adjusted audit

Author: ian-whaling

src/igvfd/audit/construct_library_set.py

@@ -9,6 +9,19 @@
 )
 
 
+def get_assay_terms(value, system):
+    assay_terms = set()
+    for sample in value.get('applied_to_samples', []):
+        sample_object = system.get('request').embed(
+            sample + '@@object_with_select_calculated_properties?field=file_sets')
+        file_sets = sample_object.get('file_sets', [])
+        for file_set in file_sets:
+            if file_set.startswith('/measurement-sets/'):
+                input_file_set_object = system.get('request').embed(input_file_set + '@@object?skip_calculated=true')
+                assay_terms.add(input_file_set_object.get('assay_term'))
+    return list(assay_terms)
+
+
 @audit_checker('ConstructLibrarySet', frame='object')
 def audit_construct_library_set_associated_phenotypes(value, system):
     '''
@@ -97,26 +110,35 @@ def audit_integrated_content_files(value, system):
     '''
     [
         {
-            "audit_description": "Guide libraries are expected to link to an integrated content file of guide RNA sequences.",
+            "audit_description": "Guide libraries used in CRISPR assays are expected to link to an integrated content file of guide RNA sequences.",
             "audit_category": "missing guide RNA sequences",
             "audit_level": "NOT_COMPLIANT"
         },
         {
-            "audit_description": "Reporter libraries are expected to link to an integrated content file of MPRA sequence designs.",
+            "audit_description": "Reporter libraries used in MPRA assays are expected to link to an integrated content file of MPRA sequence designs.",
             "audit_category": "missing MPRA sequence designs",
             "audit_level": "NOT_COMPLIANT"
         }
     ]
     '''
     audit_message_guide = get_audit_message(audit_integrated_content_files, index=0)
     audit_message_reporter = get_audit_message(audit_integrated_content_files, index=1)
+    assay_terms = get_assay_terms(value, system)
+    CRISPR_assays = [
+        '/assay-terms/OBI_0003659/'  # in vitro CRISPR screen assay
+        '/assay-terms/OBI_0003660/'  # in vitro CRISPR screen using single-cell RNA-seq
+        '/assay-terms/OBI_0003661/'  # in vitro CRISPR screen using flow cytometry
+    ]
+    MPRA_assays = [
+        '/assay-terms/OBI_0002675/'  # massively parallel reporter assay
+    ]
     library_expectation = {
-        'guide library': ('guide RNA sequences', audit_message_guide),
-        'reporter library': ('MPRA sequence designs', audit_message_reporter),
+        'guide library': ('guide RNA sequences', audit_message_guide, CRISPR_assays),
+        'reporter library': ('MPRA sequence designs', audit_message_reporter, MPRA_assays),
     }
     integrated_content_files = value.get('integrated_content_files', '')
     library_type = value.get('file_set_type', '')
-    if library_type in library_expectation:
+    if library_type in library_expectation and any(assay_term in library_expectation[library_type][2] for assay_term in assay_terms):
         file_expectation = library_expectation[library_type][0]
         audit_message = library_expectation[library_type][1]
         if integrated_content_files:

src/igvfd/mappings/construct_library_set.json

@@ -1,6 +1,6 @@
 {
-    "hash": "c2f24a479121ea32c2e8fd5687fff44d",
-    "index_name": "construct_library_set_c2f24a47",
+    "hash": "53b59edfed6d4f2d5101620baad2df0f",
+    "index_name": "construct_library_set_53b59edf",
     "item_type": "construct_library_set",
     "mapping": {
         "dynamic_templates": [

src/igvfd/tests/test_audit_construct_library_set.py

@@ -184,8 +184,20 @@ def test_audit_construct_library_set_with_invalid_chroms(
 def test_audit_construct_library_set_guide_library_guide_rna_sequences(
     testapp,
     construct_library_set_genome_wide,
-    tabular_file
+    tabular_file,
+    assay_term_crispr,
+    measurement_set,
+    tissue
 ):
+    testapp.patch_json(
+        measurement_set['@id'],
+        {'assay_term': assay_term_crispr['@id'],
+         'samples': tissue['@id']}
+    )
+    testapp.patch_json(
+        tissue['@id'],
+        {'construct_library_sets': construct_library_set_genome_wide['@id']}
+    )
     res = testapp.get(construct_library_set_genome_wide['@id'] + '@@audit')
     assert any(
         error['category'] == 'missing guide RNA sequences'
@@ -213,8 +225,21 @@ def test_audit_construct_library_set_guide_library_guide_rna_sequences(
 def test_audit_construct_library_set_mpra_sequence_designs(
     testapp,
     construct_library_set_reporter,
-    tabular_file
+    tabular_file,
+    assay_term_mpra,
+    measurement_set,
+    tissue,
+    assay_term_starr
 ):
+    testapp.patch_json(
+        measurement_set['@id'],
+        {'assay_term': assay_term_mpra['@id'],
+         'samples': tissue['@id']}
+    )
+    testapp.patch_json(
+        tissue['@id'],
+        {'construct_library_sets': construct_library_set_reporter['@id']}
+    )
     res = testapp.get(construct_library_set_reporter['@id'] + '@@audit')
     assert any(
         error['category'] == 'missing MPRA sequence designs'
@@ -229,6 +254,19 @@ def test_audit_construct_library_set_mpra_sequence_designs(
         error['category'] == 'missing MPRA sequence designs'
         for error in res.json['audit'].get('NOT_COMPLIANT', [])
     )
+    testapp.patch_json(
+        measurement_set['@id'],
+        {'assay_term': assay_term_starr['@id']}
+    )
+    res = testapp.get(construct_library_set_reporter['@id'] + '@@audit')
+    assert all(
+        error['category'] != 'missing MPRA sequence designs'
+        for error in res.json['audit'].get('NOT_COMPLIANT', [])
+    )
+    testapp.patch_json(
+        measurement_set['@id'],
+        {'assay_term': assay_term_mpra['@id']}
+    )
     testapp.patch_json(
         tabular_file['@id'],
         {'content_type': 'MPRA sequence designs'}