{
  "abstract": "Enzymatic DNA labeling is a powerful tool with applications in biochemistry, molecular biology, biotechnology, medical science, and genomic research. This paper contributes to the evolving field of DNA-based data storage by presenting a formal framework for modeling DNA labeling in strings, specifically tailored for data storage purposes. Our approach involves a known DNA molecule as a template for labeling, employing patterns induced by a set of designed labels to represent information. One hypothetical implementation can use CRISPR-Cas9 and gRNA reagents for labeling. Various aspects of the general labeling channel, including fixed-length labels, are explored, and upper bounds on the maximum size of the corresponding codes are given. The study includes the development of an efficient encoder-decoder pair that is proven to be optimal in terms of maximum code size under specific conditions. The codewords for this framework are codesets, i.e., each codeword is a collection of a few labels. Of special interest are codes whose codesets contain fixed-length labels. Their construction and analysis are tied to de Bruijn sequences and constrained coding.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.24171",
  "author_total": 4,
  "authors": [
    {
      "name": "Daniella Bar-Lev"
    },
    {
      "name": "Eitan Yaakobi"
    },
    {
      "name": "Zohar Yakhini"
    },
    {
      "name": "Tuvi Etzion"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ekwrwcq5ax2e6.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.24171",
  "fulltext_url": null,
  "id": "ekwrwcq5ax2e6",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.24171",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.IT"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "openalex",
      "1312|DNA and Biological Computing"
    ]
  ],
  "openalex": "W7223014663",
  "pdf_url": "https://arxiv.org/pdf/2610.24171",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-16",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ekwrwcq5ax2e6.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:30:57Z",
      "native_id": "2610.24171",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.24171"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|DNA and Biological Computing",
      "subfield": "molecular-biology"
    }
  ],
  "title": "Representing Information on DNA using Patterns Induced by Enzymatic Labeling",
  "title_text": "Representing Information on DNA using Patterns Induced by Enzymatic Labeling",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:44Z",
  "url": "https://research.draconitic.com/paper/ekwrwcq5ax2e6",
  "venue": "arXiv",
  "versions": []
}