{
  "annotation_id": "31184112-212c-44ff-979b-cf9c50f948b9",
  "date_created": "2026-03-02T18:00:38.973000Z",
  "date_modified": "2026-03-02T18:00:38.973000Z",
  "file_hash": "5b583ebae538ab32224fadc73f5c107f004c0563b4094eb2791e25fb2eeb0462",
  "private": false,
  "record": {
    "abstract": "We discuss two new approaches to extract relevant biological information on\nthe Transcription Factors (and in particular to identify their binding\nsequences) from the statistical distribution of oligonucleotides in the\nupstream region of the genes. Both the methods are based on the notion of a\n``regulatory network\u0027\u0027 responsible for the various expression patterns of the\ngenes. In particular we concentrate on families of coregulated genes and look\nfor the simultaneous presence in the upstream regions of these genes of the\nsame set of transcription factor binding sites. We discuss two instances which\nwell exemplify the features of the two methods: the coregulation of glycolysis\nin Drosophila melanogaster and the diauxic shift in Saccharomyces cerevisiae.",
    "arxiv_id": "physics/0201033",
    "authors": [
      "M. Caselle",
      "F. Di Cunto",
      "M. Pellegrino",
      "P. Provero"
    ],
    "categories": [
      "physics.bio-ph",
      "cond-mat",
      "q-bio.GN"
    ],
    "title": "Finding regulatory sites from statistical analysis of nucleotide   frequencies in the upstream region of eukaryotic genes",
    "url": "https://arxiv.org/abs/physics/0201033"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "b2caf9ee-6671-4f59-b3a9-1dbf3f7c4183",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}