Merge branch 'staging' of github.com:HumanCellAtlas/metadata-schema i…

…nto ac-tissue-dissociation-Issue1592

changelog.md

@@ -9,6 +9,14 @@ and (starting with v4.0.0) this project adheres to [Semantic Versioning](http://
 
 ## [Released](https://github.com/HumanCellAtlas/metadata-schema/)
 
+### [type/biomaterial/donor_organism.json - v17.1.0] - 2024-12-11
+### Added
+Added non-required gender identity field.
+
+### [module/ontology/gender_identity_ontology.json - v1.0.0] - 2024-12-11
+### Added
+Added ontology module for gender identity.
+
 ### [module/biomaterial/medical_history.json - v7.0.0] - 2024-11-06
 ### Changed
 Changed medication field type Fix#1589

docs/jsonBrowser/module.md

@@ -170,6 +170,17 @@ text | The name of a process type being used. | string | yes |  | Process type |
 ontology | An ontology term identifier in the form prefix:accession. | string | no |  | Process type ontology ID |  | EFO:0009128; EFO:0009121
 ontology_label | The preferred label for the ontology term referred to in the ontology field. This may differ from the user-supplied value in the text field. | string | no |  | Process type ontology label |  | enzymatic dissociation; blood draw
 
+## Gender identity ontology<a name='Gender identity ontology'></a>
+_A term that may be associated with a gender-related ontology term._
+
+Location: module/ontology/gender_identity_ontology.json
+
+Property name | Description | Type | Required? | Object reference? | User friendly name | Allowed values | Example 
+--- | --- | --- | --- | --- | --- | --- | --- 
+text | The gender identity of the human donor at the time of the experiment. | string | yes |  | Gender identity |  | Female Gender; Agender; Non-Binary Gender
+ontology | An ontology term identifier in the form prefix:accession. | string | no |  | Gender identity ontology ID |  | NCIT:C46110; NCIT:C205469; NCIT:C160941
+ontology_label | The preferred label for the ontology term referred to in the ontology field. This may differ from the user-supplied value in the text field. | string | no |  | Gender identity ontology label |  | Female Gender; Agender; Non-Binary Gender
+
 ## Sequencing ontology<a name='Sequencing ontology'></a>
 _A term that may be associated with a process-related ontology term._
 

docs/jsonBrowser/required_fields.md

@@ -264,6 +264,10 @@ text | The name of a library construction approach being used. | string |  | Lib
 Property name | Description | Type | Object reference? | User friendly name | Allowed values | Example 
 --- | --- | --- | --- | --- | --- | --- 
 text | The name of a process type being used. | string |  | Process type |  | enzymatic dissociation; blood draw
+### Gender identity ontology<a name='Gender identity ontology'></a>
+Property name | Description | Type | Object reference? | User friendly name | Allowed values | Example 
+--- | --- | --- | --- | --- | --- | --- 
+text | The gender identity of the human donor at the time of the experiment. | string |  | Gender identity |  | Female Gender; Agender; Non-Binary Gender
 ### Sequencing ontology<a name='Sequencing ontology'></a>
 Property name | Description | Type | Object reference? | User friendly name | Allowed values | Example 
 --- | --- | --- | --- | --- | --- | --- 

docs/jsonBrowser/type.md

@@ -447,6 +447,7 @@ height | Height of organism in Height unit. | string | no |  | Height |  | 160;
 height_unit | The unit in which Height is expressed. | object | no | [See module  length_unit_ontology](module.md#length-unit-ontology) | Height unit |  | 
 weight | Weight of organism in Weight unit. | string | no |  | Weight |  | 60; 40-60
 weight_unit | The unit in which Weight is expressed. | object | no | [See module  mass_unit_ontology](module.md#mass-unit-ontology) | Weight unit |  | 
+gender_identity | The donor's personal sense of their own gender at the time of the experiment. | object | no | [See module  gender_identity_ontology](module.md#gender-identity-ontology) | Gender identity |  | 
 
 ## Organoid
 _Information about an organoid biomaterial._

json_schema/module/ontology/gender_identity_ontology.json

@@ -0,0 +1,49 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "description": "A term that may be associated with a gender-related ontology term.",
+  "additionalProperties": false,
+  "required": [
+    "text"
+  ],
+  "title": "Gender identity ontology",
+  "name": "gender_identity_ontology",
+  "type": "object",
+  "properties": {
+    "describedBy" : {
+      "description": "The URL reference to the schema.",
+      "pattern" : "^(http|https)://schema.(.*?)humancellatlas.org/module/ontology/(([0-9]{1,}.[0-9]{1,}.[0-9]{1,})|([a-zA-Z]*?))/gender_identity_ontology",
+      "type": "string"
+    },
+    "schema_version": {
+      "description": "Version number in major.minor.patch format.",
+      "type": "string",
+      "pattern": "^[0-9]{1,}.[0-9]{1,}.[0-9]{1,}$",
+      "example": "4.6.1"
+    },
+    "text": {
+      "description": "The gender identity of the human donor at the time of the experiment.",
+      "type": "string",
+      "user_friendly": "Gender identity",
+      "example": "Female Gender; Agender; Non-Binary Gender"
+    },
+    "ontology": {
+      "description": "An ontology term identifier in the form prefix:accession.",
+      "type": "string",
+      "graph_restriction":  {
+        "ontologies" : ["obo:ncit"],
+        "classes": ["NCIT:C17357"],
+        "relations": ["rdfs:subClassOf"],
+        "direct": false,
+        "include_self": false
+      },
+      "user_friendly": "Gender identity ontology ID",
+      "example": "NCIT:C46110; NCIT:C205469; NCIT:C160941"
+    },
+    "ontology_label": {
+      "description": "The preferred label for the ontology term referred to in the ontology field. This may differ from the user-supplied value in the text field.",
+      "type": "string",
+      "user_friendly": "Gender identity ontology label",
+      "example": "Female Gender; Agender; Non-Binary Gender"
+    }
+  }
+}

json_schema/type/biomaterial/donor_organism.json

@@ -199,6 +199,12 @@
             "type": "object",
             "$ref": "module/ontology/mass_unit_ontology.json",
             "user_friendly": "Weight unit"
+        },
+        "gender_identity": {
+            "description": "The donor's personal sense of their own gender at the time of the experiment.",
+            "type": "object",
+            "$ref": "module/ontology/gender_identity_ontology.json",
+            "user_friendly": "Gender identity"
         }
     }
 }

json_schema/versions.json

@@ -1,5 +1,5 @@
 {
-    "last_update_date": "2024-11-06T17:01:14Z",
+    "last_update_date": "2024-12-11T09:29:09Z",
     "version_numbers": {
         "core": {
             "biomaterial": {
@@ -45,6 +45,7 @@
                 "ethnicity_ontology": "5.3.9",
                 "file_content_ontology": "2.0.0",
                 "file_format_ontology": "1.0.0",
+                "gender_identity_ontology": "1.0.0",
                 "instrument_ontology": "5.3.6",
                 "length_unit_ontology": "5.3.5",
                 "library_amplification_ontology": "1.2.5",
@@ -94,7 +95,7 @@
             "biomaterial": {
                 "cell_line": "16.0.0",
                 "cell_suspension": "14.0.0",
-                "donor_organism": "17.0.0",
+                "donor_organism": "17.1.0",
                 "imaged_specimen": "3.5.0",
                 "organoid": "11.5.0",
                 "specimen_from_organism": "10.9.0"

src/human_readable_json.py

@@ -118,9 +118,9 @@ def generateMarkdown(self, schemas, entity_type):
                     #     print(schema["title"] + "\t "+ property + "\t"+ link)
 
                     if "enum" in schema["properties"][property]:
-                        enum_values = ", ".join(schema["properties"][property]["enum"])
+                        enum_values = ", ".join(str(enum) for enum in schema["properties"][property]["enum"])
                     elif "enum" in schema["properties"][property].get("items", ""):
-                        enum_values = ", ".join(schema["properties"][property]["items"]["enum"])
+                        enum_values = ", ".join(str(enum) for enum in schema["properties"][property]["items"]["enum"])
                     else:
                         enum_values = ""
                     file.write(property + " | "+

src/schema_linter.py

@@ -4,7 +4,6 @@
 import re
 import json
 import sys
-import argparse
 from urllib.request import urlopen
 from urllib.error import HTTPError
 
@@ -16,7 +15,7 @@
 
 required_schema_fields = ['$schema', 'description', 'additionalProperties', 'title', 'name', 'type', 'properties']
 
-allowed_schema_fields = ['$schema', 'description', 'additionalProperties', 'required', 'title', 'name', 'type', 'properties', 'definitions', 'dependencies', 'if', 'then', 'else', 'minProperties']
+allowed_schema_fields = ['$schema', 'description', 'additionalProperties', 'required', 'title', 'name', 'type', 'properties', 'definitions', 'dependencies', 'if', 'then', 'else', 'allOf', 'minProperties']
 
 # Properties
 
@@ -38,24 +37,6 @@
 
 graph_restriction_attributes = ['ontologies', 'classes', 'relations', 'direct', 'include_self']
 
-# Accepted environments and conversion for OLS API url
-
-ENVIRONMENTS = ['develop', 'integration', 'staging', 'master']
-
-OLS_ENVIRONMENT = {
-    "develop": "dev",
-    "integration": "integration",
-    "staging": "staging",
-    "master": "staging"
-}
-
-def argument_parser():
-    # Create the parser, define arguments and return it
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--environment', '-e', type=str, dest='environment', help='environment the OLS API feeds on',
-                        default='staging', action='store', choices=ENVIRONMENTS)
-    return parser
-
 
 class SchemaLinter:
     def __init__(self):
@@ -163,26 +144,30 @@ def lintSchema(self, path, ols_api):
                 errors.append(schema_filename + ".json: Keyword `type` missing from property `" + property + "`.")
 
             else:
-                # type attribute must be set to one of the valid JSON types
-                if properties[property]['type'] not in ["string", "number", "boolean", "array", "object", "integer"]:
-                    errors.append(schema_filename + ".json: Type `" + properties[property]['type'] + "` is not a valid JSON type.")
-
-                # Property of type array must contain the attribute items
-                if properties[property]['type'] == "array" and 'items' not in properties[property].keys():
-                    errors.append(schema_filename + ".json: Property `" + property + "` is type array but doesn't contain items.")
-
-                # Property of type array must contains the attribute items
-                # items must have either type or $ref attribute
-                if properties[property]['type'] == "array" and 'items' in properties[property].keys() and '$ref' not in properties[property]['items'].keys() and 'type' not in properties[property]['items'].keys():
-                    errors.append(schema_filename + ".json: Property `" + property + "` is type array but items attribute doesn't contain type or $ref attribute.")
-
-                # Property of type object must contains the attribute $ref
-                if properties[property]['type'] == "object" and '$ref' not in properties[property].keys():
-                    errors.append(schema_filename + ".json: Property `" + property + "` is type object but doesn't contain $ref.")
+                # change property to list to test all values of array
+                properties[property]['type'] = properties[property]['type'] if isinstance(properties[property]['type'], list) else [properties[property]['type']]
+
+                for property_type in properties[property]['type']:
+                    # type attribute must be set to one of the valid JSON types
+                    if property_type not in ["string", "number", "boolean", "array", "object", "integer", "null"]:
+                        errors.append(schema_filename + ".json: Type `" + property_type + "` is not a valid JSON type.")
+
+                    # Property of type array must contain the attribute items
+                    if property_type == "array" and 'items' not in properties[property].keys():
+                        errors.append(schema_filename + ".json: Property `" + property + "` is type array but doesn't contain items.")
+
+                    # Property of type array must contains the attribute items
+                    # items must have either type or $ref attribute
+                    if property_type == "array" and 'items' in properties[property].keys() and '$ref' not in properties[property]['items'].keys() and 'type' not in properties[property]['items'].keys():
+                        errors.append(schema_filename + ".json: Property `" + property + "` is type array but items attribute doesn't contain type or $ref attribute.")
+
+                    # Property of type object must contains the attribute $ref
+                    if property_type == "object" and '$ref' not in properties[property].keys():
+                        errors.append(schema_filename + ".json: Property `" + property + "` is type object but doesn't contain $ref.")
 
             # format must be a valid JSON format
-            if 'format' in properties[property].keys() and properties[property]['format'] not in ["date", "date-time", "email"]:
-                errors.append(schema_filename + ".json: Format `" + properties[property]['format'] + "` is not a valid JSON format).")
+            if 'format' in properties[property].keys() and properties[property]['format'] not in ["date", "date-time", "email", "uri"]:
+                errors.append(schema_filename + ".json: Format `" + properties[property]['format'] + "` is not a valid JSON format.")
 
             # description should be a sentence - start with capital letter and end with full stop
             if 'description' in properties[property].keys() and not re.match('^[A-Z][^?!]*[.]$', properties[property]['description']):
@@ -329,11 +314,8 @@ def get_json_from_file(self, filename, warn = False):
 
 
 if __name__ == "__main__":
-    # Define the environment, transforming 'develop' and 'master' to their respective OLS valid environment to
-    # define the proper OLS API URL.
-    arguments = argument_parser().parse_args(sys.argv[1:])
-    environment = OLS_ENVIRONMENT[arguments.environment]
-    ols_api = 'https://ontology.{}.archive.data.humancellatlas.org/api'.format(environment)
+    # As of November 2024, we are now using the OLS4 for ontology checkup
+    ols_api = 'https://www.ebi.ac.uk/ols/api'
 
     schema_path = '../json_schema' if cwd == 'src' else 'json_schema'
     jsons = [os.path.join(dirpath, f)