| |
|
|
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Café. |
|
Data corrente: |
16/05/2022 |
|
Data da última atualização: |
16/05/2022 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
SOUSA, I. C. de; NASCIMENTO, M.; SANT’ANNA, I. de C.; CAIXETA, E. T.; AZEVEDO, C. F.; CRUZ, C. D.; SILVA, F. L. da; ALKIMIM, E. R.; NASCIMENTO, A. C. C.; SERÃO, N. V. L. |
|
Afiliação: |
ITHALO COELHO DE SOUSA, IOWA STATE UNIVERSITY; MOYSÉS NASCIMENTO, UFV; ISABELA DE CASTRO SANT’ANNA, IAC; EVELINE TEIXEIRA CAIXETA MOURA, CNPCa; CAMILA FERREIRA AZEVEDO, UFV; COSME DAMIÃO CRUZ, UFV; FELIPE LOPES DA SILVA, UFV; EMILLY RUAS ALKIMIM, UFMT; ANA CAROLINA CAMPANA NASCIMENTO, UFV; NICK VERGARA LOPES SERÃO, IOWA STATE UNIVERSITY. |
|
Título: |
Marker effects and heritability estimates using additive-dominance genomic architectures via artificial neural networks in Coffea canephora. |
|
Ano de publicação: |
2022 |
|
Fonte/Imprenta: |
Plos One, v. 17, n.1, e0262055, 2022. |
|
DOI: |
https://doi.org/10.1371/journal.pone.0262055 |
|
Idioma: |
Inglês |
|
Conteúdo: |
Many methodologies are used to predict the genetic merit in animals and plants, but some of them require priori assumptions that may increase the complexity of the model. Artificial neural network (ANN) has advantage to not require priori assumptions about the relationships between inputs and the output allowing great flexibility to handle different types of complex non-additive effects, such as dominance and epistasis. Despite this advantage, the biological interpretability of ANNs is still limited. The aim of this research was to estimate the heritability and markers effects for two traits in Coffea canephora using an additive-dominance architecture ANN and to compare it with genomic best linear unbiased prediction (GBLUP). The data used consists of 51 clones of C. canephora varietal Conilon, 32 of varietal group Robusta and 82 intervarietal hybrids. From this, 165 phenotyped individuals were genotyped for 14,387 SNPs. Due to the high computational cost of ANNs, we used Bagging decision tree to reduce the dimensionality of the data, selecting the markers that accumulated 70% of the total importance. An ANN with three hidden layers was run, each varying from 1 to 40 neurons summing 64,000 neural networks. The network architectures with the best predictive ability were selected. The best architectures were composed by 4, 15, and 33 neurons in the first, second and third hidden layers, respectively, for yield, and by 13, 20, and 24 neurons, respectively for rust resistance. The predictive ability was greater when using ANN with three hidden layers than using one hidden layer and GBLUP, with 0.72 and 0.88 for yield and coffee leaf rust resistance, respectively. The concordance rate (CR) of the 10% larger markers effects among the methods varied between 10% and 13.8%, for additive effects and between 5.4% and 11.9% for dominance effects. The narrow-sense (h2a ) and dominance-only (h2a ) heritability estimates were 0.25 and 0.06, respectively, for yield, and 0.67 and 0.03, respectively for rust resistance. The ANN was able to estimate the heritabilities from an additive-dominance genomic architectures and the ANN with three hidden layers obtained best predictive ability when compared with those obtained from GBLUP and ANN with one hidden layer. MenosMany methodologies are used to predict the genetic merit in animals and plants, but some of them require priori assumptions that may increase the complexity of the model. Artificial neural network (ANN) has advantage to not require priori assumptions about the relationships between inputs and the output allowing great flexibility to handle different types of complex non-additive effects, such as dominance and epistasis. Despite this advantage, the biological interpretability of ANNs is still limited. The aim of this research was to estimate the heritability and markers effects for two traits in Coffea canephora using an additive-dominance architecture ANN and to compare it with genomic best linear unbiased prediction (GBLUP). The data used consists of 51 clones of C. canephora varietal Conilon, 32 of varietal group Robusta and 82 intervarietal hybrids. From this, 165 phenotyped individuals were genotyped for 14,387 SNPs. Due to the high computational cost of ANNs, we used Bagging decision tree to reduce the dimensionality of the data, selecting the markers that accumulated 70% of the total importance. An ANN with three hidden layers was run, each varying from 1 to 40 neurons summing 64,000 neural networks. The network architectures with the best predictive ability were selected. The best architectures were composed by 4, 15, and 33 neurons in the first, second and third hidden layers, respectively, for yield, and by 13, 20, and 24 neurons, respectively for rust resistance. T... Mostrar Tudo |
|
Palavras-Chave: |
Rede neural artificial. |
|
Thesagro: |
Coffea Canephora; Marcador Genético. |
|
Thesaurus Nal: |
Dominance (genetics); Neural networks. |
|
Categoria do assunto: |
-- |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/doc/1143026/1/Marker-effects-and-heritability.pdf
|
|
Marc: |
LEADER 03240naa a2200301 a 4500
001 2143026
005 2022-05-16
008 2022 bl uuuu u00u1 u #d
024 7 $ahttps://doi.org/10.1371/journal.pone.0262055$2DOI
100 1 $aSOUSA, I. C. de
245 $aMarker effects and heritability estimates using additive-dominance genomic architectures via artificial neural networks in Coffea canephora.$h[electronic resource]
260 $c2022
520 $aMany methodologies are used to predict the genetic merit in animals and plants, but some of them require priori assumptions that may increase the complexity of the model. Artificial neural network (ANN) has advantage to not require priori assumptions about the relationships between inputs and the output allowing great flexibility to handle different types of complex non-additive effects, such as dominance and epistasis. Despite this advantage, the biological interpretability of ANNs is still limited. The aim of this research was to estimate the heritability and markers effects for two traits in Coffea canephora using an additive-dominance architecture ANN and to compare it with genomic best linear unbiased prediction (GBLUP). The data used consists of 51 clones of C. canephora varietal Conilon, 32 of varietal group Robusta and 82 intervarietal hybrids. From this, 165 phenotyped individuals were genotyped for 14,387 SNPs. Due to the high computational cost of ANNs, we used Bagging decision tree to reduce the dimensionality of the data, selecting the markers that accumulated 70% of the total importance. An ANN with three hidden layers was run, each varying from 1 to 40 neurons summing 64,000 neural networks. The network architectures with the best predictive ability were selected. The best architectures were composed by 4, 15, and 33 neurons in the first, second and third hidden layers, respectively, for yield, and by 13, 20, and 24 neurons, respectively for rust resistance. The predictive ability was greater when using ANN with three hidden layers than using one hidden layer and GBLUP, with 0.72 and 0.88 for yield and coffee leaf rust resistance, respectively. The concordance rate (CR) of the 10% larger markers effects among the methods varied between 10% and 13.8%, for additive effects and between 5.4% and 11.9% for dominance effects. The narrow-sense (h2a ) and dominance-only (h2a ) heritability estimates were 0.25 and 0.06, respectively, for yield, and 0.67 and 0.03, respectively for rust resistance. The ANN was able to estimate the heritabilities from an additive-dominance genomic architectures and the ANN with three hidden layers obtained best predictive ability when compared with those obtained from GBLUP and ANN with one hidden layer.
650 $aDominance (genetics)
650 $aNeural networks
650 $aCoffea Canephora
650 $aMarcador Genético
653 $aRede neural artificial
700 1 $aNASCIMENTO, M.
700 1 $aSANT’ANNA, I. de C.
700 1 $aCAIXETA, E. T.
700 1 $aAZEVEDO, C. F.
700 1 $aCRUZ, C. D.
700 1 $aSILVA, F. L. da
700 1 $aALKIMIM, E. R.
700 1 $aNASCIMENTO, A. C. C.
700 1 $aSERÃO, N. V. L.
773 $tPlos One$gv. 17, n.1, e0262055, 2022.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Café (CNPCa) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
Registro Completo
|
Biblioteca(s): |
Embrapa Cerrados; Embrapa Unidades Centrais. |
|
Data corrente: |
04/01/2016 |
|
Data da última atualização: |
29/02/2016 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Circulação/Nível: |
B - 1 |
|
Autoria: |
SOUZA, L. M. de; SOUSA, D. M. G. de; REIS JUNIOR, F. B. dos; MENDES, I. de C. |
|
Afiliação: |
LEANDRO MORAES DE SOUZA, UNB; DJALMA MARTINHAO GOMES DE SOUSA, CPAC; FABIO BUENO DOS REIS JUNIOR, CPAC; IEDA DE CARVALHO MENDES, CPAC. |
|
Título: |
Carbono da biomassa microbiana em Latossolos determinado por oxidação úmida e combustão a temperatura elevada. |
|
Complemento do título: |
Microbial biomass carbon in Oxisol determined by wet oxidation and combustion at high temperature |
|
Ano de publicação: |
2015 |
|
Fonte/Imprenta: |
Pesquisa Agropecuária Brasileira, Brasília, DF, v. 50, n. 11, p. 1061-1070, nov. 2015. |
|
Idioma: |
Português |
|
Conteúdo: |
O objetivo deste trabalho foi avaliar as relações entre os métodos de oxidação úmida e combustão a alta temperatura, utilizados em determinações do carbono da biomassa microbiana, e verificar a necessidade do uso de fatores de correção entre os dois métodos. Foram utilizadas 96 amostras de solo, coletadas à profundidade de 0?10 cm em Latossolos Vermelhos argilosos de Cerrado, sob cultivos anuais, pastagens, eucalipto e vegetação nativa. O carbono da biomassa microbiana foi determinado a partir de extratos de K2 SO4, pelo método de fumigação?extração, por meio de oxidação úmida com dicromato de potássio com aquecimento externo, e por combustão a alta temperatura em analisador de C orgânico total. Observou?se relação linear positiva e significativa entre os teores de C orgânico determinados pelos dois métodos. O método de combustão a alta temperatura detecta, em média, 6,3% mais C orgânico do que o método por oxidação úmida. |
|
Palavras-Chave: |
Analisador de carbono; Bioindicador; Bioindictors; Carbon anayzer; Carbono orgânico; Fumigação-extração; Fumigation-extraction; Organic carbon. |
|
Thesaurus NAL: |
Soil quality. |
|
Categoria do assunto: |
-- |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/137906/1/Djalma-Carbono-da-biomassa.pdf
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/136532/1/Carbono-da-biomassa.pdf
|
|
Marc: |
LEADER 01807naa a2200265 a 4500
001 2035360
005 2016-02-29
008 2015 bl uuuu u00u1 u #d
100 1 $aSOUZA, L. M. de
245 $aCarbono da biomassa microbiana em Latossolos determinado por oxidação úmida e combustão a temperatura elevada.
260 $c2015
520 $aO objetivo deste trabalho foi avaliar as relações entre os métodos de oxidação úmida e combustão a alta temperatura, utilizados em determinações do carbono da biomassa microbiana, e verificar a necessidade do uso de fatores de correção entre os dois métodos. Foram utilizadas 96 amostras de solo, coletadas à profundidade de 0?10 cm em Latossolos Vermelhos argilosos de Cerrado, sob cultivos anuais, pastagens, eucalipto e vegetação nativa. O carbono da biomassa microbiana foi determinado a partir de extratos de K2 SO4, pelo método de fumigação?extração, por meio de oxidação úmida com dicromato de potássio com aquecimento externo, e por combustão a alta temperatura em analisador de C orgânico total. Observou?se relação linear positiva e significativa entre os teores de C orgânico determinados pelos dois métodos. O método de combustão a alta temperatura detecta, em média, 6,3% mais C orgânico do que o método por oxidação úmida.
650 $aSoil quality
653 $aAnalisador de carbono
653 $aBioindicador
653 $aBioindictors
653 $aCarbon anayzer
653 $aCarbono orgânico
653 $aFumigação-extração
653 $aFumigation-extraction
653 $aOrganic carbon
700 1 $aSOUSA, D. M. G. de
700 1 $aREIS JUNIOR, F. B. dos
700 1 $aMENDES, I. de C.
773 $tPesquisa Agropecuária Brasileira, Brasília, DF$gv. 50, n. 11, p. 1061-1070, nov. 2015.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Cerrados (CPAC) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
