Multi-trait regressor stacking increased genomic prediction accuracy of sorghum grain composition

Cereal grains, primarily composed of starch, protein, and fat, are major source of staple for human and animal nutrition. Sorghum, a cereal crop, serves as a dietary staple for over half a billion people in the semi-arid tropics of Africa and South Asia. Genomic prediction has enabled plant breeders to estimate breeding values of unobserved genotypes and environments. Therefore, the use of genomic prediction will be extremely valuable for compositional traits for which phenotyping is labor-intensive and destructive for most accurate results. We studied the potential of Bayesian multi-output regressor stacking (BMORS) model in improving prediction performance over single trait single environment (STSE) models using a grain sorghum diversity panel (GSDP) and a biparental recombinant inbred lines (RILs) population. A total of five highly correlated grain composition traits: amylose, fat, gross energy, protein and starch, with genomic heritability ranging from 0.24 to 0.59 in the GSDP and 0.69 to 0.83 in the RILs were studied. Average prediction accuracies from the STSE model were within a range of 0.4 to 0.6 for all traits across both populations except amylose (0.25) in the GSDP. Prediction accuracy for BMORS increased by 41% and 32% on average over STSE in the GSDP and RILs, respectively. Predicting whole environments by training with remaining environments in BMORS yielded higher average prediction accuracy than from STSE model. Our results show regression stacking methods such as BMORS have potential to accurately predict unobserved individuals and environments, and implementation of such models can accelerate genetic gain.