EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A transformer-based genomic prediction method fused with knowledge-guided module

Cuiling Wu iD, Yiyi Zhang, Zhiwen Ying, Ling Li, Jun Wang, Hui Yu, Mengchen Zhang, Xianzhong Feng, Xinghua Wei, Xiaogang Xu

Briefings in Bioinformatics · 22.11.2023 · 25 (1)

DOI: 10.1093/bib/bbad438 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 06.12.2023. Verfasst von Cuiling Wu und 9 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Intelligent Computing, Zhejiang Lab, Hangzhou 311121, China. Hauptthemen laut MEDLINE: Genome-Wide Association Study, Models, Genetic. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Program of Zhejiang Lab.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Genomic prediction (GP) uses single nucleotide polymorphisms (SNPs) to establish associations between markers and phenotypes. Selection of early individuals by genomic estimated breeding value shortens the generation interval and speeds up the breeding process. Recently, methods based on deep learning (DL) have gained great attention in the field of GP. In this study, we explore the application of Transformer-based structures to GP and develop a novel deep-learning model named GPformer. GPformer obtains a global view by gleaning beneficial information from all relevant SNPs regardless of the physical distance between SNPs. Comprehensive experimental results on five different crop datasets show that GPformer outperforms ridge regression-based linear unbiased prediction (RR-BLUP), support vector regression (SVR), light gradient boosting machine (LightGBM) and deep neural network genomic prediction (DNNGP) in terms of mean absolute error, Pearson’s correlation coefficient and the proposed metric consistent index. Furthermore, we introduce a knowledge-guided module (KGM) to extract genome-wide association studies-based information, which is fused into GPformer as prior knowledge. KGM is very flexible and can be plugged into any DL network. Ablation studies of KGM on three datasets illustrate the efficiency of KGM adequately. Moreover, GPformer is robust and stable to hyperparameters and can generalize to each phenotype of every dataset, which is suitable for practical application scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Genome-Wide Association StudyModels, GeneticHumansGenotypeBayes TheoremGenomicsPhenotypePolymorphism, Single Nucleotide

Stichwörter der Autor:innen

Transformerdeep learninggenomic predictionknowledge-guided moduleprediction method

Autor:innen und Institutionen

  • Institute of Intelligent Computing, Zhejiang Lab, Hangzhou 311121, China.
  • Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130012, China.
  • State Key Laboratory of Rice Biology, China National Rice Research Institute, Hangzhou 310006, China.
  • School of Computer and Information Engineering, Zhejiang Gongshang University, Hangzhou 310018, China.

ORCID-Profile: Cuiling Wu

Förderung

  • Research Program of Zhejiang Lab

Zitieren

APA

Wu, C., Zhang, Y., Ying, Z., Li, L., Wang, J., Yu, H., Zhang, M., Feng, X., Wei, X., & Xu, X. (2023). A transformer-based genomic prediction method fused with knowledge-guided module. Briefings in Bioinformatics, 25(1). https://doi.org/10.1093/bib/bbad438

Vancouver

Wu C, Zhang Y, Ying Z, Li L, Wang J, Yu H, et al. A transformer-based genomic prediction method fused with knowledge-guided module. Briefings in Bioinformatics. 2023;25(1). doi:10.1093/bib/bbad438

BibTeX
@article{Wu2023,
  author = {Wu, Cuiling and Zhang, Yiyi and Ying, Zhiwen and Li, Ling and Wang, Jun and Yu, Hui and Zhang, Mengchen and Feng, Xianzhong and Wei, Xinghua and Xu, Xiaogang},
  title = {A transformer-based genomic prediction method fused with knowledge-guided module},
  journal = {Briefings in Bioinformatics},
  year = {2023},
  volume = {25},
  number = {1},
  doi = {10.1093/bib/bbad438}
}
Kostenlos starten →