Enhancing genomic prediction with genome-wide association studies in multiparental maize populations

Abstract

Genome-wide association mapping using dense marker sets has identified some nucleotide variants affecting complex traits that have been validated with fine-mapping and functional analysis. However, many sequence variants associated with complex traits in maize have small effects and low repeatability. In contrast to genome-wide association study (GWAS), genomic prediction (GP) is typically based on models incorporating information from all available markers, rather than modeling effects of individual loci. We considered methods to integrate results of GWASs into GP models in the context of multiple interconnected families. We compared association tests based on a biallelic additive model constraining the effect of a single-nucleotide polymorphism (SNP) to be equal across all families in which it segregates to a model in which the effect of a SNP can vary across families. Association SNPs were then included as fixed effects into a GP model that also included the random effects of the whole genome background. Simulation studies revealed that the effectiveness of this joint approach depends on the extent of polygenicity of the traits. Congruent with this finding, cross-validation studies indicated that GP including the fixed effects of the most significantly associated SNPs along with the polygenic background was more accurate than the polygenic background model alone for moderately complex but not highly polygenic traits measured in the maize nested association mapping population. Individual SNPs with strong and robust association signals can effectively improve GP. Our approach provides a new integrative modeling approach for both reliable gene discovery and robust GP.

Figure 1

Prediction ability (R²) of the simulated oligogenic and polygenic traits. ‘Causal' represents the model including the causal variants as fixed effects (with effects estimated in the training set), ‘GBLUP' represents the ‘background only model' with no fixed effects of SNPs and ‘Main-effect GWAS+REML LMM' denotes linear mixed models combining significant GWAS associations and polygenic background effects. The horizontal axis indicates the P-value thresholds for declaring a significant locus, ‘Bon', represents the Bonferroni correction P-value. The margins represent 95% confidence intervals of the mean prediction R² across 50 cross-validation runs.

Figure 2

GWAS repeatability plot for the three agronomic traits. Each data point represents the resample model inclusion probability (RMIP) of an SNP with a significant association in one or more of 50 GWAS analyses of training data sets containing 80% of lines. Two filters were applied to the significant SNPs: first, only one associated locus per cM interval was considered, certifying the chosen SNPs to be the most competitive in the neighboring region, and second, the chosen SNPs' P-values needed to pass the Bonferroni correction (P-value<3.8 × 10⁻⁸). Asterisks denote those loci that have average P-values significant at the Bonferroni corrected P-value across 50 GWAS analyses. Venn diagrams show the numbers of highly repeatable loci (RMIP⩾0.05) identified in the two models.

Figure 3

Within-family prediction ability (R²) for three agronomic traits using GBLUP and new models. S.e. bars are imposed on each mean prediction ability value. Models with different letters above the bar indicate the average prediction R² values are significantly different (α<0.05; Tukey's honestly significant difference). Prediction R² values are averages across 25 NAM populations and 50 runs of cross-validations. The main-effect and nested-effect GWAS models failed to detect significant SNPs in 21 and 29 runs, respectively. For those cases, the prediction R² for the respective models was equal to the corresponding GBLUP models.