---
ontology:
  id: scientific
  version: 0.3.0
  description: Scientific research domain ontology — studies, methods, data, provenance
  extends:
    - research
namespaces:
  semantic:
    children:
      science:
        description: Hypotheses, methods, measurements, samples
        type_hint: semantic
      instruments:
        description: Research instruments and devices
        type_hint: semantic
      catalogs:
        description: Datasets, catalogs, distributions, services
        type_hint: semantic
      publications:
        description: Research publications and scholarly outputs
        type_hint: semantic
      funding:
        description: Grants and research funding
        type_hint: semantic
  episodic:
    children:
      studies:
        description: Studies, investigations, cohorts
        type_hint: episodic
      provenance:
        description: Data provenance and derivation events
        type_hint: episodic
  procedural:
    children:
      protocols:
        description: Methods and protocol applications
        type_hint: procedural
entity_types:
  - name: study
    description: A scientific study with a defined design
    base: episodic
    traits:
      - cited
      - dated
      - stakeholders
    schema:
      required:
        - study_id
        - title
      properties:
        study_id:
          type: string
        title:
          type: string
        study_type:
          type: string
          enum:
            - observational
            - experimental
            - randomized-controlled
            - cohort
            - case-control
            - cross-sectional
            - computational
        start_date:
          type: string
          format: date
        end_date:
          type: string
          format: date
        status:
          type: string
          enum:
            - planned
            - in-progress
            - completed
            - retracted
        objective:
          type: string
        principal_investigator:
          type: string
    source_vocab: OBI
    source_class: study design
    prior_art: obi:StudyDesign / IAO investigation
    disposition: mint
    subtype_of:
      - inquiry
  - name: research-investigation
    description: A research investigation spanning planning, execution and reporting
    base: episodic
    traits:
      - cited
      - dated
      - stakeholders
    schema:
      required:
        - investigation_id
        - title
      properties:
        investigation_id:
          type: string
        title:
          type: string
        description:
          type: string
        start_date:
          type: string
          format: date
        end_date:
          type: string
          format: date
        status:
          type: string
          enum:
            - planned
            - active
            - completed
            - published
            - retracted
        ethical_approval_id:
          type: string
        funding_ref:
          type: string
        publication_refs:
          type: array
          items:
            type: string
    source_vocab: OBI
    source_class: investigation
    prior_art: obi:Investigation / schema.org MedicalStudy
    disposition: mint
    subtype_of:
      - inquiry
  - name: cohort
    description: A defined study population (subjects of an investigation)
    base: episodic
    traits:
      - cited
      - dated
    schema:
      required:
        - cohort_id
        - title
      properties:
        cohort_id:
          type: string
        title:
          type: string
          description: "Inherited from research.ontology.yaml's inquiry: the cohort's human-readable name (e.g. 'Framingham Heart Study Cohort 1948'), distinct from cohort_id (the internal identifier)"
        cohort_size:
          type: integer
        inclusion_criteria:
          type: string
        exclusion_criteria:
          type: string
        study_ref:
          type: string
        follow_up_duration:
          type: string
        demographics_summary:
          type: string
    source_vocab: OBI
    source_class: study population
    prior_art: obi:StudyPopulation / NCIt cohort
    disposition: mint
    subtype_of:
      - inquiry
  - name: method
    description: A scientific method or assay
    base: procedural
    traits:
      - cited
      - versioned
    schema:
      required:
        - name
        - method_type
      properties:
        name:
          type: string
          description: "Renamed from method_name to match research-procedure's field name directly (no duplicate field: the registry's sha256-pinned vendoring isolates already-vendored consumers from this rename until they re-vendor)"
        method_type:
          type: string
        description:
          type: string
        instrument_ref:
          type: string
        reagents:
          type: array
          items:
            type: string
        output_type:
          type: string
    source_vocab: OBI
    source_class: assay
    prior_art: obi:Assay / IAO plan specification
    disposition: mint
    subtype_of:
      - research-procedure
  - name: protocol-application
    description: The execution of a protocol (distinct from the method specification)
    base: procedural
    traits:
      - cited
      - versioned
      - dated
    schema:
      required:
        - name
      properties:
        name:
          type: string
          description: "Renamed from protocol_name to match research-procedure's field name directly"
        version:
          type: string
        procedure_steps:
          type: array
          items:
            type: string
        protocol_type:
          type: string
        ethics_approval_id:
          type: string
        doi:
          type: string
          format: uri
        instrument_requirements:
          type: string
    source_vocab: OBI
    source_class: OBI:0000070 protocol application
    prior_art: obi:ProtocolApplication / schema.org StudyAction
    disposition: mint
    subtype_of:
      - research-procedure
  - name: sample-organism
    description: A material sample (organism, tissue, or specimen)
    base: semantic
    traits:
      - cited
      - dated
    schema:
      required:
        - sample_id
        - organism_name
      properties:
        sample_id:
          type: string
        taxon_id:
          type: string
        organism_name:
          type: string
        tissue_type:
          type: string
        collection_date:
          type: string
          format: date
        preservation_method:
          type: string
        collection_site:
          type: string
    source_vocab: OBI
    source_class: specimen
    prior_art: obi:Specimen / obi:Organism
    disposition: mint
  - name: measurement
    description: A measurement datum (a value specification)
    base: semantic
    traits:
      - cited
      - dated
    schema:
      required:
        - measurement_id
        - value
        - variable
      properties:
        measurement_id:
          type: string
        variable:
          type: string
          description: "Renamed from measured_property to match research.ontology.yaml's observation field name directly"
        value:
          type: string
        unit:
          type: string
        measurement_method:
          type: string
        instrument_ref:
          type: string
        timestamp:
          type: string
          format: date-time
    source_vocab: OBI
    source_class: measurement datum
    prior_art: obi:MeasurementDatum / schema.org Observation
    disposition: mint
    subtype_of:
      - observation
  - name: hypothesis
    description: A falsifiable scientific hypothesis
    base: semantic
    traits:
      - cited
    schema:
      required:
        - statement
        - investigation_ref
      properties:
        statement:
          type: string
        investigation_ref:
          type: string
        hypothesis_type:
          type: string
          enum:
            - 'null'
            - directional
            - mechanistic
            - predictive
            - exploratory
        operationalization:
          type: string
        status:
          type: string
          enum:
            - untested
            - supported
            - refuted
            - inconclusive
        derived_from:
          type: string
    source_vocab: IAO
    source_class: IAO:0000415 hypothesis
    prior_art: obi:ObjectiveSpecification / IAO hypothesis
    disposition: mint
    subtype_of:
      - proposition
  - name: research-instrument
    description: A research instrument or device
    base: semantic
    traits:
      - cited
      - versioned
    schema:
      required:
        - instrument_id
        - instrument_type
        - name
      properties:
        instrument_id:
          type: string
        name:
          type: string
          description: "Inherited from research.ontology.yaml's apparatus: the instrument's human-readable display name (e.g. 'Illumina NovaSeq 6000'), distinct from instrument_id (the internal identifier)"
        instrument_type:
          type: string
          enum:
            - sequencer
            - mass-spectrometer
            - microscope
            - assay-platform
            - imaging-device
            - survey-platform
            - flow-cytometer
            - other
        manufacturer:
          type: string
        model:
          type: string
        serial_number:
          type: string
        calibration_date:
          type: string
          format: date
        location:
          type: string
    source_vocab: OBI
    source_class: device
    prior_art: obi:Device / IAO:0000070 device
    disposition: mint
    subtype_of:
      - apparatus
  - name: research-publication
    description: A research publication or scholarly output
    base: semantic
    traits:
      - cited
      - versioned
      - documented
    schema:
      required:
        - title
        - publication_type
      properties:
        title:
          type: string
        publication_type:
          type: string
          enum:
            - journal-article
            - preprint
            - book-chapter
            - conference-paper
            - dataset-descriptor
            - technical-report
        doi:
          type: string
          format: uri
        authors:
          type: array
          items:
            type: string
        journal_or_venue:
          type: string
        year:
          type: integer
        reports_investigation:
          type: string
        open_access:
          type: boolean
    source_vocab: IAO
    source_class: IAO:0000311 publication
    prior_art: IAO publication / schema.org ScholarlyArticle
    disposition: mint
    subtype_of:
      - scholarly-output
  - name: research-funding
    description: A grant providing monetary support for research
    base: semantic
    traits:
      - cited
      - dated
    schema:
      required:
        - grant_id
        - funder
      properties:
        grant_id:
          type: string
        funder:
          type: string
          description: "Renamed from funder_name to match research.ontology.yaml's funding-instrument field name directly"
        amount:
          type: string
        currency:
          type: string
        start_date:
          type: string
          format: date
        end_date:
          type: string
          format: date
        funding_scheme:
          type: string
        investigation_ref:
          type: string
    source_vocab: schema.org
    source_class: MonetaryGrant
    prior_art: schema.org/MonetaryGrant
    disposition: extend
    subtype_of:
      - funding-instrument
  - name: dataset
    description: A published dataset
    base: semantic
    traits:
      - cited
      - versioned
      - documented
    schema:
      required:
        - title
        - identifier
      properties:
        title:
          type: string
        description:
          type: string
        identifier:
          type: string
        theme:
          type: string
        license:
          type: string
        temporal_coverage:
          type: string
        spatial_coverage:
          type: string
        creator:
          type: string
        distribution_ref:
          type: array
          items:
            type: string
    source_vocab: W3C DCAT 3
    source_class: dcat:Dataset
    prior_art: dcat:Dataset / schema.org Dataset
    disposition: reuse
    subtype_of:
      - research-artifact
  - name: data-distribution
    description: A specific representation of a dataset (a downloadable/accessible form)
    base: semantic
    traits:
      - cited
      - versioned
      - documented
    schema:
      required:
        - access_url
        - dataset_ref
        - title
      properties:
        access_url:
          type: string
          format: uri
        title:
          type: string
          description: "Inherited from research.ontology.yaml's research-artifact"
        download_url:
          type: string
          format: uri
        media_type:
          type: string
        byte_size:
          type: integer
        format:
          type: string
        checksum:
          type: string
        license:
          type: string
        dataset_ref:
          type: string
    source_vocab: W3C DCAT 3
    source_class: dcat:Distribution
    prior_art: https://www.w3.org/TR/vocab-dcat-3/
    disposition: reuse
    subtype_of:
      - research-artifact
  - name: data-service
    description: A data access service (an endpoint serving datasets)
    base: semantic
    traits:
      - cited
      - versioned
      - documented
    schema:
      required:
        - endpoint_url
        - title
      properties:
        endpoint_url:
          type: string
          format: uri
        title:
          type: string
          description: "Inherited from research.ontology.yaml's research-artifact"
        endpoint_description:
          type: string
        serves_dataset:
          type: array
          items:
            type: string
        contact_point:
          type: string
        license:
          type: string
        access_rights:
          type: string
          enum:
            - open
            - restricted
            - embargoed
        service_type:
          type: string
    source_vocab: W3C DCAT 3
    source_class: dcat:DataService
    prior_art: https://www.w3.org/TR/vocab-dcat-3/
    disposition: reuse
    subtype_of:
      - research-artifact
  - name: dataset-series
    description: A collection of datasets published as a series
    base: semantic
    traits:
      - cited
      - versioned
      - documented
    schema:
      required:
        - title
      properties:
        title:
          type: string
        description:
          type: string
        temporal_coverage:
          type: string
        frequency:
          type: string
        first_member_ref:
          type: string
        last_member_ref:
          type: string
        theme:
          type: string
        license:
          type: string
    source_vocab: W3C DCAT 3
    source_class: dcat:DatasetSeries
    prior_art: https://www.w3.org/TR/vocab-dcat-3/
    disposition: reuse
    subtype_of:
      - research-artifact
  - name: data-catalog
    description: A curated catalog of datasets and services
    base: semantic
    traits:
      - cited
      - versioned
      - documented
    schema:
      required:
        - title
        - catalog_url
      properties:
        title:
          type: string
        catalog_url:
          type: string
          format: uri
        publisher:
          type: string
        themes:
          type: array
          items:
            type: string
        dataset_count:
          type: integer
        license:
          type: string
        access_rights:
          type: string
          enum:
            - open
            - restricted
            - embargoed
    source_vocab: W3C DCAT 3
    source_class: dcat:Catalog
    prior_art: dcat:Catalog / schema.org DataCatalog
    disposition: reuse
    subtype_of:
      - research-artifact
  - name: data-provenance
    description: A provenance record tracing how a data artifact was generated and derived
    base: episodic
    traits:
      - cited
      - dated
    schema:
      required:
        - entity_ref
        - generated_by
      properties:
        entity_ref:
          type: string
        generated_by:
          type: string
        derived_from:
          type: string
        attributed_to:
          type: string
        generation_time:
          type: string
          format: date-time
        usage_ref:
          type: string
        revision_of:
          type: string
    source_vocab: W3C PROV-O
    source_class: prov:Entity + prov:Activity
    prior_art: prov:Entity / prov:Activity / prov:wasDerivedFrom
    disposition: mint
relationships:
  catalogs:
    description: A data-catalog catalogs a dataset (dcat:dataset)
    from:
      - data-catalog
    to:
      - dataset
    symmetric: false
  funded-by:
    description: A research-investigation is funded by a research-funding grant (schema:funding)
    from:
      - research-investigation
    to:
      - research-funding
    symmetric: false
  has-input:
    description: A protocol-application has a sample-organism as input (RO:0002233 has input)
    from:
      - protocol-application
    to:
      - sample-organism
    symmetric: false
  has-output:
    description: A protocol-application has a measurement as output (RO:0002234 has output)
    from:
      - protocol-application
    to:
      - measurement
    symmetric: false
  is-about:
    description: An information artifact is about another entity (IAO:0000136 is about) — a hypothesis about a measurement, a publication about an investigation
    from:
      - hypothesis
      - research-publication
    to:
      - measurement
      - research-investigation
    symmetric: false
  participates-in:
    description: A sample-organism participates in a research-investigation (RO:0000056 participates in)
    from:
      - sample-organism
    to:
      - research-investigation
    symmetric: false
  was-derived-from:
    description: A data-provenance record traces a dataset derived from another (prov:wasDerivedFrom)
    from:
      - data-provenance
    to:
      - dataset
    symmetric: false
  was-generated-by:
    description: A dataset was generated by a protocol-application (prov:wasGeneratedBy)
    from:
      - dataset
    to:
      - protocol-application
    symmetric: false
  uses_method:
    description: A study uses a method (RO:0000056 participates-in)
    from:
      - study
    to:
      - method
    symmetric: false
  has_sample:
    description: A study has a sample (RO:0002233 has-input)
    from:
      - study
    to:
      - sample-organism
    symmetric: false
  produces:
    description: A method produces a measurement (RO:0002234 has-output)
    from:
      - method
    to:
      - measurement
    symmetric: false
  measured_on:
    description: A measurement is taken on a sample
    from:
      - measurement
    to:
      - sample-organism
    symmetric: false
  tests:
    description: An investigation tests a hypothesis
    from:
      - research-investigation
    to:
      - hypothesis
    symmetric: false
  applies:
    description: An investigation applies a protocol-application
    from:
      - research-investigation
    to:
      - protocol-application
    symmetric: false
  uses_instrument:
    description: A protocol-application uses a research-instrument
    from:
      - protocol-application
    to:
      - research-instrument
    symmetric: false
  reports_in:
    description: An investigation is reported in a publication (IAO:0000136 is-about)
    from:
      - research-investigation
    to:
      - research-publication
    symmetric: false
  funded_by:
    description: An investigation is funded by a grant (schema:funder)
    from:
      - research-investigation
    to:
      - research-funding
    symmetric: false
  enrolls:
    description: An investigation enrolls a cohort
    from:
      - research-investigation
    to:
      - cohort
    symmetric: false
discovery:
  enabled: true
  confidence_threshold: 0.8
  patterns:
    - content_pattern: \b(study|trial|investigation|cohort|randomi[sz]ed controlled)\b
      suggest_entity: study
      suggest_namespace: _episodic/studies
    - content_pattern: \b(assay|protocol|method|procedure|RNA-seq|ChIP-seq)\b
      suggest_entity: method
      suggest_namespace: _semantic/science
    - content_pattern: \b(specimen|material sample|organism|cell line|tissue|taxon)\b
      suggest_entity: sample-organism
      suggest_namespace: _semantic/science
    - content_pattern: \b(measurement|measured value|reading|datum)\b
      suggest_entity: measurement
      suggest_namespace: _semantic/science
    - content_pattern: \b(hypothesis|we hypothesi[sz]e|null hypothesis)\b
      suggest_entity: hypothesis
      suggest_namespace: _semantic/science
    - content_pattern: \b(protocol application|batch|run performed|executed protocol)\b
      suggest_entity: protocol-application
      suggest_namespace: _procedural/protocols
    - content_pattern: \b(ClinicalTrials\.gov|OSF|PROSPERO|multi-omics)\b
      suggest_entity: research-investigation
      suggest_namespace: _episodic/studies
    - content_pattern: \b(sequencer|mass spectrometer|microscope|flow cytometer|instrument)\b
      suggest_entity: research-instrument
      suggest_namespace: _semantic/instruments
    - content_pattern: \b(DOI|preprint|journal article|ScholarlyArticle)\b
      suggest_entity: research-publication
      suggest_namespace: _semantic/publications
    - content_pattern: \b(MonetaryGrant|grant number|funded by|award)\b
      suggest_entity: research-funding
      suggest_namespace: _semantic/funding
    - content_pattern: \b(dataset|data catalog|DCAT|distribution|data download)\b
      suggest_entity: dataset
      suggest_namespace: _semantic/catalogs
    - content_pattern: \b(prov:wasDerivedFrom|provenance|lineage|wasGeneratedBy)\b
      suggest_entity: data-provenance
      suggest_namespace: _episodic/provenance