MtCro: multi-task deep learning framework improves multi-trait genomic prediction of crops
Abstract Genomic Selection (GS) predicts traits using genome-wide markers, speeding up genetic progress and enhancing breeding efficiency. Recent emphasis has been placed on deep learning models to enhance prediction accuracy. However, current deep learning models focus on learning specific phenotyp...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | Plant Methods |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13007-024-01321-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862235438514176 |
|---|---|
| author | Dian Chao Hao Wang Fengqiang Wan Shen Yan Wei Fang Yang Yang |
| author_facet | Dian Chao Hao Wang Fengqiang Wan Shen Yan Wei Fang Yang Yang |
| author_sort | Dian Chao |
| collection | DOAJ |
| description | Abstract Genomic Selection (GS) predicts traits using genome-wide markers, speeding up genetic progress and enhancing breeding efficiency. Recent emphasis has been placed on deep learning models to enhance prediction accuracy. However, current deep learning models focus on learning specific phenotypes for the given task, overlooking the inter-correlations among different phenotypes. In response, we introduce MtCro, a multi-task learning approach that simultaneously captures diverse plant phenotypes within a shared parameter space. Extensive experiments reveal that MtCro outperforms mainstream models, including DNNGP and SoyDNGP, with performance gains of 1-9% on the Wheat2000 dataset, 1-8% on Wheat599, and 1-3% on Maize8652. Furthermore, comparative analysis shows a consistent 2-3% improvement in multi-phenotype predictions, emphasizing the impact of inter-phenotype correlations on accuracy. By leveraging multi-task learning, MtCro efficiently captures diverse plant phenotypes, enhancing both model training efficiency and prediction accuracy, ultimately accelerating the progress of plant genetic breeding. Our code is available on https://github.com/chaodian12/mtcro . |
| format | Article |
| id | doaj-art-c700da16c039451383d0efc067b514e4 |
| institution | Kabale University |
| issn | 1746-4811 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | Plant Methods |
| spelling | doaj-art-c700da16c039451383d0efc067b514e42025-02-09T12:38:45ZengBMCPlant Methods1746-48112025-02-0121111410.1186/s13007-024-01321-0MtCro: multi-task deep learning framework improves multi-trait genomic prediction of cropsDian Chao0Hao Wang1Fengqiang Wan2Shen Yan3Wei Fang4Yang Yang5School of Computer Science and Engineering, Nanjing University of Science and TechnologyInstitute of Crop Sciences, Chinese Academy of Agricultural SciencesSchool of Computer Science and Engineering, Nanjing University of Science and TechnologyInstitute of Crop Sciences, Chinese Academy of Agricultural SciencesInstitute of Crop Sciences, Chinese Academy of Agricultural SciencesSchool of Computer Science and Engineering, Nanjing University of Science and TechnologyAbstract Genomic Selection (GS) predicts traits using genome-wide markers, speeding up genetic progress and enhancing breeding efficiency. Recent emphasis has been placed on deep learning models to enhance prediction accuracy. However, current deep learning models focus on learning specific phenotypes for the given task, overlooking the inter-correlations among different phenotypes. In response, we introduce MtCro, a multi-task learning approach that simultaneously captures diverse plant phenotypes within a shared parameter space. Extensive experiments reveal that MtCro outperforms mainstream models, including DNNGP and SoyDNGP, with performance gains of 1-9% on the Wheat2000 dataset, 1-8% on Wheat599, and 1-3% on Maize8652. Furthermore, comparative analysis shows a consistent 2-3% improvement in multi-phenotype predictions, emphasizing the impact of inter-phenotype correlations on accuracy. By leveraging multi-task learning, MtCro efficiently captures diverse plant phenotypes, enhancing both model training efficiency and prediction accuracy, ultimately accelerating the progress of plant genetic breeding. Our code is available on https://github.com/chaodian12/mtcro .https://doi.org/10.1186/s13007-024-01321-0Deep learningGenomic predictionMulti-task learningCrop breeding |
| spellingShingle | Dian Chao Hao Wang Fengqiang Wan Shen Yan Wei Fang Yang Yang MtCro: multi-task deep learning framework improves multi-trait genomic prediction of crops Plant Methods Deep learning Genomic prediction Multi-task learning Crop breeding |
| title | MtCro: multi-task deep learning framework improves multi-trait genomic prediction of crops |
| title_full | MtCro: multi-task deep learning framework improves multi-trait genomic prediction of crops |
| title_fullStr | MtCro: multi-task deep learning framework improves multi-trait genomic prediction of crops |
| title_full_unstemmed | MtCro: multi-task deep learning framework improves multi-trait genomic prediction of crops |
| title_short | MtCro: multi-task deep learning framework improves multi-trait genomic prediction of crops |
| title_sort | mtcro multi task deep learning framework improves multi trait genomic prediction of crops |
| topic | Deep learning Genomic prediction Multi-task learning Crop breeding |
| url | https://doi.org/10.1186/s13007-024-01321-0 |
| work_keys_str_mv | AT dianchao mtcromultitaskdeeplearningframeworkimprovesmultitraitgenomicpredictionofcrops AT haowang mtcromultitaskdeeplearningframeworkimprovesmultitraitgenomicpredictionofcrops AT fengqiangwan mtcromultitaskdeeplearningframeworkimprovesmultitraitgenomicpredictionofcrops AT shenyan mtcromultitaskdeeplearningframeworkimprovesmultitraitgenomicpredictionofcrops AT weifang mtcromultitaskdeeplearningframeworkimprovesmultitraitgenomicpredictionofcrops AT yangyang mtcromultitaskdeeplearningframeworkimprovesmultitraitgenomicpredictionofcrops |