{
  "annotation_id": "0ab9f5be-0728-4989-a4bf-92851913f0af",
  "date_created": "2026-03-02T18:01:31.815000Z",
  "date_modified": "2026-03-02T18:01:31.815000Z",
  "file_hash": "f106f470e29ac03ca8654b51f40cc394e618be08b23baed4af6ae9b40a75e19a",
  "private": false,
  "record": {
    "abstract": "The minimum description length (MDL) principle states that the best model to\naccount for some data minimizes the sum of the lengths, in bits, of the\ndescriptions of the model and the residual error. The description length is\nthus a criterion for model selection. Description-length analysis of HLA\nalleles from the Chicago MACS cohort enables classification of alleles\nassociated with plasma HIV RNA, an indicator of infection progression.\nProgression variation is most strongly associated with HLA-B. Individuals\nwithout B58s supertype alleles average viral RNA levels 3.6-fold greater than\nindividuals with them.",
    "arxiv_id": "q-bio/0505050",
    "authors": [
      "Peter T. Hraber",
      "Bette T. Korber",
      "Steven Wolinsky",
      "Henry A. Erlich",
      "Elizabeth A. Trachtenberg",
      "Thomas B. Kepler"
    ],
    "categories": [
      "q-bio.QM",
      "cs.IT",
      "math.IT"
    ],
    "doi": "10.1007/11946465_1",
    "journal_ref": "Lecture Notes in Computer Science Volume 4345, 2006, pp 1-12",
    "title": "HLA and HIV Infection Progression: Application of the Minimum   Description Length Principle to Statistical Genetics",
    "url": "https://arxiv.org/abs/q-bio/0505050"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "bc1f1703-d825-4c81-85e0-2317ad77d0f5",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}