nwb-linkml/nwb_schema_language/src/data/tests/nwb.file.yaml

groups:
- neurodata_type_def: NWBFile
  neurodata_type_inc: NWBContainer
  name: root
  doc: An NWB file storing cellular-based neurophysiology data from a single
    experimental session.
  attributes:
  - name: nwb_version
    dtype: text
    value: "2.6.0"
    doc: File version string. Use semantic versioning, e.g. 1.2.1. This will be the
      name of the format with trailing major, minor and patch numbers.
  datasets:
  - name: file_create_date
    dtype: isodatetime
    dims:
    - num_modifications
    shape:
    - null
    doc: 'A record of the date the file was created and of subsequent modifications.
      The date is stored in UTC with local timezone offset as ISO 8601
      extended formatted strings: 2018-09-28T14:43:54.123+02:00. Dates stored in
      UTC end in "Z" with no timezone offset. Date accuracy is up to milliseconds.
      The file can be created after the experiment was run, so this may differ from
      the experiment start time. Each modification to the nwb file adds a new entry
      to the array.'
  - name: identifier
    dtype: text
    doc: A unique text identifier for the file. For example, concatenated lab name,
      file creation date/time and experimentalist, or a hash of these and/or other
      values. The goal is that the string should be unique to all other files.
  - name: session_description
    dtype: text
    doc: A description of the experimental session and data in the file.
  - name: session_start_time
    dtype: isodatetime
    doc: 'Date and time of the experiment/session start. The date is stored
      in UTC with local timezone offset as ISO 8601 extended formatted string:
      2018-09-28T14:43:54.123+02:00.
      Dates stored in UTC end in "Z" with no timezone offset. Date accuracy is
      up to milliseconds.'
  - name: timestamps_reference_time
    dtype: isodatetime
    doc: 'Date and time corresponding to time zero of all timestamps. The
      date is stored in UTC with local timezone offset as ISO 8601 extended formatted
      string: 2018-09-28T14:43:54.123+02:00. Dates stored in UTC end in "Z" with
      no timezone offset. Date accuracy is up to milliseconds. All times stored
      in the file use this time as reference (i.e., time zero).'
  groups:
  - name: acquisition
    doc: Data streams recorded from the system, including ephys, ophys, tracking,
      etc. This group should be read-only after the experiment is completed and
      timestamps are corrected to a common timebase. The data stored here may be links
      to raw data stored in external NWB files. This will allow keeping bulky raw
      data out of the file while preserving the option of keeping some/all in the
      file. Acquired data includes tracking and experimental data streams
      (i.e., everything measured from the system). If bulky data is stored in the /acquisition
      group, the data can exist in a separate NWB file that is linked to by the file
      being used for processing and analysis.
    groups:
    - neurodata_type_inc: NWBDataInterface
      doc: Acquired, raw data.
      quantity: '*'
    - neurodata_type_inc: DynamicTable
      doc: Tabular data that is relevant to acquisition
      quantity: '*'
  - name: analysis
    doc: Lab-specific and custom scientific analysis of data. There is no defined
      format for the content of this group - the format is up to the individual user/lab.
      To facilitate sharing analysis data between labs, the contents here
      should be stored in standard types (e.g., neurodata_types) and appropriately documented.
      The file can store lab-specific and custom data analysis without
      restriction on its form or schema, reducing data formatting restrictions on
      end users. Such data should be placed in the analysis group. The analysis data
      should be documented so that it could be shared with other labs.
    groups:
    - neurodata_type_inc: NWBContainer
      doc: Custom analysis results.
      quantity: '*'
    - neurodata_type_inc: DynamicTable
      doc: Tabular data that is relevant to data stored in analysis
      quantity: '*'
  - name: scratch
    doc: 'A place to store one-off analysis results. Data placed here is not intended for
      sharing. By placing data here, users acknowledge that there is no guarantee that
      their data meets any standard.'
    quantity: '?'
    groups:
    - neurodata_type_inc: NWBContainer
      doc: Any one-off containers
      quantity: '*'
    - neurodata_type_inc: DynamicTable
      doc: Any one-off tables
      quantity: '*'
    datasets:
    - neurodata_type_inc: ScratchData
      doc: Any one-off datasets
      quantity: '*'
  - name: processing
    doc: "The home for ProcessingModules. These modules perform intermediate analysis\
      \ of data that is necessary to perform before scientific analysis. Examples\
      \ include spike clustering, extracting position from tracking data, stitching\
      \ together image slices. ProcessingModules can be large\
      \ and express many data sets from relatively complex analysis (e.g., spike detection\
      \ and clustering) or small, representing extraction of position information\
      \ from tracking video, or even binary lick/no-lick decisions. Common software\
      \ tools (e.g., klustakwik, MClust) are expected to read/write data here. \
      \ 'Processing' refers to intermediate analysis of the acquired data to make\
      \ it more amenable to scientific analysis."
    groups:
    - neurodata_type_inc: ProcessingModule
      doc: Intermediate analysis of acquired data.
      quantity: '*'
  - name: stimulus
    doc: 'Data pushed into the system (eg, video stimulus, sound, voltage, etc) and
      secondary representations of that data (eg, measurements of something used as
      a stimulus). This group should be made read-only after experiment complete and timestamps
      are corrected to common timebase. Stores both presented stimuli and stimulus
      templates, the latter in case the same stimulus is presented multiple times,
      or is pulled from an external stimulus library. Stimuli are here
      defined as any signal that is pushed into the system as part of the experiment
      (eg, sound, video, voltage, etc). Many different experiments can use the same
      stimuli, and stimuli can be re-used during an experiment. The stimulus group
      is organized so that one version of template stimuli can be stored and these
      be used multiple times. These templates can exist in the present file or can
      be linked to a remote library file.'
    groups:
    - name: presentation
      doc: Stimuli presented during the experiment.
      groups:
      - neurodata_type_inc: TimeSeries
        doc: TimeSeries objects containing data of presented stimuli.
        quantity: '*'
    - name: templates
      doc: 'Template stimuli. Timestamps in templates are based on stimulus
        design and are relative to the beginning of the stimulus. When templates are
        used, the stimulus instances must convert presentation times to the experiment`s
        time reference frame.'
      groups:
      - neurodata_type_inc: TimeSeries
        doc: TimeSeries objects containing template data of presented stimuli.
        quantity: '*'
      - neurodata_type_inc: Images
        doc: Images objects containing images of presented stimuli.
        quantity: '*'
  - name: general
    doc: "Experimental metadata, including protocol, notes and description of hardware\
      \ device(s).  The metadata stored in this section should be used to\
      \ describe the experiment. Metadata necessary for interpreting the data is stored\
      \ with the data. General experimental metadata, including animal\
      \ strain, experimental protocols, experimenter, devices, etc, are stored under\
      \ 'general'. Core metadata (e.g., that required to interpret data fields) is\
      \ stored with the data itself, and implicitly defined by the file specification\
      \ (e.g., time is in seconds). The strategy used here for storing non-core metadata\
      \ is to use free-form text fields, such as would appear in sentences or paragraphs\
      \ from a Methods section. Metadata fields are text to enable them to be more\
      \ general, for example to represent ranges instead of numerical values. Machine-readable\
      \ metadata is stored as attributes to these free-form datasets. All entries\
      \ in the below table are to be included when data is present. Unused groups\
      \ (e.g., intracellular_ephys in an optophysiology experiment) should not be\
      \ created unless there is data to store within them."
    datasets:
    - name: data_collection
      dtype: text
      doc: Notes about data collection and analysis.
      quantity: '?'
    - name: experiment_description
      dtype: text
      doc: General description of the experiment.
      quantity: '?'
    - name: experimenter
      dtype: text
      doc: Name of person(s) who performed the experiment. Can also specify roles
        of different people involved.
      quantity: '?'
      dims:
      - num_experimenters
      shape:
      - null
    - name: institution
      dtype: text
      doc: Institution(s) where experiment was performed.
      quantity: '?'
    - name: keywords
      dtype: text
      dims:
      - num_keywords
      shape:
      - null
      doc: Terms to search over.
      quantity: '?'
    - name: lab
      dtype: text
      doc: Laboratory where experiment was performed.
      quantity: '?'
    - name: notes
      dtype: text
      doc: Notes about the experiment.
      quantity: '?'
    - name: pharmacology
      dtype: text
      doc: Description of drugs used, including how and when they were administered.
        Anesthesia(s), painkiller(s), etc., plus dosage, concentration, etc.
      quantity: '?'
    - name: protocol
      dtype: text
      doc: Experimental protocol, if applicable. e.g., include IACUC protocol number.
      quantity: '?'
    - name: related_publications
      dtype: text
      doc: Publication information. PMID, DOI, URL, etc.
      dims:
      - num_publications
      shape:
      - null
      quantity: '?'
    - name: session_id
      dtype: text
      doc: Lab-specific ID for the session.
      quantity: '?'
    - name: slices
      dtype: text
      doc: Description of slices, including information about preparation thickness,
        orientation, temperature, and bath solution.
      quantity: '?'
    - name: source_script
      dtype: text
      doc: Script file or link to public source code used to create this NWB file.
      quantity: '?'
      attributes:
      - name: file_name
        dtype: text
        doc: Name of script file.
    - name: stimulus
      dtype: text
      doc: Notes about stimuli, such as how and where they were presented.
      quantity: '?'
    - name: surgery
      dtype: text
      doc: Narrative description about surgery/surgeries, including date(s) and who
        performed surgery.
      quantity: '?'
    - name: virus
      dtype: text
      doc: Information about virus(es) used in experiments, including virus ID, source,
        date made, injection location, volume, etc.
      quantity: '?'
    groups:
    - neurodata_type_inc: LabMetaData
      doc: Place-holder than can be extended so that lab-specific meta-data can be
        placed in /general.
      quantity: '*'
    - name: devices
      doc: Description of hardware devices used during experiment, e.g., monitors,
        ADC boards, microscopes, etc.
      quantity: '?'
      groups:
      - neurodata_type_inc: Device
        doc: Data acquisition devices.
        quantity: '*'
    - name: subject
      neurodata_type_inc: Subject
      doc: Information about the animal or person from which the data was measured.
      quantity: '?'
    - name: extracellular_ephys
      doc: Metadata related to extracellular electrophysiology.
      quantity: '?'
      groups:
      - neurodata_type_inc: ElectrodeGroup
        doc: Physical group of electrodes.
        quantity: '*'
      - name: electrodes
        neurodata_type_inc: DynamicTable
        doc: A table of all electrodes (i.e. channels) used for recording.
        quantity: '?'
        datasets:
        - name: x
          neurodata_type_inc: VectorData
          dtype: float32
          doc: x coordinate of the channel location in the brain (+x is posterior).
          quantity: '?'
        - name: y
          neurodata_type_inc: VectorData
          dtype: float32
          doc: y coordinate of the channel location in the brain (+y is inferior).
          quantity: '?'
        - name: z
          neurodata_type_inc: VectorData
          dtype: float32
          doc: z coordinate of the channel location in the brain (+z is right).
          quantity: '?'
        - name: imp
          neurodata_type_inc: VectorData
          dtype: float32
          doc: Impedance of the channel, in ohms.
          quantity: '?'
        - name: location
          neurodata_type_inc: VectorData
          dtype: text
          doc: Location of the electrode (channel). Specify the area, layer, comments
            on estimation of area/layer, stereotaxic coordinates if in vivo, etc. Use
            standard atlas names for anatomical regions when possible.
        - name: filtering
          neurodata_type_inc: VectorData
          dtype: text
          doc: Description of hardware filtering, including the filter name and frequency cutoffs.
          quantity: '?'
        - name: group
          neurodata_type_inc: VectorData
          dtype:
            target_type: ElectrodeGroup
            reftype: object
          doc: Reference to the ElectrodeGroup this electrode is a part of.
        - name: group_name
          neurodata_type_inc: VectorData
          dtype: text
          doc: Name of the ElectrodeGroup this electrode is a part of.
        - name: rel_x
          neurodata_type_inc: VectorData
          dtype: float32
          doc: x coordinate in electrode group
          quantity: '?'
        - name: rel_y
          neurodata_type_inc: VectorData
          dtype: float32
          doc: y coordinate in electrode group
          quantity: '?'
        - name: rel_z
          neurodata_type_inc: VectorData
          dtype: float32
          doc: z coordinate in electrode group
          quantity: '?'
        - name: reference
          neurodata_type_inc: VectorData
          dtype: text
          doc: Description of the reference electrode and/or reference scheme used for this electrode, e.g.,
            "stainless steel skull screw" or "online common average referencing".
          quantity: '?'
    - name: intracellular_ephys
      doc: Metadata related to intracellular electrophysiology.
      quantity: '?'
      datasets:
      - name: filtering
        dtype: text
        doc: '[DEPRECATED] Use IntracellularElectrode.filtering instead. Description
          of filtering used. Includes filtering type and parameters, frequency fall-off,
          etc. If this changes between TimeSeries, filter description should be stored
          as a text attribute for each TimeSeries.'
        quantity: '?'
      groups:
      - neurodata_type_inc: IntracellularElectrode
        doc: An intracellular electrode.
        quantity: '*'
      - name: sweep_table
        neurodata_type_inc: SweepTable
        doc: '[DEPRECATED] Table used to group different PatchClampSeries. SweepTable
              is being replaced by IntracellularRecordingsTable and SimultaneousRecordingsTable
              tables. Additional SequentialRecordingsTable, RepetitionsTable and
              ExperimentalConditions tables provide enhanced support for experiment metadata.'
        quantity: '?'
      - name: intracellular_recordings
        neurodata_type_inc: IntracellularRecordingsTable
        doc: A table to group together a stimulus and response from a single electrode
          and a single simultaneous recording. Each row in the table represents a
          single recording consisting typically of a stimulus and a corresponding
          response. In some cases, however, only a stimulus or a response are recorded
          as as part of an experiment. In this case both, the stimulus and response
          will point to the same TimeSeries while the idx_start and count of the invalid
          column will be set to -1, thus, indicating that no values have been recorded
          for the stimulus or response, respectively. Note, a recording MUST contain
          at least a stimulus or a response. Typically the stimulus and response are
          PatchClampSeries. However, the use of AD/DA channels that are not associated
          to an electrode is also common in intracellular electrophysiology, in which
          case other TimeSeries may be used.
        quantity: '?'
      - name: simultaneous_recordings
        neurodata_type_inc: SimultaneousRecordingsTable
        doc: A table for grouping different intracellular recordings from the IntracellularRecordingsTable
          table together that were recorded simultaneously from different electrodes
        quantity: '?'
      - name: sequential_recordings
        neurodata_type_inc: SequentialRecordingsTable
        doc: A table for grouping different sequential recordings from the SimultaneousRecordingsTable
          table together. This is typically used to group together sequential recordings
          where the a sequence of stimuli of the same type with varying parameters
          have been presented in a sequence.
        quantity: '?'
      - name: repetitions
        neurodata_type_inc: RepetitionsTable
        doc: A table for grouping different sequential intracellular recordings together.
          With each SequentialRecording typically representing a particular type of
          stimulus, the RepetitionsTable table is typically used to group sets of
          stimuli applied in sequence.
        quantity: '?'
      - name: experimental_conditions
        neurodata_type_inc: ExperimentalConditionsTable
        doc: A table for grouping different intracellular recording repetitions together
          that belong to the same experimental experimental_conditions.
        quantity: '?'
    - name: optogenetics
      doc: Metadata describing optogenetic stimuluation.
      quantity: '?'
      groups:
      - neurodata_type_inc: OptogeneticStimulusSite
        doc: An optogenetic stimulation site.
        quantity: '*'
    - name: optophysiology
      doc: Metadata related to optophysiology.
      quantity: '?'
      groups:
      - neurodata_type_inc: ImagingPlane
        doc: An imaging plane.
        quantity: '*'
  - name: intervals
    doc: Experimental intervals, whether that be logically distinct sub-experiments
      having a particular scientific goal, trials (see trials subgroup) during an
      experiment, or epochs (see epochs subgroup) deriving from analysis of data.
    quantity: '?'
    groups:
    - name: epochs
      neurodata_type_inc: TimeIntervals
      doc: Divisions in time marking experimental stages or sub-divisions of a single
        recording session.
      quantity: '?'
    - name: trials
      neurodata_type_inc: TimeIntervals
      doc: Repeated experimental events that have a logical grouping.
      quantity: '?'
    - name: invalid_times
      neurodata_type_inc: TimeIntervals
      doc: Time intervals that should be removed from analysis.
      quantity: '?'
    - neurodata_type_inc: TimeIntervals
      doc: Optional additional table(s) for describing other experimental time intervals.
      quantity: '*'
  - name: units
    neurodata_type_inc: Units
    doc: Data about sorted spike units.
    quantity: '?'

- neurodata_type_def: LabMetaData
  neurodata_type_inc: NWBContainer
  doc: Lab-specific meta-data.

- neurodata_type_def: Subject
  neurodata_type_inc: NWBContainer
  doc: Information about the animal or person from which the data was measured.
  datasets:
  - name: age
    dtype: text
    doc: Age of subject. Can be supplied instead of 'date_of_birth'.
    quantity: '?'
    attributes:
      - name: reference
        doc: "Age is with reference to this event. Can be 'birth' or
          'gestational'. If reference is omitted, 'birth' is implied."
        dtype: text
        required: false
        default_value: birth
  - name: date_of_birth
    dtype: isodatetime
    doc: Date of birth of subject. Can be supplied instead of 'age'.
    quantity: '?'
  - name: description
    dtype: text
    doc: Description of subject and where subject came from (e.g., breeder, if
      animal).
    quantity: '?'
  - name: genotype
    dtype: text
    doc: Genetic strain. If absent, assume Wild Type (WT).
    quantity: '?'
  - name: sex
    dtype: text
    doc: Gender of subject.
    quantity: '?'
  - name: species
    dtype: text
    doc: Species of subject.
    quantity: '?'
  - name: strain
    dtype: text
    doc: Strain of subject.
    quantity: '?'
  - name: subject_id
    dtype: text
    doc: ID of animal/person used/participating in experiment (lab convention).
    quantity: '?'
  - name: weight
    dtype: text
    doc: Weight at time of experiment, at time of surgery and at other important
      times.
    quantity: '?'

datasets:
- neurodata_type_def: ScratchData
  neurodata_type_inc: NWBData
  doc: Any one-off datasets
  attributes:
  - name: notes
    doc: 'Any notes the user has about the dataset being stored'
    dtype: text