EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

GE-BiFormer: bidirectional cross-attention integration of genomic and Enviromic data for genotype-by-environment prediction in maize

Shuchang Zhou, Weipeng Fang, Runing Gao, Xi Long, Lu Chen, Xianliang Hu, Ting Zhao iD

Briefings in Bioinformatics · 03.07.2026 · 27 (4)

DOI: 10.1093/bib/bbag437 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 10.08.2026. Verfasst von Shuchang Zhou und 6 weiteren Autor:innen. Beteiligte Einrichtung: Zhejiang Provincial Key Laboratory of Crop Genetic Resources, Institute of Crop Science, Plant Precision Breeding Academy, College of Agriculture and…. Hauptthemen laut MEDLINE: Zea mays, Genotype, Gene-Environment Interaction, Genomics. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: the Open Project of Zhejiang Key Laboratory of Crop Germplasm Innovation and Utilization., the Natural Science Foundation of Zhejiang Province, Biological Breeding-National Science and Technology Major Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Phenotypic variation is shaped by genotype, environment, and their interactions. Accurately predicting crop performance across diverse environments therefore requires models capable of capturing these complex and context-dependent relationships. Here, we developed GE-BiFormer, an explainable multimodal deep learning framework for genotype-by-environment prediction. GE-BiFormer integrates genomic and enviromic information through dual-path feature disentanglement, tokenized bidirectional cross-attention, and mixture-of-experts routing, enabling fine-grained modeling of genetic effects, environmental responses, and their interplay. We evaluated GE-BiFormer using the Genomes to Fields maize dataset. After preprocessing, the dataset contained approximately 360,000 non-missing genotype-environment-trait observations across six traits. The evaluation focused on three breeding-relevant scenarios: predicting known genotypes in unseen environments, predicting novel genotypes in known environments, and predicting novel genotypes in entirely untested environments. Across these scenarios, GE-BiFormer consistently outperformed GBLUP, classical machine learning methods, and recent deep learning approaches. External validation on an independent winter wheat dataset further demonstrated the broad applicability and cross-dataset robustness of GE-BiFormer across crop species. In addition, SHAP analysis identified biologically interpretable environmental drivers, while mixture-of-experts routing revealed trait-specific computational specialization. Together, these results demonstrate that GE-BiFormer provides a practical and interpretable framework for environment-aware genomic selection and climate-adaptive crop breeding.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Zea maysGenotypeGene-Environment InteractionGenomicsGenome, PlantDeep LearningPhenotypeModels, Genetic

Stichwörter der Autor:innen

Enviromicsbidirectional cross-attentiondeep learninggenomic predictiongenotype-by-environment interactionmultimodal data integration

Autor:innen und Institutionen

  • Zhejiang Provincial Key Laboratory of Crop Genetic Resources, Institute of Crop Science, Plant Precision Breeding Academy, College of Agriculture and Biotechnology, Zhejiang University, Hangzhou, China.
  • School of Mathematical Sciences, Zhejiang University, Hangzhou, China.

ORCID-Profile: Ting Zhao

Förderung

  • the Open Project of Zhejiang Key Laboratory of Crop Germplasm Innovation and Utilization.
  • the Natural Science Foundation of Zhejiang Province
  • Biological Breeding-National Science and Technology Major Project
  • SanNongJiuFang Project of Zhejiang Province

Zitieren

APA

Zhou, S., Fang, W., Gao, R., Long, X., Chen, L., Hu, X., & Zhao, T. (2026). GE-BiFormer: bidirectional cross-attention integration of genomic and Enviromic data for genotype-by-environment prediction in maize. Briefings in Bioinformatics, 27(4). https://doi.org/10.1093/bib/bbag437

Vancouver

Zhou S, Fang W, Gao R, Long X, Chen L, Hu X, et al. GE-BiFormer: bidirectional cross-attention integration of genomic and Enviromic data for genotype-by-environment prediction in maize. Briefings in Bioinformatics. 2026;27(4). doi:10.1093/bib/bbag437

BibTeX
@article{Zhou2026,
  author = {Zhou, Shuchang and Fang, Weipeng and Gao, Runing and Long, Xi and Chen, Lu and Hu, Xianliang and Zhao, Ting},
  title = {GE-BiFormer: bidirectional cross-attention integration of genomic and Enviromic data for genotype-by-environment prediction in maize},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {4},
  doi = {10.1093/bib/bbag437}
}
Kostenlos starten →