Cargando…

A Multi-Trait Gaussian Kernel Genomic Prediction Model under Three Tunning Strategies

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Kismiantini, Montesinos-López, Abelardo, Cano-Páez, Bernabe, Montesinos-López, J. Cricelio, Chavira-Flores, Moisés, Montesinos-López, Osval A., Crossa, José
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9778253/
https://www.ncbi.nlm.nih.gov/pubmed/36553548
http://dx.doi.org/10.3390/genes13122279
_version_ 1784856312574640128
author Kismiantini,
Montesinos-López, Abelardo
Cano-Páez, Bernabe
Montesinos-López, J. Cricelio
Chavira-Flores, Moisés
Montesinos-López, Osval A.
Crossa, José
author_facet Kismiantini,
Montesinos-López, Abelardo
Cano-Páez, Bernabe
Montesinos-López, J. Cricelio
Chavira-Flores, Moisés
Montesinos-López, Osval A.
Crossa, José
author_sort Kismiantini,
collection PubMed
description 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.
format Online
Article
Text
id pubmed-9778253
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-97782532022-12-23 A Multi-Trait Gaussian Kernel Genomic Prediction Model under Three Tunning Strategies Kismiantini, Montesinos-López, Abelardo Cano-Páez, Bernabe Montesinos-López, J. Cricelio Chavira-Flores, Moisés Montesinos-López, Osval A. Crossa, José Genes (Basel) Article 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. MDPI 2022-12-03 /pmc/articles/PMC9778253/ /pubmed/36553548 http://dx.doi.org/10.3390/genes13122279 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kismiantini,
Montesinos-López, Abelardo
Cano-Páez, Bernabe
Montesinos-López, J. Cricelio
Chavira-Flores, Moisés
Montesinos-López, Osval A.
Crossa, José
A Multi-Trait Gaussian Kernel Genomic Prediction Model under Three Tunning Strategies
title A Multi-Trait Gaussian Kernel Genomic Prediction Model under Three Tunning Strategies
title_full A Multi-Trait Gaussian Kernel Genomic Prediction Model under Three Tunning Strategies
title_fullStr A Multi-Trait Gaussian Kernel Genomic Prediction Model under Three Tunning Strategies
title_full_unstemmed A Multi-Trait Gaussian Kernel Genomic Prediction Model under Three Tunning Strategies
title_short A Multi-Trait Gaussian Kernel Genomic Prediction Model under Three Tunning Strategies
title_sort multi-trait gaussian kernel genomic prediction model under three tunning strategies
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9778253/
https://www.ncbi.nlm.nih.gov/pubmed/36553548
http://dx.doi.org/10.3390/genes13122279
work_keys_str_mv AT kismiantini amultitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT montesinoslopezabelardo amultitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT canopaezbernabe amultitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT montesinoslopezjcricelio amultitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT chavirafloresmoises amultitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT montesinoslopezosvala amultitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT crossajose amultitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT kismiantini multitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT montesinoslopezabelardo multitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT canopaezbernabe multitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT montesinoslopezjcricelio multitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT chavirafloresmoises multitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT montesinoslopezosvala multitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies
AT crossajose multitraitgaussiankernelgenomicpredictionmodelunderthreetunningstrategies