903 - Update Test Bucket to 2024-09-10

api/scpca_portal/config/local.py

@@ -17,7 +17,7 @@ class Local(Common):
     AWS_REGION = None
 
     # AWS S3
-    TEST_INPUT_BUCKET_NAME = "scpca-portal-public-test-inputs/2024-07-19/"
+    TEST_INPUT_BUCKET_NAME = "scpca-portal-public-test-inputs/2024-09-10/"
     AWS_S3_INPUT_BUCKET_NAME = TEST_INPUT_BUCKET_NAME if Common.TEST else "scpca-portal-inputs"
     AWS_S3_OUTPUT_BUCKET_NAME = "scpca-local-data"
 

api/scpca_portal/metadata_file.py

@@ -28,6 +28,8 @@
     ("citation_doi", "doi", None),
 ]
 
+PROJECT_METADATA_VALUES_TRANSFORMS = {"diagnoses": lambda d: ", ".join(sorted(d.split(";")))}
+
 LIBRARY_METADATA_KEYS = [
     ("library_id", "scpca_library_id", None),
     ("sample_id", "scpca_sample_id", None),
@@ -48,6 +50,7 @@ def load_projects_metadata(*, filter_on_project_id: str = None):
 
     for project_metadata in projects_metadata:
         transform_keys(project_metadata, PROJECT_METADATA_KEYS)
+        transform_values(project_metadata, PROJECT_METADATA_VALUES_TRANSFORMS)
 
     if filter_on_project_id:
         return [pm for pm in projects_metadata if pm["scpca_project_id"] == filter_on_project_id]
@@ -84,6 +87,16 @@ def transform_keys(data_dict: Dict, key_transforms: List[Tuple]):
     return data_dict
 
 
+def transform_values(data_dict: Dict, value_transforms: List[Tuple]):
+    """
+    Transform values in data dict according to transformation functions in value transform dict.
+    """
+    for key, transformation_function in value_transforms.items():
+        data_dict[key] = transformation_function(data_dict[key])
+
+    return data_dict
+
+
 class MetadataFilenames:
     SINGLE_CELL_METADATA_FILE_NAME = "single_cell_metadata.tsv"
     SPATIAL_METADATA_FILE_NAME = "spatial_metadata.tsv"

api/scpca_portal/models/project.py

@@ -446,7 +446,6 @@ def update_project_aggregate_properties(self):
         """
 
         additional_metadata_keys = set()
-        diagnoses = set()
         diagnoses_counts = Counter()
         disease_timings = set()
         modalities = set()
@@ -457,7 +456,6 @@ def update_project_aggregate_properties(self):
 
         for sample in self.samples.all():
             additional_metadata_keys.update(sample.additional_metadata.keys())
-            diagnoses.add(sample.diagnosis)
             diagnoses_counts.update({sample.diagnosis: 1})
             disease_timings.add(sample.disease_timing)
             modalities.update(sample.modalities)
@@ -487,7 +485,6 @@ def update_project_aggregate_properties(self):
             additional_metadata_keys.remove("multiplexed_with")
 
         self.additional_metadata_keys = ", ".join(sorted(additional_metadata_keys, key=str.lower))
-        self.diagnoses = ", ".join(sorted(diagnoses))
         self.diagnoses_counts = ", ".join(diagnoses_strings)
         self.disease_timings = ", ".join(disease_timings)
         self.modalities = sorted(modalities)

api/scpca_portal/test/expected_values/project_SCPCP999990.py

@@ -15,8 +15,8 @@ class Project_SCPCP999990:
             "SCPCP999990/bulk/SCPCP999990_bulk_metadata.tsv",
             "SCPCP999990/bulk/SCPCP999990_bulk_quant.tsv",
         ],
-        "diagnoses": "diagnosis1, diagnosis2, diagnosis5, diagnosis8",
-        "diagnoses_counts": "diagnosis1 (1), diagnosis2 (1), diagnosis5 (1), diagnosis8 (1)",
+        "diagnoses": "diagnosis1, diagnosis2, diagnosis5",
+        "diagnoses_counts": "diagnosis1 (1), diagnosis2 (1), diagnosis5 (2)",
         "disease_timings": "Initial diagnosis",
         # This value is not determined until after computed file generation, and should be 3
         "downloadable_sample_count": 0,
@@ -67,7 +67,7 @@ class Sample_SCPCS999990:
             "is_cell_line": False,
             "is_xenograft": False,
             "multiplexed_with": [],
-            "sample_cell_count_estimate": 3432,
+            "sample_cell_count_estimate": 3424,
             "scpca_id": SCPCA_ID,
             "sex": "M",
             "seq_units": "cell",
@@ -137,7 +137,7 @@ class Sample_SCPCS999997:
             "age": "2",
             "age_timing": "collection",
             "demux_cell_count_estimate": None,
-            "diagnosis": "diagnosis8",
+            "diagnosis": "diagnosis5",
             "disease_timing": "Initial diagnosis",
             "has_bulk_rna_seq": False,
             "has_cite_seq_data": False,
@@ -148,7 +148,7 @@ class Sample_SCPCS999997:
             "is_cell_line": False,
             "is_xenograft": False,
             "multiplexed_with": [],
-            "sample_cell_count_estimate": 1568,
+            "sample_cell_count_estimate": 1570,
             "scpca_id": SCPCA_ID,
             "sex": "M",
             "seq_units": "cell",
@@ -260,7 +260,7 @@ class Summary3:
 
     class Summary4:
         VALUES = {
-            "diagnosis": "diagnosis8",
+            "diagnosis": "diagnosis5",
             "sample_count": 1,
             "seq_unit": "cell",
             "technology": "10Xv3",

api/scpca_portal/test/expected_values/project_SCPCP999991.py

@@ -49,7 +49,7 @@ class Sample_SCPCS999992:
             "age": "2",
             "age_timing": "unknown",
             "demux_cell_count_estimate": 0,
-            "diagnosis": "diagnosis3",
+            "diagnosis": "diagnosis4",
             "disease_timing": "Initial diagnosis",
             "has_bulk_rna_seq": False,
             "has_cite_seq_data": False,
@@ -76,7 +76,7 @@ class Sample_SCPCS999993:
             "age": "2",
             "age_timing": "diagnosis",
             "demux_cell_count_estimate": 0,
-            "diagnosis": "diagnosis4",
+            "diagnosis": "diagnosis3",
             "disease_timing": "Initial diagnosis",
             "has_bulk_rna_seq": False,
             "has_cite_seq_data": False,
@@ -114,7 +114,7 @@ class Sample_SCPCS999995:
             "is_cell_line": False,
             "is_xenograft": False,
             "multiplexed_with": [],
-            "sample_cell_count_estimate": 3433,
+            "sample_cell_count_estimate": 3428,
             "scpca_id": SCPCA_ID,
             "sex": "M",
             "seq_units": "cell",
@@ -167,15 +167,15 @@ class Library_SCPCL999995:
 
     class Summary1:
         VALUES = {
-            "diagnosis": "diagnosis3",
+            "diagnosis": "diagnosis4",
             "sample_count": 1,
             "seq_unit": "nucleus",
             "technology": "10Xv3.1",
         }
 
     class Summary2:
         VALUES = {
-            "diagnosis": "diagnosis4",
+            "diagnosis": "diagnosis3",
             "sample_count": 1,
             "seq_unit": "nucleus",
             "technology": "10Xv3.1",

api/scpca_portal/test/expected_values/project_SCPCP999992.py

@@ -14,8 +14,8 @@ class Project_SCPCP999992:
             "SCPCP999992/merged/SCPCP999992_merged_adt.h5ad",
             "SCPCP999992/merged/SCPCP999992_merged_rna.h5ad",
         ],
-        "diagnoses": "diagnosis7, diagnosis9",
-        "diagnoses_counts": "diagnosis7 (1), diagnosis9 (1)",
+        "diagnoses": "diagnosis7",
+        "diagnoses_counts": "diagnosis7 (2)",
         "disease_timings": "Initial diagnosis",
         # This value is not determined until after computed file generation, and should be 2
         "downloadable_sample_count": 0,
@@ -79,7 +79,7 @@ class Sample_SCPCS999998:
             "age": "2",
             "age_timing": "unknown",
             "demux_cell_count_estimate": None,
-            "diagnosis": "diagnosis9",
+            "diagnosis": "diagnosis7",
             "disease_timing": "Initial diagnosis",
             "has_bulk_rna_seq": False,
             "has_cite_seq_data": True,
@@ -90,7 +90,7 @@ class Sample_SCPCS999998:
             "is_cell_line": False,
             "is_xenograft": False,
             "multiplexed_with": [],
-            "sample_cell_count_estimate": 5245,
+            "sample_cell_count_estimate": 5247,
             "scpca_id": SCPCA_ID,
             "sex": "M",
             "seq_units": "cell",
@@ -161,7 +161,7 @@ class Summary1:
 
     class Summary2:
         VALUES = {
-            "diagnosis": "diagnosis9",
+            "diagnosis": "diagnosis7",
             "sample_count": 1,
             "seq_unit": "cell",
             "technology": "10Xv2_5prime",

api/scpca_portal/test/views/test_filter_options.py

@@ -26,7 +26,7 @@ def test_get(self):
         self.assertEqual(response.status_code, status.HTTP_200_OK)
 
         response = response.json()
-        self.assertEqual(len(response["diagnoses"]), 4)
+        self.assertEqual(len(response["diagnoses"]), 2)
         self.assertEqual(len(response["modalities"]), 1)  # CITE-seq only.
         self.assertEqual(len(response["seq_units"]), 2)
         self.assertEqual(len(response["technologies"]), 5)