Learning Structurally Stabilized Representations for Multi-modal Lossless DNA Storage
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913455774105600 |
|---|---|
| author | Cao, Ben He, Tiantian Li, Xue Wang, Bin Wu, Xiaohu Zhang, Qiang Ong, Yew-Soon |
| author_facet | Cao, Ben He, Tiantian Li, Xue Wang, Bin Wu, Xiaohu Zhang, Qiang Ong, Yew-Soon |
| contents | In this paper, we present Reed-Solomon coded single-stranded representation learning (RSRL), a novel end-to-end model for learning representations for multi-modal lossless DNA storage. In contrast to existing learning-based methods, the proposed RSRL is inspired by both error-correction codec and structural biology. Specifically, RSRL first learns the representations for the subsequent storage from the binary data transformed by the Reed-Solomon codec. Then, the representations are masked by an RS-code-informed mask to focus on correcting the burst errors occurring in the learning process. With the decoded representations with error corrections, a novel biologically stabilized loss is formulated to regularize the data representations to possess stable single-stranded structures. By incorporating these novel strategies, the proposed RSRL can learn highly durable, dense, and lossless representations for the subsequent storage tasks into DNA sequences. The proposed RSRL has been compared with a number of strong baselines in real-world tasks of multi-modal data storage. The experimental results obtained demonstrate that RSRL can store diverse types of data with much higher information density and durability but much lower error rates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00779 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Structurally Stabilized Representations for Multi-modal Lossless DNA Storage Cao, Ben He, Tiantian Li, Xue Wang, Bin Wu, Xiaohu Zhang, Qiang Ong, Yew-Soon Machine Learning Artificial Intelligence Emerging Technologies Information Theory Biomolecules In this paper, we present Reed-Solomon coded single-stranded representation learning (RSRL), a novel end-to-end model for learning representations for multi-modal lossless DNA storage. In contrast to existing learning-based methods, the proposed RSRL is inspired by both error-correction codec and structural biology. Specifically, RSRL first learns the representations for the subsequent storage from the binary data transformed by the Reed-Solomon codec. Then, the representations are masked by an RS-code-informed mask to focus on correcting the burst errors occurring in the learning process. With the decoded representations with error corrections, a novel biologically stabilized loss is formulated to regularize the data representations to possess stable single-stranded structures. By incorporating these novel strategies, the proposed RSRL can learn highly durable, dense, and lossless representations for the subsequent storage tasks into DNA sequences. The proposed RSRL has been compared with a number of strong baselines in real-world tasks of multi-modal data storage. The experimental results obtained demonstrate that RSRL can store diverse types of data with much higher information density and durability but much lower error rates. |
| title | Learning Structurally Stabilized Representations for Multi-modal Lossless DNA Storage |
| topic | Machine Learning Artificial Intelligence Emerging Technologies Information Theory Biomolecules |
| url | https://arxiv.org/abs/2408.00779 |