (GA-VSS). Los modelos fueron apropiadamente validados mediante un subconjunto de predicción. Los resultados claramente sugieren que los descriptores 3D no ofrecen información relevante para modelar las clases. Por otro lado, k-NN muestra mejores resultados que CP-ANN.Instituto de Investigaciones Fisicoquímicas Teóricas y Aplicadas2014info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionArticulohttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfA19-A30http://sedici.unlp.edu.ar/handle/10915/112921spainfo:eu-repo/semantics/altIdentifier/url/https://revistas.usfq.edu.ec/index.php/avances/article/view/169info:eu-repo/semantics/altIdentifier/issn/1390-5384info:eu-repo/semantics/altIdentifier/doi/10.18272/aci.v6i2.169info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-10-22T17:07:13Zoai:sedici.unlp.edu.ar:10915/112921Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-10-22 17:07:13.571SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Quantitative Structure-Activity Relationship study for pesticides by means of classification techniques
Estudio de la Relación Cuantitativa Estructura-Actividad de pesticidas mediante técnicas de clasificación
title Quantitative Structure-Activity Relationship study for pesticides by means of classification techniques
spellingShingle Quantitative Structure-Activity Relationship study for pesticides by means of classification techniques
Cárdenas, Fernando
Química
Pesticides
k-NN
CP-ANN
GA-VSS
QSAR Theory
title_short Quantitative Structure-Activity Relationship study for pesticides by means of classification techniques
title_full Quantitative Structure-Activity Relationship study for pesticides by means of classification techniques
title_fullStr Quantitative Structure-Activity Relationship study for pesticides by means of classification techniques
title_full_unstemmed Quantitative Structure-Activity Relationship study for pesticides by means of classification techniques
title_sort Quantitative Structure-Activity Relationship study for pesticides by means of classification techniques
dc.creator.none.fl_str_mv Cárdenas, Fernando
Tripaldi, Piercosimo
Rojas Villa, Cristian Xavier
author Cárdenas, Fernando
author_facet Cárdenas, Fernando
Tripaldi, Piercosimo
Rojas Villa, Cristian Xavier
author_role author
author2 Tripaldi, Piercosimo
Rojas Villa, Cristian Xavier
author2_role author
author
dc.subject.none.fl_str_mv Química
Pesticides
k-NN
CP-ANN
GA-VSS
QSAR Theory
topic Química
Pesticides
k-NN
CP-ANN
GA-VSS
QSAR Theory
dc.description.none.fl_txt_mv The aim of this work was the comparison between k-Nearest Neighbors (k-NN) and Counterpropagation Artificial Neural network (CP-ANN) classification methods for modeling the toxicity of a set of 192 organochlorinated, organophosphates, carbamates, and pyrethroid pesticides measured as effective concentration (EC50). The EC50 values were divided into three classes, i.e. low, intermediate, and high toxicity. The 4885 molecular descriptors were calculated using the Dragon software, and then were simultaneously analyzed through k-NN classification analysis coupled with Genetic Algorithms - Variable Subset Selection (GA-VSS) technique. The models were properly validated through an external test set of compounds. The results clearly suggest that 3D-descriptors did not offer relevant information for modeling the classes. On the other hand, k-NN showed better results than CP-ANN.
El objetivo de este trabajo fue la comparación entre los métodos de clasificación del vecino más cercano (k-NN) y las redes neuronales artificiales de contrapropagación (CP-ANN) para modelar la toxicidad de un conjunto de 192 pesticidas organoclorados, organofosforados, carbamatos y piretroides, medidos como Concentración Efectiva (EC50) y que fueron divididos en tres clases, es decir, baja, intermedia y alta toxicidad. Se calcularon 4885 descriptores moleculares usando el programa DRAGON, los que fueron simultáneamente analizados mediante el método k-NN acoplado con la técnica de selección de variables de los Algoritmos Genéticos (GA-VSS). Los modelos fueron apropiadamente validados mediante un subconjunto de predicción. Los resultados claramente sugieren que los descriptores 3D no ofrecen información relevante para modelar las clases. Por otro lado, k-NN muestra mejores resultados que CP-ANN.
Instituto de Investigaciones Fisicoquímicas Teóricas y Aplicadas
description The aim of this work was the comparison between k-Nearest Neighbors (k-NN) and Counterpropagation Artificial Neural network (CP-ANN) classification methods for modeling the toxicity of a set of 192 organochlorinated, organophosphates, carbamates, and pyrethroid pesticides measured as effective concentration (EC50). The EC50 values were divided into three classes, i.e. low, intermediate, and high toxicity. The 4885 molecular descriptors were calculated using the Dragon software, and then were simultaneously analyzed through k-NN classification analysis coupled with Genetic Algorithms - Variable Subset Selection (GA-VSS) technique. The models were properly validated through an external test set of compounds. The results clearly suggest that 3D-descriptors did not offer relevant information for modeling the classes. On the other hand, k-NN showed better results than CP-ANN.
publishDate 2014
dc.date.none.fl_str_mv 2014
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Articulo
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/112921
url http://sedici.unlp.edu.ar/handle/10915/112921
dc.language.none.fl_str_mv spa
language spa
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://revistas.usfq.edu.ec/index.php/avances/article/view/169
info:eu-repo/semantics/altIdentifier/issn/1390-5384
info:eu-repo/semantics/altIdentifier/doi/10.18272/aci.v6i2.169
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.format.none.fl_str_mv application/pdf
A19-A30
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1846783374798094336
score 12.982451

Publicaciones similares