bertron_schema.yaml

# yaml-language-server: $schema=https://linkml.io/linkml-model/linkml_model/jsonschema/meta.schema.json

id: https://w3id.org/ber-data/bertron-schema
name: bertron-schema
title: BERtron schema
description: Schema for BERtron common data model.
version: 0.0.2
license: BSD-3
see_also:
  - https://ber-data.github.io/bertron-schema
prefixes:
  bertron: https://w3id.org/ber-data/bertron-schema/
  linkml: https://w3id.org/linkml/
  schema: http://schema.org/
  UO: http://purl.obolibrary.org/obo/UO_
  MIXS: https://w3id.org/mixs/
  WGS84: http://www.w3.org/2003/01/geo/wgs84_pos#
default_prefix: bertron
default_range: string
default_curi_maps:
  - semweb_context
imports:
  - linkml:types
  - bertron_types

classes:
  Entity:
    tree_root: true
    class_uri: schema:Thing
    description: |
      An object retrieved by BERtron from a BER data API.
    attributes:
      ber_data_source:
        description: The BER member from whence the entity originated.
        range: BERSourceType
        required: true
      # TODO!
      # credit_metadata:
      #   description: Citation metadata for the entity.
      #   range: CreditMetadata
      #   required: true
      coordinates:
        description: The geographic coordinates associated with an entity. For entities with a bounding box, the centroid is used as the geographic reference.
        range: Coordinates
      entity_type:
        description: What kind of entity is this -- e.g. sequence data; a soil core; a well; field site; sample; etc.
        range: EntityType
        multivalued: true
        required: true
      description:
        description: Textual description of the entity.
        required: false
        slot_uri: schema:description
        examples:
        - value: "River water sample taken by AquaTROLL 9000."
        - value: "Genome sequence of P. aeruginosa strain IDDQD"
      id:
        aliases:
        - BER data source internal identifier
        - CURIE
        description: The unique ID used for the entity within the BER resource. It may not necessarily be resolvable outside the resource.
        comments:
        - If the data source does not use CURIEs, we cannot guarantee that IDs will be unique between all the BER sources.
        # identifier: true
        # required: true
        range: string
        slot_uri: schema:identifier
      name:
        description: Human-readable string representing an entity.
        multivalued: false
        slot_uri: schema:name
        examples:
        - value: "Pseudomonas aeruginosa strain IDDQD"
        - value: "Soil core FW-106"
      alt_ids:
        aliases:
        - CURIEs
        - database cross-references
        - dbxrefs
        - IDs
        - alternative identifiers
        - alternative IDs
        - alternative PIDs
        - PIDs
        description: Fully-qualified URI or CURIE used as an identifier for an entity.
        range: uriorcurie
        multivalued: true
        examples:
          - value: "NCBItaxon:172684329"
          - value: "ISGN:1986497"
        comments:
        - The entity `id` should not appear in this list.
      alt_names:
        aliases:
        - alternative names
        - synonyms
        description: Textual identifiers for an entity.
        range: Name
        multivalued: true
        comments:
        - The entity `name` should not appear in this list.
      part_of_collection:
        description: Administrative collection (e.g. project, campaign, whatever) that the entity was generated as part of. May also be called a project.
        multivalued: true
        required: false
        range: DataCollection
      uri:
        aliases:
          - url
        description: Permanent resolvable URI for the entity at the data source.
        range: uriorcurie
        required: true
      properties:
        description: Provide extended context that may be relevant and applicable to the entity you're describing.
        multivalued: true
        required: false
        range: Any
        any_of:
          - range:
              TextValue
          - range:
              QuantityValue
        mappings:
          - MIXS:0000008
        examples:
          - object:
              attribute:
                id: MIXS:0000117
                label: total phosphorus
              raw_value: "2.2 ppm"
              unit: ppm
              numeric_value: 2.2
          - object:
              attribute:
                id: MIXS:0000011
                label: collection date
              raw_value: "2025-06-12"
          - object:
              attribute:
                id: MIXS:0000012
                label: env_broad_scale
              value: "terrestrial biome"
              value_cv_id: "ENVO:00000446"
          - object:
              attribute:
                id: PATO:0001687
                label: elevation
              numeric_value: 2.2
              unit: UO:0000008
              raw_value: "2.2 m"

  Coordinates:
    description: The coordinates defining the position associated with the entity.
    attributes:
      latitude:
        description: latitude
        examples:
          - value: "-33.460524"
        mappings:
          - schema:latitude
        broad_mappings:
          - MIXS:0000009
        range: decimal degree
        required: true
        slot_uri: WGS84:lat
      longitude:
        description: longitude
        examples:
          - value: "150.168149"
        mappings:
          - schema:longitude
        broad_mappings:
          - MIXS:0000009
        range: decimal degree
        required: true
        slot_uri: WGS84:long

  Name:
    description: The name or label for an entity. This may be a primary name,
      alternative name, synonym, acronym, or any other label used to refer to an
      entity.
    attributes:
      name_type:
        description: Brief description of the name and/or its relationship to the entity.
        range: NameType
        multivalued: false
      name:
        description: The string used as a name.
        examples:
        - value: Heat-inducible transcription repressor HrcA
        - value: FW106 groundwater metagenome
        required: true
        slot_uri: schema:name

  DataCollection:
    description: Administrative unit (e.g. project, proposal, etc.) in which one or more entities is collected.
    comments:
      - May be equivalent to FundingReference in the CreditMetadata schema.
    attributes:
      id:
        aliases:
        - proposal ID
        - project ID
        description: The unique ID used for the grouped set of data within the BER resource. It may not necessarily be resolvable outside the resource.
        comments:
        - If the data source does not use CURIEs, we cannot guarantee that IDs will be unique between all the BER sources.
        # identifier: true
        # required: true
        range: string
        slot_uri: schema:identifier
      title:
        aliases:
        - name
        description: Human-readable string representing the grouped set of data.
        multivalued: false
        slot_uri: schema:name
      description:
        description: Textual description of the grouped set of data.
        required: false
        slot_uri: schema:description
      alt_ids:
        aliases:
        - CURIEs
        - database cross-references
        - dbxrefs
        - IDs
        - alternative identifiers
        - alternative IDs
        - alternative PIDs
        - PIDs
        description: Fully-qualified URI or CURIE used as an identifier for a grouped set of data.
        range: uriorcurie
        multivalued: true
        comments:
        - The project `id` should not appear in this list.
      alt_titles:
        aliases:
        - alternative titles
        description: Alternative versions of the title/name of a grouped set of data.
        range: Name
        multivalued: true
        comments:
        - The project `title` should not appear in this list.
      url:
        description: Permanent resolvable URI for the collection at the data source.
        range: uriorcurie
        required: true

enums:

  BERSourceType:
    description: The BER data source from whence the entity originated.
    todos:
    - Check which data sources will be accessible via BERtron and update this list.
    permissible_values:
      EMSL:
      ESS-DIVE:
      JGI:
      MONET:
      NMDC:

  EntityType:
    description: The type of entity captured in this record.
    todos:
    - Complete this list!
    permissible_values:
      biodata:
      jgi_biosample:
      sample:
      sequence:
      taxon:
      unspecified:
      project:
        description: An enterprise (potentially individual but typically collaborative), planned to achieve a particular aim.
        aliases:
          - study
          - proposal
      site:
        description: An entity that describes a location of experimentation or sample collection
        todos:
          - Better description from an ontology!
      dataset:
        description: A single or collection or data generated from an experimental entity
        todos:
          - Better description from an ontology!

  NameType:
    description: The relationship between a name and a synonym of that name.
    todos:
    - Add in skos mappings.
    permissible_values:
      broad_synonym:
        title: broad synonym
        description: The synonym refers to a broader group of entities than the name.
      exact_synonym:
        title: exact synonym
        description: String with exactly the same meaning and connotations as the original name.
      narrow_synonym:
        title: narrow synonym
        description: The synonym refers to a narrower group of entities than the name.
      related_synonym:
        title: related synonym
        description: The synonym has overlap with the name but the precise relationship is not defined.
      acronym:
        title: acronym
        description: An acronym or abbreviation for the name.