Comparing genomic prediction models by means of cross validation

Mostrar todas las versiones(2)

Fil: Schrauf, Matías Florián. Universidad de Buenos Aires. Facultad de Agronomía. Buenos Aires, Argentina.

Guardado en:
Detalles Bibliográficos
Autores principales: Schrauf, Matías Florián, Campos, Gustavo de los, Munilla Leguizamón, Sebastián
Formato: Artículo publishedVersion
Lenguaje:Inglés
Publicado: 2021
Materias:
GENOMIC SELECTION
CROSS VALIDATION
PLANT BREEDING
GENOMIC MODELS
MODEL SELECTION
Acceso en línea:http://ri.agro.uba.ar/greenstone3/library/collection/arti/document/2021schrauf
Aporte de:
FAUBA Digital - Facultad de Agronomía (UBA) de Universidad de Buenos Aires
id snrd:2021schrauf
record_format dspace
spelling snrd:2021schrauf2025-09-08T09:43:08Z Schrauf, Matías Florián Campos, Gustavo de los Munilla Leguizamón, Sebastián 2021 Fil: Schrauf, Matías Florián. Universidad de Buenos Aires. Facultad de Agronomía. Buenos Aires, Argentina. Fil: Schrauf, Matías Florián. Wageningen University and Research. Wageningen Livestock Research. Animal Breeding and Genomics. Wageningen, Países Bajos. Fil: Campos, Gustavo de los. Michigan State University. Departments of Epidemiology, Biostatistics, Statistics and Probabilty. Institute for Quantitative Health Science and Engineering. East Lansing, MI, Estados Unidos. Fil: Munilla Leguizamón, Sebastián. Universidad de Buenos Aires. Facultad de Agronomía. Buenos Aires, Argentina. Fil: Munilla Leguizamón, Sebastián. Universidad de Buenos Aires. Facultad de Ciencias Veterinarias. Instituto de Investigaciones en Producción Animal (INPA). Buenos Aires, Argentina. Fil: Munilla Leguizamón, Sebastián. CONICET - Universidad de Buenos Aires. Facultad de Ciencias Veterinarias. Instituto de Investigaciones en Producción Animal (INPA). Buenos Aires, Argentina. 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. tbls., grafs. application/pdf 10.3389/fpls.2021.734512 http://ri.agro.uba.ar/greenstone3/library/collection/arti/document/2021schrauf eng info:eu-repo/semantics/openAccess openAccess openAccess http://ri.agro.uba.ar/greenstone3/library/page/biblioteca#section4 Frontiers in Plant Science Vol.12 art. 734512 http://www.frontiersin.org GENOMIC SELECTION CROSS VALIDATION PLANT BREEDING GENOMIC MODELS MODEL SELECTION Comparing genomic prediction models by means of cross validation info:ar-repo/semantics/artículo info:eu-repo/semantics/article publishedVersion info:eu-repo/semantics/publishedVersion
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-140
collection FAUBA Digital - Facultad de Agronomía (UBA)
language Inglés
orig_language_str_mv eng
topic GENOMIC SELECTION
CROSS VALIDATION
PLANT BREEDING
GENOMIC MODELS
MODEL SELECTION
spellingShingle GENOMIC SELECTION
CROSS VALIDATION
PLANT BREEDING
GENOMIC MODELS
MODEL SELECTION
Schrauf, Matías Florián
Campos, Gustavo de los
Munilla Leguizamón, Sebastián
Comparing genomic prediction models by means of cross validation
topic_facet GENOMIC SELECTION
CROSS VALIDATION
PLANT BREEDING
GENOMIC MODELS
MODEL SELECTION
description Fil: Schrauf, Matías Florián. Universidad de Buenos Aires. Facultad de Agronomía. Buenos Aires, Argentina.
format Artículo
Artículo
publishedVersion
publishedVersion
author Schrauf, Matías Florián
Campos, Gustavo de los
Munilla Leguizamón, Sebastián
author_facet Schrauf, Matías Florián
Campos, Gustavo de los
Munilla Leguizamón, Sebastián
author_sort Schrauf, Matías Florián
title Comparing genomic prediction models by means of cross validation
title_short Comparing genomic prediction models by means of cross validation
title_full Comparing genomic prediction models by means of cross validation
title_fullStr Comparing genomic prediction models by means of cross validation
title_full_unstemmed Comparing genomic prediction models by means of cross validation
title_sort comparing genomic prediction models by means of cross validation
publishDate 2021
url http://ri.agro.uba.ar/greenstone3/library/collection/arti/document/2021schrauf
work_keys_str_mv AT schraufmatiasflorian comparinggenomicpredictionmodelsbymeansofcrossvalidation
AT camposgustavodelos comparinggenomicpredictionmodelsbymeansofcrossvalidation
AT munillaleguizamonsebastian comparinggenomicpredictionmodelsbymeansofcrossvalidation
_version_ 1851371339736154112

Ejemplares similares