{
  "annotation_id": "9b577223-9782-40e9-9d9e-1b1a97843279",
  "date_created": "2026-03-02T18:01:32.179000Z",
  "date_modified": "2026-03-02T18:01:32.179000Z",
  "file_hash": "fb6db69cdecf38d72944ae9443a861defafb0dd6310fbb94182771489721a114",
  "private": false,
  "record": {
    "abstract": "We introduce a novel method to analyse complete genomes and recognise some\ndistinctive features by means of an adaptive compression algorithm, which is\nnot DNA-oriented. We study the Information Content as a function of the number\nof symbols encoded by the algorithm. Preliminar results are shown concerning\nregions having a sublinear type of information growth, which is strictly\nconnected to the presence of highly repetitive subregions that might be\nsupposed to have a regulatory function within the genome.",
    "arxiv_id": "q-bio/0402046",
    "authors": [
      "Giulia Menconi"
    ],
    "categories": [
      "q-bio.GN",
      "cond-mat.stat-mech",
      "physics.data-an"
    ],
    "title": "Sublinear Growth of Information in DNA Sequences",
    "url": "https://arxiv.org/abs/q-bio/0402046"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "77ecf132-b1e2-4824-8020-8381fb7c9911",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}