ENCD-6099-audit-index-reads-no-read-structure (#4071)

src/encoded/audit/file.py

@@ -629,6 +629,17 @@ def audit_file_index_of(value, system):
             )
             yield AuditFailure('inconsistent index file', detail, level='ERROR')
 
+
+def audit_index_reads_read_structure(value, system):
+    if value['output_type'] == 'index reads':
+        if 'read_structure' not in value or \
+            'read_structure' in value and len(value['read_structure']) == 0:
+            detail = (
+                f'Index file {audit_link(path_to_text(value["@id"]), value["@id"])} '
+                f'is missing read structure information.'
+            )
+            yield AuditFailure('missing read structure', detail, level='INTERNAL_ACTION')
+
 function_dispatcher = {
     'audit_step_run': audit_file_processed_step_run,
     'audit_derived_from': audit_file_processed_derived_from,
@@ -643,6 +654,7 @@ def audit_file_index_of(value, system):
     'audit_read_structure': audit_read_structure,
     'audit_file_matching_md5sum': audit_file_matching_md5sum,
     'audit_file_index_of': audit_file_index_of,
+    'audit_index_reads_read_structure': audit_index_reads_read_structure,
 }
 
 

src/encoded/schemas/changelogs/file.md

@@ -8,6 +8,7 @@
 * Added *fragments* to the enum list for *output_type*, the new output type is to be submitted as tar.gz only
 * Added *sparse peak count matrix* to the enum list for *output_type*
 * Added *functional conservation quantifications* to the enum list for *output_type*
+* Added *cell barcode* and *element barcode* to the enum list for *sequence_element* of the *read_structure* property
 
 ### Schema version 29
 * Added Ultima Genomics platform to dependency that enforces that *read_length* property should not be specified for FASTQ files produced by Oxford Nanopore and PacBio platforms.

src/encoded/schemas/file.json

@@ -1996,6 +1996,8 @@
                         "enum": [
                             "adapter",
                             "barcode",
+                            "cell barcode",
+                            "element barcode",
                             "UMI"
                         ]
                     },

src/encoded/tests/data/inserts/file.json

@@ -2808,6 +2808,16 @@
                 "sequence_element": "UMI",
                 "start": 13,
                 "end": 18
+            },
+            {
+                "sequence_element": "cell barcode",
+                "start": 19,
+                "end": 25
+            },
+            {
+                "sequence_element": "element barcode",
+                "start": 26,
+                "end": 33
             }
         ]
     },

src/encoded/tests/test_audit_file.py

@@ -1127,3 +1127,25 @@ def test_audit_incorrect_index(testapp,
     assert any(error['category'] == 'inconsistent index file'
         and 'multiple non-Illumina fastq' in error['detail']
         for error in errors_list)
+
+
+def test_audit_index_reads_read_structure(testapp, fastq_index):
+    res = testapp.get(fastq_index['@id'] + '@@index-data')
+    errors = res.json['audit']
+    errors_list = [error for v in errors.values() for error in v if error['category'] == 'missing read structure']
+    assert errors_list
+    testapp.patch_json(
+        fastq_index['@id'],
+        {
+            'read_structure': [{
+                'sequence_element': 'cell barcode',
+                'start': 1,
+                'end': 20
+            }]
+        }
+    )
+    res = testapp.get(fastq_index['@id'] + '@@index-data')
+    errors = [error for v in res.json['audit'].values() for error in v]
+    assert not any(
+        error['category'] == 'missing read structure' for error in errors
+    )