用语言模型解决序列重建，提升DNA存储纠错能力。
Trace Reconstruction with Language Models
- 将重建任务转为下一个词预测，用Transformer解码器建模序列
- 在真实数据上微调后，无错恢复率显著高于现有算法
- 适合从事生物计算与高密度存储研究的读者
通用序列重建问题旨在从独立受插入、删除和替换噪声污染的多个副本中恢复原始序列。该问题在DNA数据存储中具有重要应用，因其信息密度高且寿命长。但合成、存储和测序过程引入的错误需通过算法与编码纠正，序列重建常作为数据读取的关键步骤。本文提出TReconLM，一种解码器仅的Transformer模型，将重建问题建模为下一个标记预测任务。TReconLM在合成数据上预训练，再在真实数据上微调以适配特定技术误差模式，性能超越现有最先进算法，包括先前的深度学习方法，能更高比例地无误恢复原始序列。代码已开源：https://github.com/MLI-lab/TReconLM。
原文摘要 · Abstract (English)
The general trace reconstruction problem seeks to recover an original sequence from its noisy copies independently corrupted by insertions, deletions, and substitutions. This problem arises in applications such as DNA data storage, a promising storage medium due to its high information density and longevity. However, errors introduced during DNA synthesis, storage, and sequencing require correction through algorithms and codes, with trace reconstruction often used as part of data retrieval. In this work, we propose TReconLM, a decoder-only transformer that solves trace reconstruction as a next-token prediction task. TReconLM outperforms state-of-the-art trace reconstruction algorithms, including prior deep-learning approaches, recovering a substantially higher fraction of sequences without error. We pretrain on synthetic data generated from a simple error model and fine-tune on real-world data to adapt to technology-specific error patterns. Code is available at https://github.com/MLI-lab/TReconLM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。