Optimizing genomic prediction with transfer learning under a ridge regression framework
The Plant Genome · 2025-09 · 18 (3)
DOI: 10.1002/tpg2.70049 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Plant Genome, online erschienen am 17.07.2025. Verfasst von Osval A Montesinos-López und 8 weiteren Autor:innen. Beteiligte Einrichtung: Facultad de Telemática, Universidad de Colima, Colima, México. Hauptthemen laut MEDLINE: Triticum, Genomics, Genome, Plant, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bill & Melinda Gates Foundation (INV-003439 BMGF/FCDO Accelerating Genetic Gains in Maize and Wheat for Improved Livelihoods [AGG]), USAID, Foundation for Research Levy on Agricultural Products (FFL).
Abstract (Originalsprache)
Genomic selection (GS) is a predictive plant and animal methodology that allows the selection of plants and animals based on predictions without the need to measure the phenotype. However, its practical application requires challenging prediction accuracy due to the noise observations collected in experiments in these areas. Many strategies and approaches have been proposed to improve the prediction accuracy of this methodology. This paper explores the use of transfer learning in the context of GS. Transfer learning with (1) ridge regression (RR) (Transfer RR) and (2) analytic RR (ARR) (Transfer ARR) were applied from cultivars in the proxy environment to predict those cultivars in the goal environments. Also, we compared the performance of models RR and ARR without transfer learning. We used 11 real multi‐environment datasets (wheat and rice) and evaluated them in terms of Pearson's correlation (Cor) and normalized root mean square error (NRMSE). Our study shows empirical evidence that the Transfer RR or Transfer ARR approaches significantly enhanced predictive performance. Across the datasets, Transfer RR (or Transfer ARR) method improved Cor by 22.962% and NRMSE by 5.757%, in comparison to models RR and ARR. These results underscore the potential of Transfer RR (or Transfer ARR) when enhancing predictive accuracy in this context.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Facultad de Telemática, Universidad de Colima, Colima, México.
- Colegio de Postgraduados Campus Córdoba, Veracruz, Mexico.
- Centro Universitario de Ciencias Exactas e Ingenierías (CUCEI), Universidad de Guadalajara, Guadalajara, México.
- International Maize and Wheat Improvement Center (CIMMYT), Edo. de México, México.
- Colegio de Postgraduados, Edo. de México, México.
ORCID-Profile: Eduardo A Barajas-Ramirez, Susanne Dreisigacker, José Crossa
Förderung
- Bill & Melinda Gates Foundation (INV-003439 BMGF/FCDO Accelerating Genetic Gains in Maize and Wheat for Improved Livelihoods [AGG])
- USAID
- Foundation for Research Levy on Agricultural Products (FFL)
- Wellcome Trust
- United States Agency for International Development
Zitieren
APA
Montesinos-López, O. A., Barajas-Ramirez, E. A., Salinas-Ruiz, J., Montesinos-López, A., Gerard, G., Vitale, P., Dreisigacker, S., Pierre, C. S., & Crossa, J. (2025). Optimizing genomic prediction with transfer learning under a ridge regression framework. The Plant Genome, 18(3). https://doi.org/10.1002/tpg2.70049
Vancouver
Montesinos-López OA, Barajas-Ramirez EA, Salinas-Ruiz J, Montesinos-López A, Gerard G, Vitale P, et al. Optimizing genomic prediction with transfer learning under a ridge regression framework. The Plant Genome. 2025;18(3). doi:10.1002/tpg2.70049
BibTeX
@article{MontesinosLpez2025,
author = {Montesinos-López, Osval A and Barajas-Ramirez, Eduardo A and Salinas-Ruiz, Josafhat and Montesinos-López, Abelardo and Gerard, Guillermo and Vitale, Paolo and Dreisigacker, Susanne and Pierre, Carolina Saint and Crossa, José},
title = {Optimizing genomic prediction with transfer learning under a ridge regression framework},
journal = {The Plant Genome},
year = {2025},
volume = {18},
number = {3},
doi = {10.1002/tpg2.70049}
}
EUVIMED