Hybrid breeding of rice via genomic selection

Abstract

Hybrid breeding is the main strategy for improving productivity in many crops, especially in rice and maize. Genomic hybrid breeding is a technology that uses whole-genome markers to predict future hybrids. Predicted superior hybrids are then field evaluated and released as new hybrid cultivars after their superior performances are confirmed. This will increase the opportunity of selecting true superior hybrids with minimum costs. Here, we used genomic best linear unbiased prediction to perform hybrid performance prediction using an existing rice population of 1495 hybrids. Replicated 10-fold cross-validations showed that the prediction abilities on ten agronomic traits ranged from 0.35 to 0.92. Using the 1495 rice hybrids as a training sample, we predicted six agronomic traits of 100 hybrids derived from half diallel crosses involving 21 parents that are different from the parents of the hybrids in the training sample. The prediction abilities were relatively high, varying from 0.54 (yield) to 0.92 (grain length). We concluded that the current population of 1495 hybrids can be used to predict hybrids from seemingly unrelated parents. Eventually, we used this training population to predict all potential hybrids of cytoplasm male sterile lines from 3000 rice varieties from the 3K Rice Genome Project. Using a breeding index combining 10 traits, we identified the top and bottom 200 predicted hybrids. SNP genotypes of the training population and parameters estimated from this training population are available for general uses and further validation in genomic hybrid prediction of all potential hybrids generated from all varieties of rice.

Keywords: best linear unbiased prediction; cross-validation; cytoplasm male sterile system; genomic prediction; hybrid rice.

Figure 1

Flow chart of GS using the 1495 hybrid population as the training sample.

Figure 2

Estimated broad‐sense heritability and prediction ability for ten traits of the 1495 hybrid population. Heritability is defined as the genetic variance estimated from the ANOVA divided by the total phenotypic variance. Prediction ability is defined as the correlation between the predicted and observed trait values obtained from 10‐fold CV (replicated ten times).

Figure 3

Plots of predicted phenotypes against observed phenotypes of 100 hybrid rice from the half diallel cross experiment. The training sample is the 1495 hybrid population. The six panels represent plots of six traits (YD, GN, KGW, PH, GL and GW) where Geng is colour coded in red and Xian is colour coded in blue.

Figure 4

PCA plots and boxplots of selected hybrids. Panel (a): Eigenvalue plotted against the number of principal components for 10 predicted trait values from all 44 636 predicted hybrids (a 44 636 × 10 data matrix); Panel (b): 3D plot of the first three principal components of the 44 636 × 10 data matrix, where the best 200 and the worst 200 hybrids are colour coded blue and yellow, respectively; Panel (c): The differences between the top 200 hybrids and the bottom 200 hybrids for ten predicted traits and the BI.

Figure 5

Prediction ability of different models. Panel (a): Prediction ability for ten traits of the rice population with 1495 hybrids under the additive and additive and dominance (A–D) models. Panel (b): Prediction ability of the G × E interaction model compared with environment specific prediction for ten agronomical traits.