{
  "annotation_id": "93b25571-2d3a-4c6d-9ee1-48774de9227b",
  "date_created": "2026-03-02T18:01:35.823000Z",
  "date_modified": "2026-03-02T18:01:35.823000Z",
  "file_hash": "55c6602b5d2625418ce8c634b89c1e67f985c9e4215387035c02d6d76660f519",
  "private": false,
  "record": {
    "abstract": "When the same set of genes appear in two top ranking gene lists in two\ndifferent studies, it is often of interest to estimate the probability for this\nbeing a chance event. This overlapping probability is well known to follow the\nhypergeometric distribution. Usually, the lengths of top-ranking gene lists are\nassumed to be fixed, by using a pre-set criterion on, e.g., $p$-value for the\nt-test. We investigate how overlapping probability changes with the gene\nselection criterion, or simply, with the length of the top-ranking gene lists.\nIt is concluded that overlapping probability is indeed a function of the gene\nlist length, and its statistical significance should be quoted in the context\nof gene selection criterion.",
    "arxiv_id": "q-bio/0606017",
    "authors": [
      "Wen Fury",
      "Franak Batliwalla",
      "Peter K. Gregersen",
      "Wentian Li"
    ],
    "categories": [
      "q-bio.QM"
    ],
    "doi": "10.1109/IEMBS.2006.260828",
    "journal_ref": "Proceedings of 28th Annual International Conference of the\n  Engineering in Medicine and Biology Society, IEEE (2006), pages 5531-5534",
    "title": "Overlapping Probabilities of Top Ranking Gene Lists, Hypergeometric   Distribution, and Stringency of Gene Selection Criterion",
    "url": "https://arxiv.org/abs/q-bio/0606017"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "7df95ab2-e261-487c-a8bc-0e3abcb0778d",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}