| |
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Florestas. Para informações adicionais entre em contato com cnpf.biblioteca@embrapa.br. |
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Florestas. |
|
Data corrente: |
18/01/2017 |
|
Data da última atualização: |
18/01/2017 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
GLÓRIA, L. S.; CRUZ, C. D.; VIEIRA, R. A. M.; RESENDE, M. D. V. de; LOPES, P. S.; SIQUEIRA, O. H. G. B. D. de; SILVA, F. F. e. |
|
Afiliação: |
Leonardo Siqueira Glória, UFV; Cosme Damião Cruz, UFV; Ricardo Augusto Mendonça Vieira, Universidade Estadual do Norte Fluminense; MARCOS DEON VILELA DE RESENDE, CNPF; Paulo Sávio Lopes, UFV; Otávio H. G. B. Dias de Siqueira, UFV; Fabyano Fonseca e Silva, UFV. |
|
Título: |
Accessing marker effects and heritability estimates from genome prediction by Bayesian regularized neural networks. |
|
Ano de publicação: |
2016 |
|
Fonte/Imprenta: |
Livestock Science, v. 191, p. 91-96, Sept. 2016. |
|
DOI: |
http://dx.doi.org/10.1016/j.livsci.2016.07.015 |
|
Idioma: |
Inglês |
|
Conteúdo: |
Recently, there is an increasing interest on semi- and non-parametric methods for genome-enabled prediction, among which the Bayesian regularized artificial neural networks (BRANN) stand. We aimed to evaluate the predictive performance of BRANN and to exploit SNP effects and heritability estimates using two different approaches (relative importance-RI, and relative contribution-RC). Additionally, we aimed also to compare BRANN with the traditional RR-BLUP and BLASSO by using simulated datasets. The simplest BRANN (net1), RR-BLUP and BLASSO methods outperformed other more parameterized BRANN (net2, net3, ? net6) in terms of predictive ability. For both simulated traits (Y1 and Y2) the net1 provided the best h2 estimates (0.33 for both, being the true h2=0.35), whereas RR-BLUP (0.18 and 0.22 for Y1 and Y2, respectively) and BLASSO (0.20 and 0.26 for Y1 and Y2, respectively) underestimated h2. The marker effects estimated from net1 (using RI and RC approaches) and RR-BLUP were similar, but the shrinkage strength was remarkable for BLASSO on both traits. For Y1, the correlation between the true fifty QTL effects and the effects estimated for the SNPs located in the same QTL positions were 0.61, 0.60, 0.60 and 0.55, for RI, RC, RR-BLUP and BLASSO; and for Y2, these correlations were 0.81, 0.81, 0.81 and 0.71, respectively. In summary, we believe that estimates of SNP effects are promising quantitative tools to bring discussions on chromosome regions contributing most effectively to the phenotype expression when using ANN for genomic predictions. MenosRecently, there is an increasing interest on semi- and non-parametric methods for genome-enabled prediction, among which the Bayesian regularized artificial neural networks (BRANN) stand. We aimed to evaluate the predictive performance of BRANN and to exploit SNP effects and heritability estimates using two different approaches (relative importance-RI, and relative contribution-RC). Additionally, we aimed also to compare BRANN with the traditional RR-BLUP and BLASSO by using simulated datasets. The simplest BRANN (net1), RR-BLUP and BLASSO methods outperformed other more parameterized BRANN (net2, net3, ? net6) in terms of predictive ability. For both simulated traits (Y1 and Y2) the net1 provided the best h2 estimates (0.33 for both, being the true h2=0.35), whereas RR-BLUP (0.18 and 0.22 for Y1 and Y2, respectively) and BLASSO (0.20 and 0.26 for Y1 and Y2, respectively) underestimated h2. The marker effects estimated from net1 (using RI and RC approaches) and RR-BLUP were similar, but the shrinkage strength was remarkable for BLASSO on both traits. For Y1, the correlation between the true fifty QTL effects and the effects estimated for the SNPs located in the same QTL positions were 0.61, 0.60, 0.60 and 0.55, for RI, RC, RR-BLUP and BLASSO; and for Y2, these correlations were 0.81, 0.81, 0.81 and 0.71, respectively. In summary, we believe that estimates of SNP effects are promising quantitative tools to bring discussions on chromosome regions contributing most effectively ... Mostrar Tudo |
|
Palavras-Chave: |
Genetic parameters; QTL; Redes neurais. |
|
Thesagro: |
Parâmetro Genético. |
|
Thesaurus Nal: |
Marker-assisted selection; Neural networks. |
|
Categoria do assunto: |
G Melhoramento Genético |
|
Marc: |
LEADER 02443naa a2200277 a 4500
001 2061138
005 2017-01-18
008 2016 bl uuuu u00u1 u #d
024 7 $ahttp://dx.doi.org/10.1016/j.livsci.2016.07.015$2DOI
100 1 $aGLÓRIA, L. S.
245 $aAccessing marker effects and heritability estimates from genome prediction by Bayesian regularized neural networks.$h[electronic resource]
260 $c2016
520 $aRecently, there is an increasing interest on semi- and non-parametric methods for genome-enabled prediction, among which the Bayesian regularized artificial neural networks (BRANN) stand. We aimed to evaluate the predictive performance of BRANN and to exploit SNP effects and heritability estimates using two different approaches (relative importance-RI, and relative contribution-RC). Additionally, we aimed also to compare BRANN with the traditional RR-BLUP and BLASSO by using simulated datasets. The simplest BRANN (net1), RR-BLUP and BLASSO methods outperformed other more parameterized BRANN (net2, net3, ? net6) in terms of predictive ability. For both simulated traits (Y1 and Y2) the net1 provided the best h2 estimates (0.33 for both, being the true h2=0.35), whereas RR-BLUP (0.18 and 0.22 for Y1 and Y2, respectively) and BLASSO (0.20 and 0.26 for Y1 and Y2, respectively) underestimated h2. The marker effects estimated from net1 (using RI and RC approaches) and RR-BLUP were similar, but the shrinkage strength was remarkable for BLASSO on both traits. For Y1, the correlation between the true fifty QTL effects and the effects estimated for the SNPs located in the same QTL positions were 0.61, 0.60, 0.60 and 0.55, for RI, RC, RR-BLUP and BLASSO; and for Y2, these correlations were 0.81, 0.81, 0.81 and 0.71, respectively. In summary, we believe that estimates of SNP effects are promising quantitative tools to bring discussions on chromosome regions contributing most effectively to the phenotype expression when using ANN for genomic predictions.
650 $aMarker-assisted selection
650 $aNeural networks
650 $aParâmetro Genético
653 $aGenetic parameters
653 $aQTL
653 $aRedes neurais
700 1 $aCRUZ, C. D.
700 1 $aVIEIRA, R. A. M.
700 1 $aRESENDE, M. D. V. de
700 1 $aLOPES, P. S.
700 1 $aSIQUEIRA, O. H. G. B. D. de
700 1 $aSILVA, F. F. e
773 $tLivestock Science$gv. 191, p. 91-96, Sept. 2016.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Florestas (CNPF) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 2 | |
| 1. |  | CARDOZO FILHO, J. de L.; MONTEIRO, R. do N.; SILVA, L. P. da; BLOCH JUNIOR, C.; STÁBELI, R. G.; CALDERON, L. de A. Identification of a phylloseptin from Amazon Phyllomedusa palliata(Anura: Hylidae) by Maldi TOT/TOF MS. In: CONGRESSO DA SOCIEDADE BRASILEIRA DE TOXINOLOGIA, 11., 2010, Araxá. Toxinas naturais: conhecimento atual e novos desafios. [S.l.]: Sociedade Brasileira de Toxinologia, 2010. Pôster.| Tipo: Resumo em Anais de Congresso |
| Biblioteca(s): Embrapa Recursos Genéticos e Biotecnologia. |
|    |
| 2. | | CARDOZO FILHO, J. de L.; SOARES, A. A.; SILVA, L. P. da; MONTEIRO, J. R. do N.; ALVES, S. C. de L.; SILVA, R. S.; KAYANO, A. M.; BLOCH JUNIOR, C.; STÁBELI, R. G.; CALDERON, L. de A. Identification of peptides from Amazon Leptodactylus knudseni (Anura: Leptodactylidae) by Maldi TOF/TOF MS. In: CONGRESSO DA SOCIEDADE BRASILEIRA DE TOXINOLOGIA, 11., 2010, Araxá. Toxinas naturais: conhecimento atual e novos desafios. [S.l.]: Sociedade Brasileira de Toxinologia, 2010. Pôster.| Tipo: Resumo em Anais de Congresso |
| Biblioteca(s): Embrapa Recursos Genéticos e Biotecnologia. |
| |
| Registros recuperados : 2 | |
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
