Merge pull request #597 from biocore/csymons_cheek_samples

Cheek Samples

Author: cassidysymons

microsetta_private_api/admin/admin_impl.py

@@ -787,6 +787,7 @@ def list_barcode_query_fields(token_info):
             'input': 'select',
             'values': {
                 "Blood (skin prick)": "Blood (skin prick)",
+                "Cheek": "Cheek",
                 "Saliva": "Saliva",
                 "Ear wax": "Ear wax",
                 "Forehead": "Forehead",

microsetta_private_api/api/_sample.py

@@ -148,11 +148,15 @@ def update_sample_association(account_id, source_id, sample_id, body,
         # sample_site will not be present if its environmental. this will
         # default to None if the key is not present
         sample_site = body.get('sample_site')
+
+        barcode_meta = body.get('barcode_meta')
+
         sample_info = SampleInfo(
             sample_id,
             sample_datetime,
             sample_site,
-            body["sample_notes"]
+            body["sample_notes"],
+            barcode_meta
         )
 
         sample_repo.update_info(account_id, source_id, sample_info,

microsetta_private_api/api/microsetta_private_api.yaml

@@ -3589,7 +3589,7 @@ components:
       nullable: true
     sample_site:
       enum: ["Blood (skin prick)", "Saliva", "Ear wax", "Forehead", "Fur", "Hair", "Left hand", "Left leg", "Mouth", "Nares", "Nasal mucus",
-             "Right hand", "Right leg", "Stool", "Tears", "Torso", "Vaginal mucus", null]
+             "Right hand", "Right leg", "Stool", "Tears", "Torso", "Vaginal mucus", "Cheek", null]
       example: "Stool"
     sample_edit_locked:
       type: boolean

microsetta_private_api/api/tests/test_api.py

@@ -182,6 +182,7 @@
     'account_id': None,
     'source_id': None,
     'sample_site': None,
+    'barcode_meta': {},
     'sample_project_ids': [1]}
 
 DUMMY_FILLED_SAMPLE_INFO = {
@@ -583,7 +584,8 @@ def create_dummy_sample_objects(filled=False):
         info_dict["sample_id"],
         datetime_obj,
         info_dict["sample_site"],
-        info_dict["sample_notes"]
+        info_dict["sample_notes"],
+        {}
     )
 
     sample = Sample(info_dict["sample_id"],

microsetta_private_api/api/tests/test_integration.py

@@ -1443,6 +1443,7 @@ def _test_edit_sample_info(self, source_type):
         if store_sample_site:
             fuzzy_info['sample_site'] = "Tears"
         fuzzy_info['sample_datetime'] = datetime.datetime.utcnow()
+        fuzzy_info['barcode_meta'] = {}
 
         # Many fields are not writable, each should individually cause failure.
         readonly_fields = [

microsetta_private_api/db/patches/0146.sql

@@ -0,0 +1,23 @@
+-- Beginning with cheek samples, we're collecting metadata that are explicitly
+-- linked to sample collection (unlike surveys, which are implicitly linked
+-- to samples via sources), but not globally collected, and therefore don't
+-- belong in the ag.ag_kit_barcodes table. A new table will store these
+-- fields and could eventually be extended to a much more robust framework.
+
+-- First, we need to set up an ENUM type to enforce values for the type of
+-- product used to last wash their face
+CREATE TYPE SAMPLE_SITE_LAST_WASHED_PRODUCT_TYPE AS ENUM ('Soap (includes bar and liquid soap)', 'Foaming face wash', 'Face cleanser', 'Just water', 'Other (e.g. shampoo, body wash, all-in-one or all-over wash)', 'Not sure');
+
+-- Then, create the table to store the data
+-- Note: the date and time are stored separately because we're not enforcing
+-- either as a required field. As such, using a timestamp type would not be
+-- appropriate since it forces us into a both or neither paradigm.
+CREATE TABLE ag.ag_kit_barcodes_cheek (
+    ag_kit_barcode_id UUID NOT NULL PRIMARY KEY,
+    sample_site_last_washed_date DATE,
+    sample_site_last_washed_time TIME,
+    sample_site_last_washed_product SAMPLE_SITE_LAST_WASHED_PRODUCT_TYPE,
+
+    -- Foreign key relationship on ag_kit_barcode_id
+    CONSTRAINT fk_ag_kit_barcode_id FOREIGN KEY (ag_kit_barcode_id) REFERENCES ag.ag_kit_barcodes (ag_kit_barcode_id)
+);

microsetta_private_api/model/sample.py

@@ -26,13 +26,17 @@ def __init__(self, sample_id, datetime_collected, site, notes, barcode,
         self.account_id = account_id
 
         self.accession_urls = []
+        self.barcode_meta = {}
         self.kit_id = kit_id
 
         self._sample_project_ids = sample_project_ids
 
     def set_accession_urls(self, accession_urls):
         self.accession_urls = accession_urls
 
+    def set_barcode_meta(self, barcode_meta):
+        self.barcode_meta = barcode_meta
+
     def get_project_ids(self):
         return self._sample_project_ids
 
@@ -81,18 +85,25 @@ def to_api(self):
             "account_id": self.account_id,
             "sample_projects": list(self.sample_projects),
             "accession_urls": self.accession_urls,
-            "kit_id": self.kit_id
+            "kit_id": self.kit_id,
+            "barcode_meta": self.barcode_meta
         }
 
 
 # A SampleInfo represents the set of end user editable fields whose lifetime
 # matches that of the association between a sample and a source
 class SampleInfo:
-    def __init__(self, sample_id, datetime_collected, site, notes):
+    def __init__(self, sample_id, datetime_collected, site, notes,
+                 barcode_meta=None):
         self.id = sample_id
         # NB: datetime_collected may be None if sample not yet used
         self.datetime_collected = datetime_collected
         # NB: notes may be None
         self.notes = notes
         # NB: site may be None if sample not yet used
         self.site = site
+
+        if barcode_meta is None:
+            self.barcode_meta = {}
+        else:
+            self.barcode_meta = barcode_meta

microsetta_private_api/repo/metadata_repo/_constants.py

@@ -237,7 +237,7 @@
         'host_body_habitat': 'UBERON:feces',
         'env_material': 'feces',
         'env_package': 'human-gut',
-        'description': 'American Gut Project Stool sample',
+        'description': 'Microsetta Initiative Stool sample',
         'host_body_site': 'UBERON:feces'},
     'Forehead': {
         'host_body_product': 'UBERON:sebum',
@@ -356,7 +356,18 @@
         'env_package': 'human-associated',
         'description': 'American Gut Project Ear wax sample',
         'empo_3': 'Animal secretion',
-        'host_body_site': 'UBERON:external auditory meatus'}
+        'host_body_site': 'UBERON:external auditory meatus'},
+    'Cheek': {
+        'host_body_product': 'UBERON:sebum',
+        'sample_type': 'skin of cheek',
+        'scientific_name': 'human skin metagenome',
+        'taxon_id': '539655',
+        'host_body_habitat': 'UBERON:skin',
+        'empo_3': 'Animal surface',
+        'env_material': 'sebum material',
+        'env_package': 'human-skin',
+        'description': 'Microsetta Initiative cheek skin sample',
+        'host_body_site': 'UBERON:skin of cheek'}
 }
 
 

microsetta_private_api/repo/metadata_repo/_repo.py

@@ -710,6 +710,10 @@ def _to_pandas_series(metadata, multiselect_map):
                     index.append(shortname)
                     values.append(answer)
 
+    for variable, value in sample_detail.barcode_meta.items():
+        index.append(variable)
+        values.append(value)
+
     for variable, value in sample_invariants.items():
         index.append(variable)
         values.append(value)

microsetta_private_api/repo/metadata_repo/tests/test_repo.py

@@ -67,7 +67,10 @@ def setUp(self):
                 "sample": MM({
                     "sample_projects": ["American Gut Project"],
                     "datetime_collected": "2013-10-15T09:30:00",
-                    "site": "Stool"
+                    "site": "Stool",
+                    "barcode_meta": {
+                        "sample_site_last_washed_date": "01/10/2025"
+                    }
                 }),
                 'survey_answers': [
                     {'template': 1,
@@ -134,7 +137,8 @@ def setUp(self):
                 "sample": MM({
                     "sample_projects": ["American Gut Project"],
                     "datetime_collected": "2013-10-15T09:30:00",
-                    "site": "Stool"
+                    "site": "Stool",
+                    "barcode_meta": {}
                 }),
                 'survey_answers': [
                     {'template': 1,
@@ -170,7 +174,8 @@ def setUp(self):
                 "sample": MM({
                     "sample_projects": ["American Gut Project"],
                     "datetime_collected": "2013-10-15T09:30:00",
-                    "site": "Stool"
+                    "site": "Stool",
+                    "barcode_meta": {}
                 }),
                 'survey_answers': [
                     {'template': SurveyTemplateRepo.DIET_ID,
@@ -406,13 +411,13 @@ def test_to_pandas_dataframe(self):
                              'true', 'true', 'false', 'false',
                              UNSPECIFIED,
                              'okay', 'No', "2013-10-15T09:30:00", '000004216',
-                             'US:CA', 'CA', '33', '-117'],
+                             'US:CA', 'CA', '33', '-117', '01/10/2025'],
                             ['XY0004216', 'bar', 'Vegan foo', 'Yes',
                              UNSPECIFIED, UNSPECIFIED, UNSPECIFIED,
                              'No', 'false', 'true', 'true', 'false',
                              'foobar', UNSPECIFIED, UNSPECIFIED,
                              "2013-10-15T09:30:00", 'XY0004216',
-                             'US:CA', 'CA', '33', '-117']],
+                             'US:CA', 'CA', '33', '-117', 'not provided']],
                            columns=['sample_name', 'host_subject_id',
                                     'diet_type', 'multivitamin',
                                     'probiotic_frequency',
@@ -425,7 +430,8 @@ def test_to_pandas_dataframe(self):
                                     'sample2specific', 'abc', 'def',
                                     'collection_timestamp',
                                     'anonymized_name', 'geo_loc_name',
-                                    'state', 'latitude', 'longitude']
+                                    'state', 'latitude', 'longitude',
+                                    'sample_site_last_washed_date']
                            ).set_index('sample_name')
 
         for k, v in HUMAN_SITE_INVARIANTS['Stool'].items():
@@ -453,15 +459,16 @@ def test_to_pandas_series(self):
         values = ['foo', '', 'No', 'Unspecified', 'Unspecified',
                   'Unspecified', 'No', 'true', 'true', 'false',
                   'false', 'okay', 'No',
-                  '2013-10-15T09:30:00', 'US:CA', 'CA', '33', '-117']
+                  '2013-10-15T09:30:00', 'US:CA', 'CA', '33', '-117',
+                  '01/10/2025']
         index = ['HOST_SUBJECT_ID', 'DIET_TYPE', 'MULTIVITAMIN',
                  'PROBIOTIC_FREQUENCY', 'VITAMIN_B_SUPPLEMENT_FREQUENCY',
                  'VITAMIN_D_SUPPLEMENT_FREQUENCY',
                  'OTHER_SUPPLEMENT_FREQUENCY',
                  'ALLERGIC_TO_blahblah', 'ALLERGIC_TO_stuff', 'ALLERGIC_TO_x',
                  'ALLERGIC_TO_baz', 'abc', 'def',
                  'COLLECTION_TIMESTAMP', 'GEO_LOC_NAME', 'STATE', 'LATITUDE',
-                 'LONGITUDE']
+                 'LONGITUDE', 'sample_site_last_washed_date']
 
         for k, v in HUMAN_SITE_INVARIANTS['Stool'].items():
             values.append(v)