VMGP: A unified variational auto-encoder based multi-task model for multi-phenotype, multi-environment, and cross-population genomic selection in plants
Plant breeding stands as a cornerstone for agricultural productivity and the safeguarding of food security. The advent of Genomic Selection heralds a new epoch in breeding, characterized by its capacity to harness whole-genome variation for genomic prediction. This approach transcends the need for p...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2025-12-01
|
| Series: | Artificial Intelligence in Agriculture |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589721725000704 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839639906636267520 |
|---|---|
| author | Xiangyu Zhao Fuzhen Sun Jinlong Li Dongfeng Zhang Qiusi Zhang Zhongqiang Liu Changwei Tan Hongxiang Ma Kaiyi Wang |
| author_facet | Xiangyu Zhao Fuzhen Sun Jinlong Li Dongfeng Zhang Qiusi Zhang Zhongqiang Liu Changwei Tan Hongxiang Ma Kaiyi Wang |
| author_sort | Xiangyu Zhao |
| collection | DOAJ |
| description | Plant breeding stands as a cornerstone for agricultural productivity and the safeguarding of food security. The advent of Genomic Selection heralds a new epoch in breeding, characterized by its capacity to harness whole-genome variation for genomic prediction. This approach transcends the need for prior knowledge of genes associated with specific traits. Nonetheless, the vast dimensionality of genomic data juxtaposed with the relatively limited number of phenotypic samples often leads to the “curse of dimensionality”, where traditional statistical, machine learning, and deep learning methods are prone to overfitting and suboptimal predictive performance. To surmount this challenge, we introduce a unified Variational auto-encoder based Multi-task Genomic Prediction model (VMGP) that integrates self-supervised genomic compression and reconstruction with multiple prediction tasks. This approach provides a robust solution, offering a formidable predictive framework that has been rigorously validated across public datasets for wheat, rice, and maize. Our model demonstrates exceptional capabilities in multi-phenotype and multi-environment genomic prediction, successfully navigating the complexities of cross-population genomic selection and underscoring its unique strengths and utility. Furthermore, by integrating VMGP with model interpretability, we can effectively triage relevant single nucleotide polymorphisms, thereby enhancing prediction performance and proposing potential cost-effective genotyping solutions. The VMGP framework, with its simplicity, stable predictive prowess, and open-source code, is exceptionally well-suited for broad dissemination within plant breeding programs. It is particularly advantageous for breeders who prioritize phenotype prediction yet may not possess extensive knowledge in deep learning or proficiency in parameter tuning. |
| format | Article |
| id | doaj-art-f0cf5c90cfe24b6184faae896b52f80c |
| institution | Matheson Library |
| issn | 2589-7217 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Artificial Intelligence in Agriculture |
| spelling | doaj-art-f0cf5c90cfe24b6184faae896b52f80c2025-07-04T04:46:46ZengKeAi Communications Co., Ltd.Artificial Intelligence in Agriculture2589-72172025-12-01154829842VMGP: A unified variational auto-encoder based multi-task model for multi-phenotype, multi-environment, and cross-population genomic selection in plantsXiangyu Zhao0Fuzhen Sun1Jinlong Li2Dongfeng Zhang3Qiusi Zhang4Zhongqiang Liu5Changwei Tan6Hongxiang Ma7Kaiyi Wang8Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China; National Engineering Research Center for Information Technology in Agriculture, Beijing, China; Beijing Key Laboratory of Crop Molecular Design and Intelligent Breeding, Beijing, ChinaSchool of Computer Science and Technology, Shandong University of Technology, Zibo, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China; Beijing Key Laboratory of Crop Molecular Design and Intelligent Breeding, Beijing, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China; Beijing Key Laboratory of Crop Molecular Design and Intelligent Breeding, Beijing, ChinaYangzhou University, Yangzhou, ChinaYangzhou University, Yangzhou, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China; National Engineering Research Center for Information Technology in Agriculture, Beijing, China; Beijing Key Laboratory of Crop Molecular Design and Intelligent Breeding, Beijing, China; Corresponding author at: Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China.Plant breeding stands as a cornerstone for agricultural productivity and the safeguarding of food security. The advent of Genomic Selection heralds a new epoch in breeding, characterized by its capacity to harness whole-genome variation for genomic prediction. This approach transcends the need for prior knowledge of genes associated with specific traits. Nonetheless, the vast dimensionality of genomic data juxtaposed with the relatively limited number of phenotypic samples often leads to the “curse of dimensionality”, where traditional statistical, machine learning, and deep learning methods are prone to overfitting and suboptimal predictive performance. To surmount this challenge, we introduce a unified Variational auto-encoder based Multi-task Genomic Prediction model (VMGP) that integrates self-supervised genomic compression and reconstruction with multiple prediction tasks. This approach provides a robust solution, offering a formidable predictive framework that has been rigorously validated across public datasets for wheat, rice, and maize. Our model demonstrates exceptional capabilities in multi-phenotype and multi-environment genomic prediction, successfully navigating the complexities of cross-population genomic selection and underscoring its unique strengths and utility. Furthermore, by integrating VMGP with model interpretability, we can effectively triage relevant single nucleotide polymorphisms, thereby enhancing prediction performance and proposing potential cost-effective genotyping solutions. The VMGP framework, with its simplicity, stable predictive prowess, and open-source code, is exceptionally well-suited for broad dissemination within plant breeding programs. It is particularly advantageous for breeders who prioritize phenotype prediction yet may not possess extensive knowledge in deep learning or proficiency in parameter tuning.http://www.sciencedirect.com/science/article/pii/S2589721725000704Genomic selectionVariational auto-encoderMulti-taskDeep learningGenomic prediction |
| spellingShingle | Xiangyu Zhao Fuzhen Sun Jinlong Li Dongfeng Zhang Qiusi Zhang Zhongqiang Liu Changwei Tan Hongxiang Ma Kaiyi Wang VMGP: A unified variational auto-encoder based multi-task model for multi-phenotype, multi-environment, and cross-population genomic selection in plants Artificial Intelligence in Agriculture Genomic selection Variational auto-encoder Multi-task Deep learning Genomic prediction |
| title | VMGP: A unified variational auto-encoder based multi-task model for multi-phenotype, multi-environment, and cross-population genomic selection in plants |
| title_full | VMGP: A unified variational auto-encoder based multi-task model for multi-phenotype, multi-environment, and cross-population genomic selection in plants |
| title_fullStr | VMGP: A unified variational auto-encoder based multi-task model for multi-phenotype, multi-environment, and cross-population genomic selection in plants |
| title_full_unstemmed | VMGP: A unified variational auto-encoder based multi-task model for multi-phenotype, multi-environment, and cross-population genomic selection in plants |
| title_short | VMGP: A unified variational auto-encoder based multi-task model for multi-phenotype, multi-environment, and cross-population genomic selection in plants |
| title_sort | vmgp a unified variational auto encoder based multi task model for multi phenotype multi environment and cross population genomic selection in plants |
| topic | Genomic selection Variational auto-encoder Multi-task Deep learning Genomic prediction |
| url | http://www.sciencedirect.com/science/article/pii/S2589721725000704 |
| work_keys_str_mv | AT xiangyuzhao vmgpaunifiedvariationalautoencoderbasedmultitaskmodelformultiphenotypemultienvironmentandcrosspopulationgenomicselectioninplants AT fuzhensun vmgpaunifiedvariationalautoencoderbasedmultitaskmodelformultiphenotypemultienvironmentandcrosspopulationgenomicselectioninplants AT jinlongli vmgpaunifiedvariationalautoencoderbasedmultitaskmodelformultiphenotypemultienvironmentandcrosspopulationgenomicselectioninplants AT dongfengzhang vmgpaunifiedvariationalautoencoderbasedmultitaskmodelformultiphenotypemultienvironmentandcrosspopulationgenomicselectioninplants AT qiusizhang vmgpaunifiedvariationalautoencoderbasedmultitaskmodelformultiphenotypemultienvironmentandcrosspopulationgenomicselectioninplants AT zhongqiangliu vmgpaunifiedvariationalautoencoderbasedmultitaskmodelformultiphenotypemultienvironmentandcrosspopulationgenomicselectioninplants AT changweitan vmgpaunifiedvariationalautoencoderbasedmultitaskmodelformultiphenotypemultienvironmentandcrosspopulationgenomicselectioninplants AT hongxiangma vmgpaunifiedvariationalautoencoderbasedmultitaskmodelformultiphenotypemultienvironmentandcrosspopulationgenomicselectioninplants AT kaiyiwang vmgpaunifiedvariationalautoencoderbasedmultitaskmodelformultiphenotypemultienvironmentandcrosspopulationgenomicselectioninplants |