PREDICTION OF PHENOTYPIC AND GENOTYPIC VALUES BY BLUP/GWS AND NEURAL NETWORKS

Detalhes bibliográficos
Autor(a) principal: Coutinho, Alisson Esdras
Data de Publicação: 2018
Outros Autores: Neder, Diogo Gonçalves, Silva, Mairykon Coêlho da, Arcelino, Eliane Cristina, Brito, Silvan Gomes de, Carvalho Filho, José Luiz Sandes de
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Revista Caatinga
Texto Completo: https://periodicos.ufersa.edu.br/caatinga/article/view/6501
Resumo: Genome-wide selection (GWS) uses simultaneously the effect of the thousands markers covering the entire genome to predict genomic breeding values for individuals under selection. The possible benefits of GWS are the reduction of the breeding cycle, increase in gains per unit of time, and decrease of costs. However, the success of the GWS is dependent on the choice of the method to predict the effects of markers. Thus, the objective of this work was to predict genomic breeding values (GEBV) through artificial neural networks (ANN), based on the estimation of the effect of the markers, compared to the Ridge Regression-Best Linear Unbiased Predictor/Genome Wide Selection (RR-BLUP/GWS). Simulations were performed by software R to provide correlations concerning ANN and RR-BLUP/GWS. The prediction methods were evaluated using correlations between phenotypic and genotypic values and predicted GEBV. The results showed the superiority of the ANN in predicting GEBV in simulations with higher and lower marker densities, with higher levels of linkage disequilibrium and heritability.
id UFERSA-1_ff1cf050a97a91da43dfde3759c6f098
oai_identifier_str oai:ojs.periodicos.ufersa.edu.br:article/6501
network_acronym_str UFERSA-1
network_name_str Revista Caatinga
repository_id_str
spelling PREDICTION OF PHENOTYPIC AND GENOTYPIC VALUES BY BLUP/GWS AND NEURAL NETWORKSPREDIÇÃO DE VALORES FENOTÍPICOS E GENOTÍPICOS VIA RR-BLUP/GWS E REDES NEURAISPlant breeding. Correlation. Molecular markers.Melhoramento genético. Correlação. Marcadores moleculares.Genome-wide selection (GWS) uses simultaneously the effect of the thousands markers covering the entire genome to predict genomic breeding values for individuals under selection. The possible benefits of GWS are the reduction of the breeding cycle, increase in gains per unit of time, and decrease of costs. However, the success of the GWS is dependent on the choice of the method to predict the effects of markers. Thus, the objective of this work was to predict genomic breeding values (GEBV) through artificial neural networks (ANN), based on the estimation of the effect of the markers, compared to the Ridge Regression-Best Linear Unbiased Predictor/Genome Wide Selection (RR-BLUP/GWS). Simulations were performed by software R to provide correlations concerning ANN and RR-BLUP/GWS. The prediction methods were evaluated using correlations between phenotypic and genotypic values and predicted GEBV. The results showed the superiority of the ANN in predicting GEBV in simulations with higher and lower marker densities, with higher levels of linkage disequilibrium and heritability.A seleção genômica ampla (Genome Wide Selection - GWS) utiliza simultaneamente o efeito de milhares de marcadores cobrindo todo o genoma para predizer o valor genético genômico dos indivíduos no processo de seleção. Os possíveis benefícios de seu uso são a redução do ciclo de melhoramento, propiciando maior ganho por unidade de tempo e diminuição de custos. O sucesso da GWS está atrelado a escolha do método de predição dos efeitos dos marcadores. Assim, neste trabalho, visou-se aplicar as redes neurais artificiais (Artificial Neural Networks - ANNs), com a finalidade de predizer os valores genéticos genômicos (Genomic Breeding Values - GEBVs) baseado na estimação dos efeitos dos marcadores comparados a regressão de cumeeira – melhor preditor não viesado/seleção genômica ampla (Ridge Regression – Best Linear Unbiased Predictor/Genome Wide Selection – RR-BLUP/GWS). Foram efetuadas simulações por meio do software R, fornecendo as correlações referentes às ANNs e a RR-BLUP/GWS. Os métodos de predição foram avaliados utilizando correlações entre o valor fenotípico e valor genotípico com o valor genético genômico predito. Os resultados demonstraram superioridade das ANNs na predição dos GEBVs nos cenários com maior e menor densidade de marcadores, paralelo a níveis mais altos de desequilíbrio de ligação e maior herdabilidade.Universidade Federal Rural do Semi-Árido2018-05-28info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://periodicos.ufersa.edu.br/caatinga/article/view/650110.1590/1983-21252018v31n301rcREVISTA CAATINGA; Vol. 31 No. 3 (2018); 532-540Revista Caatinga; v. 31 n. 3 (2018); 532-5401983-21250100-316Xreponame:Revista Caatingainstname:Universidade Federal Rural do Semi-Árido (UFERSA)instacron:UFERSAenghttps://periodicos.ufersa.edu.br/caatinga/article/view/6501/pdfCopyright (c) 2018 Revista Caatingainfo:eu-repo/semantics/openAccessCoutinho, Alisson EsdrasNeder, Diogo GonçalvesSilva, Mairykon Coêlho daArcelino, Eliane CristinaBrito, Silvan Gomes deCarvalho Filho, José Luiz Sandes de2023-07-20T13:08:02Zoai:ojs.periodicos.ufersa.edu.br:article/6501Revistahttps://periodicos.ufersa.edu.br/index.php/caatinga/indexPUBhttps://periodicos.ufersa.edu.br/index.php/caatinga/oaipatricio@ufersa.edu.br|| caatinga@ufersa.edu.br1983-21250100-316Xopendoar:2024-04-29T09:46:29.080219Revista Caatinga - Universidade Federal Rural do Semi-Árido (UFERSA)true
dc.title.none.fl_str_mv PREDICTION OF PHENOTYPIC AND GENOTYPIC VALUES BY BLUP/GWS AND NEURAL NETWORKS
PREDIÇÃO DE VALORES FENOTÍPICOS E GENOTÍPICOS VIA RR-BLUP/GWS E REDES NEURAIS
title PREDICTION OF PHENOTYPIC AND GENOTYPIC VALUES BY BLUP/GWS AND NEURAL NETWORKS
spellingShingle PREDICTION OF PHENOTYPIC AND GENOTYPIC VALUES BY BLUP/GWS AND NEURAL NETWORKS
Coutinho, Alisson Esdras
Plant breeding. Correlation. Molecular markers.
Melhoramento genético. Correlação. Marcadores moleculares.
title_short PREDICTION OF PHENOTYPIC AND GENOTYPIC VALUES BY BLUP/GWS AND NEURAL NETWORKS
title_full PREDICTION OF PHENOTYPIC AND GENOTYPIC VALUES BY BLUP/GWS AND NEURAL NETWORKS
title_fullStr PREDICTION OF PHENOTYPIC AND GENOTYPIC VALUES BY BLUP/GWS AND NEURAL NETWORKS
title_full_unstemmed PREDICTION OF PHENOTYPIC AND GENOTYPIC VALUES BY BLUP/GWS AND NEURAL NETWORKS
title_sort PREDICTION OF PHENOTYPIC AND GENOTYPIC VALUES BY BLUP/GWS AND NEURAL NETWORKS
author Coutinho, Alisson Esdras
author_facet Coutinho, Alisson Esdras
Neder, Diogo Gonçalves
Silva, Mairykon Coêlho da
Arcelino, Eliane Cristina
Brito, Silvan Gomes de
Carvalho Filho, José Luiz Sandes de
author_role author
author2 Neder, Diogo Gonçalves
Silva, Mairykon Coêlho da
Arcelino, Eliane Cristina
Brito, Silvan Gomes de
Carvalho Filho, José Luiz Sandes de
author2_role author
author
author
author
author
dc.contributor.author.fl_str_mv Coutinho, Alisson Esdras
Neder, Diogo Gonçalves
Silva, Mairykon Coêlho da
Arcelino, Eliane Cristina
Brito, Silvan Gomes de
Carvalho Filho, José Luiz Sandes de
dc.subject.por.fl_str_mv Plant breeding. Correlation. Molecular markers.
Melhoramento genético. Correlação. Marcadores moleculares.
topic Plant breeding. Correlation. Molecular markers.
Melhoramento genético. Correlação. Marcadores moleculares.
description Genome-wide selection (GWS) uses simultaneously the effect of the thousands markers covering the entire genome to predict genomic breeding values for individuals under selection. The possible benefits of GWS are the reduction of the breeding cycle, increase in gains per unit of time, and decrease of costs. However, the success of the GWS is dependent on the choice of the method to predict the effects of markers. Thus, the objective of this work was to predict genomic breeding values (GEBV) through artificial neural networks (ANN), based on the estimation of the effect of the markers, compared to the Ridge Regression-Best Linear Unbiased Predictor/Genome Wide Selection (RR-BLUP/GWS). Simulations were performed by software R to provide correlations concerning ANN and RR-BLUP/GWS. The prediction methods were evaluated using correlations between phenotypic and genotypic values and predicted GEBV. The results showed the superiority of the ANN in predicting GEBV in simulations with higher and lower marker densities, with higher levels of linkage disequilibrium and heritability.
publishDate 2018
dc.date.none.fl_str_mv 2018-05-28
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://periodicos.ufersa.edu.br/caatinga/article/view/6501
10.1590/1983-21252018v31n301rc
url https://periodicos.ufersa.edu.br/caatinga/article/view/6501
identifier_str_mv 10.1590/1983-21252018v31n301rc
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv https://periodicos.ufersa.edu.br/caatinga/article/view/6501/pdf
dc.rights.driver.fl_str_mv Copyright (c) 2018 Revista Caatinga
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2018 Revista Caatinga
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidade Federal Rural do Semi-Árido
publisher.none.fl_str_mv Universidade Federal Rural do Semi-Árido
dc.source.none.fl_str_mv REVISTA CAATINGA; Vol. 31 No. 3 (2018); 532-540
Revista Caatinga; v. 31 n. 3 (2018); 532-540
1983-2125
0100-316X
reponame:Revista Caatinga
instname:Universidade Federal Rural do Semi-Árido (UFERSA)
instacron:UFERSA
instname_str Universidade Federal Rural do Semi-Árido (UFERSA)
instacron_str UFERSA
institution UFERSA
reponame_str Revista Caatinga
collection Revista Caatinga
repository.name.fl_str_mv Revista Caatinga - Universidade Federal Rural do Semi-Árido (UFERSA)
repository.mail.fl_str_mv patricio@ufersa.edu.br|| caatinga@ufersa.edu.br
_version_ 1797674026606264320

Registros relacionados