A comparison between three tuning strategies for gaussian kernels in the context of univariate genomic prediction

Genomic prediction is revolutionizing plant breeding since candidate genotypes can be selected without the need to measure their trait in the field. When a reference population contains both phenotypic and genotypic information, it is trained by a statistical machine learning method that is subseque...

Descripción completa

Detalles Bibliográficos
Autores: Montesinos-Lopez, O.A., Carter, A., Bernal Sandoval, D.A., Cano-Paez, B., Montesinos-López, A., Crossa, J.
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:México
Institución:Centro Internacional de Mejoramiento de Maíz y Trigo
Repositorio:Repositorio Institucional de Publicaciones Multimedia del CIMMYT
OAI Identifier:oai:repository.cimmyt.org:10883/22400
Acceso en línea:https://hdl.handle.net/10883/22400
Access Level:acceso abierto
Palabra clave:AGRICULTURAL SCIENCES AND BIOTECHNOLOGY
Tuning
Genomic Prediction
Gaussian Kernel
Grid Search
Bayesian Optimization
KERNELS
MACHINE LEARNING
FORECASTING
TRITICUM AESTIVUM
WHEAT
Genetic Resources
id MX_e73a7c8b2bb0dae0f6a2e24e99cfbac0
oai_identifier_str oai:repository.cimmyt.org:10883/22400
network_acronym_str MX
network_name_str México
repository_id_str
spelling A comparison between three tuning strategies for gaussian kernels in the context of univariate genomic predictionMontesinos-Lopez, O.A.Carter, A.Bernal Sandoval, D.A.Cano-Paez, B.Montesinos-López, A.Crossa, J.AGRICULTURAL SCIENCES AND BIOTECHNOLOGYTuningGenomic PredictionGaussian KernelGrid SearchBayesian OptimizationKERNELSMACHINE LEARNINGFORECASTINGTRITICUM AESTIVUMWHEATGenetic ResourcesGenomic prediction is revolutionizing plant breeding since candidate genotypes can be selected without the need to measure their trait in the field. When a reference population contains both phenotypic and genotypic information, it is trained by a statistical machine learning method that is subsequently used for making predictions of breeding or phenotypic values of candidate genotypes that were only genotyped. Nevertheless, the successful implementation of the genomic selection (GS) methodology depends on many factors. One key factor is the type of statistical machine learning method used since some are unable to capture nonlinear patterns available in the data. While kernel methods are powerful statistical machine learning algorithms that capture complex nonlinear patterns in the data, their successful implementation strongly depends on the careful tuning process of the involved hyperparameters. As such, in this paper we compare three methods of tuning (manual tuning, grid search, and Bayesian optimization) for the Gaussian kernel under a Bayesian best linear unbiased predictor model. We used six real datasets of wheat (Triticum aestivum L.) to compare the three strategies of tuning. We found that if we want to obtain the major benefits of using Gaussian kernels, it is very important to perform a careful tuning process. The best prediction performance was observed when the tuning process was performed with grid search and Bayesian optimization. However, we did not observe relevant differences between the grid search and Bayesian optimization approach. The observed gains in terms of prediction performance were between 2.1% and 27.8% across the six datasets under study.MDPI2023-01-14T01:10:13Z2023-01-14T01:10:13Z2022Published Versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/10883/2240010.3390/genes1312228212 art. 2282.132073-4425Genesreponame:Repositorio Institucional de Publicaciones Multimedia del CIMMYTinstname:Centro Internacional de Mejoramiento de Maíz y Trigoinstacron:CIMMYTEnglishhttps://github.com/osval78/Univariate_Tuning_Kernel_MethodBasel (Switzerland)CIMMYT manages Intellectual Assets as International Public Goods. The user is free to download, print, store and share this work. In case you want to translate or create any other derivative work and share or distribute such translation/derivative work, please contact CIMMYT-Knowledge-Center@cgiar.org indicating the work you want to use and the kind of use you intend; CIMMYT will contact you with the suitable license for that purposeOpen Accessinfo:eu-repo/semantics/openAccessoai:repository.cimmyt.org:10883/224002024-10-11T19:55:38Z
dc.title.none.fl_str_mv A comparison between three tuning strategies for gaussian kernels in the context of univariate genomic prediction
title A comparison between three tuning strategies for gaussian kernels in the context of univariate genomic prediction
spellingShingle A comparison between three tuning strategies for gaussian kernels in the context of univariate genomic prediction
Montesinos-Lopez, O.A.
AGRICULTURAL SCIENCES AND BIOTECHNOLOGY
Tuning
Genomic Prediction
Gaussian Kernel
Grid Search
Bayesian Optimization
KERNELS
MACHINE LEARNING
FORECASTING
TRITICUM AESTIVUM
WHEAT
Genetic Resources
title_short A comparison between three tuning strategies for gaussian kernels in the context of univariate genomic prediction
title_full A comparison between three tuning strategies for gaussian kernels in the context of univariate genomic prediction
title_fullStr A comparison between three tuning strategies for gaussian kernels in the context of univariate genomic prediction
title_full_unstemmed A comparison between three tuning strategies for gaussian kernels in the context of univariate genomic prediction
title_sort A comparison between three tuning strategies for gaussian kernels in the context of univariate genomic prediction
dc.creator.none.fl_str_mv Montesinos-Lopez, O.A.
Carter, A.
Bernal Sandoval, D.A.
Cano-Paez, B.
Montesinos-López, A.
Crossa, J.
author Montesinos-Lopez, O.A.
author_facet Montesinos-Lopez, O.A.
Carter, A.
Bernal Sandoval, D.A.
Cano-Paez, B.
Montesinos-López, A.
Crossa, J.
author_role author
author2 Carter, A.
Bernal Sandoval, D.A.
Cano-Paez, B.
Montesinos-López, A.
Crossa, J.
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv AGRICULTURAL SCIENCES AND BIOTECHNOLOGY
Tuning
Genomic Prediction
Gaussian Kernel
Grid Search
Bayesian Optimization
KERNELS
MACHINE LEARNING
FORECASTING
TRITICUM AESTIVUM
WHEAT
Genetic Resources
topic AGRICULTURAL SCIENCES AND BIOTECHNOLOGY
Tuning
Genomic Prediction
Gaussian Kernel
Grid Search
Bayesian Optimization
KERNELS
MACHINE LEARNING
FORECASTING
TRITICUM AESTIVUM
WHEAT
Genetic Resources
description Genomic prediction is revolutionizing plant breeding since candidate genotypes can be selected without the need to measure their trait in the field. When a reference population contains both phenotypic and genotypic information, it is trained by a statistical machine learning method that is subsequently used for making predictions of breeding or phenotypic values of candidate genotypes that were only genotyped. Nevertheless, the successful implementation of the genomic selection (GS) methodology depends on many factors. One key factor is the type of statistical machine learning method used since some are unable to capture nonlinear patterns available in the data. While kernel methods are powerful statistical machine learning algorithms that capture complex nonlinear patterns in the data, their successful implementation strongly depends on the careful tuning process of the involved hyperparameters. As such, in this paper we compare three methods of tuning (manual tuning, grid search, and Bayesian optimization) for the Gaussian kernel under a Bayesian best linear unbiased predictor model. We used six real datasets of wheat (Triticum aestivum L.) to compare the three strategies of tuning. We found that if we want to obtain the major benefits of using Gaussian kernels, it is very important to perform a careful tuning process. The best prediction performance was observed when the tuning process was performed with grid search and Bayesian optimization. However, we did not observe relevant differences between the grid search and Bayesian optimization approach. The observed gains in terms of prediction performance were between 2.1% and 27.8% across the six datasets under study.
publishDate 2022
dc.date.none.fl_str_mv 2022
2023-01-14T01:10:13Z
2023-01-14T01:10:13Z
dc.type.none.fl_str_mv Published Version
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/10883/22400
10.3390/genes13122282
url https://hdl.handle.net/10883/22400
identifier_str_mv 10.3390/genes13122282
dc.language.none.fl_str_mv English
language_invalid_str_mv English
dc.relation.none.fl_str_mv https://github.com/osval78/Univariate_Tuning_Kernel_Method
dc.rights.none.fl_str_mv Open Access
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Open Access
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.coverage.none.fl_str_mv Basel (Switzerland)
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv 12 art. 2282.
13
2073-4425
Genes
reponame:Repositorio Institucional de Publicaciones Multimedia del CIMMYT
instname:Centro Internacional de Mejoramiento de Maíz y Trigo
instacron:CIMMYT
instname_str Centro Internacional de Mejoramiento de Maíz y Trigo
instacron_str CIMMYT
institution CIMMYT
reponame_str Repositorio Institucional de Publicaciones Multimedia del CIMMYT
collection Repositorio Institucional de Publicaciones Multimedia del CIMMYT
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1858177459831177216
score 15,811543

Similares en LA Referencia