{
  "annotation_id": "54230639-d9e1-40f6-b6fd-b328291fcdc3",
  "date_created": "2026-03-02T18:00:42.611000Z",
  "date_modified": "2026-03-02T18:00:42.611000Z",
  "file_hash": "be5d158d6454484868fadc79cc904775b217f8f9bce853634213a909f49ceea2",
  "private": false,
  "record": {
    "abstract": "The primitive data for deducing the Miyazawa-Jernigan contact energy or\nBLOSUM score matrix consists of pair frequency counts. Each amino acid\ncorresponds to a conditional probability distribution. Based on the deviation\nof such conditional probability from random background, a scheme for reduction\nof amino acid alphabet is proposed. It is observed that evident discrepancy\nexists between reduced alphabets obtained from raw data of the\nMiyazawa-Jernigan\u0027s and BLOSUM\u0027s residue pair counts. Taking homologous\nsequence database SCOP40 as a test set, we detect homology with the obtained\ncoarse-grained substitution matrices. It is verified that the reduced alphabets\nobtained well preserve information contained in the original 20-letter\nalphabet.",
    "arxiv_id": "physics/0211031",
    "authors": [
      "Xin Liu",
      "Di Liu",
      "Ji Qi",
      "Wei-Mou Zheng"
    ],
    "categories": [
      "physics.bio-ph",
      "physics.data-an",
      "q-bio"
    ],
    "doi": "10.1103/PhysRevE.66.021906",
    "journal_ref": "PRE 66, 021906 (2002)",
    "title": "Simplified amino acid alphabets based on deviation of conditional   probability from random background",
    "url": "https://arxiv.org/abs/physics/0211031"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "0885a88f-b786-4cf4-bd02-81fdcf39ad5d",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}