{
  "id": "insdc_accession",
  "name": "INSDC sequence accession (GenBank, ENA, DDBJ)",
  "status": "draft",
  "doc": "Accession number of a sequence record in the databases of the International Nucleotide Sequence Database Collaboration: GenBank at NCBI, the European Nucleotide Archive (ENA) at EMBL-EBI and DDBJ. The three exchange their records and share one accession space. Older nucleotide records have one letter and five digits or two letters and six digits; bulk records such as whole-genome shotgun contigs have four to six letters and eight to ten digits; coding sequence (protein) records have three letters and five digits, as in AAA35559. A version such as .1 may follow. RefSeq, read archive, BioSample and BioProject accessions are separate datatypes.",
  "categories": [
    {
      "id": "science",
      "name": "Scientific"
    }
  ],
  "langs": [
    {
      "id": "common",
      "name": "Common to most languages"
    }
  ],
  "is_pii": false,
  "classification": "identifier",
  "regexp": "^([A-Z]\\d{5}|[A-Z]{2}\\d{6}|[A-Z]{4,6}\\d{8,10}|[A-J][A-Z]{2}\\d{5})(\\.\\d+)?$",
  "examples": [
    {
      "value": "X58356",
      "description": "Nicotiana sylvestris gene for a 33 kDa chloroplast ribonucleoprotein; Bioregistry example"
    },
    {
      "value": "X58356.1",
      "description": "The same record with its version"
    },
    {
      "value": "NM_000546",
      "valid": false,
      "description": "RefSeq accession, not an INSDC one"
    }
  ],
  "mappings": {
    "bioregistry": "insdc"
  },
  "links": [
    {
      "type": "doc",
      "url": "https://www.insdc.org/"
    },
    {
      "type": "other",
      "url": "https://bioregistry.io/registry/insdc"
    }
  ],
  "type": "datatype",
  "translations": {}
}