Enhancing wheat genomic prediction by a hybrid kernel approach

Abstract

This study integrates genomic and pedigree data by leveraging advanced modeling techniques, aiming to enhance the predictive performance of genomic selection models by capturing complex genetic relationships through the interaction of both matrices and exploring the utility of non-linear methods, such as kernel matrices. Our goal was to improve genomic prediction accuracy by combining the pedigree-based or genetic similarity matrix ( A ) with the genomic similarity matrix ( G ). Using various wheat datasets, we performed five single-environment models and five multi-environment models that incorporated genotype-by-environment (G × E) interactions. The proposed models S5 and M5 significantly enhanced prediction accuracy by incorporating two novel symmetric kernels, C and P , derived from the interaction of genomic and pedigree matrices. These hybrid kernels captured additional, independent genetic variation not explained by conventional matrices. The proposed prediction model outperformed the standard conventional models in most single-environment and multi-environment models. The genomic models with non-linear kernels were better predictors than the linear prediction models.

Keywords: genomics; genotype by environment interaction; merging genomics and pedigree; pedigree; single-environment.

Figure 1

Average Pearson’s correlation coefficients (AVG) and corresponding standard errors (SE) across four cycles of 5-fold cross-validation for single-environment genomic prediction models of grain yield. Results are shown for the following datasets: EYT_16_17 (B2IR, B5IR, BEHT, BLHT, BDRT, and F5IR), EYT_22_23 (B2IR, B5IR, BEHT, BLHT, BDRT, and F5IR), EYT_23_24 (B2IR, B5IR, BEHT, BLHT, and F5IR), and Wheat 599 (E1, E2, E3, and E4).

Figure 2

Average Pearson’s correlation coefficients (AVG) and corresponding standard errors (SE) across ten cycles of 2-fold cross-validation for single-environment genomic prediction models of grain yield. Results are shown for the following datasets: EYT_16_17 (B2IR, B5IR, BEHT, BLHT, BDRT, and F5IR), EYT_22_23 (B2IR, B5IR, BEHT, BLHT, BDRT, and F5IR), EYT_23_24 (B2IR, B5IR, BEHT, BLHT, and F5IR), and Wheat 599 (E1, E2, E3, and E4).

Figure 3

Average Pearson’s correlation coefficients (AVG) and corresponding standard errors (SE) across four cycles of 5-fold cross-validation for multi-environment genomic prediction models of grain yield. Results are shown for the following datasets: EYT_16_17 (B2IR, B5IR, BEHT, BLHT, BDRT, and F5IR), EYT_22_23 (B2IR, B5IR, BEHT, BLHT, BDRT, and F5IR), EYT_23_24 (B2IR, B5IR, BEHT, BLHT, and F5IR), and Wheat 599 (E1, E2, E3, and E4).

Figure 4

Average Pearson’s correlation coefficients (AVG) and corresponding standard errors (SE) across ten cycles of 2-fold cross-validation for multi-environment genomic prediction models of grain yield. Results are shown for the following datasets: EYT_16_17 (B2IR, B5IR, BEHT, BLHT, BDRT, and F5IR), EYT_22_23 (B2IR, B5IR, BEHT, BLHT, BDRT, and F5IR), EYT_23_24 (B2IR, B5IR, BEHT, BLHT, and F5IR), and Wheat 599 (E1, E2, E3, and E4).