11.3.0rc1

Author: pkalita-lbl

nmdc_schema/nmdc-pydantic.py

@@ -2226,14 +2226,17 @@ class StatusEnum(str, Enum):
     fail = "fail"
 
 
-class AnalyteCategoryEnum(str, Enum):
-    metagenome = "metagenome"
-    metatranscriptome = "metatranscriptome"
-    metaproteome = "metaproteome"
-    metabolome = "metabolome"
-    lipidome = "lipidome"
-    nom = "nom"
-    amplicon_sequencing_assay = "amplicon_sequencing_assay"
+class NucleotideSequencingEnum(str, Enum):
+    Metagenome = "metagenome"
+    Metatranscriptome = "metatranscriptome"
+    Amplicon = "amplicon_sequencing_assay"
+
+
+class MassSpectrometryEnum(str, Enum):
+    Metaproteome = "metaproteome"
+    Metabolome = "metabolome"
+    Lipidome = "lipidome"
+    Natural_Organic_Matter = "nom"
 
 
 class ExtractionTargetEnum(str, Enum):
@@ -10532,7 +10535,7 @@ class Biosample(Sample):
          'comments': ['Time should be entered as HH:MM(:SS) in GMT. See here for a '
                       'converter: https://www.worldtimebuddy.com/pst-to-gmt-converter'],
          'domain_of': ['Biosample'],
-         'examples': [{'value': '813'}, {'value': '48835'}],
+         'examples': [{'value': '13:33'}, {'value': '13:33:55'}],
          'notes': ['MIxS collection_date accepts (truncated) ISO8601. DH taking '
                    'seconds optional time only'],
          'rank': 1,
@@ -10544,7 +10547,7 @@ class Biosample(Sample):
          'comments': ['Time should be entered as HH:MM(:SS) in GMT. See here for a '
                       'converter: https://www.worldtimebuddy.com/pst-to-gmt-converter'],
          'domain_of': ['Biosample'],
-         'examples': [{'value': '813'}, {'value': '48835'}],
+         'examples': [{'value': '13:33'}, {'value': '13:33:55'}],
          'notes': ['MIxS collection_date accepts (truncated) ISO8601. DH taking '
                    'seconds optional time only'],
          'rank': 3,
@@ -10674,7 +10677,7 @@ class Biosample(Sample):
          'comments': ['Time should be entered as HH:MM(:SS) in GMT. See here for a '
                       'converter: https://www.worldtimebuddy.com/pst-to-gmt-converter'],
          'domain_of': ['Biosample'],
-         'examples': [{'value': '813'}, {'value': '48835'}],
+         'examples': [{'value': '13:33'}, {'value': '13:33:55'}],
          'notes': ['MIxS collection_date accepts (truncated) ISO8601. DH taking '
                    'seconds optional time only'],
          'rank': 5,
@@ -15215,7 +15218,7 @@ class DataGeneration(PlannedProcess):
                                                               'syntax': '{id_nmdc_prefix}:(dobj)-{id_shoulder}-{id_blade}$'}}}})
 
     add_date: Optional[str] = Field(None, description="""The date on which the information was added to the database.""", json_schema_extra = { "linkml_meta": {'alias': 'add_date', 'domain_of': ['Biosample', 'DataGeneration']} })
-    analyte_category: AnalyteCategoryEnum = Field(..., description="""The type of analyte(s) that were measured in the data generation process and analyzed
+    analyte_category: str = Field(..., description="""The type of analyte(s) that were measured in the data generation process and analyzed
   in the Workflow Chain
 """, json_schema_extra = { "linkml_meta": {'alias': 'analyte_category', 'domain_of': ['DataGeneration']} })
     associated_studies: List[str] = Field(..., description="""The study associated with a resource.""", json_schema_extra = { "linkml_meta": {'alias': 'associated_studies',
@@ -15368,7 +15371,9 @@ class NucleotideSequencing(DataGeneration):
          'comments': ['For example data generated from an Illumina or Pacific '
                       'Biosciences instrument.'],
          'from_schema': 'https://w3id.org/nmdc/nmdc',
-         'slot_usage': {'id': {'name': 'id',
+         'slot_usage': {'analyte_category': {'name': 'analyte_category',
+                                             'range': 'NucleotideSequencingEnum'},
+                        'id': {'name': 'id',
                                'pattern': '^(nmdc):(dgns|omprc)-([0-9][a-z]{0,6}[0-9])-([A-Za-z0-9]{1,})$',
                                'structured_pattern': {'interpolated': True,
                                                       'syntax': '{id_nmdc_prefix}:(dgns|omprc)-{id_shoulder}-{id_blade}$'}}}})
@@ -15414,7 +15419,7 @@ class NucleotideSequencing(DataGeneration):
          'slot_uri': 'MIXS:0000045',
          'string_serialization': '{text}'} })
     add_date: Optional[str] = Field(None, description="""The date on which the information was added to the database.""", json_schema_extra = { "linkml_meta": {'alias': 'add_date', 'domain_of': ['Biosample', 'DataGeneration']} })
-    analyte_category: AnalyteCategoryEnum = Field(..., description="""The type of analyte(s) that were measured in the data generation process and analyzed
+    analyte_category: NucleotideSequencingEnum = Field(..., description="""The type of analyte(s) that were measured in the data generation process and analyzed
   in the Workflow Chain
 """, json_schema_extra = { "linkml_meta": {'alias': 'analyte_category', 'domain_of': ['DataGeneration']} })
     associated_studies: List[str] = Field(..., description="""The study associated with a resource.""", json_schema_extra = { "linkml_meta": {'alias': 'associated_studies',
@@ -15621,7 +15626,9 @@ class MassSpectrometry(DataGeneration):
                                                                                                       {'equals_string': 'gas_chromatography'}],
                                                                                            'name': 'eluent_introduction_category'}}},
                     'title': 'has_chromatography_configuration_required_if_lc_or_gc'}],
-         'slot_usage': {'has_chromatography_configuration': {'name': 'has_chromatography_configuration',
+         'slot_usage': {'analyte_category': {'name': 'analyte_category',
+                                             'range': 'MassSpectrometryEnum'},
+                        'has_chromatography_configuration': {'name': 'has_chromatography_configuration',
                                                              'pattern': '^(nmdc):chrcon-([0-9][a-z]{0,6}[0-9])-([A-Za-z0-9]{1,})$',
                                                              'structured_pattern': {'interpolated': True,
                                                                                     'syntax': '{id_nmdc_prefix}:chrcon-{id_shoulder}-{id_blade}$'}},
@@ -15653,7 +15660,7 @@ class MassSpectrometry(DataGeneration):
          'structured_pattern': {'interpolated': True,
                                 'syntax': '{id_nmdc_prefix}:mscon-{id_shoulder}-{id_blade}$'}} })
     add_date: Optional[str] = Field(None, description="""The date on which the information was added to the database.""", json_schema_extra = { "linkml_meta": {'alias': 'add_date', 'domain_of': ['Biosample', 'DataGeneration']} })
-    analyte_category: AnalyteCategoryEnum = Field(..., description="""The type of analyte(s) that were measured in the data generation process and analyzed
+    analyte_category: MassSpectrometryEnum = Field(..., description="""The type of analyte(s) that were measured in the data generation process and analyzed
   in the Workflow Chain
 """, json_schema_extra = { "linkml_meta": {'alias': 'analyte_category', 'domain_of': ['DataGeneration']} })
     associated_studies: List[str] = Field(..., description="""The study associated with a resource.""", json_schema_extra = { "linkml_meta": {'alias': 'associated_studies',

nmdc_schema/nmdc.py

@@ -1,5 +1,5 @@
 # Auto generated from nmdc.yaml by pythongen.py version: 0.0.1
-# Generation date: 2024-12-07T20:12:39
+# Generation date: 2025-01-08T12:52:37
 # Schema: NMDC
 #
 # id: https://w3id.org/nmdc/nmdc
@@ -5626,7 +5626,7 @@ class DataGeneration(PlannedProcess):
 
     id: Union[str, DataGenerationId] = None
     type: Union[str, URIorCURIE] = None
-    analyte_category: Union[str, "AnalyteCategoryEnum"] = None
+    analyte_category: str = None
     associated_studies: Union[Union[str, StudyId], List[Union[str, StudyId]]] = None
     has_input: Union[Union[str, SampleId], List[Union[str, SampleId]]] = None
     add_date: Optional[str] = None
@@ -5638,8 +5638,8 @@ class DataGeneration(PlannedProcess):
     def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
         if self._is_empty(self.analyte_category):
             self.MissingRequiredField("analyte_category")
-        if not isinstance(self.analyte_category, AnalyteCategoryEnum):
-            self.analyte_category = AnalyteCategoryEnum(self.analyte_category)
+        if not isinstance(self.analyte_category, str):
+            self.analyte_category = str(self.analyte_category)
 
         if self._is_empty(self.associated_studies):
             self.MissingRequiredField("associated_studies")
@@ -5690,9 +5690,9 @@ class NucleotideSequencing(DataGeneration):
 
     id: Union[str, NucleotideSequencingId] = None
     type: Union[str, URIorCURIE] = None
-    analyte_category: Union[str, "AnalyteCategoryEnum"] = None
     associated_studies: Union[Union[str, StudyId], List[Union[str, StudyId]]] = None
     has_input: Union[Union[str, SampleId], List[Union[str, SampleId]]] = None
+    analyte_category: Union[str, "NucleotideSequencingEnum"] = None
     gold_sequencing_project_identifiers: Optional[Union[Union[str, ExternalIdentifier], List[Union[str, ExternalIdentifier]]]] = empty_list()
     insdc_bioproject_identifiers: Optional[Union[Union[str, ExternalIdentifier], List[Union[str, ExternalIdentifier]]]] = empty_list()
     insdc_experiment_identifiers: Optional[Union[Union[str, ExternalIdentifier], List[Union[str, ExternalIdentifier]]]] = empty_list()
@@ -5706,6 +5706,11 @@ def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
         if not isinstance(self.id, NucleotideSequencingId):
             self.id = NucleotideSequencingId(self.id)
 
+        if self._is_empty(self.analyte_category):
+            self.MissingRequiredField("analyte_category")
+        if not isinstance(self.analyte_category, NucleotideSequencingEnum):
+            self.analyte_category = NucleotideSequencingEnum(self.analyte_category)
+
         if not isinstance(self.gold_sequencing_project_identifiers, list):
             self.gold_sequencing_project_identifiers = [self.gold_sequencing_project_identifiers] if self.gold_sequencing_project_identifiers is not None else []
         self.gold_sequencing_project_identifiers = [v if isinstance(v, ExternalIdentifier) else ExternalIdentifier(v) for v in self.gold_sequencing_project_identifiers]
@@ -5748,9 +5753,9 @@ class MassSpectrometry(DataGeneration):
 
     id: Union[str, MassSpectrometryId] = None
     type: Union[str, URIorCURIE] = None
-    analyte_category: Union[str, "AnalyteCategoryEnum"] = None
     associated_studies: Union[Union[str, StudyId], List[Union[str, StudyId]]] = None
     has_input: Union[Union[str, SampleId], List[Union[str, SampleId]]] = None
+    analyte_category: Union[str, "MassSpectrometryEnum"] = None
     eluent_introduction_category: Optional[Union[str, "EluentIntroductionCategoryEnum"]] = None
     generates_calibration: Optional[Union[str, CalibrationInformationId]] = None
     has_chromatography_configuration: Optional[Union[str, ChromatographyConfigurationId]] = None
@@ -5762,6 +5767,11 @@ def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
         if not isinstance(self.id, MassSpectrometryId):
             self.id = MassSpectrometryId(self.id)
 
+        if self._is_empty(self.analyte_category):
+            self.MissingRequiredField("analyte_category")
+        if not isinstance(self.analyte_category, MassSpectrometryEnum):
+            self.analyte_category = MassSpectrometryEnum(self.analyte_category)
+
         if self.eluent_introduction_category is not None and not isinstance(self.eluent_introduction_category, EluentIntroductionCategoryEnum):
             self.eluent_introduction_category = EluentIntroductionCategoryEnum(self.eluent_introduction_category)
 
@@ -7713,20 +7723,27 @@ def _addvals(cls):
         setattr(cls, "pass",
             PermissibleValue(text="pass"))
 
-class AnalyteCategoryEnum(EnumDefinitionImpl):
+class NucleotideSequencingEnum(EnumDefinitionImpl):
 
     metagenome = PermissibleValue(text="metagenome")
     metatranscriptome = PermissibleValue(text="metatranscriptome")
+    amplicon_sequencing_assay = PermissibleValue(
+        text="amplicon_sequencing_assay",
+        meaning=OBI["0002767"])
+
+    _defn = EnumDefinition(
+        name="NucleotideSequencingEnum",
+    )
+
+class MassSpectrometryEnum(EnumDefinitionImpl):
+
     metaproteome = PermissibleValue(text="metaproteome")
     metabolome = PermissibleValue(text="metabolome")
     lipidome = PermissibleValue(text="lipidome")
     nom = PermissibleValue(text="nom")
-    amplicon_sequencing_assay = PermissibleValue(
-        text="amplicon_sequencing_assay",
-        meaning=OBI["0002767"])
 
     _defn = EnumDefinition(
-        name="AnalyteCategoryEnum",
+        name="MassSpectrometryEnum",
     )
 
 class ExtractionTargetEnum(EnumDefinitionImpl):
@@ -10854,7 +10871,7 @@ class slots:
                    model_uri=NMDC.file_size_bytes, domain=None, range=Optional[int])
 
 slots.analyte_category = Slot(uri=NMDC.analyte_category, name="analyte_category", curie=NMDC.curie('analyte_category'),
-                   model_uri=NMDC.analyte_category, domain=None, range=Union[str, "AnalyteCategoryEnum"])
+                   model_uri=NMDC.analyte_category, domain=None, range=str)
 
 slots.type = Slot(uri=RDF.type, name="type", curie=RDF.curie('type'),
                    model_uri=NMDC.type, domain=None, range=Union[str, URIorCURIE])
@@ -12534,6 +12551,9 @@ class slots:
                    model_uri=NMDC.NucleotideSequencing_id, domain=NucleotideSequencing, range=Union[str, NucleotideSequencingId],
                    pattern=re.compile(r'^[a-zA-Z0-9][a-zA-Z0-9_\.]+:[a-zA-Z0-9_][a-zA-Z0-9_\-\/\.,]*$'))
 
+slots.NucleotideSequencing_analyte_category = Slot(uri=NMDC.analyte_category, name="NucleotideSequencing_analyte_category", curie=NMDC.curie('analyte_category'),
+                   model_uri=NMDC.NucleotideSequencing_analyte_category, domain=NucleotideSequencing, range=Union[str, "NucleotideSequencingEnum"])
+
 slots.MassSpectrometry_id = Slot(uri=NMDC.id, name="MassSpectrometry_id", curie=NMDC.curie('id'),
                    model_uri=NMDC.MassSpectrometry_id, domain=MassSpectrometry, range=Union[str, MassSpectrometryId],
                    pattern=re.compile(r'^[a-zA-Z0-9][a-zA-Z0-9_\.]+:[a-zA-Z0-9_][a-zA-Z0-9_\-\/\.,]*$'))
@@ -12544,6 +12564,9 @@ class slots:
 slots.MassSpectrometry_has_mass_spectrometry_configuration = Slot(uri=NMDC.has_mass_spectrometry_configuration, name="MassSpectrometry_has_mass_spectrometry_configuration", curie=NMDC.curie('has_mass_spectrometry_configuration'),
                    model_uri=NMDC.MassSpectrometry_has_mass_spectrometry_configuration, domain=MassSpectrometry, range=Optional[Union[str, MassSpectrometryConfigurationId]])
 
+slots.MassSpectrometry_analyte_category = Slot(uri=NMDC.analyte_category, name="MassSpectrometry_analyte_category", curie=NMDC.curie('analyte_category'),
+                   model_uri=NMDC.MassSpectrometry_analyte_category, domain=MassSpectrometry, range=Union[str, "MassSpectrometryEnum"])
+
 slots.MassSpectrometryConfiguration_name = Slot(uri=NMDC.name, name="MassSpectrometryConfiguration_name", curie=NMDC.curie('name'),
                    model_uri=NMDC.MassSpectrometryConfiguration_name, domain=MassSpectrometryConfiguration, range=str)
 

nmdc_schema/nmdc.schema.json

@@ -15,20 +15,6 @@
             "title": "AnalysisTypeEnum",
             "type": "string"
         },
-        "AnalyteCategoryEnum": {
-            "description": "",
-            "enum": [
-                "metagenome",
-                "metatranscriptome",
-                "metaproteome",
-                "metabolome",
-                "lipidome",
-                "nom",
-                "amplicon_sequencing_assay"
-            ],
-            "title": "AnalyteCategoryEnum",
-            "type": "string"
-        },
         "ArchStrucEnum": {
             "description": "",
             "enum": [
@@ -9750,7 +9736,7 @@
                     ]
                 },
                 "analyte_category": {
-                    "$ref": "#/$defs/AnalyteCategoryEnum",
+                    "$ref": "#/$defs/MassSpectrometryEnum",
                     "description": "The type of analyte(s) that were measured in the data generation process and analyzed\n  in the Workflow Chain\n"
                 },
                 "associated_studies": {
@@ -10012,6 +9998,17 @@
             "title": "MassSpectrometryConfiguration",
             "type": "object"
         },
+        "MassSpectrometryEnum": {
+            "description": "",
+            "enum": [
+                "metaproteome",
+                "metabolome",
+                "lipidome",
+                "nom"
+            ],
+            "title": "MassSpectrometryEnum",
+            "type": "string"
+        },
         "MassSpectrumCollectionModeEnum": {
             "description": "",
             "enum": [
@@ -12479,7 +12476,7 @@
                     ]
                 },
                 "analyte_category": {
-                    "$ref": "#/$defs/AnalyteCategoryEnum",
+                    "$ref": "#/$defs/NucleotideSequencingEnum",
                     "description": "The type of analyte(s) that were measured in the data generation process and analyzed\n  in the Workflow Chain\n"
                 },
                 "associated_studies": {
@@ -12672,6 +12669,16 @@
             "title": "NucleotideSequencing",
             "type": "object"
         },
+        "NucleotideSequencingEnum": {
+            "description": "",
+            "enum": [
+                "metagenome",
+                "metatranscriptome",
+                "amplicon_sequencing_assay"
+            ],
+            "title": "NucleotideSequencingEnum",
+            "type": "string"
+        },
         "OccupDocumentEnum": {
             "description": "",
             "enum": [