include-dcc · RobertJCarroll · Mar 12, 2026 · Mar 12, 2026
diff --git a/docs/schema/include_access_model.yaml b/docs/schema/include_access_model.yaml
@@ -835,10 +835,11 @@ slots:
     title: DOI
     from_schema: https://includedcc.org/include-access-model
     slot_uri: includedcc:do_id
-    owner: DOI
+    owner: Dataset
     domain_of:
     - Study
     - DOI
+    - Dataset
     range: DOI
     multivalued: false
   subject_id:
@@ -979,12 +980,13 @@ slots:
     title: Name
     from_schema: https://includedcc.org/include-access-model
     slot_uri: includedcc:name
-    owner: ActivityDefinition
+    owner: Dataset
     domain_of:
     - VirtualBiorepository
     - Investigator
     - EncounterDefinition
     - ActivityDefinition
+    - Dataset
     range: string
     required: false
   email:
@@ -1176,9 +1178,10 @@ slots:
     title: Publication
     from_schema: https://includedcc.org/include-access-model
     slot_uri: includedcc:publication
-    owner: Study
+    owner: Dataset
     domain_of:
     - Study
+    - Dataset
     range: Publication
     multivalued: true
     inlined: true
@@ -1737,10 +1740,11 @@ slots:
     title: Description
     from_schema: https://includedcc.org/include-access-model
     slot_uri: includedcc:description
-    owner: ActivityDefinition
+    owner: Dataset
     domain_of:
     - EncounterDefinition
     - ActivityDefinition
+    - Dataset
     range: string
   encounter_definition_id:
     name: encounter_definition_id
@@ -1773,9 +1777,10 @@ slots:
     title: File ID
     from_schema: https://includedcc.org/include-access-model
     slot_uri: includedcc:file_id
-    owner: File
+    owner: Dataset
     domain_of:
     - File
+    - Dataset
     range: File
   filename:
     name: filename
@@ -1891,6 +1896,39 @@ slots:
     domain_of:
     - FileHash
     range: string
+  dataset_id:
+    name: dataset_id
+    definition_uri: https://includedcc.org/include-access-model/dataset_id
+    description: Unique identifier for a Dataset.
+    title: Dataset ID
+    from_schema: https://includedcc.org/include-access-model
+    slot_uri: includedcc:dataset_id
+    owner: Dataset
+    domain_of:
+    - Dataset
+    range: Dataset
+  data_collection_start:
+    name: data_collection_start
+    definition_uri: https://includedcc.org/include-access-model/data_collection_start
+    description: The date that data collection started. May include only a year.
+    title: Data Collection Start
+    from_schema: https://includedcc.org/include-access-model
+    slot_uri: includedcc:data_collection_start
+    owner: Dataset
+    domain_of:
+    - Dataset
+    range: string
+  data_collection_end:
+    name: data_collection_end
+    definition_uri: https://includedcc.org/include-access-model/data_collection_end
+    description: The date that data collection started. May include only a year.
+    title: Data Collection End
+    from_schema: https://includedcc.org/include-access-model
+    slot_uri: includedcc:data_collection_end
+    owner: Dataset
+    domain_of:
+    - Dataset
+    range: string
   Study_study_id:
     name: Study_study_id
     definition_uri: https://includedcc.org/include-access-model/study_id
@@ -2235,6 +2273,41 @@ slots:
     usage_slot_name: sample_id
     range: Sample
     multivalued: true
+  Dataset_dataset_id:
+    name: Dataset_dataset_id
+    definition_uri: https://includedcc.org/include-access-model/dataset_id
+    description: Unique identifier for a Dataset.
+    title: Dataset ID
+    from_schema: https://includedcc.org/include-access-model
+    is_a: dataset_id
+    domain: Dataset
+    slot_uri: includedcc:dataset_id
+    identifier: true
+    alias: dataset_id
+    owner: Dataset
+    domain_of:
+    - Dataset
+    is_usage_slot: true
+    usage_slot_name: dataset_id
+    range: string
+    required: true
+  Dataset_file_id:
+    name: Dataset_file_id
+    definition_uri: https://includedcc.org/include-access-model/file_id
+    description: The list of files comprising this dataset.
+    title: File ID
+    from_schema: https://includedcc.org/include-access-model
+    is_a: file_id
+    domain: Dataset
+    slot_uri: includedcc:file_id
+    alias: file_id
+    owner: Dataset
+    domain_of:
+    - Dataset
+    is_usage_slot: true
+    usage_slot_name: file_id
+    range: File
+    multivalued: true
 classes:
   Record:
     name: Record
@@ -2643,9 +2716,35 @@ classes:
     - hash_type
     - hash_value
     class_uri: includedcc:FileHash
+  Dataset:
+    name: Dataset
+    definition_uri: https://includedcc.org/include-access-model/Dataset
+    description: Set of files grouped together for release.
+    title: Dataset
+    from_schema: https://includedcc.org/include-access-model
+    slots:
+    - Dataset_dataset_id
+    - name
+    - description
+    - do_id
+    - Dataset_file_id
+    - publication
+    - data_collection_start
+    - data_collection_end
+    slot_usage:
+      dataset_id:
+        name: dataset_id
+        identifier: true
+        range: string
+        required: true
+      file_id:
+        name: file_id
+        description: The list of files comprising this dataset.
+        multivalued: true
+    class_uri: includedcc:Dataset
 metamodel_version: 1.7.0
 source_file: include_access_model.yaml
-source_file_date: '2026-03-09T16:30:20'
-source_file_size: 35097
-generation_date: '2026-03-09T16:31:10'
+source_file_date: '2026-03-12T10:52:04'
+source_file_size: 36264
+generation_date: '2026-03-12T10:53:07'
 
diff --git a/src/include_access_model/datamodel/include_access_model.py b/src/include_access_model/datamodel/include_access_model.py
@@ -1,5 +1,5 @@
 # Auto generated from include_access_model.yaml by pythongen.py version: 0.0.1
-# Generation date: 2026-03-09T16:30:56
+# Generation date: 2026-03-12T10:52:49
 # Schema: include-access-model
 #
 # id: https://includedcc.org/include-access-model
@@ -141,6 +141,10 @@ class FileFileId(extended_str):
     pass
 
 
+class DatasetDatasetId(extended_str):
+    pass
+
+
 @dataclass(repr=False)
 class Record(YAMLRoot):
     """
@@ -994,6 +998,59 @@ def __post_init__(self, *_: str, **kwargs: Any):
         super().__post_init__(**kwargs)
 
 
+@dataclass(repr=False)
+class Dataset(YAMLRoot):
+    """
+    Set of files grouped together for release.
+    """
+    _inherited_slots: ClassVar[list[str]] = []
+
+    class_class_uri: ClassVar[URIRef] = INCLUDEDCC["Dataset"]
+    class_class_curie: ClassVar[str] = "includedcc:Dataset"
+    class_name: ClassVar[str] = "Dataset"
+    class_model_uri: ClassVar[URIRef] = INCLUDEDCC.Dataset
+
+    dataset_id: Union[str, DatasetDatasetId] = None
+    name: Optional[str] = None
+    description: Optional[str] = None
+    do_id: Optional[Union[str, DOIDoId]] = None
+    file_id: Optional[Union[Union[str, FileFileId], list[Union[str, FileFileId]]]] = empty_list()
+    publication: Optional[Union[Union[dict, Publication], list[Union[dict, Publication]]]] = empty_list()
+    data_collection_start: Optional[str] = None
+    data_collection_end: Optional[str] = None
+
+    def __post_init__(self, *_: str, **kwargs: Any):
+        if self._is_empty(self.dataset_id):
+            self.MissingRequiredField("dataset_id")
+        if not isinstance(self.dataset_id, DatasetDatasetId):
+            self.dataset_id = DatasetDatasetId(self.dataset_id)
+
+        if self.name is not None and not isinstance(self.name, str):
+            self.name = str(self.name)
+
+        if self.description is not None and not isinstance(self.description, str):
+            self.description = str(self.description)
+
+        if self.do_id is not None and not isinstance(self.do_id, DOIDoId):
+            self.do_id = DOIDoId(self.do_id)
+
+        if not isinstance(self.file_id, list):
+            self.file_id = [self.file_id] if self.file_id is not None else []
+        self.file_id = [v if isinstance(v, FileFileId) else FileFileId(v) for v in self.file_id]
+
+        if not isinstance(self.publication, list):
+            self.publication = [self.publication] if self.publication is not None else []
+        self.publication = [v if isinstance(v, Publication) else Publication(**as_dict(v)) for v in self.publication]
+
+        if self.data_collection_start is not None and not isinstance(self.data_collection_start, str):
+            self.data_collection_start = str(self.data_collection_start)
+
+        if self.data_collection_end is not None and not isinstance(self.data_collection_end, str):
+            self.data_collection_end = str(self.data_collection_end)
+
+        super().__post_init__(**kwargs)
+
+
 # Enumerations
 class EnumProgram(EnumDefinitionImpl):
     """
@@ -1792,6 +1849,15 @@ class slots:
 slots.hash_value = Slot(uri=INCLUDEDCC.hash_value, name="hash_value", curie=INCLUDEDCC.curie('hash_value'),
                    model_uri=INCLUDEDCC.hash_value, domain=None, range=Optional[str])
 
+slots.dataset_id = Slot(uri=INCLUDEDCC.dataset_id, name="dataset_id", curie=INCLUDEDCC.curie('dataset_id'),
+                   model_uri=INCLUDEDCC.dataset_id, domain=None, range=Optional[Union[str, DatasetDatasetId]])
+
+slots.data_collection_start = Slot(uri=INCLUDEDCC.data_collection_start, name="data_collection_start", curie=INCLUDEDCC.curie('data_collection_start'),
+                   model_uri=INCLUDEDCC.data_collection_start, domain=None, range=Optional[str])
+
+slots.data_collection_end = Slot(uri=INCLUDEDCC.data_collection_end, name="data_collection_end", curie=INCLUDEDCC.curie('data_collection_end'),
+                   model_uri=INCLUDEDCC.data_collection_end, domain=None, range=Optional[str])
+
 slots.Study_study_id = Slot(uri=INCLUDEDCC.study_id, name="Study_study_id", curie=INCLUDEDCC.curie('study_id'),
                    model_uri=INCLUDEDCC.Study_study_id, domain=Study, range=Union[str, StudyStudyId])
 
@@ -1848,3 +1914,9 @@ class slots:
 
 slots.File_sample_id = Slot(uri=INCLUDEDCC.sample_id, name="File_sample_id", curie=INCLUDEDCC.curie('sample_id'),
                    model_uri=INCLUDEDCC.File_sample_id, domain=File, range=Optional[Union[Union[str, SampleSampleId], list[Union[str, SampleSampleId]]]])
+
+slots.Dataset_dataset_id = Slot(uri=INCLUDEDCC.dataset_id, name="Dataset_dataset_id", curie=INCLUDEDCC.curie('dataset_id'),
+                   model_uri=INCLUDEDCC.Dataset_dataset_id, domain=Dataset, range=Union[str, DatasetDatasetId])
+
+slots.Dataset_file_id = Slot(uri=INCLUDEDCC.file_id, name="Dataset_file_id", curie=INCLUDEDCC.curie('file_id'),
+                   model_uri=INCLUDEDCC.Dataset_file_id, domain=Dataset, range=Optional[Union[Union[str, FileFileId], list[Union[str, FileFileId]]]])