Artificial intelligence meets genomic selection: comparing deep learning and GBLUP across diverse plant datasets
Frontiers in Genetics · 29.04.2025 · 16
DOI: 10.3389/fgene.2025.1568705 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Genetics, online erschienen am 29.04.2025. Verfasst von Abelardo Montesinos-López und 6 weiteren Autor:innen. Beteiligte Einrichtung: Departamento de Matemáticas, Centro Universitario de Ciencias Exactas e Ingenierías (CUCEI), Universidad de Guadalajara, Guadalajara, Jalisco, Mexico. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Departamento de Matemáticas, Centro Universitario de Ciencias Exactas e Ingenierías (CUCEI), Universidad de Guadalajara, Guadalajara, Jalisco, Mexico.
- Facultad de Telemática, Universidad de Colima, Colima, Mexico.
- Institut National des Sciences Appliquées de Lyon: Lyon, Villeurbanne, France.
- International Maize and Wheat Improvement Center (CIMMYT), Texcoco, Mexico.
- Colegio de Postgraduate Program in Socioeconomics, Statistics, and Informatics (PSEI) at the Montecillo Campus, Texcoco, Mexico.
- Department of Plant Breeding at SLU, Swedish University of Agricultural Sciences, Uppsala, Sweden.
Zitieren
APA
Montesinos-López, A., Montesinos-López, O. A., Ramos-Pulido, S., Mosqueda-González, B. A., Guerrero-Arroyo, E. A., Crossa, J., & Ortiz, R. (2025). Artificial intelligence meets genomic selection: comparing deep learning and GBLUP across diverse plant datasets. Frontiers in Genetics, 16. https://doi.org/10.3389/fgene.2025.1568705
Vancouver
Montesinos-López A, Montesinos-López OA, Ramos-Pulido S, Mosqueda-González BA, Guerrero-Arroyo EA, Crossa J, et al. Artificial intelligence meets genomic selection: comparing deep learning and GBLUP across diverse plant datasets. Frontiers in Genetics. 2025;16. doi:10.3389/fgene.2025.1568705
BibTeX
@article{MontesinosLpez2025,
author = {Montesinos-López, Abelardo and Montesinos-López, Osval A and Ramos-Pulido, Sofia and Mosqueda-González, Brandon Alejandro and Guerrero-Arroyo, Edgar Alejandro and Crossa, José and Ortiz, Rodomiro},
title = {Artificial intelligence meets genomic selection: comparing deep learning and GBLUP across diverse plant datasets},
journal = {Frontiers in Genetics},
year = {2025},
volume = {16},
doi = {10.3389/fgene.2025.1568705}
}
EUVIMED