ReaGP: integrating residual units and attention mechanisms in convolution neural network for genomic prediction
We introduced a novel deep learning method for genomic prediction, which integrates residual units, attention mechanisms and frequency-encoded genomic data. Comprehensive evaluation on pig, dairy cow, Huaxi cattle, wheat and rice datasets demonstrated that ReaGP was a promising tool for most traits. Thus, ReaGP could be considered as an efficient deep learning method for genomic prediction in farm animals and crops. The source code in this study is available at https://github.com/LiJing5467/ReaGP .
Authors
- Peng Guo (ORCID: https://orcid.org/0000-0001-5392-3915)
- Haoran Ma (ORCID: https://orcid.org/0000-0002-2484-9004)
- Zhida Zhao
- Yuanxu Zhang
- Yuanqing Wang
- Junya Li
- Xue Gao
- Bo Zhu
- Zezhao Wang
- Lupei Zhang
- Huijiang Gao
- Lingyang Xu
- Jing Li
- Yan Chen
Institutions
- Tianjin Agricultural University (CN)
- Animal Husbandry & Veterinary (IN)
- Chinese Academy of Agricultural Sciences (CN)
- Institute of Animal Sciences (CN)
- National Beef Cattle Industrial Technology System (CN)
Publication Details
- Journal
- Genetics Selection Evolution
- Published
- 2026-01-13
- DOI
- https://doi.org/10.1186/s12711-025-01015-8
- Primary Topic
- Genetic and phenotypic traits in livestock
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- People's Government of Jilin Province
- Chinese Academy of Agricultural Sciences
- National Key Research and Development Program of China