Libpitt/961 dataset hierarchy

src/app.py

@@ -4160,7 +4160,7 @@ def get_prov_info():
     HEADER_PROCESSED_DATASET_STATUS = "processed_dataset_status"
     HEADER_PROCESSED_DATASET_PORTAL_URL = "processed_dataset_portal_url"
     ORGAN_TYPES = Ontology.ops(
-        as_data_dict=True, data_as_val=True, val_key="organ_uberon", prop_callback=None
+        as_data_dict=True, data_as_val=True, val_key="organ_uberon", key_callback=None
     ).organ_types()
     HEADER_PREVIOUS_VERSION_SENNET_IDS = "previous_version_sennet_ids"
 
@@ -4536,7 +4536,7 @@ def get_prov_info_for_dataset(id):
     HEADER_PROCESSED_DATASET_PORTAL_URL = "processed_dataset_portal_url"
     HEADER_DATASET_SAMPLES = "dataset_samples"
     ORGAN_TYPES = Ontology.ops(
-        as_data_dict=True, data_as_val=True, val_key="organ_uberon", prop_callback=None
+        as_data_dict=True, data_as_val=True, val_key="organ_uberon", key_callback=None
     ).organ_types()
 
     headers = [
@@ -4781,7 +4781,7 @@ def get_sample_prov_info():
     HEADER_ORGAN_TYPE = "organ_type"
     HEADER_ORGAN_SENNET_ID = "organ_sennet_id"
     ORGAN_TYPES = Ontology.ops(
-        as_data_dict=True, data_as_val=True, val_key="organ_uberon", prop_callback=None
+        as_data_dict=True, data_as_val=True, val_key="organ_uberon", key_callback=None
     ).organ_types()
 
     # Processing and validating query parameters
@@ -6754,7 +6754,7 @@ def verify_ubkg_properties(json_data_dict):
     SOURCE_TYPES = Ontology.ops(as_data_dict=True).source_types()
     SAMPLE_CATEGORIES = Ontology.ops(as_data_dict=True).specimen_categories()
     ORGAN_TYPES = Ontology.ops(
-        as_data_dict=True, key="organ_uberon", prop_callback=None
+        as_data_dict=True, key="organ_uberon", key_callback=None
     ).organ_types()
     DATASET_TYPE = Ontology.ops(as_data_dict=True).dataset_types()
 
@@ -6849,7 +6849,7 @@ def check_multiple_organs_constraint(
                 )
                 if count >= 1:
                     organ_codes = Ontology.ops(
-                        as_data_dict=True, val_key="term", key="organ_uberon", prop_callback=None
+                        as_data_dict=True, val_key="term", key="organ_uberon", key_callback=None
                     ).organ_types()
                     organ = organ_codes[organ_code]
                     abort_bad_req(

src/lib/ontology.py

@@ -19,11 +19,42 @@ def modify_entities_cache():
     @classmethod
     def organs_by_organ_uberon(cls: Ontology) -> dict:
         return cls.ops(
-            as_data_dict=True, prop_callback=None, data_as_val=True, key="organ_uberon"
+            as_data_dict=True, key_callback=None, data_as_val=True, key="organ_uberon"
         ).organ_types()
 
     @classmethod
-    def dataset_type_hierarchy(cls: Ontology) -> dict:
-        return cls.ops(
-            as_data_dict=True, prop_callback=None, data_as_val=False, key="dataset_type", val_key="dataset_modalities"
-        ).dataset_types()
+    def dataset_type_hierarchy(cls: Ontology, dataset_type: str = None) -> dict:
+        def prop_callback(dict):
+            return dict['name']
+
+        def val_callback(dict):
+            if 'modalities' not in dict:
+                return []
+
+            list_of_facets = []
+            for modality in dict['modalities']:
+                for analyte in modality['analytes']:
+                    list_of_facets.append({
+                        "modality": modality['name'],
+                        "analyte": analyte['name'],
+                        "dataset_type": dict['dataset_type']['name']
+                    })
+            return list_of_facets
+
+        all_facets = cls.ops(
+            as_data_dict=True, key_callback=prop_callback, val_callback=val_callback, data_as_val=True,
+        ).dataset_types_hierarchy()
+
+        if dataset_type is not None: 
+            if dataset_type in all_facets:
+                return all_facets[dataset_type]
+            else:
+                return [{
+                    "modality": 'N/A',
+                    "analyte": 'N/A',
+                    "dataset_type": dataset_type
+                }]
+        else:
+            matrix = list(all_facets.values())
+
+            return [item for sublist in matrix for item in sublist]

src/requirements.txt

@@ -18,8 +18,8 @@ neo4j==5.28.1
 # Use the branch name of commons from github for testing new changes made in commons from different branch
 # Default is main branch specified in docker-compose.development.yml if not set
 # git+https://github.com/hubmapconsortium/commons.git@${COMMONS_BRANCH}#egg=hubmap-commons
-hubmap-commons==2.1.21
-atlas-consortia-commons==1.1.5
+hubmap-commons==2.1.26
+atlas-consortia-commons==1.1.7
 #git+https://github.com/x-atlas-consortia/commons.git@{COMMONS_BRANCH}#egg=atlas_consortia_commons
 
 deepdiff==8.6.2

src/schema/schema_triggers.py

@@ -1844,7 +1844,7 @@ def get_dataset_title(property_key, normalized_type, user_token, existing_data_d
     # the threshold, we will just use the number in the title.
     organs_description_phrase = f"{len(organ_abbrev_set)} organs"
     organ_types_dict = Ontology.ops(
-        as_data_dict=True, prop_callback=None, key="organ_uberon", val_key="term"
+        as_data_dict=True, key_callback=None, key="organ_uberon", val_key="term"
     ).organ_types()
 
     if len(organ_abbrev_set) <= MAX_ENTITY_LIST_LENGTH:
@@ -2029,7 +2029,7 @@ def get_display_subtype(
             ):
                 if "organ" in existing_data_dict:
                     organ_types = Ontology.ops(
-                        as_data_dict=True, prop_callback=None, key="organ_uberon", val_key="term"
+                        as_data_dict=True, key_callback=None, key="organ_uberon", val_key="term"
                     ).organ_types()
                     display_subtype = get_val_by_key(
                         existing_data_dict["organ"], organ_types, "ubkg.organ_types"
@@ -2042,7 +2042,7 @@ def get_display_subtype(
 
             else:
                 sample_categories = Ontology.ops(
-                    as_data_dict=True, prop_callback=None
+                    as_data_dict=True, key_callback=None
                 ).specimen_categories()
                 display_subtype = get_val_by_key(
                     existing_data_dict["sample_category"],
@@ -3995,7 +3995,7 @@ def _get_organ_description(organ_code):
     str: The organ code description
     """
     ORGAN_TYPES = Ontology.ops(
-        as_arr=False, prop_callback=None, as_data_dict=True, data_as_val=True
+        as_arr=False, key_callback=None, as_data_dict=True, data_as_val=True
     ).organ_types()
 
     for key in ORGAN_TYPES:
@@ -4318,15 +4318,15 @@ def get_organ_hierarchy(
     organ_hierarchy = None
     if equals(existing_data_dict["sample_category"], "organ"):
         organ_types_categories = Ontology.ops(
-            as_data_dict=True, prop_callback=None, key="organ_uberon", val_key="category"
+            as_data_dict=True, key_callback=None, key="organ_uberon", val_key="category"
         ).organ_types()
 
         organ_hierarchy = existing_data_dict["organ"]
         if organ_types_categories.get(organ_hierarchy) is not None:
             return property_key, organ_types_categories[organ_hierarchy]["term"]
 
         organ_types = Ontology.ops(
-            as_data_dict=True, prop_callback=None, key="organ_uberon", val_key="term"
+            as_data_dict=True, key_callback=None, key="organ_uberon", val_key="term"
         ).organ_types()
         if existing_data_dict["organ"] in organ_types:
             organ_name = organ_types[organ_hierarchy]
@@ -4367,18 +4367,9 @@ def get_dataset_type_hierarchy(
         dict: The dataset type hierarchy with keys of 'first_level' and 'second_level'
     """
 
-    if equals(existing_data_dict["entity_type"], "Dataset"):
-        dataset_type_hierarchy = Ontology.dataset_type_hierarchy()
-        if existing_data_dict["dataset_type"] not in dataset_type_hierarchy:
-            return property_key, {
-                "first_level": existing_data_dict["dataset_type"],
-                "second_level": existing_data_dict["dataset_type"],
-            }
-
-        return property_key, {
-            "first_level": dataset_type_hierarchy[existing_data_dict["dataset_type"]],
-            "second_level": existing_data_dict["dataset_type"],
-        }
+    if equals(existing_data_dict["entity_type"], "Dataset") and equals(existing_data_dict["creation_action"], "Create Dataset Activity"):
+        dataset_type_hierarchy = Ontology.dataset_type_hierarchy(dataset_type=existing_data_dict["dataset_type"])
+        return property_key, dataset_type_hierarchy
     else:
         return property_key, None