A generative adversarial network for multiple reads reconstruction in DNA storage
Abstract DNA storage is widely considered as a promising solution to the data explosion problem. However, the synthesis, PCR and sequencing processes usually result in erroneous reads involving base insertions, deletions, and substitutions. Specially this situation is even more serious in the 3rd ge...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-83806-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559457595654144 |
|---|---|
| author | Xiaodong Zheng Ranze Xie Xiangyu Yao Yanqing Su Ling Chu Peng Xu Wenbin Liu |
| author_facet | Xiaodong Zheng Ranze Xie Xiangyu Yao Yanqing Su Ling Chu Peng Xu Wenbin Liu |
| author_sort | Xiaodong Zheng |
| collection | DOAJ |
| description | Abstract DNA storage is widely considered as a promising solution to the data explosion problem. However, the synthesis, PCR and sequencing processes usually result in erroneous reads involving base insertions, deletions, and substitutions. Specially this situation is even more serious in the 3rd generation of sequencing technologies. Different from previous error-correction and multiple sequence alignment methods, we first transform the multiple reads into a noisy mage, and then construct a conditional generative adversarial network to produce a “smooth” image which refers to the consensus sequence. Results on two real datasets demonstrate that our model can completely reconstruct the tested sequences with as high as 5.9% errors. This means that the proposed DNA-GAN can be applied on 3rd generation nanopore sequencing environments, while the transformer-based models are only tested on next-generation sequencing datasets. Furthermore, DNA-GAN exhibits excellent robustness even when as much as 20% of the clusters are contaminated with irrelevant reads. To the best of our knowledge, this work is the first to use GAN for multi-reads reconstruction in DNA-based storage. |
| format | Article |
| id | doaj-art-a82a33f1c88c48dc8e4a994892fab0c8 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-a82a33f1c88c48dc8e4a994892fab0c82025-01-05T12:28:09ZengNature PortfolioScientific Reports2045-23222024-12-0114111010.1038/s41598-024-83806-5A generative adversarial network for multiple reads reconstruction in DNA storageXiaodong Zheng0Ranze Xie1Xiangyu Yao2Yanqing Su3Ling Chu4Peng Xu5Wenbin Liu6Institution of Computational Science and Technology, Guangzhou UniversityInstitution of Computational Science and Technology, Guangzhou UniversityInstitution of Computational Science and Technology, Guangzhou UniversityInstitution of Computational Science and Technology, Guangzhou UniversityInstitution of Computational Science and Technology, Guangzhou UniversityInstitution of Computational Science and Technology, Guangzhou UniversityInstitution of Computational Science and Technology, Guangzhou UniversityAbstract DNA storage is widely considered as a promising solution to the data explosion problem. However, the synthesis, PCR and sequencing processes usually result in erroneous reads involving base insertions, deletions, and substitutions. Specially this situation is even more serious in the 3rd generation of sequencing technologies. Different from previous error-correction and multiple sequence alignment methods, we first transform the multiple reads into a noisy mage, and then construct a conditional generative adversarial network to produce a “smooth” image which refers to the consensus sequence. Results on two real datasets demonstrate that our model can completely reconstruct the tested sequences with as high as 5.9% errors. This means that the proposed DNA-GAN can be applied on 3rd generation nanopore sequencing environments, while the transformer-based models are only tested on next-generation sequencing datasets. Furthermore, DNA-GAN exhibits excellent robustness even when as much as 20% of the clusters are contaminated with irrelevant reads. To the best of our knowledge, this work is the first to use GAN for multi-reads reconstruction in DNA-based storage.https://doi.org/10.1038/s41598-024-83806-5 |
| spellingShingle | Xiaodong Zheng Ranze Xie Xiangyu Yao Yanqing Su Ling Chu Peng Xu Wenbin Liu A generative adversarial network for multiple reads reconstruction in DNA storage Scientific Reports |
| title | A generative adversarial network for multiple reads reconstruction in DNA storage |
| title_full | A generative adversarial network for multiple reads reconstruction in DNA storage |
| title_fullStr | A generative adversarial network for multiple reads reconstruction in DNA storage |
| title_full_unstemmed | A generative adversarial network for multiple reads reconstruction in DNA storage |
| title_short | A generative adversarial network for multiple reads reconstruction in DNA storage |
| title_sort | generative adversarial network for multiple reads reconstruction in dna storage |
| url | https://doi.org/10.1038/s41598-024-83806-5 |
| work_keys_str_mv | AT xiaodongzheng agenerativeadversarialnetworkformultiplereadsreconstructionindnastorage AT ranzexie agenerativeadversarialnetworkformultiplereadsreconstructionindnastorage AT xiangyuyao agenerativeadversarialnetworkformultiplereadsreconstructionindnastorage AT yanqingsu agenerativeadversarialnetworkformultiplereadsreconstructionindnastorage AT lingchu agenerativeadversarialnetworkformultiplereadsreconstructionindnastorage AT pengxu agenerativeadversarialnetworkformultiplereadsreconstructionindnastorage AT wenbinliu agenerativeadversarialnetworkformultiplereadsreconstructionindnastorage AT xiaodongzheng generativeadversarialnetworkformultiplereadsreconstructionindnastorage AT ranzexie generativeadversarialnetworkformultiplereadsreconstructionindnastorage AT xiangyuyao generativeadversarialnetworkformultiplereadsreconstructionindnastorage AT yanqingsu generativeadversarialnetworkformultiplereadsreconstructionindnastorage AT lingchu generativeadversarialnetworkformultiplereadsreconstructionindnastorage AT pengxu generativeadversarialnetworkformultiplereadsreconstructionindnastorage AT wenbinliu generativeadversarialnetworkformultiplereadsreconstructionindnastorage |