Mark unimplemented ontologies with subset (#134)

* Mark unimplemented ontologies with subset * Update XLSX generator
ghga-de · Aug 2, 2023 · aa382d3 · aa382d3
1 parent f17e0ec
commit aa382d3
Show file tree

Hide file tree

Showing 24 changed files with 162 additions and 8 deletions.
diff --git a/docs/schema_markdown/Biospecimen.md b/docs/schema_markdown/Biospecimen.md
@@ -37,6 +37,7 @@ URI: [GHGA:Biospecimen](https://w3id.org/GHGA/Biospecimen)
  * [Biospecimen➞isolation](Biospecimen_isolation.md)  <sub>0..1</sub>
      * Description: Method or device employed for collecting/isolating a biospecimen or a sample.
      * Range: [String](types/String.md)
+     * in subsets: (ontology)
  * [Biospecimen➞storage](Biospecimen_storage.md)  <sub>0..1</sub>
      * Description: Methods by which a biospecimen or a sample is stored (e.g. frozen in liquid nitrogen).
      * Range: [String](types/String.md)
@@ -51,6 +52,7 @@ URI: [GHGA:Biospecimen](https://w3id.org/GHGA/Biospecimen)
      * Range: [VitalStatusEnum](VitalStatusEnum.md)
  * [Biospecimen➞tissue](Biospecimen_tissue.md)  <sub>1..1</sub>
      * Range: [String](types/String.md)
+     * in subsets: (ontology)
 
 ### Mixed in from IdentifiedByAliasMixin:
 

diff --git a/docs/schema_markdown/Biospecimen_isolation.md b/docs/schema_markdown/Biospecimen_isolation.md
@@ -21,3 +21,10 @@ URI: [GHGA:Biospecimen_isolation](https://w3id.org/GHGA/Biospecimen_isolation)
 ## Used by
 
  * [Biospecimen](Biospecimen.md)
+
+## Other properties
+
+|  |  |  |
+| --- | --- | --- |
+| **In Subsets:** | | ontology |
+
diff --git a/docs/schema_markdown/Biospecimen_tissue.md b/docs/schema_markdown/Biospecimen_tissue.md
@@ -21,3 +21,10 @@ URI: [GHGA:Biospecimen_tissue](https://w3id.org/GHGA/Biospecimen_tissue)
 ## Used by
 
  * [Biospecimen](Biospecimen.md)
+
+## Other properties
+
+|  |  |  |
+| --- | --- | --- |
+| **In Subsets:** | | ontology |
+
diff --git a/docs/schema_markdown/Individual.md b/docs/schema_markdown/Individual.md
@@ -40,12 +40,15 @@ URI: [GHGA:Individual](https://w3id.org/GHGA/Individual)
  * [Individual➞geographical_region](Individual_geographical_region.md)  <sub>0..1</sub>
      * Description: The geographical region where the Individual is located. Any demarcated area of the Earth; may be determined by both natural and human boundaries.
      * Range: [String](types/String.md)
+     * in subsets: (ontology)
  * [Individual➞ancestries](Individual_ancestries.md)  <sub>0..\*</sub>
      * Description: A person's descent or lineage, from a person or from a population.
      * Range: [String](types/String.md)
+     * in subsets: (ontology)
  * [Individual➞phenotypic_features](Individual_phenotypic_features.md)  <sub>0..\*</sub>
      * Description: The Phenotypic Feature entity that is associated with this Biospecimen at the time of retrieval from the organism. Typically, a concept from Human Phenotype Ontology. For example, 'HP:0100244' indicates that the Individual - from_which_the_Biospecimen was extracted from - exhibits_'Fibrosarcoma'_as_one_of_its_phenotype.
      * Range: [String](types/String.md)
+     * in subsets: (ontology)
 
 ### Mixed in from IdentifiedByAliasMixin:
 

diff --git a/docs/schema_markdown/Individual_ancestries.md b/docs/schema_markdown/Individual_ancestries.md
@@ -21,3 +21,10 @@ URI: [GHGA:Individual_ancestries](https://w3id.org/GHGA/Individual_ancestries)
 ## Used by
 
  * [Individual](Individual.md)
+
+## Other properties
+
+|  |  |  |
+| --- | --- | --- |
+| **In Subsets:** | | ontology |
+
diff --git a/docs/schema_markdown/Individual_geographical_region.md b/docs/schema_markdown/Individual_geographical_region.md
@@ -21,3 +21,10 @@ URI: [GHGA:Individual_geographical_region](https://w3id.org/GHGA/Individual_geog
 ## Used by
 
  * [Individual](Individual.md)
+
+## Other properties
+
+|  |  |  |
+| --- | --- | --- |
+| **In Subsets:** | | ontology |
+
diff --git a/docs/schema_markdown/Individual_phenotypic_features.md b/docs/schema_markdown/Individual_phenotypic_features.md
@@ -21,3 +21,10 @@ URI: [GHGA:Individual_phenotypic_features](https://w3id.org/GHGA/Individual_phen
 ## Used by
 
  * [Individual](Individual.md)
+
+## Other properties
+
+|  |  |  |
+| --- | --- | --- |
+| **In Subsets:** | | ontology |
+
diff --git a/docs/schema_markdown/Ontology.md b/docs/schema_markdown/Ontology.md
@@ -0,0 +1,35 @@
+
+# Subset: ontology
+
+
+This slot is part of an ontology which is currently not otherwise encoded in the schema.
+
+URI: [GHGA:ontology](https://w3id.org/GHGA/ontology)
+
+
+### Classes
+
+
+### Mixins
+
+
+### Slots
+
+ * [Biospecimen➞isolation](Biospecimen_isolation.md)
+ * [Biospecimen➞tissue](Biospecimen_tissue.md)
+ * [Individual➞ancestries](Individual_ancestries.md)
+ * [Individual➞geographical_region](Individual_geographical_region.md)
+ * [Individual➞phenotypic_features](Individual_phenotypic_features.md) - The Phenotypic Feature entity that is associated with this Biospecimen at the time of retrieval from the organism. Typically, a concept from Human Phenotype Ontology. For example, 'HP:0100244' indicates that the Individual - from_which_the_Biospecimen was extracted from - exhibits_'Fibrosarcoma'_as_one_of_its_phenotype.
+ * [Sample➞isolation](Sample_isolation.md)
+ * [Sample➞type](Sample_type.md) - The type of sample.
+ * [ancestries](ancestries.md) - A person's descent or lineage, from a person or from a population.
+ * [geographical_region](geographical_region.md) - The geographical region where the Individual is located. Any demarcated area of the Earth; may be determined by both natural and human boundaries.
+ * [isolation](isolation.md) - Method or device employed for collecting/isolating a biospecimen or a sample.
+ * [phenotypic_features](phenotypic_features.md) - Phenotypic feature concepts that the entity is associated with.
+ * [tissue](tissue.md)
+
+### Types
+
+
+### Enums
+
diff --git a/docs/schema_markdown/Sample.md b/docs/schema_markdown/Sample.md
@@ -33,12 +33,14 @@ URI: [GHGA:Sample](https://w3id.org/GHGA/Sample)
  * [Sample➞type](Sample_type.md)  <sub>0..1</sub>
      * Description: The type of sample.
      * Range: [SampleTypeEnum](SampleTypeEnum.md)
+     * in subsets: (ontology)
  * [Sample➞description](Sample_description.md)  <sub>1..1</sub>
      * Description: Short textual description of the sample (How the sample was collected, sample source, Protocol followed for processing the sample etc).
      * Range: [String](types/String.md)
  * [Sample➞isolation](Sample_isolation.md)  <sub>0..1</sub>
      * Description: Method or device employed for collecting/isolating a biospecimen or a sample.
      * Range: [String](types/String.md)
+     * in subsets: (ontology)
  * [Sample➞storage](Sample_storage.md)  <sub>0..1</sub>
      * Description: Methods by which a biospecimen or a sample is stored (e.g. frozen in liquid nitrogen).
      * Range: [String](types/String.md)

diff --git a/docs/schema_markdown/Sample_isolation.md b/docs/schema_markdown/Sample_isolation.md
@@ -21,3 +21,10 @@ URI: [GHGA:Sample_isolation](https://w3id.org/GHGA/Sample_isolation)
 ## Used by
 
  * [Sample](Sample.md)
+
+## Other properties
+
+|  |  |  |
+| --- | --- | --- |
+| **In Subsets:** | | ontology |
+
diff --git a/docs/schema_markdown/Sample_type.md b/docs/schema_markdown/Sample_type.md
@@ -21,3 +21,10 @@ URI: [GHGA:Sample_type](https://w3id.org/GHGA/Sample_type)
 ## Used by
 
  * [Sample](Sample.md)
+
+## Other properties
+
+|  |  |  |
+| --- | --- | --- |
+| **In Subsets:** | | ontology |
+
diff --git a/docs/schema_markdown/ancestries.md b/docs/schema_markdown/ancestries.md
@@ -20,3 +20,10 @@ None &#8594;  <sub>0..\*</sub> [String](types/String.md)
 
 ## Used by
 
+
+## Other properties
+
+|  |  |  |
+| --- | --- | --- |
+| **In Subsets:** | | ontology |
+
diff --git a/docs/schema_markdown/geographical_region.md b/docs/schema_markdown/geographical_region.md
@@ -20,3 +20,10 @@ None &#8594;  <sub>0..1</sub> [String](types/String.md)
 
 ## Used by
 
+
+## Other properties
+
+|  |  |  |
+| --- | --- | --- |
+| **In Subsets:** | | ontology |
+
diff --git a/docs/schema_markdown/index.md b/docs/schema_markdown/index.md
@@ -4,7 +4,7 @@
 
 **metamodel version:** 1.7.0
 
-**version:** 1.0.1
+**version:** 1.1.0
 
 
 The submission centric metadata schema for the German Human Genome-Phenome Archive (GHGA).
@@ -340,6 +340,7 @@ The submission centric metadata schema for the German Human Genome-Phenome Archi
 
 ### Subsets
 
+ * [Ontology](Ontology.md) - This slot is part of an ontology which is currently not otherwise encoded in the schema.
 
 ### Types
 

diff --git a/docs/schema_markdown/isolation.md b/docs/schema_markdown/isolation.md
@@ -21,3 +21,10 @@ None &#8594;  <sub>0..1</sub> [String](types/String.md)
 
 ## Used by
 
+
+## Other properties
+
+|  |  |  |
+| --- | --- | --- |
+| **In Subsets:** | | ontology |
+
diff --git a/docs/schema_markdown/phenotypic_features.md b/docs/schema_markdown/phenotypic_features.md
@@ -20,3 +20,10 @@ None &#8594;  <sub>0..\*</sub> [String](types/String.md)
 
 ## Used by
 
+
+## Other properties
+
+|  |  |  |
+| --- | --- | --- |
+| **In Subsets:** | | ontology |
+
diff --git a/docs/schema_markdown/tissue.md b/docs/schema_markdown/tissue.md
@@ -20,3 +20,10 @@ None &#8594;  <sub>0..1</sub> [String](types/String.md)
 
 ## Used by
 
+
+## Other properties
+
+|  |  |  |
+| --- | --- | --- |
+| **In Subsets:** | | ontology |
+
diff --git a/scripts/generate_xlsx.py b/scripts/generate_xlsx.py
@@ -95,10 +95,24 @@ def mv_help(self) -> str:
         """The multiple values help text"""
         return "multiple values" if self.slot_def.multivalued else "single value"
 
+    def in_ontology_subset(self, slot_def: SlotDefinition) -> bool:
+        """Returns a bool indicating whether or not the given slot is marked as
+        non-implemented ontology slot."""
+        SUBSET_NAME="ontology"
+        in_subset_usage = slot_def.in_subset
+        in_subset_root = self.schema.get_slot(slot_def.name).in_subset
+        return (
+            isinstance(in_subset_usage, list) and SUBSET_NAME in in_subset_usage or 
+            isinstance(in_subset_root, list) and SUBSET_NAME in in_subset_root or 
+            in_subset_usage == SUBSET_NAME or
+            in_subset_root == SUBSET_NAME
+        )
+
+
     @property
     def restriction_help(self) -> str:
         """The restriction help text"""
-        if self.enum_name or self.slot_def.pattern:
+        if self.enum_name or self.slot_def.pattern or self.in_ontology_subset(self.slot_def):
             return "controlled vocabulary"
         elif self.cls_name:
             id_slot = self.schema.get_identifier_slot(self.cls_name)

diff --git a/spreadsheets/ghga_submission_full.xlsx b/spreadsheets/ghga_submission_full.xlsx
diff --git a/spreadsheets/ghga_submission_individual.xlsx b/spreadsheets/ghga_submission_individual.xlsx
diff --git a/spreadsheets/ghga_submission_minimal.xlsx b/spreadsheets/ghga_submission_minimal.xlsx
diff --git a/spreadsheets/ghga_submission_sample.xlsx b/spreadsheets/ghga_submission_sample.xlsx
diff --git a/spreadsheets/ghga_submission_seq.xlsx b/spreadsheets/ghga_submission_seq.xlsx
diff --git a/src/schema/submission.yaml b/src/schema/submission.yaml
@@ -2,7 +2,7 @@ id: https://w3id.org/GHGA-Submission-Metadata-Schema
 name: GHGA-Submission-Metadata-Schema
 description: >-
   The submission centric metadata schema for the German Human Genome-Phenome Archive (GHGA).
-version: 1.0.1
+version: 1.1.0
 imports:
   - linkml:types
 
@@ -437,6 +437,8 @@ classes:
         description: >-
           The type of sample.
         range: SampleTypeEnum
+        in_subset:
+          - ontology
         required: false
       description:
         description: >-
@@ -1053,7 +1055,8 @@ slots:
 
   phenotypic_features:
     description: Phenotypic feature concepts that the entity is associated with.
-    pattern: .*
+    in_subset:
+      - ontology
     # range: PhenotypicFeaturesEnum
     multivalued: true
 
@@ -1072,7 +1075,8 @@ slots:
   ancestries:
     description: >-
       A person's descent or lineage, from a person or from a population.
-    pattern: HANCESTRO:.*
+    in_subset:
+      - ontology
     # range: AncestryEnum
     multivalued: true
 
@@ -1353,7 +1357,8 @@ slots:
   isolation:
     description: >-
       Method or device employed for collecting/isolating a biospecimen or a sample.
-    pattern: SNOMED:.*
+    in_subset:
+      - ontology
     # range: IsolationEnum
 
   storage:
@@ -1385,7 +1390,8 @@ slots:
     description: >-
       The geographical region where the Individual is located.
       Any demarcated area of the Earth; may be determined by both natural and human boundaries.
-    pattern: HANCESTRO:.*
+    in_subset:
+      - ontology
     # range: GeographicalRegionEnum
 
   vital_status:
@@ -1471,14 +1477,21 @@ slots:
       DOI identifier of a publication.
 
   tissue:
-    pattern: BTO:.*
+    in_subset:
+      - ontology
     # range: TissueEnum
 
   trios:
     description: The Trios associated with an entity.
     range: Trio
     multivalued: true
 
+subsets:
+  ontology:
+    description: >-
+      This slot is part of an ontology which is currently not otherwise encoded
+      in the schema.
+
 enums:
   DataUseModifierEnum:
     description: Permitted values for data use modifier