Learning Structurally Stabilized Representations for Multi-modal Lossless DNA Storage

TL;DR

This paper introduces RSRL, a novel end-to-end model inspired by error correction and structural biology, for learning highly durable, dense, and lossless multi-modal DNA storage representations, outperforming existing methods.

Contribution

The paper proposes RSRL, a new model that integrates Reed-Solomon coding, error correction, and biological stabilization to improve DNA data storage.

Findings

Higher information density achieved

Lower error rates in storage

Enhanced durability of representations

Abstract

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.