Kismiantini, Abelardo Montesinos-López, Bernabe Cano-Páez, J. Cricelio Montesinos-López, Moisés Chavira-Flores, Osval A. Montesinos-López, José Crossa
While genomic selection (GS) began revolutionizing plant breeding when it was proposed around 20 years ago, its practical implementation is still challenging as many factors affect its accuracy. One such factor is the choice of the statistical machine learning method. For this reason, we explore the tuning process under a multi-trait framework using the Gaussian kernel with a multi-trait Bayesian Best Linear Unbiased Predictor (GBLUP) model. We explored three methods of tuning (manual, grid search and Bayesian optimization) using 5 real datasets of breeding programs. We found that using grid search and Bayesian optimization improve between 1.9 and 6.8% the prediction accuracy regarding of using manual tuning. While the improvement in prediction accuracy in some cases can be marginal, it is very important to carry out the tuning process carefully to improve the accuracy of the GS methodology, even though this entails greater computational resources. © 2022 by the authors.
Statistics Study Program, Universitas Negeri Yogyakarta, Yogyakarta, 55281, Indonesia; Centro Universitario de Ciencias Exactas e Ingenierías (CUCEI), Universidad de Guadalajara, Jalisco, Guadalajara, 44430, Mexico; Facultad de Ciencias, Universidad Nacional Autónoma de México (UNAM), México City, 04510, Mexico; Department of Public Health Sciences, University of California Davis, Davis, 95616, CA, United States; Instituto de Investigaciones en Matemáticas Aplicadas y Sistemas (IIMAS), Universidad Nacional Autónoma de México (UNAM), México City, 04510, Mexico; Facultad de Telemática, Universidad de Colima, Colima, Colima, 28040, Mexico; International Maize and Wheat Improvement Center (CIMMYT), Km 45, Carretera Mexico, Edo. de México, Veracruz, 52640, Mexico; Colegio de Postgraduados, Edo. de México, Montecillos, 56230, Mexico
