external_identifiers.yaml

id: https://w3id.org/nmdc/external_identifiers
name: external_identifiers
title: NMDC External Identifiers
description: >-
  External identifiers

license: https://creativecommons.org/publicdomain/zero/1.0/

imports:
  - attribute_values # in cycle with basic_classes

prefixes:
  gold: "https://bioregistry.io/gold:"
  linkml: https://w3id.org/linkml/
  nmdc: https://w3id.org/nmdc/
  skos: http://www.w3.org/2004/02/skos/core#

default_prefix: nmdc
default_range: string

slots:

  img_identifiers:
    title: IMG Identifiers
    is_a: external_database_identifiers
    description: >-
      A list of identifiers that relate the biosample to records in the IMG database.
    todos:
      - add is_a or mixin modeling, like other external_database_identifiers
      - what class would IMG records belong to?! Are they Studies, Biosamples, or something else?
    pattern: '^img\.taxon:[a-zA-Z0-9_][a-zA-Z0-9_\/\.]*$' # DOI-like pattern. Could be more conservative if we leave this out of the external_database_identifiers hierarchy

  ## mixins

  igsn_identifiers:
    mixin: true

  gold_identifiers:
    mixin: true
    see_also:
      - https://gold.jgi.doe.gov/

  emsl_identifiers:
    mixin: true

  mgnify_identifiers:
    mixin: true
    see_also:
      - https://www.ebi.ac.uk/metagenomics/

  insdc_identifiers:
    mixin: true
    aliases:
      - EBI identifiers
      - NCBI identifiers
      - DDBJ identifiers
    description: >-
      Any identifier covered by the International Nucleotide Sequence Database Collaboration
    comments:
      - note that we deliberately abstract over which of the partner databases accepted the initial submission
      - "the first letter of the accession indicates which partner accepted the initial submission: E for ENA, D for DDBJ, or S or N for NCBI."
    see_also:
      - https://www.insdc.org/
      - https://ena-docs.readthedocs.io/en/latest/submit/general-guide/accessions.html

  neon_identifiers:
    mixin: true
    description: identifiers for entities according to NEON

  jgi_portal_identifiers:
    mixin: true
    description: identifiers for entities according to JGI Portal
    see_also:
      - https://data.jgi.doe.gov/

  gnps_identifiers:
    mixin: true

  ## studies

  study_identifiers:
    abstract: true
    is_a: external_database_identifiers

  jgi_portal_study_identifiers:
    is_a: study_identifiers
    mixins:
      - jgi_portal_identifiers
    id_prefixes:
      - jgi.proposal
    pattern: '^jgi.proposal:\d+$'
    examples:
      - value: jgi.proposal:507130
    comments:
      - Could this could be considered a related identifier?
      - Curie suffix is the Site Award Number from an OSTI award page
      - Site Award Number 507130 == award doi doi:10.46936/10.25585/60000017 -- GOLD study identifier gold:Gs0154044
      - bioregistry.io/jgi.proposal:507130 ==https://genome.jgi.doe.gov/portal/BioDefcarcycling/BioDefcarcycling.info.html
    title: JGI Portal Study identifiers
    description: >-
      Identifiers that link a NMDC study to a website hosting raw and analyzed data for a JGI proposal. 
      The suffix of the curie can used to query the GOLD API and is interoperable with an award DOI from OSTI and a GOLD study identifier.

  neon_study_identifiers:
    is_a: study_identifiers
    mixins:
      - neon_identifiers

  insdc_sra_ena_study_identifiers:
    is_a: study_identifiers
    mixins:
      - insdc_identifiers
    aliases:
      - EBI ENA study identifiers
      - NCBI SRA identifiers
      - DDBJ SRA identifiers
    pattern: "^insdc.sra:(E|D|S)RP[0-9]{6,}$"
    description: identifiers for corresponding project in INSDC SRA / ENA
    examples:
      - value: https://bioregistry.io/insdc.sra:SRP121659
        description: Avena fatua rhizosphere microbial communities - H1_Rhizo_Litter_2 metatranscriptome
    see_also:
      - https://github.com/bioregistry/bioregistry/issues/109
      - https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=studies
      - https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=studies

  insdc_bioproject_identifiers:
    is_a: study_identifiers
    mixins:
      - insdc_identifiers
    aliases:
      - NCBI bioproject identifiers
      - DDBJ bioproject identifiers
    pattern: "^bioproject:PRJ[DEN][A-Z][0-9]+$"
    description: identifiers for corresponding project in INSDC Bioproject
    comments:
      - these are distinct IDs from INSDC SRA/ENA project identifiers, but are usually(?) one to one
    examples:
      - value: https://bioregistry.io/bioproject:PRJNA366857
        description: Avena fatua rhizosphere microbial communities - H1_Rhizo_Litter_2 metatranscriptome
    see_also:
      - https://www.ncbi.nlm.nih.gov/bioproject/
      - https://www.ddbj.nig.ac.jp/bioproject/index-e.html

  gold_study_identifiers:
    is_a: study_identifiers
    mixins:
      - gold_identifiers
    pattern: "^gold:Gs[0-9]+$"
    description: identifiers for corresponding project(s) in GOLD
    comments:
      - uses the prefix GS (but possibly in a different case)
    examples:
      - value: https://bioregistry.io/gold:Gs0110115
    see_also:
      - https://gold.jgi.doe.gov/studies
    title: GOLD Study Identifiers

  mgnify_project_identifiers:
    is_a: study_identifiers
    mixins:
      - mgnify_identifiers
    pattern: "^mgnify.proj:[A-Z]+[0-9]+$"
    description: identifiers for corresponding project in MGnify
    examples:
      - value: https://bioregistry.io/mgnify.proj:MGYS00005757

  gnps_task_identifiers:
    is_a: study_identifiers
    mixins:
      - gnps_identifiers
    title: GNPS task identifiers
    description: identifiers that link a NMDC study to a web-based report about metabolomics analysis progress and results
    comments:
      - this could be considered a related identifier, as the metabolomics progress and results aren't a study per se
      - this identifier was registered with bioregistry but not identifiers.org
    see_also:
      - https://microbiomedata.github.io/nmdc-schema/MetabolomicsAnalysis/
    examples:
      - value: gnps.task:4b848c342a4f4abc871bdf8a09a60807
    pattern: "^gnps\\.task:[a-f0-9]+$"


  emsl_project_identifiers:
    title: EMSL Project Identifiers
    is_a: study_identifiers
    mixins:
      - emsl_identifiers
    description: Identifiers that link a NMDC study to the EMSL user facility website hosting the project description of an EMSL user project
    see_also:
      - https://github.com/microbiomedata/nmdc-schema/issues/927#issuecomment-1802136437
    pattern: "^emsl\\.project:[0-9]{5}$"
    examples:
      - value: emsl.project:60141
    notes:
      - these identifiers are all currently 5 digits long but that could change in the future
    todos:
      - elaborate on description

  ## samples

  biosample_identifiers:
    abstract: true
    is_a: external_database_identifiers

  neon_biosample_identifiers:
    is_a: biosample_identifiers
    mixins:
      - neon_identifiers

  gold_biosample_identifiers:
    is_a: biosample_identifiers
    mixins:
      - gold_identifiers
    pattern: "^gold:Gb[0-9]+$"
    description: identifiers for corresponding sample in GOLD
    examples:
      - value: https://bioregistry.io/gold:Gb0312930
    range: uriorcurie

  insdc_biosample_identifiers:
    is_a: biosample_identifiers
    mixins:
      - insdc_identifiers
    aliases:
      - EBI biosample identifiers
      - NCBI biosample identifiers
      - DDBJ biosample identifiers
    pattern: "^biosample:SAM[NED]([A-Z])?[0-9]+$"
    description: identifiers for corresponding sample in INSDC
    examples:
      - value: https://bioregistry.io/biosample:SAMEA5989477
      - value: https://bioregistry.io/biosample:SAMD00212331
        description: I13_N_5-10 sample from Soil fungal diversity along elevational gradients
    see_also:
      - https://github.com/bioregistry/bioregistry/issues/108
      - https://www.ebi.ac.uk/biosamples/
      - https://www.ncbi.nlm.nih.gov/biosample
      - https://www.ddbj.nig.ac.jp/biosample/index-e.html

  insdc_secondary_sample_identifiers:
    is_a: biosample_identifiers
    mixins:
      - insdc_identifiers
    pattern: "^biosample:(E|D|S)RS[0-9]{6,}$"
    description: secondary identifiers for corresponding sample in INSDC
    comments:
      - "ENA redirects these to primary IDs, e.g. https://www.ebi.ac.uk/ena/browser/view/DRS166340 -> SAMD00212331"
      - MGnify uses these as their primary sample IDs
    examples:
      - value: https://bioregistry.io/insdc.sra:DRS166340
        description: I13_N_5-10 sample from Soil fungal diversity along elevational gradients

  emsl_biosample_identifiers:
    title: EMSL Biosample Identifiers
    description: >-
      A list of identifiers for the biosample from the EMSL database.  This is
      used to link the biosample, as modeled by NMDC, to the biosample in the planned EMSL NEXUS database.
    is_a: biosample_identifiers
    mixins:
      - emsl_identifiers
    todos:
      - removed "planned" once NEXUS is online
      - determine real expansion for emsl prefix

  igsn_biosample_identifiers:
    title: IGSN Biosample Identifiers
    description: >-
      A list of identifiers for the biosample from the IGSN database.
    is_a: biosample_identifiers
    mixins:
      - igsn_identifiers

  ## DataGeneration

  omics_processing_identifiers:
    abstract: true
    is_a: external_database_identifiers

  gold_sequencing_project_identifiers:
    is_a: omics_processing_identifiers
    mixins:
      - gold_identifiers
    pattern: "^gold:Gp[0-9]+$"
    description: identifiers for corresponding sequencing project in GOLD
    examples:
      - value: https://bioregistry.io/gold:Gp0108335

  insdc_experiment_identifiers:
    is_a: external_database_identifiers
    pattern: "^insdc.sra:(E|D|S)RX[0-9]{6,}$"
    mixins:
      - insdc_identifiers

  ## analysis run

  analysis_identifiers:
    abstract: true
    is_a: external_database_identifiers

  gold_analysis_project_identifiers:
    is_a: analysis_identifiers
    mixins:
      - gold_identifiers
    pattern: "^gold:Ga[0-9]+$"
    description: identifiers for corresponding analysis projects in GOLD
    examples:
      - value: https://bioregistry.io/gold:Ga0526289

  jgi_portal_analysis_project_identifiers:
    is_a: analysis_identifiers
    mixins:
      - jgi_portal_identifiers
    id_prefixes:
      - jgi.analysis
    pattern: '^jgi.analysis:[0-9]+$'
    description: identifiers for corresponding analysis projects in JGI Portal
    examples:
      - value: https://data.jgi.doe.gov/search?q=1414320
        description: Metagenome - Draft Assembly YELL_051-M-20210705-comp-DNA1

  insdc_analysis_identifiers:
    is_a: analysis_identifiers
    comments:
      - in INSDC this is a run but it corresponds to a GOLD analysis
    pattern: "^insdc.sra:(E|D|S)RR[0-9]{6,}$"
    mixins:
      - insdc_identifiers
    examples:
      - value: https://www.ebi.ac.uk/metagenomics/runs/DRR218479
        description: Illumina MiSeq paired end sequencing of SAMD00212331
      - value: https://www.ebi.ac.uk/ena/browser/view/ERR436051

  mgnify_analysis_identifiers:
    is_a: analysis_identifiers
    notes:
      - 'removed pattern: "^mgnify:MGYA[0-9]+$" ## TODO https://github.com/bioregistry/bioregistry/issues/109'
    mixins:
      - mgnify_identifiers
    examples:
      - value: https://www.ebi.ac.uk/metagenomics/analyses/MGYA00002270
        description: combined analyses (taxonomic, functional) of sample ERS438107

  ## assemblies

  assembly_identifiers:
    abstract: true

  insdc_assembly_identifiers:
    is_a: assembly_identifiers
    pattern: "^insdc.sra:[A-Z]+[0-9]+(\\.[0-9]+)?$"
    mixins:
      - insdc_identifiers