|
|
| Acesso ao texto completo restrito à biblioteca da Embrapa Gado de Corte. Para informações adicionais entre em contato com cnpgc.biblioteca@embrapa.br. |
Registro Completo |
Biblioteca(s): |
Embrapa Gado de Corte. |
Data corrente: |
04/01/2023 |
Data da última atualização: |
04/01/2023 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
SANTANA, T. E. Z.; SILVA, J. C. F.; SILVA, L. O. C. da; ALVARENGA, A. B.; MENEZES, G. R. de O.; TORRES JUNIOR, R. A. de A.; DUARTE, M. de S.; SILVA, F. F. e. |
Afiliação: |
TALITA ESTEFANI ZUNINO SANTANA, UNIVERSIDADE FEDERAL DE VIÇOSA; JOSE CLEYDSON F. SILVA, UNIVERSIDADE FEDERAL DE VIÇOSA; LUIZ OTAVIO CAMPOS DA SILVA, CNPGC; AMANDA BOTELHO ALVARENGA, PURDUE UNIVERSITY; GILBERTO ROMEIRO DE OLIVEIRA MENEZE, CNPGC; ROBERTO AUGUSTO DE A TORRES JUNIOR, CNPGC; MARCIO DE SOUZA DUARTE, UNIVERSITY GUELPH; FABYANO FONSECA E SILVA, UNIVERSIDADE FEDERAL DE VIÇOSA. |
Título: |
Genome-enabled classification of stayability in Nellore cattle under a machine learning framework. |
Ano de publicação: |
2022 |
Fonte/Imprenta: |
Livestock Science, v. 260, article 104935, 2022. |
ISSN: |
1871-1413 |
DOI: |
https://doi.org/10.1016/j.livsci.2022.104935 |
Idioma: |
Inglês |
Conteúdo: |
Stayability (STAY) is a binary trait with significant value economically. It measures both the cow`s reproductive performance and longevity simultaneously. Thus, STAY is one of the most important female selection criterion in Nellore beef cattle breeding programs. The "success" for STAY is defined as the ability of a cow to stay in the herd up to 76 months of age and to have at least three calve. Despite its importance, STAY has not been investigated under a machine learning (ML) framework, which might allow to intuitively capture linear and nonlinear relationships (e.g., non-additive effects) between a response variable and other predictor variables. In this study, we compared different ML tools using a genome-enabled approach to classify daughters (non-genotyped animals but with STAY records) of genotyped sires. In total, 44,626 STAY records from daughters of 559 bulls genotyped with the 777K SNP panel were available for this study. The genotyped data were subdivided into three SNP sets based on the top-ranked effect on STAY: 1K-, 3K-, and 5K-SNP panels. The following ML algorithms were evaluated: AdaBoost (ADA), Naïve Bayes (NB), Decision Tree (DT), Deep Neural Network (DNN), k-Nearest Neighbors (NN), Multi-Layer Perceptron Neural Network (MLP), and Support Vector Machine (SVM). The analyses were performed using free Scikit-learn for the Python programming language. No relevant improvements in the learning process of the evaluated algorithms were observed when the number of SNPs in the genotype dataset was increased (i.e., 1K-, 3K-, or 5K-SNP panel). In short, NB outperformed the other algorithms considering, for example, the balanced accuracy (0.62 ± 0.01) and sensitivity (0.56 ± 0.02) metrics. In conclusion, the use of the 1K-SNP panel allowed efficient genomic classification and the NB algorithm outperformed the other methods as indicated by various classification metrics. To best of our knowledge, this is the first study using ML and genome-enabled classification of STAY in beef cattle. MenosStayability (STAY) is a binary trait with significant value economically. It measures both the cow`s reproductive performance and longevity simultaneously. Thus, STAY is one of the most important female selection criterion in Nellore beef cattle breeding programs. The "success" for STAY is defined as the ability of a cow to stay in the herd up to 76 months of age and to have at least three calve. Despite its importance, STAY has not been investigated under a machine learning (ML) framework, which might allow to intuitively capture linear and nonlinear relationships (e.g., non-additive effects) between a response variable and other predictor variables. In this study, we compared different ML tools using a genome-enabled approach to classify daughters (non-genotyped animals but with STAY records) of genotyped sires. In total, 44,626 STAY records from daughters of 559 bulls genotyped with the 777K SNP panel were available for this study. The genotyped data were subdivided into three SNP sets based on the top-ranked effect on STAY: 1K-, 3K-, and 5K-SNP panels. The following ML algorithms were evaluated: AdaBoost (ADA), Naïve Bayes (NB), Decision Tree (DT), Deep Neural Network (DNN), k-Nearest Neighbors (NN), Multi-Layer Perceptron Neural Network (MLP), and Support Vector Machine (SVM). The analyses were performed using free Scikit-learn for the Python programming language. No relevant improvements in the learning process of the evaluated algorithms were observed when the number ... Mostrar Tudo |
Thesagro: |
Gado de Corte; Gado Nelore; Touro. |
Thesaurus Nal: |
Beef cattle; Bulls; Daughters; Genome; Genomics; Nellore. |
Categoria do assunto: |
-- |
Marc: |
LEADER 02992naa a2200337 a 4500 001 2150623 005 2023-01-04 008 2022 bl uuuu u00u1 u #d 022 $a1871-1413 024 7 $ahttps://doi.org/10.1016/j.livsci.2022.104935$2DOI 100 1 $aSANTANA, T. E. Z. 245 $aGenome-enabled classification of stayability in Nellore cattle under a machine learning framework.$h[electronic resource] 260 $c2022 520 $aStayability (STAY) is a binary trait with significant value economically. It measures both the cow`s reproductive performance and longevity simultaneously. Thus, STAY is one of the most important female selection criterion in Nellore beef cattle breeding programs. The "success" for STAY is defined as the ability of a cow to stay in the herd up to 76 months of age and to have at least three calve. Despite its importance, STAY has not been investigated under a machine learning (ML) framework, which might allow to intuitively capture linear and nonlinear relationships (e.g., non-additive effects) between a response variable and other predictor variables. In this study, we compared different ML tools using a genome-enabled approach to classify daughters (non-genotyped animals but with STAY records) of genotyped sires. In total, 44,626 STAY records from daughters of 559 bulls genotyped with the 777K SNP panel were available for this study. The genotyped data were subdivided into three SNP sets based on the top-ranked effect on STAY: 1K-, 3K-, and 5K-SNP panels. The following ML algorithms were evaluated: AdaBoost (ADA), Naïve Bayes (NB), Decision Tree (DT), Deep Neural Network (DNN), k-Nearest Neighbors (NN), Multi-Layer Perceptron Neural Network (MLP), and Support Vector Machine (SVM). The analyses were performed using free Scikit-learn for the Python programming language. No relevant improvements in the learning process of the evaluated algorithms were observed when the number of SNPs in the genotype dataset was increased (i.e., 1K-, 3K-, or 5K-SNP panel). In short, NB outperformed the other algorithms considering, for example, the balanced accuracy (0.62 ± 0.01) and sensitivity (0.56 ± 0.02) metrics. In conclusion, the use of the 1K-SNP panel allowed efficient genomic classification and the NB algorithm outperformed the other methods as indicated by various classification metrics. To best of our knowledge, this is the first study using ML and genome-enabled classification of STAY in beef cattle. 650 $aBeef cattle 650 $aBulls 650 $aDaughters 650 $aGenome 650 $aGenomics 650 $aNellore 650 $aGado de Corte 650 $aGado Nelore 650 $aTouro 700 1 $aSILVA, J. C. F. 700 1 $aSILVA, L. O. C. da 700 1 $aALVARENGA, A. B. 700 1 $aMENEZES, G. R. de O. 700 1 $aTORRES JUNIOR, R. A. de A. 700 1 $aDUARTE, M. de S. 700 1 $aSILVA, F. F. e 773 $tLivestock Science$gv. 260, article 104935, 2022.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Gado de Corte (CNPGC) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
Registro Completo
Biblioteca(s): |
Embrapa Pecuária Sudeste. |
Data corrente: |
29/11/2019 |
Data da última atualização: |
02/12/2020 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Circulação/Nível: |
A - 1 |
Autoria: |
SILVA, V. da; RAMOS, M.; GROENEN, M.; CROOIJMANS, R.; JOHANSSON, A.; REGITANO, L. C. de A.; COUTINHO, L.; ZIMMER, R.; WALDRON, L.; GEISTLINGER, L. |
Afiliação: |
Vinicius da Silva, Wageningen University and Research; Marcel Ramos, Swedish University of Agricultural Sciences; Martien Groenen, Wageningen University and Research; Richard Crooijmans, Wageningen University and Research; Anna Johansson, Swedish University of Agricultural Sciences; LUCIANA CORREIA DE ALMEIDA REGITANO, CPPSE; Luiz Coutinho, USP; Ralf Zimmer, Universität München; Levi Waldron, University of New York; Ludwig Geistlinger, University of New York. |
Título: |
CNVRanger: association analysis of CNVs with geneexpression and quantitative phenotypes. |
Ano de publicação: |
2020 |
Fonte/Imprenta: |
Bioinformatics, v. 36, n. 3, p. 972-973, 2020. |
DOI: |
10.1093/bioinformatics/btz632 |
Idioma: |
Inglês |
Conteúdo: |
Copy number variation (CNV) is a major type of structural genomic variation that is increasingly studied acrossdifferent species for association with diseases and production traits. Established protocols for experimental detection andcomputational inference of CNVs from SNP array and next-generation sequencing data are available. We present theCNVRangerR/Bioconductor package which implements a comprehensive toolbox for structured downstream analysis ofCNVs. This includes functionality for summarizing individual CNV calls across a population, assessing overlap with func-tional genomic regions, and genome-wide association analysis with gene expression and quantitative phenotypes. |
Palavras-Chave: |
Expressão gênica; Fenótipos quantitativos; Genomic hybridization; Quantitative phenotypes; Structural genomic. |
Categoria do assunto: |
G Melhoramento Genético |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/218623/1/CNVRanger.pdf
|
Marc: |
LEADER 01575naa a2200301 a 4500 001 2115536 005 2020-12-02 008 2020 bl uuuu u00u1 u #d 024 7 $a10.1093/bioinformatics/btz632$2DOI 100 1 $aSILVA, V. da 245 $aCNVRanger$bassociation analysis of CNVs with geneexpression and quantitative phenotypes.$h[electronic resource] 260 $c2020 520 $aCopy number variation (CNV) is a major type of structural genomic variation that is increasingly studied acrossdifferent species for association with diseases and production traits. Established protocols for experimental detection andcomputational inference of CNVs from SNP array and next-generation sequencing data are available. We present theCNVRangerR/Bioconductor package which implements a comprehensive toolbox for structured downstream analysis ofCNVs. This includes functionality for summarizing individual CNV calls across a population, assessing overlap with func-tional genomic regions, and genome-wide association analysis with gene expression and quantitative phenotypes. 653 $aExpressão gênica 653 $aFenótipos quantitativos 653 $aGenomic hybridization 653 $aQuantitative phenotypes 653 $aStructural genomic 700 1 $aRAMOS, M. 700 1 $aGROENEN, M. 700 1 $aCROOIJMANS, R. 700 1 $aJOHANSSON, A. 700 1 $aREGITANO, L. C. de A. 700 1 $aCOUTINHO, L. 700 1 $aZIMMER, R. 700 1 $aWALDRON, L. 700 1 $aGEISTLINGER, L. 773 $tBioinformatics$gv. 36, n. 3, p. 972-973, 2020.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Pecuária Sudeste (CPPSE) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
Expressão de busca inválida. Verifique!!! |
|
|