{
  "id": "protein_sequence",
  "name": "Amino-acid sequence (protein or peptide)",
  "status": "draft",
  "doc": "Sequence of amino acids of a protein or peptide in the one-letter IUPAC code (A, C, D, E, F, G, H, I, K, L, M, N, P, Q, R, S, T, V, W, Y; X for an unknown residue, U and O for selenocysteine and pyrrolysine), as tables of predicted peptides, signal peptides or proteomics results store it; a translated reading frame often ends with * or a full stop for the stop codon (MSGLKISRVPVLLAALIYINISKRRISLVIV*). Words in capitals use the same letters, so a short value is a sequence only in a field named after it (Peptide, Peptide sequence, proprotein).",
  "categories": [
    {
      "id": "science",
      "name": "Scientific"
    }
  ],
  "langs": [
    {
      "id": "common",
      "name": "Common to most languages"
    }
  ],
  "is_pii": false,
  "classification": "identifier",
  "regexp": "^[ACDEFGHIKLMNPQRSTVWYXUOBZ]{8,}[*.]?$",
  "examples": [
    {
      "value": "MSGLKISRVPVLLAALIYINISKRRISLVIV*",
      "description": "a small ORF-encoded peptide of Arabidopsis (ARA-PEPs, KU Leuven)"
    },
    {
      "value": "MFGHLLSFLLLCGNVCS",
      "description": "a predicted signal peptide"
    },
    {
      "value": "msglkisrvp",
      "valid": false,
      "description": "lowercase"
    }
  ],
  "links": [
    {
      "type": "wikipedia",
      "url": "https://en.wikipedia.org/wiki/Protein_primary_structure"
    }
  ],
  "translations": {
    "ru": {
      "name": "Аминокислотная последовательность (белок или пептид)"
    }
  },
  "type": "datatype"
}