Comparing Genomic Prediction Models by Means of Cross Validation.

Autor:	Schrauf MF; Facultad de Agronomía, Universidad de Buenos Aires, Buenos Aires, Argentina.; Animal Breeding & Genomics, Wageningen Livestock Research, Wageningen University & Research, Wageningen, Netherlands., de Los Campos G; Departments of Epidemiology, Biostatistics, Statistics, and Probabilty, Institute for Quantitative Health Science and Engineering, Michigan State University, East Lansing, MI, United States., Munilla S; Facultad de Agronomía, Universidad de Buenos Aires, Buenos Aires, Argentina.; Instituto de Investigaciones en Producción Animal (INPA), CONICET-Universidad de Buenos Aires, Buenos Aires, Argentina.
Jazyk:	angličtina
Zdroj:	Frontiers in plant science [Front Plant Sci] 2021 Nov 19; Vol. 12, pp. 734512. Date of Electronic Publication: 2021 Nov 19 (Print Publication: 2021).
DOI:	10.3389/fpls.2021.734512
Abstrakt:	In the two decades of continuous development of genomic selection, a great variety of models have been proposed to make predictions from the information available in dense marker panels. Besides deciding which particular model to use, practitioners also need to make many minor choices for those parameters in the model which are not typically estimated by the data (so called "hyper-parameters"). When the focus is placed on predictions, most of these decisions are made in a direction sought to optimize predictive accuracy. Here we discuss and illustrate using publicly available crop datasets the use of cross validation to make many such decisions. In particular, we emphasize the importance of paired comparisons to achieve high power in the comparison between candidate models, as well as the need to define notions of relevance in the difference between their performances. Regarding the latter, we borrow the idea of equivalence margins from clinical research and introduce new statistical tests. We conclude that most hyper-parameters can be learnt from the data by either minimizing REML or by using weakly-informative priors, with good predictive results. In particular, the default options in a popular software are generally competitive with the optimal values. With regard to the performance assessments themselves, we conclude that the paired k-fold cross validation is a generally applicable and statistically powerful methodology to assess differences in model accuracies. Coupled with the definition of equivalence margins based on expected genetic gain, it becomes a useful tool for breeders. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2021 Schrauf, de los Campos and Munilla.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu