{
  "annotation_id": "c19a9f95-bb3b-4b0d-bca2-344719ccff39",
  "date_created": "2026-03-02T18:01:35.333000Z",
  "date_modified": "2026-03-02T18:01:35.333000Z",
  "file_hash": "5cb4c1fa7bc8c658d9345f598d2d12cb87867f570ffa03f2825266ea14c343b3",
  "private": false,
  "record": {
    "abstract": "We propose that the distribution of DNA words in genomic sequences can be\nprimarily characterized by a double Pareto-lognormal distribution, which\nexplains lognormal and power-law features found across all known genomes. Such\na distribution may be the result of completely random sequence evolution by\nduplication processes. The parametrization of genomic word frequencies allows\nfor an assessment of significance for frequent or rare sequence motifs.",
    "arxiv_id": "q-bio/0609022",
    "authors": [
      "Mikl\u00f3s Cs\u0171r\u00f6s",
      "Laurent No\u00e9",
      "Gregory Kucherov"
    ],
    "categories": [
      "q-bio.GN"
    ],
    "title": "Reconsidering the significance of genomic word frequency",
    "url": "https://arxiv.org/abs/q-bio/0609022"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "3be1b665-2a08-47b8-a43b-ff6d7f02d45e",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}