A Robust and Efficient Representation‐based DNA Storage Architecture by Deep Learning
Small Methods · 2025
DOI: 10.1002/smtd.202400959 ↗Kurz gefasst
Fachartikel in der Zeitschrift Small Methods, 2025. Verfasst von Yanqing Su und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institution of Computational Science and Technology, Guangzhou University, Guangzhou, 510006, China. Hauptthemen laut MEDLINE: Deep Learning, DNA, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province of China, Municipal School Joint Fund of Guangzhou Science and Technology Bureau.
Abstract (Originalsprache)
As one main form of multimedia data, images play a critical role in various applications. In this paper, a representation‐based architecture is proposed which takes advantage of the outstanding representation and image‐generation abilities of deep learning (DL). This architecture includes two DL models: an autoencoder and a U‐Net network which achieve the representation, construction, and refinement of images from the noisy reads in DNA storage. Simulation experiments demonstrate that it can reconstruct images of moderate quality in scenarios where insertion‐deletion‐substitution (IDS) errors are less than 6%. Combined with the feature quantization, it also offers a flexible way to achieve a balanced trade‐off between compression ratio and image quality by selecting an approximate representation channel number. Additionally, the quality of images can be boosted by using multiple reads which are a common situation in DNA storage. A wet lab practice that successfully reconstructs an image stored in 14 plasmids further proves the feasibility of the proposed architecture. Instead of storing the original image information, the representation‐based architecture provides a competitive solution which achieves robust and efficient DNA storage for large‐scale image applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Institution of Computational Science and Technology, Guangzhou University, Guangzhou, 510006, China.
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, 510006, China.
- School of Computer Science of Information Technology, Qiannan Normal University for Nationalities, Duyun, China.
ORCID-Profile: Yanqing Su, Wenbin Liu
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Guangdong Province of China
- Municipal School Joint Fund of Guangzhou Science and Technology Bureau
- Project of Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis
Zitieren
APA
Su, Y., Chu, L., Lin, W., Yao, X., Xu, P., & Liu, W. (2025). A Robust and Efficient Representation‐based DNA Storage Architecture by Deep Learning. Small Methods. https://doi.org/10.1002/smtd.202400959
Vancouver
Su Y, Chu L, Lin W, Yao X, Xu P, Liu W. A Robust and Efficient Representation‐based DNA Storage Architecture by Deep Learning. Small Methods. 2025. doi:10.1002/smtd.202400959
BibTeX
@article{Su2025,
author = {Su, Yanqing and Chu, Ling and Lin, Wanmin and Yao, Xiangyu and Xu, Peng and Liu, Wenbin},
title = {A Robust and Efficient Representation‐based DNA Storage Architecture by Deep Learning},
journal = {Small Methods},
year = {2025},
doi = {10.1002/smtd.202400959}
}
EUVIMED