EUVIMEDEUVIMED entdecken
Crossref

Residual network improves the prediction accuracy of genomic selection

Huaxuan Wu iD, Bingxi Gao, Rong Zhang, Zehang Huang, Zongjun Yin, Xiaoxiang Hu, Cai-Xia Yang, Zhi-Qiang Du

Animal Genetics · 2024

DOI: 10.1111/age.13445 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animal Genetics, 2024. Verfasst von Huaxuan Wu und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Animal Science and Technology, Yangtze University, Jingzhou, Hubei, China. Hauptthemen laut MEDLINE: Triticum, Bayes Theorem, Selection, Genetic. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 65 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Genetic improvement of complex traits in animal and plant breeding depends on the efficient and accurate estimation of breeding values. Deep learning methods have been shown to be not superior over traditional genomic selection (GS) methods, partially due to the degradation problem (i.e. with the increase of the model depth, the performance of the deeper model deteriorates). Since the deep learning method residual network (ResNet) is designed to solve gradient degradation, we examined its performance and factors related to its prediction accuracy in GS. Here we compared the prediction accuracy of conventional genomic best linear unbiased prediction, Bayesian methods (BayesA, BayesB, BayesC, and Bayesian Lasso), and two deep learning methods, convolutional neural network and ResNet, on three datasets (wheat, simulated and real pig data). ResNet outperformed other methods in both Pearson's correlation coefficient (PCC) and mean squared error (MSE) on the wheat and simulated data. For the pig backfat depth trait, ResNet still had the lowest MSE, whereas Bayesian Lasso had the highest PCC. We further clustered the pig data into four groups and, on one separated group, ResNet had the highest prediction accuracy (both PCC and MSE). Transfer learning was adopted and capable of enhancing the performance of both convolutional neural network and ResNet. Taken together, our findings indicate that ResNet could improve GS prediction accuracy, affected potentially by factors such as the genetic architecture of complex traits, data volume, and heterogeneity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TriticumBayes TheoremSelection, GeneticAnimalsSwineGenomicsSus scrofaDeep LearningModels, GeneticNeural Networks, ComputerBreeding

Stichwörter der Autor:innen

deep learninggenomic selectionprediction accuracyresidual network

Autor:innen und Institutionen

  • College of Animal Science and Technology, Yangtze University, Jingzhou, Hubei, China.
  • College of Animal Science and Technology, Anhui Agricultural University, Hefei, Anhui, China.
  • State Key Laboratory for Agrobiotechnology, China Agricultural University, Beijing, China.

ORCID-Profile: Huaxuan Wu

Zitieren

APA

Wu, H., Gao, B., Zhang, R., Huang, Z., Yin, Z., Hu, X., Yang, C. X., & Du, Z. Q. (2024). Residual network improves the prediction accuracy of genomic selection. Animal Genetics. https://doi.org/10.1111/age.13445

Vancouver

Wu H, Gao B, Zhang R, Huang Z, Yin Z, Hu X, et al. Residual network improves the prediction accuracy of genomic selection. Animal Genetics. 2024. doi:10.1111/age.13445

BibTeX
@article{Wu2024,
  author = {Wu, Huaxuan and Gao, Bingxi and Zhang, Rong and Huang, Zehang and Yin, Zongjun and Hu, Xiaoxiang and Yang, Cai-Xia and Du, Zhi-Qiang},
  title = {Residual network improves the prediction accuracy of genomic selection},
  journal = {Animal Genetics},
  year = {2024},
  doi = {10.1111/age.13445}
}
Kostenlos starten →