$base: http://biohackathon.org/bh20-seq-schema
$namespaces:
  sch: https://schema.org/
  efo: http://www.ebi.ac.uk/efo/
  obo: http://purl.obolibrary.org/obo/
  sio: http://semanticscience.org/resource/
  edam: http://edamontology.org/
  evs: http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#

$graph:

- name: hostSchema
  type: record
  fields:
    host_species:
        doc: Host species as defined in NCBITaxon, e.g. http://purl.obolibrary.org/obo/NCBITaxon_9606 for Homo sapiens
        type: string
        jsonldPredicate:
          _id: http://www.ebi.ac.uk/efo/EFO_0000532
          _type: "@id"
          noLinkCheck: true
    host_id:
        doc: Identifer for the host. If you submit multiple samples from the same host, use the same host_id for those samples
        type: string?
        jsonldPredicate:
          _id: http://semanticscience.org/resource/SIO_000115
    host_sex:
        doc: Sex of the host as defined in PATO, expect Male (http://purl.obolibrary.org/obo/PATO_0000384) or Female (http://purl.obolibrary.org/obo/PATO_0000383) or in Intersex (http://purl.obolibrary.org/obo/PATO_0001340)
        type: string?
        jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/PATO_0000047
          _type: "@id"
          noLinkCheck: true
    host_age:
        doc: Age of the host as number (e.g. 50)
        type: int?
        jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/PATO_0000011
    host_age_unit:
        doc: Unit of host age e.g. http://purl.obolibrary.org/obo/UO_0000036
        type: string?
        jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/NCIT_C42574
          _type: "@id"
          noLinkCheck: true
    host_health_status:
        doc: A condition or state at a particular time, must be one of the following (obo:NCIT_C115935 obo:NCIT_C3833 obo:NCIT_C25269 obo:GENEPIO_0002020 obo:GENEPIO_0001849 obo:NCIT_C28554 obo:NCIT_C37987)
        type: string?
        jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/NCIT_C25688
          _type: "@id"
          noLinkCheck: true
    host_treatment:
      doc: Process in which the act is intended to modify or alter host status
      type: string?
      jsonldPredicate:
          _id: http://www.ebi.ac.uk/efo/EFO_0000727
    host_vaccination:
      doc: List of vaccines given to the host
      type: string[]?
      jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/VO_0000002
    ethnicity:
      doc: Ethinicity of the host e.g. http://purl.obolibrary.org/obo/HANCESTRO_0010
      type: string?
      jsonldPredicate:
          _id: http://semanticscience.org/resource/SIO_001014
          _type: "@id"
          noLinkCheck: true
    additional_host_information:
      doc: Field for additional host information
      type: string?
      jsonldPredicate:
          _id: http://semanticscience.org/resource/SIO_001167

- name: sampleSchema
  type: record
  fields:
    sample_id:
      doc: Unique sample identifier as defined by the submitter
      type: string
      jsonldPredicate:
        _id: http://semanticscience.org/resource/SIO_000115
    collection_date:
      doc: Date when the sample was taken
      type: string
      jsonldPredicate:
        _id: http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#C25164
    collection_location:
      doc: Geographical location where the sample was collected as wikidata reference, e.g. http://www.wikidata.org/entity/Q148 (China)
      type: string
      jsonldPredicate:
        _id: http://purl.obolibrary.org/obo/GAZ_00000448
        _type: "@id"
        noLinkCheck: true
    collector_name:
      doc: Name of the person that took the sample
      type: string?
      jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/OBI_0001895
    collecting_institution:
      doc: Institute that was responsible for sampeling
      type: string?
      jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/NCIT_C41206
    specimen_source:
      doc: Method how the specimen was derived as NCIT IRI, e.g. http://purl.obolibrary.org/obo/NCIT_C155831 (=nasopharyngeal swab)
      type: string[]?
      jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/OBI_0001479
          _type: "@id"
          noLinkCheck: true
    sample_storage_conditions:
      doc: Information about storage of a specified type, e.g.  frozen specimen, paraffin, fresh ....
      type: string?
      jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/OBI_0001472
    additional_collection_information:
      doc: Add additional comment about the circumstances that a sample was taken
      type: string?
      jsonldPredicate:
          _id: http://semanticscience.org/resource/SIO_001167
    source_database_accession:
      doc: If data is deposit at a public resource (e.g. Genbank, ENA) enter the Accession Id here. Please use a resolveable URL (e.g. http://identifiers.org/insdc/LC522350.1#sequence)
      type: string[]?
      jsonldPredicate:
          _id: http://edamontology.org/data_2091
          _type: "@id"
          noLinkCheck: true

- name: virusSchema
  type: record
  fields:
    virus_species:
      doc: The name of virus species from the NCBI taxonomy database, e.g. http://purl.obolibrary.org/obo/NCBITaxon_2697049 for Severe acute respiratory syndrome coronavirus 2
      type: string
      jsonldPredicate:
          _id: http://edamontology.org/data_1875
          _type: "@id"
          noLinkCheck: true
    virus_strain:
      doc: Name of the virus strain
      type: string?
      jsonldPredicate:
          _id: http://semanticscience.org/resource/SIO_010055

- name: technologySchema
  type: record
  fields:
    sample_sequencing_technology:
      doc: Technology that was used to sequence this sample (e.g Sanger, Nanopor MiniION)
      type: string[]
      jsonldPredicate:
        _id: http://purl.obolibrary.org/obo/OBI_0600047
        _type: "@id"
        noLinkCheck: true
    sequence_assembly_method:
      doc: Protocol which provides instructions on the alignment of sequencing reads to reference genome
      type: string?
      jsonldPredicate:
        _id: http://www.ebi.ac.uk/efo/EFO_0002699
    sequencing_coverage:
      doc: Sequence coverage defined as the average number of reads representing a given nucleotide (e.g. [100]) - if multiple technologies were used multiple float values can be submitted e.g. [100, 20]
      type: double[]?
      jsonldPredicate:
        _id: http://purl.obolibrary.org/obo/FLU_0000848
    additional_technology_information:
      doc: Field for additional technology information
      type: string?
      jsonldPredicate:
        _id: http://semanticscience.org/resource/SIO_001167

- name: submitterSchema
  type: record
  fields:
    authors:
      doc: Name(s) of the author(s)
      type: string[]
      jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/NCIT_C42781
    submitter_name:
      doc: Name of the submitter(s)
      type: string[]?
      jsonldPredicate:
          _id: http://semanticscience.org/resource/SIO_000116
    submitter_address:
      doc: Address of the submitter
      type: string?
      jsonldPredicate:
          _id: http://semanticscience.org/resource/SIO_000172
    originating_lab:
      doc: Name of the laboratory that took the sample
      type: string?
      jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/NCIT_C37984
    lab_address:
      doc: Address of the laboratory where the sample was taken
      type: string?
      jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/OBI_0600047
    provider_sample_id:
      type: string?
      jsonldPredicate:
          _id: http://purl.obolibrary.org/obo/NCIT_C37900
    submitter_sample_id:
      type: string?
      jsonldPredicate:
          _id: http://www.ebi.ac.uk/efo/EFO_0001741
    publication:
      doc: Reference to publication of this sample (e.g. DOI, pubmed ID, ...)
      type: string?
      jsonldPredicate:
        _id: http://purl.obolibrary.org/obo/NCIT_C19026
    submitter_orcid:
      doc: ORCID of the submitter as a full URI, e.g. https://orcid.org/0000-0002-1825-0097
      type: string[]?
      jsonldPredicate:
          _id: http://semanticscience.org/resource/SIO_000115
          _type: "@id"
          noLinkCheck: true
    additional_submitter_information:
      doc: Field for additional submitter information
      type: string?
      jsonldPredicate:
        _id: http://semanticscience.org/resource/SIO_001167

- name: MainSchema
  type: record
  documentRoot: true
  fields:
    host: hostSchema
    sample: sampleSchema
    virus: virusSchema
    technology: technologySchema
    submitter: submitterSchema
    id:
      doc: The subject (eg the fasta/fastq file) that the metadata describes
      type: string
      jsonldPredicate:
        _id: "@id"
        _type: "@id"
        noLinkCheck: true