GRE: A Framework for Significant SNP Identification Associated with Wheat Yield Leveraging GWAS–Random Forest Joint Feature Selection and Explainable Machine Learning Genomic Selection Algorithm
Genes · 2025
DOI: 10.3390/genes16101125 ↗Kurz gefasst
Fachartikel in der Zeitschrift Genes, 2025. Verfasst von Mei Song und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Statistics, Ludong University, Yantai 264025, China. Hauptthemen laut MEDLINE: Triticum, Polymorphism, Single Nucleotide, Machine Learning, Genome-Wide Association Study. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shandong Provincial Key R&D Plan, the Taishan Scholar Young Expert, Shandong Provincial Key R&D Plan.
Abstract (Originalsprache)
Background
Facing global wheat production pressures such as environmental degradation and reduced cultivated land, breeding innovation is urgent to boost yields. Genomic selection (GS) is a useful wheat breeding technology to make the breeding process more efficient, increasing the genetic gain per unit time and cost. Precise genomic estimated breeding value (GEBV) via genome-wide markers is usually hampered by high-dimensional genomic data.
Methods
To address this, we propose GRE, a framework combining genome-wide association study (GWAS)’s biological significance and random forest (RF)’s prediction efficiency for an explainable machine learning GS model. First, GRE identifies significant SNPs affecting wheat yield traits by comparison of the constructed 24 SNP subsets (intersection/union) selected by leveraging GWAS and RF, to analyze the marker scale’s impact. Furthermore, GRE compares six GS algorithms (GBLUP and five machine learning models), evaluating performance via prediction accuracy (Pearson correlation coefficient, PCC) and error. Additionally, GRE leverages Shapley additive explanations (SHAP) explainable techniques to overcome traditional GS models’ “black box” limitation, enabling cross-scale quantitative analysis and revealing how significant SNPs affect yield traits.
Results
Results show that XGBoost and ElasticNet perform best in the union (383 SNPs) of GWAS and RF’s TOP 200 SNPs, with high accuracy (PCC > 0.864) and stability (standard deviation, SD < 0.005), and the significant SNPs identified by XGBoost are precisely explained by their main and interaction effects on wheat yield by SHAP.
Conclusions
This study provides tool support for intelligent breeding chip design, important trait gene mining, and GS technology field transformation, aiding global agricultural sustainable productivity.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mathematics and Statistics, Ludong University, Yantai 264025, China.
- School of Horticulture, Ludong University, Yantai 264025, China.
- Yantai Key Laboratory of Molecular Breeding for High-Yield and Stress-Resistant Crops and Efficient Cultivation, Yantai 264000, China.
ORCID-Profile: Yongzhen Wu
Förderung
- Shandong Provincial Key R&D Plan
- the Taishan Scholar Young Expert
- Shandong Provincial Key R&D Plan
- Taishan Scholar Young Expert
Zitieren
APA
Song, M., Zhang, S., Qiu, S., Qin, R., Zhao, C., Wu, Y., Sun, H., Liu, G., & Cui, F. (2025). GRE: A Framework for Significant SNP Identification Associated with Wheat Yield Leveraging GWAS–Random Forest Joint Feature Selection and Explainable Machine Learning Genomic Selection Algorithm. Genes. https://doi.org/10.3390/genes16101125
Vancouver
Song M, Zhang S, Qiu S, Qin R, Zhao C, Wu Y, et al. GRE: A Framework for Significant SNP Identification Associated with Wheat Yield Leveraging GWAS–Random Forest Joint Feature Selection and Explainable Machine Learning Genomic Selection Algorithm. Genes. 2025. doi:10.3390/genes16101125
BibTeX
@article{Song2025,
author = {Song, Mei and Zhang, Shanghui and Qiu, Shijie and Qin, Ran and Zhao, Chunhua and Wu, Yongzhen and Sun, Han and Liu, Guangchen and Cui, Fa},
title = {GRE: A Framework for Significant SNP Identification Associated with Wheat Yield Leveraging GWAS–Random Forest Joint Feature Selection and Explainable Machine Learning Genomic Selection Algorithm},
journal = {Genes},
year = {2025},
doi = {10.3390/genes16101125}
}
EUVIMED