arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.02417cs.ETcs.AIcs.LG
收藏

NEURODNAAI:利用深度学习框架推进基于DNA的信息存储作为可持续数字介质的神经流水线方法

NEURODNAAI: Neural pipeline approaches for the advancing dna-based information storage as a sustainable digital medium using deep learning framework

Amity Centre for Artificial Intelligence, Amity University, India(阿米蒂大学人工智能中心,阿米蒂大学,印度);Amity School of Engineering and Technology, Amity University, India(阿米蒂工程与技术学院,阿米蒂大学,印度);Amity Institute of Biotechnology, Amity University, India(阿米蒂生物技术学院,阿米蒂大学,印度)

Rakesh Thakur, Lavanya Singh, Yashika, Manomay Bundawala, Aruna Kumar

AI总结:

针对DNA存储的合成成本、测序错误及生物约束等部署难题,研究提出NeuroDNAAI框架,结合量子并行性思想与深度学习实现高保真编解码,在基准数据集上取得低误码率,为可扩展的归档级DNA存储提供统一流水线方案。

摘要:

DNA凭借其超高的密度和耐久性,是一种极具前景的数字信息存储介质。尽管此前的研究在编码理论、工作流设计和仿真工具方面取得了进展,但合成成本、测序错误以及生物约束(GC含量失衡、同聚物)等挑战限制了其实际部署。为解决这一问题,我们的框架借鉴量子并行性概念来增强编码多样性和恢复能力,将生物信息约束与深度学习相结合,以提升DNA存储中的错误缓解能力。NeuroDNAAI将二进制数据流编码为符号DNA序列,使其通过存在替换、插入和删除错误的噪声信道,并以高保真度重建数据。我们的结果表明,传统的提示或基于规则的方案无法有效适应真实噪声,而NeuroDNAAI实现了更高的准确率。在基准数据集上的实验表明,该方法对文本和图像均实现了低比特错误率。通过将理论、工作流和仿真统一到一条流水线中,NeuroDNAAI可实现可扩展、生物学上有效的归档级DNA存储。

英文摘要:

DNA is a promising medium for digital information storage for its exceptional density and durability. While prior studies advanced coding theory, workflow design, and simulation tools, challenges such as synthesis costs, sequencing errors, and biological constraints (GC-content imbalance, homopolymers) limit practical deployment. To address this, our framework draws from quantum parallelism concepts to enhance encoding diversity and resilience, integrating biologically informed constraints with deep learning to enhance error mitigation in DNA storage. NeuroDNAAI encodes binary data streams into symbolic DNA sequences, transmits them through a noisy channel with substitutions, insertions, and deletions, and reconstructs them with high fidelity. Our results show that traditional prompting or rule-based schemes fail to adapt effectively to realistic noise, whereas NeuroDNAAI achieves superior accuracy. Experiments on benchmark datasets demonstrate low bit error rates for both text and images. By unifying theory, workflow, and simulation into one pipeline, NeuroDNAAI enables scalable, biologically valid archival DNA storage

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑