Class: MetaproteomicsAnalysis

name: MetaproteomicsAnalysis
from_schema: https://w3id.org/nmdc/nmdc
is_a: AnnotatingWorkflow
slots:
- metaproteomics_analysis_category
slot_usage:
  id:
    name: id
    required: true
    structured_pattern:
      syntax: '{id_nmdc_prefix}:wfmp-{id_shoulder}-{id_blade}{id_version}$'
      interpolated: true
  was_informed_by:
    name: was_informed_by
    range: MassSpectrometry
    structured_pattern:
      syntax: '{id_nmdc_prefix}:(omprc|dgms)-{id_shoulder}-{id_blade}$'
      interpolated: true
class_uri: nmdc:MetaproteomicsAnalysis

name: MetaproteomicsAnalysis
from_schema: https://w3id.org/nmdc/nmdc
is_a: AnnotatingWorkflow
slot_usage:
  id:
    name: id
    required: true
    structured_pattern:
      syntax: '{id_nmdc_prefix}:wfmp-{id_shoulder}-{id_blade}{id_version}$'
      interpolated: true
  was_informed_by:
    name: was_informed_by
    range: MassSpectrometry
    structured_pattern:
      syntax: '{id_nmdc_prefix}:(omprc|dgms)-{id_shoulder}-{id_blade}$'
      interpolated: true
attributes:
  metaproteomics_analysis_category:
    name: metaproteomics_analysis_category
    description: The category of metaproteomics analysis being performed.
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    alias: metaproteomics_analysis_category
    owner: MetaproteomicsAnalysis
    domain_of:
    - MetaproteomicsAnalysis
    range: MetaproteomicsAnalysisCategoryEnum
    required: true
  ended_at_time:
    name: ended_at_time
    notes:
    - 'The regex for ISO-8601 format was taken from here: https://www.myintervals.com/blog/2009/05/20/iso-8601-date-validation-that-doesnt-suck/
      It may not be complete, but it is good enough for now.'
    from_schema: https://w3id.org/nmdc/nmdc
    mappings:
    - prov:endedAtTime
    rank: 1000
    alias: ended_at_time
    owner: MetaproteomicsAnalysis
    domain_of:
    - WorkflowExecution
    range: string
    pattern: ^([\+-]?\d{4}(?!\d{2}\b))((-?)((0[1-9]|1[0-2])(\3([12]\d|0[1-9]|3[01]))?|W([0-4]\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\d|[12]\d{2}|3([0-5]\d|6[1-6])))([T\s]((([01]\d|2[0-3])((:?)[0-5]\d)?|24\:?00)([\.,]\d+(?!:))?)?(\17[0-5]\d([\.,]\d+)?)?([zZ]|([\+-])([01]\d|2[0-3]):?([0-5]\d)?)?)?)?$
  execution_resource:
    name: execution_resource
    description: The computing resource or facility where the workflow was executed.
    examples:
    - value: NERSC-Cori
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    alias: execution_resource
    owner: MetaproteomicsAnalysis
    domain_of:
    - WorkflowExecution
    range: ExecutionResourceEnum
    required: true
  git_url:
    name: git_url
    description: The url that points to the exact github location of a workflow.
    examples:
    - value: https://github.com/microbiomedata/mg_annotation/releases/tag/0.1
    - value: https://github.com/microbiomedata/metaMS/blob/master/metaMS/gcmsWorkflow.py
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    alias: git_url
    owner: MetaproteomicsAnalysis
    domain_of:
    - WorkflowExecution
    range: string
    required: true
  started_at_time:
    name: started_at_time
    notes:
    - 'The regex for ISO-8601 format was taken from here: https://www.myintervals.com/blog/2009/05/20/iso-8601-date-validation-that-doesnt-suck/
      It may not be complete, but it is good enough for now.'
    from_schema: https://w3id.org/nmdc/nmdc
    mappings:
    - prov:startedAtTime
    rank: 1000
    alias: started_at_time
    owner: MetaproteomicsAnalysis
    domain_of:
    - WorkflowExecution
    range: string
    required: true
    pattern: ^([\+-]?\d{4}(?!\d{2}\b))((-?)((0[1-9]|1[0-2])(\3([12]\d|0[1-9]|3[01]))?|W([0-4]\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\d|[12]\d{2}|3([0-5]\d|6[1-6])))([T\s]((([01]\d|2[0-3])((:?)[0-5]\d)?|24\:?00)([\.,]\d+(?!:))?)?(\17[0-5]\d([\.,]\d+)?)?([zZ]|([\+-])([01]\d|2[0-3]):?([0-5]\d)?)?)?)?$
  version:
    name: version
    description: The NMDC release tag for a given workflow release used for data processing.
      If workflows are processed externally, as denoted by processing_institution,
      this value represents the best mapping between a processing institution's (e.g.,
      JGI) workflow metadata and a NMDC tagged release.
    examples:
    - value: v1.2.0
    from_schema: https://w3id.org/nmdc/nmdc
    broad_mappings:
    - NCIT:C182117
    rank: 1000
    alias: version
    owner: MetaproteomicsAnalysis
    domain_of:
    - WorkflowExecution
    range: string
  was_informed_by:
    name: was_informed_by
    description: The primary DataGeneration subclass that the WorkflowExecution subclass
      depends on.
    comments:
    - For version 1 of the proteomics workflow there are input files both from the
      NucleotideSequencing and MassSpectrometry, the MassSpectrometry record is considered
      the primary class to reference.
    from_schema: https://w3id.org/nmdc/nmdc
    structured_aliases:
      was_informed_by:
        literal_form: was_informed_by
        predicate: EXACT_SYNONYM
        contexts:
        - https://bitbucket.org/berkeleylab/jgi-jat/macros/nmdc_metadata.yaml
    narrow_mappings:
    - prov:wasInformedBy
    rank: 1000
    alias: was_informed_by
    owner: MetaproteomicsAnalysis
    domain_of:
    - WorkflowExecution
    range: MassSpectrometry
    required: true
    multivalued: true
    structured_pattern:
      syntax: '{id_nmdc_prefix}:(omprc|dgms)-{id_shoulder}-{id_blade}$'
      interpolated: true
  processing_institution_workflow_metadata:
    name: processing_institution_workflow_metadata
    description: Information about how workflow results were generated when the processing
      is done by an external organziation (e.g., JGI) such as software tool name and
      version or pipeline name and version.
    examples:
    - value: metaspades v. 3.15.2
    - value: IMG Annotation Pipeline v.5.0.25
    from_schema: https://w3id.org/nmdc/nmdc
    mappings:
    - NCIT:C165211
    rank: 1000
    alias: processing_institution_workflow_metadata
    owner: MetaproteomicsAnalysis
    domain_of:
    - WorkflowExecution
    range: string
  has_input:
    name: has_input
    description: An input to a process.
    from_schema: https://w3id.org/nmdc/nmdc
    aliases:
    - input
    rank: 1000
    alias: has_input
    owner: MetaproteomicsAnalysis
    domain_of:
    - PlannedProcess
    range: DataObject
    required: true
    multivalued: true
    structured_pattern:
      syntax: '{id_nmdc_prefix}:(dobj)-{id_shoulder}-{id_blade}$'
      interpolated: true
  has_output:
    name: has_output
    description: An output from a process.
    from_schema: https://w3id.org/nmdc/nmdc
    aliases:
    - output
    rank: 1000
    alias: has_output
    owner: MetaproteomicsAnalysis
    domain_of:
    - PlannedProcess
    range: DataObject
    multivalued: true
    structured_pattern:
      syntax: '{id_nmdc_prefix}:(dobj)-{id_shoulder}-{id_blade}$'
      interpolated: true
  processing_institution:
    name: processing_institution
    description: The organization that processed the sample.
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    alias: processing_institution
    owner: MetaproteomicsAnalysis
    domain_of:
    - PlannedProcess
    range: ProcessingInstitutionEnum
  protocol_link:
    name: protocol_link
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    alias: protocol_link
    owner: MetaproteomicsAnalysis
    domain_of:
    - Configuration
    - PlannedProcess
    - Study
    range: Protocol
  start_date:
    name: start_date
    description: The date on which any process or activity was started
    todos:
    - add date string validation pattern
    comments:
    - We are using string representations of dates until all components of our ecosystem
      can handle ISO 8610 dates
    - The date should be formatted as YYYY-MM-DD
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    alias: start_date
    owner: MetaproteomicsAnalysis
    domain_of:
    - PlannedProcess
    range: string
  end_date:
    name: end_date
    description: The date on which any process or activity was ended
    todos:
    - add date string validation pattern
    comments:
    - We are using string representations of dates until all components of our ecosystem
      can handle ISO 8610 dates
    - The date should be formatted as YYYY-MM-DD
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    alias: end_date
    owner: MetaproteomicsAnalysis
    domain_of:
    - PlannedProcess
    range: string
  qc_status:
    name: qc_status
    description: Stores information about the result of a process (ie the process
      of sequencing a library may have for qc_status of 'fail' if not enough data
      was generated)
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    alias: qc_status
    owner: MetaproteomicsAnalysis
    domain_of:
    - PlannedProcess
    range: StatusEnum
  qc_comment:
    name: qc_comment
    description: Slot to store additional comments about laboratory or workflow output.
      For workflow output it may describe the particular workflow stage that failed.
      (ie Failed at call-stage due to a malformed fastq file).
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    alias: qc_comment
    owner: MetaproteomicsAnalysis
    domain_of:
    - PlannedProcess
    range: string
  has_failure_categorization:
    name: has_failure_categorization
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    alias: has_failure_categorization
    owner: MetaproteomicsAnalysis
    domain_of:
    - PlannedProcess
    range: FailureCategorization
    multivalued: true
    inlined: true
    inlined_as_list: 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:
      workflow_execution_id:
        literal_form: workflow_execution_id
        predicate: NARROW_SYNONYM
        contexts:
        - https://bitbucket.org/berkeleylab/jgi-jat/macros/nmdc_metadata.yaml
      data_object_id:
        literal_form: data_object_id
        predicate: NARROW_SYNONYM
        contexts:
        - https://bitbucket.org/berkeleylab/jgi-jat/macros/nmdc_metadata.yaml
    rank: 1000
    identifier: true
    alias: id
    owner: MetaproteomicsAnalysis
    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}:wfmp-{id_shoulder}-{id_blade}{id_version}$'
      interpolated: true
  name:
    name: name
    description: A human readable label for an entity
    from_schema: https://w3id.org/nmdc/nmdc
    rank: 1000
    alias: name
    owner: MetaproteomicsAnalysis
    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
    alias: description
    owner: MetaproteomicsAnalysis
    domain_of:
    - ImageValue
    - NamedThing
    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
    alias: alternative_identifiers
    owner: MetaproteomicsAnalysis
    domain_of:
    - MetaboliteIdentification
    - NamedThing
    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:
      workflow_execution_class:
        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
    alias: type
    owner: MetaproteomicsAnalysis
    domain_of:
    - EukEval
    - FunctionalAnnotationAggMember
    - PeptideQuantification
    - ProteinQuantification
    - MobilePhaseSegment
    - PortionOfSubstance
    - MagBin
    - MetaboliteIdentification
    - GenomeFeature
    - FunctionalAnnotation
    - AttributeValue
    - NamedThing
    - OntologyRelation
    - FailureCategorization
    - Protocol
    - CreditAssociation
    - Doi
    range: uriorcurie
    required: true
class_uri: nmdc:MetaproteomicsAnalysis