Bayesian multitrait kernel methods improve multienvironment genome-based prediction

Montesinos-López, O A and Montesinos-López, J C and Montesinos-Lopez, A and Ramírez-Alcaraz, J M and Poland, J and Singh, R and Dreisigacker, S and Crespo, L and Mondal, S and Govidan, V and Juliana, P and Espino, J H and Shrestha, S and Varshney, R K and Crossa, J (2021) Bayesian multitrait kernel methods improve multienvironment genome-based prediction. G3: Genes, Genomes, Genetics (TSI), 12 (2). pp. 1-17. ISSN 2160-1836

PDF - Published Version Available under License ["licenses_description_cc_attribution" not defined]. Download (1MB)

Abstract

When multitrait data are available, the preferred models are those that are able to account for correlations between phenotypic traits because when the degree of correlation is moderate or large, this increases the genomic prediction accuracy. For this reason, in this article, we explore Bayesian multitrait kernel methods for genomic prediction and we illustrate the power of these models with three-real datasets. The kernels under study were the linear, Gaussian, polynomial, and sigmoid kernels; they were compared with the conventional Ridge regression and GBLUP multitrait models. The results show that, in general, the Gaussian kernel method outperformed conventional Bayesian Ridge and GBLUP multitrait linear models by 2.2–17.45% (datasets 1–3) in terms of prediction performance based on the mean square error of prediction. This improvement in terms of prediction performance of the Bayesian multitrait kernel method can be attributed to the fact that the proposed model is able to capture nonlinear patterns more efficiently than linear multitrait models. However, not all kernels perform well in the datasets used for evaluation, which is why more than one kernel should be evaluated to be able to choose the best kernel.

Item Type:	Article
Divisions:	Center of Excellence in Genomics and Systems Biology
CRP:	UNSPECIFIED
Uncontrolled Keywords:	multitrait, kernel methods, plant breeding, genomic-enabled prediction, genomic prediction, GenPred, shared data resources
Subjects:	Others > Plant Breeding Others > Genetics and Genomics
Depositing User:	Mr Nagaraju T
Date Deposited:	23 Apr 2024 09:00
Last Modified:	23 Apr 2024 09:01
URI:	http://oar.icrisat.org/id/eprint/12645
Official URL:	https://academic.oup.com/g3journal/article/12/2/jk...
Projects:	Accelerating Genetic Gains in Maize and Wheat for Improved Livelihoods
Funders:	Bill & Melinda Gates Foundation, USAID, Foundation for Research Levy on Agricultural Products, Agricultural Agreement Research Fund (JA) in Norway
Acknowledgement:	We thank all scientists, field workers, and lab assistants from the National Programs from CIMMYT and ICRISAT who collected the data used in this study. O.A.M.-L., J.C.M.-L., J.C., and A.M.-L. had the original idea of developing a multitrait kernel and run the original analyses. O.A.M.-L., J.C.M.-L., J.C., and A.M.-L. wrote the first version of the manuscript and revised and correct all the other versions. All other authors contributed by revising several versions of the manuscripts at different stages of the research-writing process and with intellectual contributions related to the generalizations of models to other datasets comprising other crops.
Links:	Google Scholar

View Statistics

Actions (login required)

View Item