Predicting Genetic Values: A Kernel-Based Best Linear Unbiased Prediction With Genomic Data

Ober, Ulrike; Erbe, Malena; Long, Norton E.; Porcu, Emilio; Schlather, Martin; Simianer, Henner

doi:10.1534/genetics.111.128694

Cited by 48 publications

(54 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other RK functions, such as the t (Tussel et al 2014) and the exponential (Endelman 2011), have also been used. However, none of them have proven to be consistently superior to the Gaussian RK function (Ober et al 2011). Assuming that the Gaussian kernel has been selected, a remaining crucial step is to tune the bandwidth parameter, which is usually based on cross-validation or penalization (Härdle 1990).…”

Section: Introductionmentioning

confidence: 99%

Selection of the Bandwidth Parameter in a Bayesian Kernel Regression Model for Genomic-Enabled Prediction

Pérez-Elizalde

Cuevas

Pérez‐Rodríguez

et al. 2015

JABES

View full text Add to dashboard Cite

One of the most widely used kernel functions in genomic-enabled prediction is the Gaussian kernel. Selection of the bandwidth parameter for kernel regression has generally been based on cross-validation. We propose a Bayesian method for estimating the bandwidth parameter h of a Gaussian kernel as the modal component of the joint posterior distribution of h and the form parameter ϕ. We present a theory for the Bayesian selection of h in a Transformed Gaussian Kernel (TGK) model and its application in two plant breeding datasets (maize and wheat) that were already predicted using the kernel averaging (KA) model in the context of Reproducing Kernel Hilbert Spaces (RKHS KA). We also compared the prediction accuracy of the proposed method with a model that also uses a Gaussian kernel and estimates the bandwidth parameter using a restricted maximum likelihood method (GK REML). Results for the wheat dataset show that the predictive ability of TGK was at least as good as the predictive ability of model RKHS KA, with TGK showing a significantly smaller Predictive Mean Squared Error (PMSE) than the other two approaches. The TGK model was statistically a better predictor than methods GK REML and RKHS KA in terms of mean PMSE and mean correlations in seven (out of 17) trait-environment combinations in the wheat dataset. Fewer differences were found between models for the maize data; the TGK model generally had similar or inferior prediction accuracy than GK REML and RKHS KA in various analyses. The superiority of GK REML over TGK based on mean PMSE was clear in seven maize traits.

show abstract

Section: Introductionmentioning

confidence: 99%

Selection of the Bandwidth Parameter in a Bayesian Kernel Regression Model for Genomic-Enabled Prediction

Pérez-Elizalde

Cuevas

Pérez‐Rodríguez

et al. 2015

JABES

View full text Add to dashboard Cite

show abstract

“…Methods include genomic BLUP (GBLUP) and its extension (VanRaden 2008;Aguilar et al 2010;Christensen and Lund 2010); penalized regression methods such as ridge regression, Lasso, and elastic net (ENet) (Usai et al 2009;Li and Sillanpaa 2012a;Ogutu et al 2012); Bayesian regression methods such as BayesA and BayesB (Meuwissen et al 2001;de los Campos et al 2009;Hayashi and Iwata 2010;Habier et al 2011); non-parametric regression methods to capture non-additive genetic effects (Gianola et al 2006;Gianola and van Kaam 2008;Long et al 2010;Ober et al 2011); methods developed in the field of machine learning such as support vector machine and random forest (RForest) (Long et al 2011a;Ogutu et al 2011); and regression methods based on dimension reduction (Solberg et al 2009;Long et al 2011b). Ridge regression and its equivalent GBLUP, BayesA and BayesB, and Bayesian lasso (Blasso; Park and Casella 2008) are popular methods, and have been evaluated in many studies (reviewed in de los .…”

Section: Introductionmentioning

confidence: 99%

“…Ridge regression and GBLUP tend to be inferior to BayesB when predicted individuals are genetically distant from the training set, because these methods depend on information on relatedness rather than LD between markers and QTLs (Habier et al 2007;Zhong et al 2009). Non-parametric regression such as RKHS tends to be superior to additive linear regression for non-additive traits (Long et al 2010;Ober et al 2011;Gonzalez-Camacho et al 2012). These factors (genetic architecture, LD structure, and relationship between the training and validation sets) may differ among populations or traits, and complex interplay between them probably influences the relative performance of the prediction methods.…”

Section: Introductionmentioning

confidence: 99%

Exploring the areas of applicability of whole-genome prediction methods for Asian rice (Oryza sativa L.)

et al. 2014

View full text Add to dashboard Cite

Our simulation results clarify the areas of applicability of nine prediction methods and suggest the factors that affect their accuracy at predicting empirical traits. Whole-genome prediction is used to predict genetic value from genome-wide markers. The choice of method is important for successful prediction. We compared nine methods using empirical data for eight phenological and morphological traits of Asian rice cultivars (Oryza sativa L.) and data simulated from real marker genotype data. The methods were genomic BLUP (GBLUP), reproducing kernel Hilbert spaces regression (RKHS), Lasso, elastic net, random forest (RForest), Bayesian lasso (Blasso), extended Bayesian lasso (EBlasso), weighted Bayesian shrinkage regression (wBSR), and the average of all methods (Ave). The objectives were to evaluate the predictive ability of these methods in a cultivar population, to characterize them by exploring the area of applicability of each method using simulation, and to investigate the causes of their different accuracies for empirical traits. GBLUP was the most accurate for one trait, RKHS and Ave for two, and RForest for three traits. In the simulation, Blasso, EBlasso, and Ave showed stable performance across the simulated scenarios, whereas the other methods, except wBSR, had specific areas of applicability; wBSR performed poorly in most scenarios. For each method, the accuracy ranking for the empirical traits was largely consistent with that in one of the simulated scenarios, suggesting that the simulation conditions reflected the factors that affected the method accuracy for the empirical results. This study will be useful for genomic prediction not only in Asian rice, but also in populations from other crops with relatively small training sets and strong linkage disequilibrium structures.

show abstract

“…GS has been successfully applied in genetic breeding of both animals and plants, including bovine (e.g., Meuwissen et al, 2001;de Roos et al, 2007;Hayes et al, 2010), mouse (Legarra et al, 2008), wheat (e.g., Crossa et al, 2007;Pérez et al, 2010;Ober et al, 2011), and maize (Messina et al, 2011). In addition, many statistical models have been developed to analyze the different types of genetic and trait data from GS, such as best linear unbiased predictor (BLUP), stepwise regression, ridge regression (RR), and Bayesian estimation (Bayes A or B) (e.g., Messina et al, 2001;Lee et al, 2008;de los Campos et al, 2009;Luan et al, 2009;Hayes et al, 2010;Pérez et al, 2010;Crossa et al, 2010;Macciotta et al, 2010;Schulz-Streeck and Piepho, 2010;Zhang et al, 2010;Ober et al, 2011). These statistical models are used for training the GS models with a training population, and predicting which GEBVs will have significantly improved polygenic traits controlled by many loci of small effect (e.g., Solberg et al, 2008;Rafalski, 2010).…”

Section: Introductionmentioning

confidence: 99%

Genomic selection of seed weight based on low-density SCAR markers in soybean

Shu¹,

Yu²,

Wang³

et al. 2013

Genet. Mol. Res.

View full text Add to dashboard Cite

ABSTRACT. With the development of molecular marker technology, crop breeding has been accelerated by marker-assisted selection for the improvement of quantitative traits. However, due to the traits' polygenic nature, traditional marker-assisted selection methods are ill-suited for identification of quantitative trait loci. Genomic selection (GS) was introduced into crop breeding to achieve more accurate predictions by considering all genes or markers simultaneously. We used dozens of sequence-characterized amplified region (SCAR) markers for genotyping soybean varieties, and we identified markers associated with hundred-seed weight. The best linear unbiased predictor and Bayesian liner regression methods were used to construct GS models to predict the hundred-seed weight trait based upon genotype information for trait selection. Both GS models showed good prediction performance in soybean, as the correlation coefficient between genomic estimated breeding values and true breeding values was as high as 0.904. This indicated that GS was performed effectively based on dozens of SCAR markers in soybean; these markers were of low density but easily detectable. Therefore, the 2179 ©FUNPEC-RP www.funpecrp.com.br Genetics and Molecular Research 12 (3): 2178-2188 (2013 Genomic selection of HSW in soybean combination of GS modeling and highly effective molecular marker technology involving SCAR markers can facilitate genetic breeding in soybean. This approach may also be suitable for genetic selection in other crops, such as wheat, maize, and rice.

show abstract

Predicting Genetic Values: A Kernel-Based Best Linear Unbiased Prediction With Genomic Data

Cited by 48 publications

References 64 publications

Selection of the Bandwidth Parameter in a Bayesian Kernel Regression Model for Genomic-Enabled Prediction

Selection of the Bandwidth Parameter in a Bayesian Kernel Regression Model for Genomic-Enabled Prediction

Exploring the areas of applicability of whole-genome prediction methods for Asian rice (Oryza sativa L.)

Genomic selection of seed weight based on low-density SCAR markers in soybean

Contact Info

Product

Resources

About