Prediction of Phenotypic and Genotypic Values by Blup/GWS and Neural Networks

Coutinho, Alisson Esdras; Neder, Diogo Gonçalves; Silva, Mairykon Coelho da; Arcelino, Eliane Cristina; Brito, Silvan Gomes de; Filho, José Luiz Sandes de Carvalho

doi:10.1590/1983-21252018v31n301rc

Cited by 6 publications

(4 citation statements)

References 29 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The adverse effect of lower heritability on selective accuracy in several scenarios has been proven in previous studies that used the RR‐BLUP (Coutinho et al., 2018; Moura et al., 2019), BayesB methods (Moura et al., 2019), BO (Ghafouri‐Kesbi et al., 2017), RF (Ghafouri‐Kesbi et al., 2017), RBF (Sant'Anna et al., 2020), and MLP methods (Coutinho et al., 2018). Guo et al.…”

Section: Resultsmentioning

confidence: 89%

Genome‐enabled prediction through machine learning methods considering different levels of trait complexity

et al. 2021

View full text Add to dashboard Cite

Genomic‐wide selection (GWS) consists of the use of a large number of molecular markers for the prediction of genetic values and has been shown to be highly relevant for genetic improvement. The objective of this work was to evaluate and compare the predictive performance of statistical (ridge regression‐best linear unbiased predictor [RR‐BLUP] and BayesB) and machine learning methods through GWS in simulated populations with traits presenting different levels of heritability and quantitative trait loci (QTL) numbers in the presence of dominant and epistatic effects. The simulated genome of population F2 was formed by 1,000 individuals and genotyped with 2,010 single nucleotide polymorphism (SNP) markers. Twenty‐six traits were simulated considering QTL numbers ranging from two to 88 and heritabilities of .3 and .6. The selective and predictive performances were evaluated using the multilayer perceptron (MLP), radial basis function (RBF), decision trees (DT), bagging (BA), random forest (RF), and boosting (BO) machine learning models and the classical RR‐BLUP and BayesB methods. A high effect of heritability was observed for the results of selective accuracy when compared to the increased QTL number. In addition, the selective accuracy based on the number of QTL demonstrates that the application of alternative machine learning models, such as RBF, BA, BO, and RF, can be suitable for the analysis according to QTL number. Machine learning methods are powerful tools for predicting genetic values with epistatic gene control in traits with different degrees of heritability and different numbers of controlling genes.

show abstract

Section: Resultsmentioning

confidence: 89%

Genome‐enabled prediction through machine learning methods considering different levels of trait complexity

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The importance of ANN in genetic improvement is confirmed in other studies. Coutinho et al [44], by means of simulated data, compared the prediction methods by ANN and RR-BLUP /GS using correlations between the phenotypic value and genotypic value with the genomic estimated breeding value (GEBV). The results showed superiority of ANN in the prediction of GEBVs in the scenarios with higher and lower density of markers, parallel to higher levels of linkage disequilibrium and greater heritability.…”

Section: Discussionmentioning

confidence: 99%

Artificial Neural Networks in the Prediction of Genetic Merit to Flowering Traits in Bean Cultivars

Rosado

Cruz

Barili³

et al. 2020

Agriculture

View full text Add to dashboard Cite

Flowering is an important agronomic trait that presents non-additive gene action. Genome-enabled prediction allow incorporating molecular information into the prediction of individual genetic merit. Artificial neural networks (ANN) recognize patterns of data and represent an alternative as a universal approximation of complex functions. In a Genomic Selection (GS) context, the ANN allows automatically to capture complicated factors such as epistasis and dominance. The objectives of this study were to predict the individual genetic merits of the traits associated with the flowering time in the common bean using the ANN approach, and to compare the predictive abilities obtained for ANN and Ridge Regression Best Linear Unbiased Predictor (RR-BLUP). We used a set of 80 bean cultivars and genotyping was performed with a set of 384 SNPs. The higher accuracy of the selective process of phenotypic values based on ANN output values resulted in a greater efficacy of the genomic estimated breeding value (GEBV). Through the root mean square error computational intelligence approaches via ANN, GEBV were shown to have greater efficacy than GS via RR-BLUP.

show abstract

“…Estudos com dados simulados mostram que progênies com maiores laços de 570 parentesco e menor número efetivo aumentam a acurácia da seleção; além de demonstrarem que em condições de altos desequilíbrio de ligação e herdabilidade, a densidade de marcadores tem menor influência na capacidade de predição (COUTINHO et al, 2018;VALENTE et al, 2016). Quanto aos métodos de predição, o RR-BLUP (Ridge Regression-Best Linear Unbiased Prediction), de forma geral, é superior ao método bayesiano (Blasso), porém em condições de alta herdabilidade e alto desequilíbrio de ligação, o método baseado em redes neurais demonstra superioridade em relação ao RR-BLUP, indicando diferença de modelos quantos aos pressupostos associados à característica estudada (ALMEIDA et al, 2016;COUTINHO et al, 2018).…”

Section: Seleção Genômicaunclassified

Seleção Genômica Ampla (Gws) E Associação Genômica Ampla (Gwas) No Melhoramento De Forrageiras: Abordagem Conceitual, Genética Quantitativa E Aplicações

Miqueloni¹,

Resende²,

Assis³

2019

Enci Bio

View full text Add to dashboard Cite

RESUMOAtualmente, desenvolvimento da tecnologia de análise genômica de alta resolução e alto rendimento tem a capacidade de gerar informações sobre milhões de pares de bases em um único ensaio, permitindo a detecção de variação em um único nucleotídeo de uma sequência de DNA. Este contexto possibilitou o surgimento de novas abordagens para a seleção assistida por marcadores, dentre elas os estudos de associação genômica ampla (GWAS), que visam o mapeamento genético por meio das associações entre os locos e a característica fenotípica na população e buscam detectar efeitos dos genes sobre os valores genéticos dos indivíduos; e a seleção genômica ampla (GWS), que detecta genótipos favoráveis por meio de informações genotípicas para inferir sobre os valores fenotípicos futuros, ou valores genômicos. Estas técnicas têm sido exploradas por meio de estudos de simulação e aplicação nos programas de melhoramento tradicionais para diversas culturas. Por outro lado, sua aplicação no melhoramento de forrageiras é restrita, especialmente no Brasil, porém com resultados promissores. Neste contexto, este estudo traz uma abordagem conceitual do tema sob a visão da genética quantitativa, buscando evidenciar sua aplicação no melhoramento genético de forrageiras. PALAVRAS-CHAVE: espécies forrageiras, mapeamento genético, marcadores moleculares. ABSTRACTThe development of high-resolution and high-throughput genomic analysis technology now is enable to generate information about millions of base pairs in only one test, allowing detection of single nucleotide variation in a DNA sequence. This context enabled the emergence of new approaches to marker-assisted selection, among them the Genome-Wide Association Studies (GWAS), which aim at genetic mapping through associations between loci and phenotypic characteristics in the population and seek to detect effects of genes on the genetic values of individuals;

show abstract

Prediction of Phenotypic and Genotypic Values by Blup/GWS and Neural Networks

Cited by 6 publications

References 29 publications

Genome‐enabled prediction through machine learning methods considering different levels of trait complexity

Genome‐enabled prediction through machine learning methods considering different levels of trait complexity

Artificial Neural Networks in the Prediction of Genetic Merit to Flowering Traits in Bean Cultivars

Seleção Genômica Ampla (Gws) E Associação Genômica Ampla (Gwas) No Melhoramento De Forrageiras: Abordagem Conceitual, Genética Quantitativa E Aplicações

Contact Info

Product

Resources

About