Artificial intelligence meets genomic selection: comparing deep learning and GBLUP across diverse plant datasets

To enhance the implementation of genomic selection (GS) in plant breeding, we conducted a comprehensive comparative analysis of deep learning (DL) models and genomic best linear unbiased predictor (GBLUP) methods across 14 real-world datasets derived from diverse plant breeding programs. We evaluate...

Full description

Saved in:
Bibliographic Details
Main Authors: Abelardo Montesinos-López, Osval A. Montesinos-López, Sofia Ramos-Pulido, Brandon Alejandro Mosqueda-González, Edgar Alejandro Guerrero-Arroyo, José Crossa, Rodomiro Ortiz
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Genetics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fgene.2025.1568705/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850174725704122368
author Abelardo Montesinos-López
Osval A. Montesinos-López
Sofia Ramos-Pulido
Brandon Alejandro Mosqueda-González
Edgar Alejandro Guerrero-Arroyo
José Crossa
José Crossa
Rodomiro Ortiz
author_facet Abelardo Montesinos-López
Osval A. Montesinos-López
Sofia Ramos-Pulido
Brandon Alejandro Mosqueda-González
Edgar Alejandro Guerrero-Arroyo
José Crossa
José Crossa
Rodomiro Ortiz
author_sort Abelardo Montesinos-López
collection DOAJ
description To enhance the implementation of genomic selection (GS) in plant breeding, we conducted a comprehensive comparative analysis of deep learning (DL) models and genomic best linear unbiased predictor (GBLUP) methods across 14 real-world datasets derived from diverse plant breeding programs. We evaluated model performance by meticulously tuning hyperparameters specific to each dataset, aiming to maximize predictive accuracy and reliability. Our results demonstrated that DL models effectively captured complex, non-linear genetic patterns, frequently providing superior predictive performance compared to GBLUP, especially in smaller datasets. However, neither method consistently outperformed the other across all evaluated traits and scenarios. The analysis revealed that the success of DL models significantly depended on careful parameter optimization, reinforcing the importance of rigorous model tuning procedures. In the discussion, we emphasize the complementary nature of DL and GBLUP methods, highlighting that the choice between these models should be driven by the specific characteristics of the traits under study and the evaluation metrics prioritized in breeding programs. These insights contribute practical guidelines for selecting and optimizing genomic prediction models to achieve robust outcomes in plant breeding contexts.
format Article
id doaj-art-1ce264fbc9954dddbba6aa31689fd4e1
institution OA Journals
issn 1664-8021
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Genetics
spelling doaj-art-1ce264fbc9954dddbba6aa31689fd4e12025-08-20T02:19:37ZengFrontiers Media S.A.Frontiers in Genetics1664-80212025-04-011610.3389/fgene.2025.15687051568705Artificial intelligence meets genomic selection: comparing deep learning and GBLUP across diverse plant datasetsAbelardo Montesinos-López0Osval A. Montesinos-López1Sofia Ramos-Pulido2Brandon Alejandro Mosqueda-González3Edgar Alejandro Guerrero-Arroyo4José Crossa5José Crossa6Rodomiro Ortiz7Departamento de Matemáticas, Centro Universitario de Ciencias Exactas e Ingenierías (CUCEI), Universidad de Guadalajara, Guadalajara, Jalisco, MexicoFacultad de Telemática, Universidad de Colima, Colima, MexicoDepartamento de Matemáticas, Centro Universitario de Ciencias Exactas e Ingenierías (CUCEI), Universidad de Guadalajara, Guadalajara, Jalisco, MexicoInstitut National des Sciences Appliquées de Lyon: Lyon, Villeurbanne, FranceDepartamento de Matemáticas, Centro Universitario de Ciencias Exactas e Ingenierías (CUCEI), Universidad de Guadalajara, Guadalajara, Jalisco, MexicoInternational Maize and Wheat Improvement Center (CIMMYT), Texcoco, MexicoColegio de Postgraduate Program in Socioeconomics, Statistics, and Informatics (PSEI) at the Montecillo Campus, Texcoco, MexicoDepartment of Plant Breeding at SLU, Swedish University of Agricultural Sciences, Uppsala, SwedenTo enhance the implementation of genomic selection (GS) in plant breeding, we conducted a comprehensive comparative analysis of deep learning (DL) models and genomic best linear unbiased predictor (GBLUP) methods across 14 real-world datasets derived from diverse plant breeding programs. We evaluated model performance by meticulously tuning hyperparameters specific to each dataset, aiming to maximize predictive accuracy and reliability. Our results demonstrated that DL models effectively captured complex, non-linear genetic patterns, frequently providing superior predictive performance compared to GBLUP, especially in smaller datasets. However, neither method consistently outperformed the other across all evaluated traits and scenarios. The analysis revealed that the success of DL models significantly depended on careful parameter optimization, reinforcing the importance of rigorous model tuning procedures. In the discussion, we emphasize the complementary nature of DL and GBLUP methods, highlighting that the choice between these models should be driven by the specific characteristics of the traits under study and the evaluation metrics prioritized in breeding programs. These insights contribute practical guidelines for selecting and optimizing genomic prediction models to achieve robust outcomes in plant breeding contexts.https://www.frontiersin.org/articles/10.3389/fgene.2025.1568705/fullbenchmarkingdeep learningGBLUPgenomic selectionplant breeding
spellingShingle Abelardo Montesinos-López
Osval A. Montesinos-López
Sofia Ramos-Pulido
Brandon Alejandro Mosqueda-González
Edgar Alejandro Guerrero-Arroyo
José Crossa
José Crossa
Rodomiro Ortiz
Artificial intelligence meets genomic selection: comparing deep learning and GBLUP across diverse plant datasets
Frontiers in Genetics
benchmarking
deep learning
GBLUP
genomic selection
plant breeding
title Artificial intelligence meets genomic selection: comparing deep learning and GBLUP across diverse plant datasets
title_full Artificial intelligence meets genomic selection: comparing deep learning and GBLUP across diverse plant datasets
title_fullStr Artificial intelligence meets genomic selection: comparing deep learning and GBLUP across diverse plant datasets
title_full_unstemmed Artificial intelligence meets genomic selection: comparing deep learning and GBLUP across diverse plant datasets
title_short Artificial intelligence meets genomic selection: comparing deep learning and GBLUP across diverse plant datasets
title_sort artificial intelligence meets genomic selection comparing deep learning and gblup across diverse plant datasets
topic benchmarking
deep learning
GBLUP
genomic selection
plant breeding
url https://www.frontiersin.org/articles/10.3389/fgene.2025.1568705/full
work_keys_str_mv AT abelardomontesinoslopez artificialintelligencemeetsgenomicselectioncomparingdeeplearningandgblupacrossdiverseplantdatasets
AT osvalamontesinoslopez artificialintelligencemeetsgenomicselectioncomparingdeeplearningandgblupacrossdiverseplantdatasets
AT sofiaramospulido artificialintelligencemeetsgenomicselectioncomparingdeeplearningandgblupacrossdiverseplantdatasets
AT brandonalejandromosquedagonzalez artificialintelligencemeetsgenomicselectioncomparingdeeplearningandgblupacrossdiverseplantdatasets
AT edgaralejandroguerreroarroyo artificialintelligencemeetsgenomicselectioncomparingdeeplearningandgblupacrossdiverseplantdatasets
AT josecrossa artificialintelligencemeetsgenomicselectioncomparingdeeplearningandgblupacrossdiverseplantdatasets
AT josecrossa artificialintelligencemeetsgenomicselectioncomparingdeeplearningandgblupacrossdiverseplantdatasets
AT rodomiroortiz artificialintelligencemeetsgenomicselectioncomparingdeeplearningandgblupacrossdiverseplantdatasets