Feature engineering and parameter tuning: improving phenomic prediction ability in multi-environmental durum wheat breeding trials
Theoretical and Applied Genetics · 2024-08 · 137 (8)
DOI: 10.1007/s00122-024-04695-w ↗Kurz gefasst
Fachartikel in der Zeitschrift Theoretical and Applied Genetics, online erschienen am 22.07.2024. Verfasst von Carina Meyenberg und 3 weiteren Autor:innen. Beteiligte Einrichtung: State Plant Breeding Institute, University of Hohenheim, Fruwirthstr. 21, 70599, Stuttgart, Germany. Hauptthemen laut MEDLINE: Triticum, Plant Breeding, Phenotype, Genotype. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, Bundesanstalt für Landwirtschaft und Ernährung, Universität Hohenheim.
Abstract (Originalsprache)
Key Message Optimized phenomic selection in durum wheat uses near-infrared spectra, feature engineering and parameter tuning. Our study reports improvements in predictive ability and emphasizes customized preprocessing for different traits and models. Abstract The success of plant breeding programs depends on efficient selection decisions. Phenomic selection has been proposed as a tool to predict phenotype performance based on near-infrared spectra (NIRS) to support selection decisions. In this study, we test the performance of phenomic selection in multi-environmental trials from our durum wheat breeding program for three breeding scenarios and use feature engineering as well as parameter tuning to improve the phenomic prediction ability. In addition, we investigate the influence of genotype and environment on the phenomic prediction ability for agronomic and quality traits. Preprocessing, based on a grid search over the Savitzky–Golay filter parameters based on 756,000 genotype best linear unbiased estimate (BLUE) computations, improved the phenomic prediction ability by up to 1500% (0.02–0.3). Furthermore, we show that preprocessing should be optimized depending on the dataset, trait, and model used for prediction. The phenomic prediction scenarios in our durum breeding program resulted in low-to-moderate prediction abilities with the highest and most stable prediction results when predicting new genotypes in the same environment as used for model training. This is consistent with the finding that NIRS capture both the genotype and genotype-by-environment $$(G\times E)$$ ( G × E ) interaction variance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- State Plant Breeding Institute, University of Hohenheim, Fruwirthstr. 21, 70599, Stuttgart, Germany.
- State Plant Breeding Institute, University of Hohenheim, Fruwirthstr. 21, 70599, Stuttgart, Germany. patrick.thorwarth@uni-hohenheim.de.
Förderung
- Deutsche Forschungsgemeinschaft
- Bundesanstalt für Landwirtschaft und Ernährung
- Universität Hohenheim
Zitieren
APA
Meyenberg, C., Braun, V., Longin, C. F. H., & Thorwarth, P. (2024). Feature engineering and parameter tuning: improving phenomic prediction ability in multi-environmental durum wheat breeding trials. Theoretical and Applied Genetics, 137(8). https://doi.org/10.1007/s00122-024-04695-w
Vancouver
Meyenberg C, Braun V, Longin CFH, Thorwarth P. Feature engineering and parameter tuning: improving phenomic prediction ability in multi-environmental durum wheat breeding trials. Theoretical and Applied Genetics. 2024;137(8). doi:10.1007/s00122-024-04695-w
BibTeX
@article{Meyenberg2024,
author = {Meyenberg, Carina and Braun, Vincent and Longin, Carl Friedrich Horst and Thorwarth, Patrick},
title = {Feature engineering and parameter tuning: improving phenomic prediction ability in multi-environmental durum wheat breeding trials},
journal = {Theoretical and Applied Genetics},
year = {2024},
volume = {137},
number = {8},
doi = {10.1007/s00122-024-04695-w}
}
EUVIMED