Bayesian multitrait kernel methods improve multienvironment genome-based prediction
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 mu...
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Journal Article |
| Lenguaje: | Inglés |
| Publicado: |
Oxford University Press
2022
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/126371 |
| _version_ | 1855535100198912000 |
|---|---|
| author | Montesinos López, Osval A. Montesinos López, José Cricelio Montesinos López, Abelardo Ramírez Alcaraz, Juan Manuel Poland, Jesse A. Singh, Ravi P. Dreisigacker, Susanne Crespo-Herrera, Leonardo A. Mondal, Suchismita Velu, Govindan Juliana, Philomin Huerta Espino, Julio Shrestha, Sandesh Varshney, Rajeev K. Crossa, José |
| author_browse | Crespo-Herrera, Leonardo A. Crossa, José Dreisigacker, Susanne Huerta Espino, Julio Juliana, Philomin Mondal, Suchismita Montesinos López, Abelardo Montesinos López, José Cricelio Montesinos López, Osval A. Poland, Jesse A. Ramírez Alcaraz, Juan Manuel Shrestha, Sandesh Singh, Ravi P. Varshney, Rajeev K. Velu, Govindan |
| author_facet | Montesinos López, Osval A. Montesinos López, José Cricelio Montesinos López, Abelardo Ramírez Alcaraz, Juan Manuel Poland, Jesse A. Singh, Ravi P. Dreisigacker, Susanne Crespo-Herrera, Leonardo A. Mondal, Suchismita Velu, Govindan Juliana, Philomin Huerta Espino, Julio Shrestha, Sandesh Varshney, Rajeev K. Crossa, José |
| author_sort | Montesinos López, Osval A. |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | 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. |
| format | Journal Article |
| id | CGSpace126371 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2022 |
| publishDateRange | 2022 |
| publishDateSort | 2022 |
| publisher | Oxford University Press |
| publisherStr | Oxford University Press |
| record_format | dspace |
| spelling | CGSpace1263712025-11-12T05:34:40Z Bayesian multitrait kernel methods improve multienvironment genome-based prediction Montesinos López, Osval A. Montesinos López, José Cricelio Montesinos López, Abelardo Ramírez Alcaraz, Juan Manuel Poland, Jesse A. Singh, Ravi P. Dreisigacker, Susanne Crespo-Herrera, Leonardo A. Mondal, Suchismita Velu, Govindan Juliana, Philomin Huerta Espino, Julio Shrestha, Sandesh Varshney, Rajeev K. Crossa, José plant breeding genomics forecasting bayesian theory 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. 2022-02-04 2022-12-28T14:59:21Z 2022-12-28T14:59:21Z Journal Article https://hdl.handle.net/10568/126371 en Open Access application/pdf Oxford University Press Montesinos-López, O. A., Montesinos-López, J. C., Montesinos-López, A., Ramírez-Alcaraz, J. M., Poland, J., Singh, R., Dreisigacker, S., Crespo, L., Mondal, S., Govidan, V., Juliana, P., Espino, J. H., Shrestha, S., Varshney, R. K., & Crossa, J. (2021). Bayesian multitrait kernel methods improve multienvironment genome-based prediction. G3 Genes|Genomes|Genetics, 12(2). https://doi.org/10.1093/g3journal/jkab406 |
| spellingShingle | plant breeding genomics forecasting bayesian theory Montesinos López, Osval A. Montesinos López, José Cricelio Montesinos López, Abelardo Ramírez Alcaraz, Juan Manuel Poland, Jesse A. Singh, Ravi P. Dreisigacker, Susanne Crespo-Herrera, Leonardo A. Mondal, Suchismita Velu, Govindan Juliana, Philomin Huerta Espino, Julio Shrestha, Sandesh Varshney, Rajeev K. Crossa, José Bayesian multitrait kernel methods improve multienvironment genome-based prediction |
| title | Bayesian multitrait kernel methods improve multienvironment genome-based prediction |
| title_full | Bayesian multitrait kernel methods improve multienvironment genome-based prediction |
| title_fullStr | Bayesian multitrait kernel methods improve multienvironment genome-based prediction |
| title_full_unstemmed | Bayesian multitrait kernel methods improve multienvironment genome-based prediction |
| title_short | Bayesian multitrait kernel methods improve multienvironment genome-based prediction |
| title_sort | bayesian multitrait kernel methods improve multienvironment genome based prediction |
| topic | plant breeding genomics forecasting bayesian theory |
| url | https://hdl.handle.net/10568/126371 |
| work_keys_str_mv | AT montesinoslopezosvala bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT montesinoslopezjosecricelio bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT montesinoslopezabelardo bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT ramirezalcarazjuanmanuel bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT polandjessea bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT singhravip bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT dreisigackersusanne bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT crespoherreraleonardoa bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT mondalsuchismita bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT velugovindan bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT julianaphilomin bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT huertaespinojulio bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT shresthasandesh bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT varshneyrajeevk bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction AT crossajose bayesianmultitraitkernelmethodsimprovemultienvironmentgenomebasedprediction |