@article{Zhang2026, 
author = {Shanghui Zhang and Mei Song and Jun Zheng and Xianggeng Huang and Xinping Zhang and Ran Qin and Chunhua Zhao and Yongzhen Wu and Han Sun and Guangchen Liu and Feng Chen and Shusong Zheng and Fa Cui},
title = {Hi4GS: An interpretable hybrid feature selection framework for genomic selection and application in identifying wheat yield-associated SNPs},
year = {2026},
journal = {The Crop Journal},
volume = {14},
number = {4},
pages = {1374-1387},
keywords = {Genomic selection, Hybridfeature selection, Interpretable machine learning, Wheat yield, SHAP},
url = {https://www.sciopen.com/article/10.1016/j.cj.2026.02.022},
doi = {10.1016/j.cj.2026.02.022},
abstract = {We present Hi4GS, a hybrid feature selection (HFS) algorithm for selecting SNP subsets from high-dimensional genotypes to improve the prediction of genomic estimated breeding value (GEBV) under genomic selection (GS). Hi4GS combines feature importance weighting with quantity determining to construct a fused feature set from which it extracts an optimal feature subset for subsequent GS. In a study of wheat using four datasets covering 11 yield traits via large-scale GS models, the SNPs selected by Hi4GS increased the average predictive accuracy by over 82% than using all SNPs. Hi4GS was used to identify SNPs potentially affecting wheat yield, and SHAP-based interpretability was applied to explain the contributions of these SNPs and their potential interactions. Hi4GS can be used for assisting in improving the prediction accuracy of GS, wheat and other plants’ yield-associated SNPs identification, and target information for breeding chip development. The free R package Hi4GS is available at https://github.com/shgs19/Hi4GS.}
}