id: https://w3id.org/nmdc/nmdc
name: NMDC
title: NMDC Schema
notes:
  - not importing any MIxS terms where the relationship between the name (SCN) and the id isn't 1:1
description: >-
  Schema for National Microbiome Data Collaborative (NMDC).

  This schema is organized into multiple modules, such as:

   * a set of core types for representing data values
   * a subset of the mixs schema
   * an annotation schema
   * the NMDC schema itself, into which the other modules are imported

license: https://creativecommons.org/publicdomain/zero/1.0/
version: 0.0.0

imports:
  - annotation # also brings core and portal_*
  - workflow_execution_activity

prefixes:
  CATH: "https://bioregistry.io/cath:"
  CHEBI: "http://purl.obolibrary.org/obo/CHEBI_"
  CHEMBL.COMPOUND: "https://bioregistry.io/chembl.compound:" # https://bioregistry.io/chembl.compound:CHEMBL465070
  CHMO: "http://purl.obolibrary.org/obo/CHMO_"
  Contaminant: http://example.org/contaminant/ # present in MongoDB
  DRUGBANK: "https://bioregistry.io/drugbank:" # https://bioregistry.io/drugbank:DB14938
  EC: "https://bioregistry.io/eccode:" # https://bioregistry.io/eccode:1.1.1.1
  EFO: http://www.ebi.ac.uk/efo/
  EGGNOG: "https://bioregistry.io/eggnog:" # https://bioregistry.io/eggnog:veNOG12876
  ENVO: "http://purl.obolibrary.org/obo/ENVO_"
  FBcv: "http://purl.obolibrary.org/obo/FBcv_"
  FMA: "http://purl.obolibrary.org/obo/FMA_"
  GO: "http://purl.obolibrary.org/obo/GO_"
  HMDB: "https://bioregistry.io/hmdb:" # https://bioregistry.io/hmdb:HMDB00001
  ISA: http://example.org/isa/
  KEGG.ORTHOLOGY: "https://bioregistry.io/kegg.orthology:"  # https://github.com/prefixcommons/biocontext/blob/master/registry/idot_context.jsonld
  MASSIVE: "https://bioregistry.io/reference/massive:"
  MESH: "https://bioregistry.io/mesh:" # https://bioregistry.io/mesh:C063233
  MS: "http://purl.obolibrary.org/obo/MS_"
  MetaNetX: http://example.org/metanetx/
  NCBITaxon: "http://purl.obolibrary.org/obo/NCBITaxon_"
  NCBI: "http://example.com/ncbitaxon/" # temporary. see https://github.com/microbiomedata/issues/issues/893
  NCIT: "http://purl.obolibrary.org/obo/NCIT_"
  OBI: http://purl.obolibrary.org/obo/OBI_
  ORCID: https://orcid.org/
  PANTHER.FAMILY: "https://bioregistry.io/panther.family:" # https://bioregistry.io/panther.family:PTHR12345
  PATO: "http://purl.obolibrary.org/obo/PATO_"
  PFAM: "https://bioregistry.io/pfam:" # https://bioregistry.io/pfam:PF11779
  PFAM.CLAN: "https://bioregistry.io/pfam.clan:" # https://bioregistry.io/pfam.clan:CL0192
  PO: "http://purl.obolibrary.org/obo/PO_"
  PR: "http://purl.obolibrary.org/obo/PR_"
  PUBCHEM.COMPOUND: "https://bioregistry.io/pubchem.compound:"
  RO: "http://purl.obolibrary.org/obo/RO_"
  RetroRules: http://example.org/retrorules/
  SO: "http://purl.obolibrary.org/obo/SO_"
  SUPFAM: "https://bioregistry.io/supfam:" # 	https://bioregistry.io/supfam:SSF57615
  TIGRFAM: "https://bioregistry.io/tigrfam:" # https://bioregistry.io/tigrfam:TIGR00010
  UBERON: "http://purl.obolibrary.org/obo/UBERON_"
  UO: "http://purl.obolibrary.org/obo/UO_"
  bioproject: "https://identifiers.org/bioproject:"
  biosample: "https://bioregistry.io/biosample:"
  cas: "https://bioregistry.io/cas:"
  doi: "https://bioregistry.io/doi:"
  edam.data: "http://edamontology.org/data_"
  emsl.project: "https://bioregistry.io/emsl.project:"
  emsl: "http://example.org/emsl_in_mongodb/"
  emsl_uuid_like: "http://example.org/emsl_uuid_like/"
  generic: https://example.org/generic/
  gnps.task: "https://bioregistry.io/gnps.task:"
  gtpo: http://example.org/gtpo/
  igsn: https://app.geosamples.org/sample/igsn/
  img.taxon: "https://bioregistry.io/img.taxon:"
  jgi.analysis: "https://data.jgi.doe.gov/search?q="
  jgi.proposal: "https://bioregistry.io/jgi.proposal:"
  jgi: http://example.org/jgi/
  kegg: "https://bioregistry.io/kegg:" # https://bioregistry.io/kegg:hsa00190
  linkml: https://w3id.org/linkml/
  mgnify.proj: "https://bioregistry.io/mgnify.proj:"
  my_emsl: "https://release.my.emsl.pnnl.gov/released_data/"
  neon.identifier: http://example.org/neon/identifier/
  neon.schema: http://example.org/neon/schema/
  nmdc: https://w3id.org/nmdc/
  prov: http://www.w3.org/ns/prov#
  rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns#
  rdfs: http://www.w3.org/2000/01/rdf-schema#
  skos: http://www.w3.org/2004/02/skos/core#
  wikidata: "http://www.wikidata.org/entity/"
  xsd: http://www.w3.org/2001/XMLSchema#

default_prefix: nmdc
default_range: string

emit_prefixes:
  - KEGG.ORTHOLOGY
  - MASSIVE
  - biosample
  - cas
  - doi
  - gnps.task
  - gold
  - img.taxon
  - jgi.proposal
  - kegg
  - rdf
  - rdfs
  - skos
  - xsd

settings:
  id_nmdc_prefix: "^(nmdc)"
  id_shoulder: "([0-9][a-z]{0,6}[0-9])"
  id_blade: "([A-Za-z0-9]{1,})"
  id_version: "(\\.[0-9]{1,})"
  id_locus: "(_[A-Za-z0-9_\\.-]+)?$"

classes:

  EukEval:
    description: This class contains information pertaining to evaluating if a Metagenome-Assembled Genome (MAG) is eukaryotic.
    comments:
      - A tool like eukCC (https://doi.org/10.1186/s13059-020-02155-4) would generate information for this class.
    slots:
      - type
      - completeness
      - contamination
      - ncbi_lineage_tax_ids
      - ncbi_lineage
    class_uri: nmdc:EukEval

  NucleotideSequencing:
    class_uri: nmdc:NucleotideSequencing
    is_a: DataGeneration
    description: A DataGeneration in which the sequence of DNA or RNA molecules is generated.
    comments: For example data generated from an Illumina or Pacific Biosciences instrument.
    slots:
      - gold_sequencing_project_identifiers
      - insdc_bioproject_identifiers
      - insdc_experiment_identifiers
      - ncbi_project_name
      - target_gene
      - target_subfragment
    slot_usage:
      id:
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(dgns|omprc)-{id_shoulder}-{id_blade}$"
          interpolated: true

  MassSpectrometry:
    class_uri: nmdc:MassSpectrometry
    is_a: DataGeneration
    description: Spectrometry where the sample is converted into gaseous ions which are characterised by their mass-to-charge ratio and relative abundance.
    exact_mappings:
      - CHMO:0000470
    slots:
      - eluent_introduction_category
      - has_calibration
      - has_chromatography_configuration
      - has_mass_spectrometry_configuration
    slot_usage:
      id:
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(dgms|omprc)-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_calibration:
        structured_pattern:
          syntax: "{id_nmdc_prefix}:calib-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_chromatography_configuration:
        structured_pattern:
          syntax: "{id_nmdc_prefix}:chrcon-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_mass_spectrometry_configuration:
        structured_pattern:
          syntax: "{id_nmdc_prefix}:mscon-{id_shoulder}-{id_blade}$"
          interpolated: true
    rules:
      - title: has_calibration_required_if_gc
        description: >-
          If eluent_introduction_category is gas_chromatography, then has_calibration is required.
        preconditions:
          slot_conditions:
            eluent_introduction_category:
              equals_string: gas_chromatography
        postconditions:
          slot_conditions:
            has_calibration:
              required: true
      - title: has_chromatography_configuration_required_if_lc_or_gc
        description: >-
          If eluent_introduction_category is liquid_chromatography or gas_chromatography, then has_chromatography_configuration is required.
        preconditions:
          slot_conditions:
            eluent_introduction_category:
              any_of:
                - equals_string: liquid_chromatography
                - equals_string: gas_chromatography
        postconditions:
          slot_conditions:
            has_chromatography_configuration:
              required: true

  Configuration:
    abstract: true
    is_a: InformationObject
    class_uri: nmdc:Configuration
    description: A set of parameters that define the actions of a process and is shared among multiple instances of the process.
    notes:
      - This class is intended to represent the parameters within a method file (or similar) that control a process.

  MassSpectrometryConfiguration:
    is_a: Configuration
    class_uri: nmdc:MassSpectrometryConfiguration
    description: A set of parameters that define and control the actions of a mass spectrometry process.
    notes:
      - This class is intended to represent a mass spectrometry method file that controls a mass spectrometry process.
    slots:
      - mass_spectrometry_acquisition_strategy
      - resolution_categories
      - mass_analyzers
      - ionization_source
      - mass_spectrum_collection_modes
      - polarity_mode
    slot_usage:
      name:
        required: true
      description:
        required: true
      id:
        structured_pattern:
          syntax: "{id_nmdc_prefix}:mscon-{id_shoulder}-{id_blade}$"
          interpolated: true
  
  ChromatographyConfiguration:
    is_a: Configuration
    class_uri: nmdc:ChromatographyConfiguration
    description: A set of parameters that define and control the actions of a chromatography process.
    notes:
      - This class is intended to represent a chromatography method file associated with a mass spectrometry process.
    slots:
      - chromatographic_category
      - ordered_mobile_phases
      - stationary_phase
      - temperature
    slot_usage:
      name:
        required: true
      description:
        required: true
      id:
        structured_pattern:
          syntax: "{id_nmdc_prefix}:chrcon-{id_shoulder}-{id_blade}$"
          interpolated: true

  FunctionalAnnotationAggMember:
    class_uri: nmdc:FunctionalAnnotationAggMember
    slots:
      - metagenome_annotation_id
      - gene_function_id
      - count
      - type
    slot_usage:
      metagenome_annotation_id:
        structured_pattern: # doesn't include act
          syntax: "{id_nmdc_prefix}:(wfmgan|wfmtan)-{id_shoulder}-{id_blade}{id_version}$"
          interpolated: true

  Database:
    class_uri: nmdc:Database
    tree_root: true
    aliases:
      - NMDC metadata object
    description:
      An abstract holder for any set of metadata and data. It does not
      need to correspond to an actual managed database top level holder class. When
      translated to JSON-Schema this is the 'root' object. It should contain pointers
      to other objects of interest. For MongoDB, the lists of objects that Database
      slots point to correspond to **collections**.
    slots:
      - biosample_set
      - calibration_set
      - chemical_entity_set
      - collecting_biosamples_from_site_set
      - configuration_set
      - data_generation_set
      - data_object_set
      - field_research_site_set
      - functional_annotation_agg
      - functional_annotation_set
      - genome_feature_set
      - instrument_set
      - material_processing_set
      - processed_sample_set
      - protocol_execution_set
      - storage_process_set
      - study_set
      - workflow_execution_set

  Pooling:
    class_uri: nmdc:Pooling
    is_a: MaterialProcessing
    description: physical combination of several instances of like material.
    slots:
    exact_mappings:
      - OBI:0600016
    slot_usage:
      has_input:
        minimum_cardinality: 2
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(bsm|procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_output:
        required: true
        minimum_cardinality: 1
        maximum_cardinality: 1
        structured_pattern:
          syntax: "{id_nmdc_prefix}:procsm-{id_shoulder}-{id_blade}$"
          interpolated: true
      id:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:poolp-{id_shoulder}-{id_blade}$"
          interpolated: true

  Extraction:
    class_uri: nmdc:Extraction
    is_a: MaterialProcessing
    description: A material separation in which a desired component of an input material is separated from the remainder.
    exact_mappings:
      - OBI:0302884
    slots:
      - substances_used
      - extraction_targets
      - input_mass
      - volume
    slot_usage:
      has_input:
        required: true
        any_of:
          - range: Biosample
          - range: ProcessedSample
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(bsm|procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_output:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true
      id:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:extrp-{id_shoulder}-{id_blade}$"
          interpolated: true
      volume:
        description: The volume of the solvent/solute being used, not the input.

  LibraryPreparation:
    class_uri: nmdc:LibraryPreparation
    aliases:
      - LibraryConstruction
    is_a: MaterialProcessing
    slots:
      - is_stranded
      - library_preparation_kit
      - library_type
      - nucl_acid_amp
      - pcr_cond
      - pcr_cycles
      - pcr_primers
      - stranded_orientation
    close_mappings:
      - OBI:0000711
    comments:
      - OBI:0000711 specifies a DNA input (but not ONLY a DNA input)
    slot_usage:
      has_input:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(bsm|procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_output:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true
      id:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:libprp-{id_shoulder}-{id_blade}$"
          interpolated: true
      pcr_cond:
        description: Description of reaction conditions and components of polymerase chain reaction performed during library preparation

  CollectingBiosamplesFromSite:
    class_uri: nmdc:CollectingBiosamplesFromSite
    is_a: PlannedProcess
    title: Collecting Biosamples From Site
    comments:
      - "this illustrates implementing a Biosample relation with a process class"
    close_mappings:
      - OBI:0000744
    slot_usage:
      has_input:
        range: Site
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(frsite|site)-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_output:
        range: Biosample
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:bsm-{id_shoulder}-{id_blade}$"
          interpolated: true
      id:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:clsite-{id_shoulder}-{id_blade}$"
          interpolated: true

  ProtocolExecution:
    class_uri: 'nmdc:ProtocolExecution'
    is_a: PlannedProcess
    description: A PlannedProces that has PlannedProcess parts. Can be used to represent the case of someone following a Protocol.
    slots:
      - has_process_parts
      - protocol_execution_category
    slot_usage:
      id:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:pex-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_input:
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(bsm|procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_output:
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_process_parts:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(extrp|filtpr|dispro|poolp|libprp|subspr|mixpro|chcpr|cspro)-{id_shoulder}-{id_blade}$"
          interpolated: true
        description: The MaterialProcessing steps that are discrete parts of the ProtocolExecution.

  SubSamplingProcess:
    class_uri: 'nmdc:SubSamplingProcess'
    description: >
      Separating a sample aliquot from the starting material for downstream activity.
    related_mappings:
      - OBI:0000744
    notes:
      - A subsample may be (a) a portion of the sample obtained by selection or division;
        (b) an individual unit of the lot taken as part of the sample; (c) the final unit of multistage sampling.
        The term 'subsample' is used either in the sense of a 'sample of a sample' or as a synonym for 'unit'.
        In practice, the meaning is usually apparent from the context or is defined.
      - TODO - Montana to visit slot descriptions
    contributors:
      - ORCID:0009-0001-1555-1601 #Anastasiya Prymolenna
      - ORCID:0000-0002-8683-0050 #Montana Smith
      - ORCID:0000-0001-9076-6066 #Mark Miller
      - ORCID:0009-0008-4013-7737 #James Tessmer
    is_a: MaterialProcessing
    slots:
      - container_size
      - contained_in
      - temperature
      - volume
      - mass
      - sampled_portion
    slot_usage:
      id:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:subspr-{id_shoulder}-{id_blade}$"
          interpolated: true
      volume:
        description: The output volume of the SubSampling Process.
      mass:
        description: The output mass of the SubSampling Process.
      has_input:
        any_of:
          - range: Biosample
          - range: ProcessedSample
        structured_pattern: # MAM 2024-05-22 isn't that inherited from a parent class?
          syntax: "{id_nmdc_prefix}:(bsm|procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_output:
        range: ProcessedSample
        description: The subsample.
        structured_pattern: # MAM 2024-05-22 isn't that inherited from a parent class?
          syntax: "{id_nmdc_prefix}:(procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true

  MixingProcess:
    class_uri: 'nmdc:MixingProcess'
    description: >
      The combining of components, particles or layers into a more homogeneous state.
    contributors:
      - ORCID:0009-0001-1555-1601 #Anastasiya Prymolenna
      - ORCID:0000-0002-8683-0050 #Montana Smith
    is_a: MaterialProcessing
    comments:
      - The mixing may be achieved manually or mechanically by shifting the material with stirrers or pumps
        or by revolving or shaking the container.
      - The process must not permit segregation of particles of different size or properties.
      - Homogeneity may be considered to have been achieved in a practical sense when the sampling error
        of the processed portion is negligible compared to the total error of the measurement system.
    slots:
      - duration
    slot_usage:
      id:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:mixpro-{id_shoulder}-{id_blade}$"
      has_input:
        any_of:
          - range: Biosample
          - range: ProcessedSample
        structured_pattern: # MAM 2024-05-22 isn't that inherited from a parent class?
          syntax: "{id_nmdc_prefix}:(bsm|procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_output:
        range: ProcessedSample
        description: The mixed sample.
        structured_pattern:
          syntax: "{id_nmdc_prefix}:procsm-{id_shoulder}-{id_blade}$"
          interpolated: true

  FiltrationProcess:
    class_uri: 'nmdc:FiltrationProcess'
    description: >-
      The process of segregation of phases; e.g. the separation of suspended solids from a liquid or gas, usually by forcing a carrier gas or liquid through a porous medium.
    related_mappings:
      - CHMO:0001640
    contributors:
      - ORCID:0009-0001-1555-1601 #Anastasiya Prymolenna
      - ORCID:0000-0002-8683-0050 #Montana Smith
      - ORCID:0000-0001-9076-6066 #Mark Miller
      - ORCID:0009-0008-4013-7737 #James Tessmer
    is_a: MaterialProcessing
    slots:
      - conditionings
      - container_size
      - filter_material
      - filter_pore_size
      - filtration_category
      - is_pressurized
      - separation_method
      - volume
    slot_usage:
      id:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:filtpr-{id_shoulder}-{id_blade}$"
          interpolated: true
      volume:
        description: The volume of sample filtered.
      has_input:
        any_of:
          - range: Biosample
          - range: ProcessedSample
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(bsm|procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_output:
        range: ProcessedSample
        structured_pattern:
          syntax: "{id_nmdc_prefix}:procsm-{id_shoulder}-{id_blade}$"
          interpolated: true

  StorageProcess:
    class_uri: 'nmdc:StorageProcess'
    description: >-
      A planned process with the objective to preserve and protect material entities by placing them in an identified 
      location which may have a controlled environment.
    is_a: PlannedProcess
    related_mappings:
      - OBI:0302893
    slots:
      - substances_used
      - contained_in
      - temperature
    slot_usage:
      substances_used:
        description: The substance(s) that a processed sample is stored in.
      id:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:storpr-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_input:
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(bsm|procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_output:
        structured_pattern:
          syntax: "{id_nmdc_prefix}:procsm-{id_shoulder}-{id_blade}$"
          interpolated: true

  ChromatographicSeparationProcess:
    class_uri: 'nmdc:ChromatographicSeparationProcess'
    description:
      The process of using a selective partitioning of the analyte or interferent between two immiscible phases.
    contributors:
      - ORCID:0009-0001-1555-1601 #Anastasiya Prymolenna
      - ORCID:0000-0002-1368-8217 #Yuri Corilo
    is_a: MaterialProcessing
    slots:
      - chromatographic_category
      - ordered_mobile_phases
      - stationary_phase
      - temperature
    slot_usage:
      id:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:cspro-{id_shoulder}-{id_blade}$"
      has_input:
        any_of:
          - range: Biosample
          - range: ProcessedSample
        structured_pattern:
          syntax: "{id_nmdc_prefix}:(bsm|procsm)-{id_shoulder}-{id_blade}$"
          interpolated: true
      has_output:
        range: ProcessedSample
        structured_pattern:
          syntax: "{id_nmdc_prefix}:procsm-{id_shoulder}-{id_blade}$"
          interpolated: true

  DissolvingProcess:
    class_uri: 'nmdc:DissolvingProcess'
    aliases:
      - Solubilization
    description: >
      A mixing step where a soluble component is mixed with a liquid component.
    exact_mappings:
      - CHMO:0002773
    contributors:
      - ORCID:0009-0001-1555-1601 #Anastasiya Prymolenna
      - ORCID:0000-0002-1368-8217 #Yuri Corilo
    is_a: MaterialProcessing
    slots:
      - duration
      - temperature
      - substances_used
    slot_usage:
      id:
        required: true
        structured_pattern:
          syntax: "{id_nmdc_prefix}:dispro-{id_shoulder}-{id_blade}$"
          interpolated: true

enums:


  StrandedOrientationEnum:
    description: This enumeration specifies information about stranded RNA library preparations.
    permissible_values:
      antisense orientation:
        description: Orientation that is complementary (non-coding) to a sequence of messenger RNA.
        comments:
          - See https://www.genome.gov/genetics-glossary/antisense
        exact_mappings:
          - SO:0000077
      sense orientation:
        description: Orientation that corresponds to the coding sequence of messenger RNA.

  MassSpectrometryAcquisitionStrategyEnum:
    permissible_values:
      data_independent_acquisition:
        description:
          - Data independent mass spectrometer acquisition method wherein the full mass range is fragmented. Examples of such an approach include MS^E, AIF, and bbCID.
        aliases:
          - DIA
          - data independent acquisition from dissociation of full mass range
        exact_mappings:
          - MS:1003227
      data_dependent_acquisition:
        description:
          Mass spectrometer data acquisition method wherein MSn spectra are triggered based on the m/z of precursor ions detected in the same run.
        aliases:
          -DDA
        exact_mappings:
          - MS:1003221
      full_scan_only:
        aliases:
          - MS
        description:
          Mass spectrometer data acquisition method wherein only MS1 data are acquired.

  ResolutionCategoryEnum:
    permissible_values:
      high:
        description: higher than unit resolution
      low:
        description: at unit resolution

  MassAnalyzerEnum:
    permissible_values:
      time_of_flight:
        aliases:
          - TOF
        description:
          Instrument that separates ions by m/z in a field-free region after acceleration to a fixed acceleration energy.
        exact_mappings:
          - MS:1000084
      quadrupole:
        aliases:
          - Quad
          - Q
        description:
          A mass spectrometer that consists of four parallel rods whose centers form the corners of a square and whose opposing poles are connected. The voltage applied to the rods is a superposition of a static potential and a sinusoidal radio frequency potential. The motion of an ion in the x and y dimensions is described by the Matthieu equation whose solutions show that ions in a particular m/z range can be transmitted along the z axis.
        exact_mappings:
          - MS:1000081
      Orbitrap:
        aliases:
          - Orbi
        description:
          An ion trapping device that consists of an outer barrel-like electrode and a coaxial inner spindle-like electrode that form an electrostatic field with quadro-logarithmic potential distribution. The frequency of harmonic oscillations of the orbitally trapped ions along the axis of the electrostatic field is independent of the ion velocity and is inversely proportional to the square root of m/z so that the trap can be used as a mass analyzer.
        exact_mappings:
          - MS:1000484
      ion_cyclotron_resonance:
        aliases:
          - ICR
        description:
          A mass spectrometer based on the principle of ion cyclotron resonance in which an ion in a magnetic field moves in a circular orbit at a frequency characteristic of its m/z value. Ions are coherently excited to a larger radius orbit using a pulse of radio frequency energy and their image charge is detected on receiver plates as a time domain signal. Fourier transformation of the time domain signal results in a frequency domain signal which is converted to a mass spectrum based in the inverse relationship between frequency and m/z.
        exact_mappings:
          - MS:1000079
      ion_trap:
        aliases:
          - LTQ
          - Ion Trap
          - Paul Trap
        description:
          A device for spatially confining ions using electric and magnetic fields alone or in combination.
        exact_mappings:
          - MS:1000264

  IonizationSourceEnum:
    permissible_values:
      electrospray_ionization:
        aliases:
          - ESI
      matrix_assisted_laser_desorption_ionization:
        aliases:
          - MALDI
      atmospheric_pressure_photo_ionization:
        aliases:
          - APPI
      atmospheric_pressure_chemical_ionization:
        aliases:
          - APCI
      electron_ionization:
        aliases:
          - EI

  MassSpectrumCollectionModeEnum:
    permissible_values:
      full_profile: { }
      reduced_profile: { }
      centroid: { }

  PolarityModeEnum:
    permissible_values:
      positive: { }
      negative: { }

  EluentIntroductionCategoryEnum:
    permissible_values:
      liquid_chromatography:
        aliases:
          - LC
        description: The processed sample is introduced into the mass spectrometer through a liquid chromatography process.
      gas_chromatography:
        aliases:
          - GC
        description: The processed sample is introduced into the mass spectrometer through a gas chromatography process.
      direct_infusion_syringe:
        description: The processed sample is introduced into the mass spectrometer through a direct infusion process using a syringe.
      direct_infusion_autosampler:
        description: The processed sample is introduced into the mass spectrometer through a direct infusion process using an autosampler.

  LibraryTypeEnum:
    permissible_values:
      DNA: { }
      RNA: { }

  ContainerCategoryEnum:
    description: The permitted types of containers used in processing metabolomic samples.
    contributors:
      - ORCID:0009-0001-1555-1601 #Anastasiya Prymolenna
      - ORCID:0000-0002-8683-0050 #Montana Smith
    permissible_values:
      v-bottom_conical_tube:
      falcon_tube:

  SeparationMethodEnum:
    description: The tool/substance used to separate or filter a solution or mixture.
    contributors:
      - ORCID:0009-0001-1555-1601 #Anastasiya Prymolenna
      - ORCID:0000-0002-8683-0050 #Montana Smith
    permissible_values:
      ptfe_96_well_filter_plate:
      syringe:

  StationaryPhaseEnum:
    description: The type of stationary phase used in a chromatography process.
    contributors:
      - ORCID:0009-0001-1555-1601 #Anastasiya Prymolenna
      - ORCID:0000-0002-4504-1039 #Katherine Heal
    permissible_values:
      BEH-HILIC:
      C18:
      C8:
      C4:
      C2:
      C1:
      C30:
      C60:
      CNT:
      CN:
      Diol:
      HILIC:
      NH2:
      Phenyl:
      Polysiloxane:
      PS-DVB:
      SAX:
      SCX:
      Silica:
      WCX:
      WAX:
      ZIC-HILIC:
      ZIC-pHILIC:
      ZIC-cHILIC:

  ProtocolCategoryEnum:
    description: The possible protocols that may be followed for an assay.
    permissible_values:
      mplex:
      derivatization:
      filter_clean_up:
      organic_matter_extraction:
      solid_phase_extraction:
      phosphorus_extraction:
      ph_measurement:
      respiration_measurement:
      texture_measurement:
      dna_extraction:
      phenol_chloroform_extraction: { }

  ChromatographicCategoryEnum:
    permissible_values:
      liquid_chromatography:
        aliases:
          - LC
      gas_chromatography:
        aliases:
          - GC
      solid_phase_extraction:
        aliases:
          - SPE
  
  SamplePortionEnum:
    permissible_values:
      supernatant:
        aliases:
          - top_layer
      pellet:
        aliases:
          - bottom_layer
      organic_layer:
      aqueous_layer:
      non_polar_layer:


slots:
  polarity_mode:
    range: PolarityModeEnum
    description: the polarity of which ions are generated and detected

  mass_spectrum_collection_modes:
    range: MassSpectrumCollectionModeEnum
    description: Indicates whether mass spectra were collected in full profile, reduced profile, or centroid mode during acquisition.
    multivalued: true

  eukaryotic_evaluation:
    range: EukEval
    description: Contains results from evaluating if a Metagenome-Assembled Genome is of eukaryotic lineage.
  ncbi_lineage_tax_ids:
    range: string
    pattern: '^\d+(-\d+)*$'
    description: Dash-delimited ordered list of NCBI taxonomy identifiers (TaxId)
    comments:
      - Example 1-131567-2759-2611352-33682-191814-2603949
  ncbi_lineage:
    range: string
    description: Comma delimited ordered list of NCBI taxonomy names.
    comments:
      - Example root,cellular organisms,Eukaryota,Discoba,Euglenozoa,Diplonemea,Diplonemidae

  has_failure_categorization:
    range: FailureCategorization
    multivalued: true
    inlined_as_list: true

  ionization_source:
    range: IonizationSourceEnum
    description: The ionization source used to introduce processed samples into a mass spectrometer
    exact_mappings:
      - MS:1000008

  mass_analyzers:
    range: MassAnalyzerEnum
    description: The kind of mass analyzer(s) used during the spectra collection.
    multivalued: true
    exact_mappings:
      - MS:1000443

  resolution_categories:
    range: ResolutionCategoryEnum
    description: The relative resolution at which spectra were collected.
    examples:
      - value:
          - high
          - low
    multivalued: true
  mass_spectrometry_acquisition_strategy:
    range: MassSpectrometryAcquisitionStrategyEnum
    description: Mode of running a mass spectrometer method by which m/z ranges are selected and ions possibly fragment.
    exact_mappings:
      - MS:1003213

  eluent_introduction_category:
    range: EluentIntroductionCategoryEnum
    description: A high-level categorization for how the processed sample is introduced into a mass spectrometer.
    examples:
      - value: liquid_chromatography
      - value: direct_infusion_syringe

  has_mass_spectrometry_configuration:
    range: MassSpectrometryConfiguration
    description: The identifier of the associated MassSpectrometryConfiguration.

  has_chromatography_configuration:
    range: ChromatographyConfiguration
    description: The identifier of the associated ChromatographyConfiguration, providing information about how a sample was introduced into the mass spectrometer.

  metagenome_annotation_id:
    range: WorkflowExecution
    description: The identifier for the analysis activity that generated the functional annotation results, where the analysis activity is an instance of the/an appropriate subclass of WorkflowExecution
    required: true
    any_of:
      - range: MetagenomeAnnotation
      - range: MetatranscriptomeAnnotation

  gene_function_id:
    range: uriorcurie
    description: The identifier for the gene function.
    examples:
      - value: KEGG.ORTHOLOGY:K00627
    required: true
  count:
    range: integer
    required: true
  functional_annotation_agg:
    range: FunctionalAnnotationAggMember
    multivalued: true
    inlined: true
    inlined_as_list: true

  ecosystem_path_id:
    range: string
    description: A unique id representing the GOLD classifiers associated with a sample.

  sample_collection_year:
    range: integer
  sample_collection_month:

  library_preparation_kit:
    range: string

  ## WHY ARE THESE COMMENTED OUT?
  #    exact_mappings:
  #      - GENEPIO:0001450
  #  processed_date: # can we move this or infer this from the date of some other process?
  #    #    range: date
  #    range: string
  #  extraction_date: # replacing with start_ and end_date
  #    #    range: date
  #    range: string

  pcr_cycles:
    range: integer
    exact_mappings:
      - OBI:0002475

  is_stranded:
    description: Is the (RNA) library stranded or non-stranded (unstranded).
    range: boolean
    comments:
      - A value of true means the library is stranded, flase means non-stranded.
  
  stranded_orientation:
    description: Lists the strand orientiation for a stranded RNA library preparation.
    range: StrandedOrientationEnum


  input_mass:
    title: sample mass used
    description: Total mass of sample used in activity.
    aliases:
      - sample mass
      - sample weight
    exact_mappings:
      - MS:1000004
    narrow_mappings:
      - MIXS:0000111
    range: QuantityValue

  library_type:
    title: library type
    examples:
      - value: DNA
    range: LibraryTypeEnum

  date_created:
    description: from database class
  etl_software_version:
    description: from database class

  object_set:
    inlined_as_list: true
    mixin: true
    multivalued: true
    description:
      Applies to a property that links a database object to a set of objects.
      This is necessary in a json document to provide context for a list, and to allow
      for a single json object that combines multiple object types
  chemical_entity_set:
    mixins:
      - object_set
    range: ChemicalEntity
    description:
      This property links a database object to the set of chemical entities
      within it.
  biosample_set:
    mixins: object_set
    range: Biosample
    description:
      This property links a database object to the set of samples within
      it.
  study_set:
    mixins: object_set
    range: Study
    description:
      This property links a database object to the set of studies within
      it.
  field_research_site_set:
    mixins: object_set
    range: FieldResearchSite

  collecting_biosamples_from_site_set:
    mixins: object_set
    range: CollectingBiosamplesFromSite

  data_object_set:
    mixins: object_set
    range: DataObject
    description:
      This property links a database object to the set of data objects
      within it.

  genome_feature_set:
    mixins: object_set
    range: GenomeFeature
    description: This property links a database object to the set of all features

  functional_annotation_set:
    mixins: object_set
    range: FunctionalAnnotation
    description:
      This property links a database object to the set of all functional
      annotations

  workflow_execution_set:
    mixins: object_set
    range: WorkflowExecution
    description: This property links a database object to the set of workflow executions.

  data_generation_set:
    mixins: object_set
    range: DataGeneration
    description:
      This property links a database object to the set of data generations
      within it.

  processed_sample_set:
    mixins: object_set
    range: ProcessedSample
    description: This property links a database object to the set of processed samples within it.

  instrument_set:
    mixins: object_set
    range: Instrument
    description: This property links a database object to the set of instruments within it.

  calibration_set:
    mixins: object_set
    range: CalibrationInformation
    description: This property links a database object to the set of calibrations within it.

  configuration_set:
    mixins: object_set
    range: Configuration
    description: This property links a database object to the set of configurations within it.

  protocol_execution_set:
    mixins: object_set
    range: ProtocolExecution
    description: This property links a database object to the set of protocol executions within it.

  storage_process_set:
    mixins: object_set
    range: StorageProcess
    description: This property links a database object to the set of storage processes within it.

  material_processing_set:
    mixins: object_set
    range: MaterialProcessing
    description: This property links a database object to the set of material processing within it.

  sample_collection_day:
    range: integer
  sample_collection_hour:
    range: integer
  sample_collection_minute:
    range: integer

  biogas_temperature:

    range: string
  soil_annual_season_temp:
    range: string

  biogas_retention_time:
    range: string

  completion_date:
    range: string

  container_size:
    range: QuantityValue
    description: The volume of the container an analyte is stored in or an activity takes place in
    contributors:
      - ORCID:0009-0001-1555-1601 #Anastasiya Prymolenna
      - ORCID:0000-0002-8683-0050 #Montana Smith

  protocol_execution_category:
    range: ProtocolCategoryEnum
    required: true

  has_process_parts:
    range: PlannedProcess
    description: A list of process parts that make up a protocol.
    required: true
    multivalued: true
    list_elements_ordered: true

  filter_material:
    description: "A porous material on which solid particles present in air or other fluid which flows through it are largely caught and retained."
    comments:
      - "Filters are made with a variety of materials: cellulose and derivatives, glass fibre, ceramic, synthetic plastics and fibres. Filters may be naturally porous or be made so by mechanical or other means. Membrane/ceramic filters are prepared with highly controlled pore size in a sheet of suitable material such as polyfluoroethylene, polycarbonate or cellulose esters. Nylon mesh is sometimes used for reinforcement. The pores constitute 80–85% of the filter volume commonly and several pore sizes are available for air sampling (0.45−0.8 μm are commonly employed)."
    range: string
  filter_pore_size:
    range: QuantityValue
    description: "A quantitative or qualitative measurement of the physical dimensions of the pores in a material."
  conditionings:
    range: string
    description: "Preliminary treatment of either phase with a suitable solution of the other phase (in the absence of main extractable solute(s)) so that when the subsequent equilibration is carried out changes in the (volume) phase ratio or in the concentrations of other components are minimized."
    multivalued: true
    list_elements_ordered: true
  separation_method:
    range: SeparationMethodEnum
    description: The method that was used to separate a substance from a solution or mixture.
  filtration_category:
    range: string
    description: The type of conditioning applied to a filter, device, etc.
  material_component_separation:
    range: string
    description: "A material processing in which components of an input material become segregated in space"
  value:
    range: QuantityValue
  modifier_substance:
    range: string
    description: The type of modification being done
  is_pressurized:
    range: boolean
    description: Whether or not pressure was applied to a thing or process.

  contained_in:
    range: ContainerCategoryEnum
    description: A type of container.
    examples:
      - value: test tube
      - value: falcon tube
      - value: whirlpak

  input_volume: # see also `volume`
    range: QuantityValue
    description: The volume of the input sample.

  ordered_mobile_phases:
    range: MobilePhaseSegment
    description: The solution(s) that moves through a chromatography column.
    multivalued: true
    list_elements_ordered: true
    inlined_as_list: true

  stationary_phase:
    range: StationaryPhaseEnum
    description: The material the stationary phase is comprised of used in chromatography.
  chromatographic_category:
    range: ChromatographicCategoryEnum
    description: The type of chromatography used in a process.

  sampled_portion:
    range: SamplePortionEnum
    multivalued: true
    description: The portion of the sample that is taken for downstream activity.