{
  "annotation_id": "0d08f70f-8a9c-42a2-8146-e865e1568408",
  "date_created": "2026-03-02T18:01:31.148000Z",
  "date_modified": "2026-03-02T18:01:31.148000Z",
  "file_hash": "926e4a409d6278012055f534251227bbf29995d875c0b4d11f1349e856043303",
  "private": false,
  "record": {
    "abstract": "Information valuable words are the strings with the significant deviation of\nreal frequency from the expected one. The expected frequency is determined\nthrough the maximum entropy principle of the reconstructed (extended) frequency\ndictionary of strings composed from the shorter words. The information valuable\nwords are found to be the complementary palindromes: they are read equally in\nopposite directions, if nucleotides are changed for the complementary ones (A\n\u003c--\u003e T; C \u003c--\u003e G) in one of them. Some properties of such symmetric words are\ndiscussed.",
    "arxiv_id": "q-bio/0503009",
    "authors": [
      "M. A. Makarova",
      "M. G. Sadovsky"
    ],
    "categories": [
      "q-bio.GN",
      "q-bio.BM"
    ],
    "title": "New symmetry in nucleotide sequences",
    "url": "https://arxiv.org/abs/q-bio/0503009"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "47d2f025-49b3-4d57-908c-3f2b6a54b703",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}