Comparison of whole-genome prediction models for traits with contrasting genetic architecture in a diversity panel of maize inbred lines

Abstract

Background: There is increasing empirical evidence that whole-genome prediction (WGP) is a powerful tool for predicting line and hybrid performance in maize. However, there is a lack of knowledge about the sensitivity of WGP models towards the genetic architecture of the trait. Whereas previous studies exclusively focused on highly polygenic traits, important agronomic traits such as disease resistances, nutrifunctional or climate adaptational traits have a genetic architecture which is either much less complex or unknown. For such cases, information about model robustness and guidelines for model selection are lacking. Here, we compared five WGP models with different assumptions about the distribution of the underlying genetic effects. As contrasting model traits, we chose three highly polygenic agronomic traits and three metabolites each with a major QTL explaining 22 to 30% of the genetic variance in a panel of 289 diverse maize inbred lines genotyped with 56,110 SNPs.

Results: We found the five WGP models to be remarkable robust towards trait architecture with the largest differences in prediction accuracies ranging between 0.05 and 0.14 for the same trait, most likely as the result of the high level of linkage disequilibrium prevailing in elite maize germplasm. Whereas RR-BLUP performed best for the agronomic traits, it was inferior to LASSO or elastic net for the three metabolites. We found the approach of genome partitioning of genetic variance, first applied in human genetics, as useful in guiding the breeder which model to choose, if prior knowledge of the trait architecture is lacking.

Conclusions: Our results suggest that in diverse germplasm of elite maize inbred lines with a high level of LD, WGP models differ only slightly in their accuracies, irrespective of the number and effects of QTL found in previous linkage or association mapping studies. However, small gains in prediction accuracies can be achieved if the WGP model is selected according to the genetic architecture of the trait. If the trait architecture is unknown e.g. for novel traits which only recently received attention in breeding, we suggest to inspect the distribution of the genetic variance explained by each chromosome for guiding model selection in WGP.

Figure 1

Visualization of the RR-BLUP estimator ($\left({\widehat{\mathbf{u}}}_{\text{RR}}\right)$) and the LASSO estimator ($\left({\widehat{\mathbf{u}}}_{\text{L}}\right)$) as solutions to a least-squares problem with different penalization [[38],[39]]. We illustrate a two-dimensional case. The blue ellipses show the contours of the RSS function around the ordinary least-square solution ($\left({\widehat{\mathbf{u}}}_{\text{OLS}}\right)$). The ridge estimator is the point at which the innermost elliptical contour touches the circular ridge penalty $\sqrt{u_1^2+u_2^2}<c_{\text{RR}}$. The LASSO estimator is the point at which the innermost elliptical contour touches the diamond shaped LASSO penalty |u₁| + |u₂|<c_L. Contrary to the ridge penalty, the LASSO penalty allows estimations to be exactly zero.

Figure 2

Characterization of the genetic architecture of different traits by genome partitioning of the genetic variance. (A) Cummulative genetic variance explained by individual chromosomes. (B) Genetic variance explained by each chromosome (number in points). The chromosomes containing either major mQTL for metabolites or putative minor QTL for agronomic traits lie above the red line. (C) Genetic variance explained by chromosomes plotted against the genetic variance explained by the GWA signals on these chromosomes.

Figure 3

SNP effects for dopamine obtained by using either RR-BLUP, LASSO, or the elastic net model. The position of the mQTL is indicated as a red triangle.