{
  "annotation_id": "c5b9a0b3-abbb-4a68-891a-5caca7f70d47",
  "date_created": "2026-03-02T18:01:31.020000Z",
  "date_modified": "2026-03-02T18:01:31.020000Z",
  "file_hash": "754d3b62262e3cc01722dea9be7205ded51651b1911cd995661225a609fe5f70",
  "private": false,
  "record": {
    "abstract": "Much of the on-going statistical analysis of DNA sequences is focused on the\nestimation of characteristics of coding and non-coding regions that would\npossibly allow discrimination of these regions. In the current approach, we\nconcentrate specifically on genes and intergenic regions. To estimate the level\nand type of correlation in these regions we apply various statistical methods\ninspired from nonlinear time series analysis, namely the probability\ndistribution of tuplets, the Mutual Information and the Identical Neighbour\nFit. The methods are suitably modified to work on symbolic sequences and they\nare first tested for validity on sequences obtained from well--known simple\ndeterministic and stochastic models. Then they are applied to the DNA sequence\nof chromosome 1 of {\\em arabidopsis thaliana}. The results suggest that\ncorrelations do exist in the DNA sequence but they are weak and that intergenic\nsequences tend to be more correlated than gene sequences. The use of\nstatistical tests with surrogate data establish these findings in a rigorous\nstatistical manner.",
    "arxiv_id": "q-bio/0404024",
    "authors": [
      "D. Kugiumtzis",
      "A. Provata"
    ],
    "categories": [
      "q-bio.GN"
    ],
    "doi": "10.1016/j.physa.2004.05.070",
    "title": "Statistical analysis of Gene and Intergenic DNA Sequences",
    "url": "https://arxiv.org/abs/q-bio/0404024"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "8ac44687-e2c5-4704-a843-708476e074d8",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}