{
  "annotation_id": "b1d1c98a-267c-40ba-b876-6f0c5aa67df8",
  "date_created": "2026-03-02T18:01:31.934000Z",
  "date_modified": "2026-03-02T18:01:31.934000Z",
  "file_hash": "ecf3dbcd93e5ef260ba30980ebd07131223843ef85900721b733ab40395f14cc",
  "private": false,
  "record": {
    "abstract": "Shannon information (SI) and its special case, divergence, are defined for a\nDNA sequence in terms of probabilities of chemical words in the sequence and\nare computed for a set of complete genomes highly diverse in length and\ncomposition. We find the following: SI (but not divergence) is inversely\nproportional to sequence length for a random sequence but is length-independent\nfor genomes; the genomic SI is always greater and, for shorter words and longer\nsequences, hundreds to thousands times greater than the SI in a random sequence\nwhose length and composition match those of the genome; genomic SIs appear to\nhave word-length dependent universal values. The universality is inferred to be\nan evolution footprint of a universal mode for genome growth.",
    "arxiv_id": "q-bio/0412037",
    "authors": [
      "Hong-Da Chen",
      "Chang-Heng Chang",
      "Li-Ching Hsieh",
      "Hoong-Chien Lee"
    ],
    "categories": [
      "q-bio.GN"
    ],
    "doi": "10.1103/PhysRevLett.94.178103",
    "title": "Divergence and Shannon information in genomes",
    "url": "https://arxiv.org/abs/q-bio/0412037"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "f5ec3c92-a19d-4adb-b9c2-e3514fef1ae8",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}