Class: Organism

name: Organism
description: A material entity that is a living or once-living individual. Organism
  instances represent the biological identity of what is in a sample, not the sample
  itself. Sub-species identity (strain, cultivar, lab isolate) is captured by slots
  on this class rather than via a separate Strain subclass.
comments:
- An Organism is not a sample; it is the biological entity that an OrganismSample
  is expected to contain, linked via expected_organism. Sub-species identity (strain_name,
  isolate_name) is captured directly on Organism.
from_schema: https://w3id.org/nmdc/nmdc
see_also:
- https://github.com/microbiomedata/nmdc-schema/issues/2959
- https://github.com/microbiomedata/nmdc-schema/issues/2803
- https://github.com/microbiomedata/nmdc-schema/issues/2971
exact_mappings:
- COB:0000022
is_a: MaterialEntity
slots:
- classified_as
- organism_genus
- organism_species
- strain_name
- isolate_name
- estimated_size
- gc_content
- ref_biomaterial
slot_usage:
  id:
    name: id
    required: true
    structured_pattern:
      syntax: '{id_nmdc_prefix}:orgn-{id_shoulder}-{id_blade}$'
      interpolated: true
  classified_as:
    name: classified_as
    description: Taxonomic classification of this organism.
    notes:
    - Narrowing `classified_as` to `NcbiTaxon` on organism-oriented classes via slot_usage
      is tracked in https://github.com/microbiomedata/nmdc-schema/issues/3016.
    range: NcbiTaxon
  estimated_size:
    name: estimated_size
    examples:
    - value: '5000000'
    in_subset:
    - jgi_isolate
    structured_aliases:
    - literal_form: Estimated Genome Size (Mb)
      predicate: BROAD_SYNONYM
      notes:
      - Exact JGI form template is access-restricted; source is the public submission
        overview.
      - 'Per @aclum: Mb is a coarser unit than bp, so a single Mb value covers many
        possible bp values; the alias is broader in granularity.'
      source: https://jgi.doe.gov/user-programs/pmo-overview/project-materials-submission-overview/
  ref_biomaterial:
    name: ref_biomaterial
    description: Reference for the organism, preferentially a DOI when a primary publication
      or genome report exists; PMID and URL are also accepted per the MIxS ref_biomaterial
      pattern (`{PMID}|{DOI}|{URL}`). Reuses MIxS ref_biomaterial (MIXS:0000025).
    comments:
    - The MIxS pattern accepts DOI, PMID, or URL. DOI is preferred when available;
      it gives a stable reference to the publication or genome report. See the `associated_dois`
      pattern elsewhere in the NMDC schema for DOI-structured alternatives.
    - The MIxS name ref_biomaterial may be renamed in a future MIxS release. See ongoing
      MIxS renaming work.
    examples:
    - description: DOI form (preferred when a primary publication exists)
      object:
        type: nmdc:TextValue
        has_raw_value: doi:10.1016/j.syapm.2018.01.009
    - description: PubMed ID form
      object:
        type: nmdc:TextValue
        has_raw_value: PMID:24296464
    - description: URL form (e.g. NCBI Genome record)
      object:
        type: nmdc:TextValue
        has_raw_value: https://www.ncbi.nlm.nih.gov/datasets/genome/GCA_000016065.1/
class_uri: nmdc:Organism

name: Organism
description: A material entity that is a living or once-living individual. Organism
  instances represent the biological identity of what is in a sample, not the sample
  itself. Sub-species identity (strain, cultivar, lab isolate) is captured by slots
  on this class rather than via a separate Strain subclass.
comments:
- An Organism is not a sample; it is the biological entity that an OrganismSample
  is expected to contain, linked via expected_organism. Sub-species identity (strain_name,
  isolate_name) is captured directly on Organism.
from_schema: https://w3id.org/nmdc/nmdc
see_also:
- https://github.com/microbiomedata/nmdc-schema/issues/2959
- https://github.com/microbiomedata/nmdc-schema/issues/2803
- https://github.com/microbiomedata/nmdc-schema/issues/2971
exact_mappings:
- COB:0000022
is_a: MaterialEntity
slot_usage:
  id:
    name: id
    required: true
    structured_pattern:
      syntax: '{id_nmdc_prefix}:orgn-{id_shoulder}-{id_blade}$'
      interpolated: true
  classified_as:
    name: classified_as
    description: Taxonomic classification of this organism.
    notes:
    - Narrowing `classified_as` to `NcbiTaxon` on organism-oriented classes via slot_usage
      is tracked in https://github.com/microbiomedata/nmdc-schema/issues/3016.
    range: NcbiTaxon
  estimated_size:
    name: estimated_size
    examples:
    - value: '5000000'
    in_subset:
    - jgi_isolate
    structured_aliases:
    - literal_form: Estimated Genome Size (Mb)
      predicate: BROAD_SYNONYM
      notes:
      - Exact JGI form template is access-restricted; source is the public submission
        overview.
      - 'Per @aclum: Mb is a coarser unit than bp, so a single Mb value covers many
        possible bp values; the alias is broader in granularity.'
      source: https://jgi.doe.gov/user-programs/pmo-overview/project-materials-submission-overview/
  ref_biomaterial:
    name: ref_biomaterial
    description: Reference for the organism, preferentially a DOI when a primary publication
      or genome report exists; PMID and URL are also accepted per the MIxS ref_biomaterial
      pattern (`{PMID}|{DOI}|{URL}`). Reuses MIxS ref_biomaterial (MIXS:0000025).
    comments:
    - The MIxS pattern accepts DOI, PMID, or URL. DOI is preferred when available;
      it gives a stable reference to the publication or genome report. See the `associated_dois`
      pattern elsewhere in the NMDC schema for DOI-structured alternatives.
    - The MIxS name ref_biomaterial may be renamed in a future MIxS release. See ongoing
      MIxS renaming work.
    examples:
    - description: DOI form (preferred when a primary publication exists)
      object:
        type: nmdc:TextValue
        has_raw_value: doi:10.1016/j.syapm.2018.01.009
    - description: PubMed ID form
      object:
        type: nmdc:TextValue
        has_raw_value: PMID:24296464
    - description: URL form (e.g. NCBI Genome record)
      object:
        type: nmdc:TextValue
        has_raw_value: https://www.ncbi.nlm.nih.gov/datasets/genome/GCA_000016065.1/
attributes:
  classified_as:
    name: classified_as
    description: Taxonomic classification of this organism.
    notes:
    - Narrowing `classified_as` to `NcbiTaxon` on organism-oriented classes via slot_usage
      is tracked in https://github.com/microbiomedata/nmdc-schema/issues/3016.
    comments:
    - Taxonomy-oriented uses (e.g. on Organism) should point to NcbiTaxon instances.
      OrganismSample reaches taxonomy indirectly via expected_organism.classified_as.
    from_schema: https://w3id.org/nmdc/nmdc
    see_also:
    - https://github.com/microbiomedata/nmdc-schema/issues/2959
    - https://github.com/microbiomedata/nmdc-schema/issues/3016
    narrow_mappings:
    - biolink:in_taxon
    rank: 1000
    owner: Organism
    domain_of:
    - Organism
    range: NcbiTaxon
    multivalued: true
    inlined: true
    inlined_as_list: true
  organism_genus:
    name: organism_genus
    description: Genus of the organism.
    notes:
    - GOLD organism_v2 Go0000189 (Shewanella loihica PV-4, queried 2026-04-21)
    - GOLD organism_v2 Go0000514 (Ruegeria pomeroyi DSS-3, queried 2026-04-21)
    - GOLD organism_v2 (Go0000058, queried 2026-04-14)
    comments:
    - Free-text submitter-provided genus name. For an ontology-grounded classification,
      use `classified_as` with a NcbiTaxon instance on the parent Organism class.
    examples:
    - value: Shewanella
    - value: Ruegeria
    - value: Campylobacter
    in_subset:
    - jgi_isolate
    from_schema: https://w3id.org/nmdc/nmdc
    structured_aliases:
    - literal_form: Genus
      predicate: EXACT_SYNONYM
      notes:
      - Exact JGI form template is access-restricted; source is the public submission
        overview.
      source: https://jgi.doe.gov/user-programs/pmo-overview/project-materials-submission-overview/
    rank: 1000
    owner: Organism
    domain_of:
    - Organism
    range: string
  organism_species:
    name: organism_species
    description: Species of the organism.
    notes:
    - GOLD organism_v2 Go0000189 (Shewanella loihica PV-4, queried 2026-04-21)
    - GOLD organism_v2 Go0000514 (Ruegeria pomeroyi DSS-3, queried 2026-04-21)
    comments:
    - Free-text submitter-provided species name. For an ontology-grounded classification,
      use `classified_as` with a NcbiTaxon instance on the parent Organism class.
    examples:
    - value: loihica
    - value: pomeroyi
    - value: sp.
      description: use when the isolate has not yet been assigned a species name
    in_subset:
    - jgi_isolate
    from_schema: https://w3id.org/nmdc/nmdc
    structured_aliases:
    - literal_form: Species
      predicate: EXACT_SYNONYM
      notes:
      - Exact JGI form template is access-restricted; source is the public submission
        overview.
      source: https://jgi.doe.gov/user-programs/pmo-overview/project-materials-submission-overview/
    rank: 1000
    owner: Organism
    domain_of:
    - Organism
    range: string
  strain_name:
    name: strain_name
    description: Strain or cultivar name of the organism.
    notes:
    - 'Microbial strain identifiers and plant cultivar names (governed by the International
      Code of Nomenclature for Cultivated Plants, ICNCP) are nomenclaturally distinct,
      but this slot accepts both for now to match the JGI Isolate (NA) v19 form''s
      combined "Strain or cultivar" field. A separate `cultivar_name` slot may be
      added if a plant-specific use case emerges; see #3056.'
    - MIxS `subspecf_gen_lin` (MIXS:0000020) covers this concept along with cultivar,
      serovar, biotype, ecotype, and other sub-species lineage types in a single slot
      using a rank-prefix encoding (e.g. "strain:PV-4"). NMDC splits the concept into
      separate slots; this slot covers the strain rank specifically.
    - Example values are strain names from GOLD organism_v2.
    examples:
    - value: PV-4
    - value: DSS-3
    - value: DSM 6724
    in_subset:
    - jgi_isolate
    from_schema: https://w3id.org/nmdc/nmdc
    structured_aliases:
    - literal_form: Strain or cultivar
      predicate: EXACT_SYNONYM
      notes:
      - Exact JGI form template is access-restricted; source is the public submission
        overview.
      source: https://jgi.doe.gov/user-programs/pmo-overview/project-materials-submission-overview/
    related_mappings:
    - MIXS:0000020
    rank: 1000
    owner: Organism
    domain_of:
    - Organism
    range: string
  isolate_name:
    name: isolate_name
    description: Isolate or mutant name.
    notes:
    - MIxS `subspecf_gen_lin` (MIXS:0000020) covers this concept along with strain,
      cultivar, serovar, biotype, ecotype, and other sub-species lineage types in
      a single slot using a rank-prefix encoding. NMDC uses a separate slot for the
      isolate rank specifically.
    - Example values are from GOLD dw_sample_taxonomy_info.isolate; "Isolate" is a
      generic placeholder used when no specific mutant or isolate name is recorded.
    examples:
    - value: Bd21-3
    - value: MR164
    - value: Isolate
    in_subset:
    - jgi_isolate
    from_schema: https://w3id.org/nmdc/nmdc
    structured_aliases:
    - literal_form: Isolate
      predicate: EXACT_SYNONYM
      notes:
      - Exact JGI form template is access-restricted; source is the public submission
        overview.
      source: https://jgi.doe.gov/user-programs/pmo-overview/project-materials-submission-overview/
    related_mappings:
    - MIXS:0000020
    rank: 1000
    owner: Organism
    domain_of:
    - Organism
    range: string
  estimated_size:
    name: estimated_size
    description: The estimated size of the genome prior to sequencing. Of particular
      importance in the sequencing of (eukaryotic) genome which could remain in draft
      form for a long or unspecified period
    title: estimated size
    notes:
    - The maximum_value here (1e11 bp = 100,000 Mb) is the eukaryote ceiling from
      JGI esplims. The tighter microbe ceiling (5,000 Mb) and the category-conditional
      required rule are enforced in submission-schema via class rules on IsolateInterface,
      keyed on biosafety_mat_cat.
    comments:
    - JGI reports values in megabases (Mb); NMDC stores them in base pairs (bp).
    examples:
    - value: '5000000'
    in_subset:
    - jgi_isolate
    from_schema: https://w3id.org/nmdc/nmdc
    structured_aliases:
    - literal_form: Estimated Genome Size (Mb)
      predicate: BROAD_SYNONYM
      notes:
      - Exact JGI form template is access-restricted; source is the public submission
        overview.
      - 'Per @aclum: Mb is a coarser unit than bp, so a single Mb value covers many
        possible bp values; the alias is broader in granularity.'
      source: https://jgi.doe.gov/user-programs/pmo-overview/project-materials-submission-overview/
    rank: 1000
    keywords:
    - size
    slot_uri: MIXS:0000024
    owner: Organism
    domain_of:
    - Organism
    range: integer
    minimum_value: 1
    maximum_value: 100000000000
  gc_content:
    name: gc_content
    description: Estimated GC content as a percentage.
    examples:
    - value: '45'
    - value: '60'
    in_subset:
    - jgi_isolate
    from_schema: https://w3id.org/nmdc/nmdc
    structured_aliases:
    - literal_form: GC Content %
      predicate: EXACT_SYNONYM
      notes:
      - Exact JGI form template is access-restricted; source is the public submission
        overview.
      source: https://jgi.doe.gov/user-programs/pmo-overview/project-materials-submission-overview/
    rank: 1000
    owner: Organism
    domain_of:
    - Organism
    range: float
    minimum_value: 0
    maximum_value: 100
    unit:
      ucum_code: '%'
  ref_biomaterial:
    name: ref_biomaterial
    description: Reference for the organism, preferentially a DOI when a primary publication
      or genome report exists; PMID and URL are also accepted per the MIxS ref_biomaterial
      pattern (`{PMID}|{DOI}|{URL}`). Reuses MIxS ref_biomaterial (MIXS:0000025).
    title: reference for biomaterial
    comments:
    - The MIxS pattern accepts DOI, PMID, or URL. DOI is preferred when available;
      it gives a stable reference to the publication or genome report. See the `associated_dois`
      pattern elsewhere in the NMDC schema for DOI-structured alternatives.
    - The MIxS name ref_biomaterial may be renamed in a future MIxS release. See ongoing
      MIxS renaming work.
    examples:
    - description: DOI form (preferred when a primary publication exists)
      object:
        type: nmdc:TextValue
        has_raw_value: doi:10.1016/j.syapm.2018.01.009
    - description: PubMed ID form
      object:
        type: nmdc:TextValue
        has_raw_value: PMID:24296464
    - description: URL form (e.g. NCBI Genome record)
      object:
        type: nmdc:TextValue
        has_raw_value: https://www.ncbi.nlm.nih.gov/datasets/genome/GCA_000016065.1/
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    slot_uri: MIXS:0000025
    owner: Organism
    domain_of:
    - Organism
    range: TextValue
    structured_pattern:
      syntax: ^({PMID}|{DOI}|{URL})$
      interpolated: true
      partial_match: true
  id:
    name: id
    description: A unique identifier for a thing. Must be either a CURIE shorthand
      for a URI or a complete URI
    notes:
    - 'abstracted pattern: prefix:typecode-authshoulder-blade(.version)?(_seqsuffix)?'
    - a minimum length of 3 characters is suggested for typecodes, but 1 or 2 characters
      will be accepted
    - typecodes must correspond 1:1 to a class in the NMDC schema. this will be checked
      via per-class id slot usage assertions
    - minting authority shoulders should probably be enumerated and checked in the
      pattern
    examples:
    - value: nmdc:mgmag-00-x012.1_7_c1
      description: https://github.com/microbiomedata/nmdc-schema/pull/499#discussion_r1018499248
    from_schema: https://w3id.org/nmdc/nmdc
    structured_aliases:
    - literal_form: workflow_execution_id
      predicate: NARROW_SYNONYM
      contexts:
      - https://bitbucket.org/berkeleylab/jgi-jat/macros/nmdc_metadata.yaml
    - literal_form: data_object_id
      predicate: NARROW_SYNONYM
      contexts:
      - https://bitbucket.org/berkeleylab/jgi-jat/macros/nmdc_metadata.yaml
    rank: 1000
    identifier: true
    owner: Organism
    domain_of:
    - NamedThing
    range: uriorcurie
    required: true
    pattern: ^[a-zA-Z0-9][a-zA-Z0-9_\.]+:[a-zA-Z0-9_][a-zA-Z0-9_\-\/\.,]*$
    structured_pattern:
      syntax: '{id_nmdc_prefix}:orgn-{id_shoulder}-{id_blade}$'
      interpolated: true
  name:
    name: name
    description: A human readable label for an entity
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    owner: Organism
    domain_of:
    - PersonValue
    - NamedThing
    - Protocol
    range: string
  description:
    name: description
    description: a human-readable description of a thing
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    slot_uri: dcterms:description
    owner: Organism
    domain_of:
    - ImageValue
    - NamedThing
    - Protocol
    range: string
  alternative_identifiers:
    name: alternative_identifiers
    description: A list of alternative identifiers for the entity.
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    owner: Organism
    domain_of:
    - NamedThing
    - MetaboliteIdentification
    range: uriorcurie
    multivalued: true
    pattern: ^[a-zA-Z0-9][a-zA-Z0-9_\.]+:[a-zA-Z0-9_][a-zA-Z0-9_\-\/\.,\(\)\=\#]*$
  type:
    name: type
    description: the class_uri of the class that has been instantiated
    notes:
    - makes it easier to read example data files
    - required for polymorphic MongoDB collections
    examples:
    - value: nmdc:Biosample
    - value: nmdc:Study
    from_schema: https://w3id.org/nmdc/nmdc
    see_also:
    - https://github.com/microbiomedata/nmdc-schema/issues/1048
    - https://github.com/microbiomedata/nmdc-schema/issues/1233
    - https://github.com/microbiomedata/nmdc-schema/issues/248
    structured_aliases:
    - literal_form: workflow_execution_class
      predicate: NARROW_SYNONYM
      contexts:
      - https://bitbucket.org/berkeleylab/jgi-jat/macros/nmdc_metadata.yaml
    rank: 1000
    slot_uri: rdf:type
    designates_type: true
    owner: Organism
    domain_of:
    - EukEval
    - FunctionalAnnotationAggMember
    - PeptideQuantification
    - ProteinQuantification
    - GenomeFeature
    - FunctionalAnnotation
    - AttributeValue
    - NamedThing
    - OntologyRelation
    - FailureCategorization
    - Protocol
    - CreditAssociation
    - Doi
    - ProvenanceMetadata
    - MobilePhaseSegment
    - PortionOfSubstance
    - MagBin
    - MetaboliteIdentification
    range: uriorcurie
    required: true
class_uri: nmdc:Organism