|
|
Registro Completo |
Biblioteca(s): |
Embrapa Arroz e Feijão; Embrapa Cerrados. |
Data corrente: |
05/05/2021 |
Data da última atualização: |
14/05/2021 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
LOPES, F. B.; MAGNABOSCO, C. de U.; PASSAFARO, T. L.; BRUNES, L. C.; COSTA, M. F. O. e; EIFERT, E. da C.; NARCISO, M. G.; ROSA, G. J. M.; LOBO, R. B.; BALDI, F. |
Afiliação: |
CLAUDIO DE ULHOA MAGNABOSCO, CPAC; MARCOS FERNANDO OLIVEIRA E COSTA, CNPAF; EDUARDO DA COSTA EIFERT, CPAC; MARCELO GONCALVES NARCISO, CNPAF. |
Título: |
Improving genomic prediction accuracy for meat tenderness in Nellore cattle using artificial neural networks. |
Ano de publicação: |
2020 |
Fonte/Imprenta: |
Journal of Animal Breeding and Genetics, v. 137, n. 5, 2020. |
Páginas: |
p. 438-448 |
Idioma: |
Inglês |
Conteúdo: |
The goal of this study was to compare the predictive performance of artificial neural networks (ANNs) with Bayesian ridge regression, Bayesian Lasso, Bayes A, Bayes B and Bayes Cπ in estimating genomic breeding values for meat tenderness in Nellore cattle. The animals were genotyped with the Illumina Bovine HD Bead Chip (HD, 777K from 90 samples) and the GeneSeek Genomic Profiler (GGP Indicus HD, 77K from 485 samples). The quality control for the genotypes was applied on each Chip and comprised removal of SNPs located on non‐autosomal chromosomes, with minor allele frequency <5%, deviation from HWE (p < 10?6), and with linkage disequilibrium >0.8. The FImpute program was used for genotype imputation. Pedigree‐based analyses indicated that meat tenderness is moderately heritable (0.35), indicating that it can be improved by direct selection. Prediction accuracies were very similar across the Bayesian regression models, ranging from 0.20 (Bayes A) to 0.22 (Bayes B) and 0.14 (Bayes Cπ) to 0.19 (Bayes A) for the additive and dominance effects, respectively. ANN achieved the highest accuracy (0.33) of genomic prediction of genetic merit. Even though deep neural networks are recognized to deliver more accurate predictions, in our study ANN with one single hidden layer, 105 neurons and rectified linear unit (ReLU) activation function was sufficient to increase the prediction of genetic merit for meat tenderness. These results indicate that an ANN with relatively simple architecture can provide superior genomic predictions for meat tenderness in Nellore cattle MenosThe goal of this study was to compare the predictive performance of artificial neural networks (ANNs) with Bayesian ridge regression, Bayesian Lasso, Bayes A, Bayes B and Bayes Cπ in estimating genomic breeding values for meat tenderness in Nellore cattle. The animals were genotyped with the Illumina Bovine HD Bead Chip (HD, 777K from 90 samples) and the GeneSeek Genomic Profiler (GGP Indicus HD, 77K from 485 samples). The quality control for the genotypes was applied on each Chip and comprised removal of SNPs located on non‐autosomal chromosomes, with minor allele frequency <5%, deviation from HWE (p < 10?6), and with linkage disequilibrium >0.8. The FImpute program was used for genotype imputation. Pedigree‐based analyses indicated that meat tenderness is moderately heritable (0.35), indicating that it can be improved by direct selection. Prediction accuracies were very similar across the Bayesian regression models, ranging from 0.20 (Bayes A) to 0.22 (Bayes B) and 0.14 (Bayes Cπ) to 0.19 (Bayes A) for the additive and dominance effects, respectively. ANN achieved the highest accuracy (0.33) of genomic prediction of genetic merit. Even though deep neural networks are recognized to deliver more accurate predictions, in our study ANN with one single hidden layer, 105 neurons and rectified linear unit (ReLU) activation function was sufficient to increase the prediction of genetic merit for meat tenderness. These results indicate that an ANN with relative... Mostrar Tudo |
Palavras-Chave: |
Bayesian regression models; Carne macia; Deep learning; Genomic selection; Maciez da carne. |
Thesagro: |
Carne; Gado de Corte; Genética Animal; Seleção Genética. |
Thesaurus Nal: |
Animal breeding; Zebu. |
Categoria do assunto: |
-- L Ciência Animal e Produtos de Origem Animal |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/223045/1/Magnabosco-Improving-genomic-prediction-accuracy-for-meat-tenderness-in.pdf
|
Marc: |
LEADER 02672naa a2200373 a 4500 001 2131678 005 2021-05-14 008 2020 bl uuuu u00u1 u #d 100 1 $aLOPES, F. B. 245 $aImproving genomic prediction accuracy for meat tenderness in Nellore cattle using artificial neural networks.$h[electronic resource] 260 $c2020 300 $ap. 438-448 520 $aThe goal of this study was to compare the predictive performance of artificial neural networks (ANNs) with Bayesian ridge regression, Bayesian Lasso, Bayes A, Bayes B and Bayes Cπ in estimating genomic breeding values for meat tenderness in Nellore cattle. The animals were genotyped with the Illumina Bovine HD Bead Chip (HD, 777K from 90 samples) and the GeneSeek Genomic Profiler (GGP Indicus HD, 77K from 485 samples). The quality control for the genotypes was applied on each Chip and comprised removal of SNPs located on non‐autosomal chromosomes, with minor allele frequency <5%, deviation from HWE (p < 10?6), and with linkage disequilibrium >0.8. The FImpute program was used for genotype imputation. Pedigree‐based analyses indicated that meat tenderness is moderately heritable (0.35), indicating that it can be improved by direct selection. Prediction accuracies were very similar across the Bayesian regression models, ranging from 0.20 (Bayes A) to 0.22 (Bayes B) and 0.14 (Bayes Cπ) to 0.19 (Bayes A) for the additive and dominance effects, respectively. ANN achieved the highest accuracy (0.33) of genomic prediction of genetic merit. Even though deep neural networks are recognized to deliver more accurate predictions, in our study ANN with one single hidden layer, 105 neurons and rectified linear unit (ReLU) activation function was sufficient to increase the prediction of genetic merit for meat tenderness. These results indicate that an ANN with relatively simple architecture can provide superior genomic predictions for meat tenderness in Nellore cattle 650 $aAnimal breeding 650 $aZebu 650 $aCarne 650 $aGado de Corte 650 $aGenética Animal 650 $aSeleção Genética 653 $aBayesian regression models 653 $aCarne macia 653 $aDeep learning 653 $aGenomic selection 653 $aMaciez da carne 700 1 $aMAGNABOSCO, C. de U. 700 1 $aPASSAFARO, T. L. 700 1 $aBRUNES, L. C. 700 1 $aCOSTA, M. F. O. e 700 1 $aEIFERT, E. da C. 700 1 $aNARCISO, M. G. 700 1 $aROSA, G. J. M. 700 1 $aLOBO, R. B. 700 1 $aBALDI, F. 773 $tJournal of Animal Breeding and Genetics$gv. 137, n. 5, 2020.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Cerrados (CPAC) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
Registro Completo
Biblioteca(s): |
Embrapa Solos. |
Data corrente: |
04/11/2022 |
Data da última atualização: |
08/11/2022 |
Tipo da produção científica: |
Documentos |
Autoria: |
COELHO, M. R.; VASQUES, G. M. |
Afiliação: |
MAURICIO RIZZATO COELHO, CNPS; GUSTAVO DE MATTOS VASQUES, CNPS. |
Título: |
Importância e potencial de mapas de atributos do solo em apoio à formulação e implementação de políticas públicas no Brasil: uma revisão. |
Ano de publicação: |
2022 |
Fonte/Imprenta: |
Rio de Janeiro: Embrapa Solos, 2022. |
Descrição Física: |
E-book: il. color. |
Série: |
(Embrapa Solos. Documentos, 234). |
ISSN: |
1517-2627 |
Idioma: |
Português |
Notas: |
E-book no formato ePub. ODS 2. |
Conteúdo: |
O presente trabalho visa contribuir para o PronaSolos, de forma modesta e sem nenhuma intenção de exaurir o tema, discutindo questões relacionadas à importância e uso potencial dos mapas de atributos do solo em apoio à elaboração e execução de políticas, programas e planos do governo brasileiro, atuais e vindouros, nos temas relacionados a solos. Para tal, mostra como tais questões foram abordadas nas mais recentes literaturas internacionais preocupadas em disponibilizar dados e informações de solos para especialistas e não especialistas no tema a fim de apoiar políticas públicas e garantir a sustentabilidade do planeta. |
Palavras-Chave: |
Atributos do solo; PronaSolos; Selo ODS 2. |
Thesagro: |
Água do Solo; Carbono; Condutividade Eletrica; Mapa; Ph; Políticas Públicas; Solo; Textura do Solo. |
Thesaurus NAL: |
Public policy; Soil map. |
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/242264/1/CNPS-DOC-234-2022.epub
|
Marc: |
LEADER 01607nam a2200325 a 4500 001 2148030 005 2022-11-08 008 2022 bl uuuu u0uu1 u #d 022 $a1517-2627 100 1 $aCOELHO, M. R. 245 $aImportância e potencial de mapas de atributos do solo em apoio à formulação e implementação de políticas públicas no Brasil$buma revisão.$h[electronic resource] 260 $aRio de Janeiro: Embrapa Solos$c2022 300 $cE-book: il. color. 490 $a(Embrapa Solos. Documentos, 234). 500 $aE-book no formato ePub. ODS 2. 520 $aO presente trabalho visa contribuir para o PronaSolos, de forma modesta e sem nenhuma intenção de exaurir o tema, discutindo questões relacionadas à importância e uso potencial dos mapas de atributos do solo em apoio à elaboração e execução de políticas, programas e planos do governo brasileiro, atuais e vindouros, nos temas relacionados a solos. Para tal, mostra como tais questões foram abordadas nas mais recentes literaturas internacionais preocupadas em disponibilizar dados e informações de solos para especialistas e não especialistas no tema a fim de apoiar políticas públicas e garantir a sustentabilidade do planeta. 650 $aPublic policy 650 $aSoil map 650 $aÁgua do Solo 650 $aCarbono 650 $aCondutividade Eletrica 650 $aMapa 650 $aPh 650 $aPolíticas Públicas 650 $aSolo 650 $aTextura do Solo 653 $aAtributos do solo 653 $aPronaSolos 653 $aSelo ODS 2 700 1 $aVASQUES, G. M.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Solos (CNPS) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
Expressão de busca inválida. Verifique!!! |
|
|