{
  "annotation_id": "54feeac1-a413-4292-91e6-035a4e7c4336",
  "date_created": "2026-03-02T18:01:31.535000Z",
  "date_modified": "2026-03-02T18:01:31.535000Z",
  "file_hash": "ccc2a59f0a92a49b2d1407f929218d3cc552274fb47f7904d0aae116d063a79f",
  "private": false,
  "record": {
    "abstract": "By using a mixture model for the density distribution of the three pseudobond\nangles formed by $C_\\alpha$ atoms of four consecutive residues, the local\nstructural states are discretized as 17 conformational letters of a protein\nstructural alphabet. This coarse-graining procedure converts a 3D structure to\na 1D code sequence. A substitution matrix between these letters is constructed\nbased on the structural alignments of the FSSP database.",
    "arxiv_id": "q-bio/0412046",
    "authors": [
      "Wei-Mou Zheng",
      "Xin Liu"
    ],
    "categories": [
      "q-bio.BM"
    ],
    "title": "A protein structural alphabet and its substitution matrix CLESUM",
    "url": "https://arxiv.org/abs/q-bio/0412046"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "09886f84-e19c-4068-9ca1-91ee660ef73b",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}