{
  "id": "refseq_accession",
  "name": "NCBI RefSeq accession",
  "status": "draft",
  "doc": "Accession of a record in RefSeq, the curated, non-redundant collection of reference genomic, transcript and protein sequences of the US National Center for Biotechnology Information (NCBI). Two letters and an underscore give the kind of molecule, for example NM_ for an mRNA, NP_ for a protein and NC_ for a complete genomic molecule, and digits follow. A version such as .6 may be added; it grows when the sequence changes. Genome records of whole-genome shotgun projects start with NZ_ and a letter code. GenBank, ENA and DDBJ accessions without an underscore are a separate datatype (insdc_accession).",
  "categories": [
    {
      "id": "science",
      "name": "Scientific"
    }
  ],
  "langs": [
    {
      "id": "common",
      "name": "Common to most languages"
    }
  ],
  "is_pii": false,
  "classification": "identifier",
  "regexp": "^(((AC|AP|NC|NG|NM|NP|NR|NT|NW|WP|XM|XP|XR|YP|ZP)_\\d+)|(NZ_[A-Z]{2,4}\\d+))(\\.\\d+)?$",
  "examples": [
    {
      "value": "NP_012345",
      "description": "40S ribosomal protein uS8 (RPS22A) of Saccharomyces cerevisiae; Bioregistry example"
    },
    {
      "value": "NM_000546.6",
      "description": "Human TP53 mRNA, transcript variant 1, with its version"
    },
    {
      "value": "NM000546",
      "valid": false,
      "description": "No underscore after the molecule code"
    }
  ],
  "mappings": {
    "bioregistry": "refseq"
  },
  "links": [
    {
      "type": "doc",
      "url": "https://www.ncbi.nlm.nih.gov/refseq/"
    },
    {
      "type": "other",
      "url": "https://bioregistry.io/registry/refseq"
    }
  ],
  "type": "datatype",
  "translations": {}
}