ENCD-5950-upgrade-files-rrm-mapped-props

src/encoded/schemas/changelogs/file.md

@@ -1,5 +1,8 @@
 ## Changelog for file.json
 
+### Schema version 29
+* Recent update removed mapped_run_type and mapped_read_length from bam files deriving from fastqs sequenced with Pacific Biosciences or Nanopore platforms
+
 ### Minor changes since schema version 28
 * Added *element enrichments* to the enum list for *file_format_type*
 * Added *curated binding sites*, *curated SNVs*, *dsQTLs*, *eQTLs* and *PWMs* to the enum list for *output_type*.

src/encoded/schemas/file.json

@@ -1079,7 +1079,7 @@
             "permission": "import_items"
         },
         "schema_version": {
-            "default": "28"
+            "default": "29"
         },
         "accession": {
             "accessionType": "FF"

src/encoded/tests/fixtures/schemas/file.py

@@ -1927,6 +1927,43 @@ def file_27(testapp, lab, award, experiment):
     return item
 
 
+@pytest.fixture
+def file_28_fastq_nanopore(testapp, lab, award, experiment, base_replicate, platform4):
+    item = {
+        'dataset': experiment['@id'],
+        'file_format': 'fastq',
+        'md5sum': '15dd66b6f21515393507f4ebfa55e77c',
+        'replicate': base_replicate['@id'],
+        'output_type': 'reads',
+        'file_size': 800,
+        'platform': platform4['uuid'],
+        'lab': lab['@id'],
+        'award': award['@id'],
+        'status': 'in progress'
+    }
+    return testapp.post_json('/file', item).json['@graph'][0]
+
+
+@pytest.fixture
+def file_28_bam_mapped_props(testapp, lab, award, experiment, file_28_fastq_nanopore):
+    item = {
+        'dataset': experiment['@id'],
+        'file_format': 'bam',
+        'md5sum': 'eeb1325f54a0ec4911c4a3df0ed32f20',
+        'output_type': 'alignments',
+        'assembly': 'hg19',
+        'file_size': 888328,
+        'derived_from': [file_28_fastq_nanopore['uuid']],
+        'lab': lab['@id'],
+        'award': award['@id'],
+        'mapped_run_type': 'single-ended',
+        'mapped_read_length': 101,
+        'status': 'in progress',  # avoid s3 upload codepath
+        'schema_version': '28'
+    }
+    return item
+
+
 @pytest.fixture
 def file_nanopore_signal(testapp, experiment, award, lab, replicate_url, platform4):
     item = {

src/encoded/tests/test_upgrade_file.py

@@ -200,3 +200,10 @@ def test_file_upgrade_27_to_28(upgrader, file_27):
     value = upgrader.upgrade('file', file_27, current_version='27', target_version='28')
     assert value['schema_version'] == '28'
     assert value['output_type'] == 'exclusion list regions'
+
+
+def test_file_upgrade_28_to_29(root, testapp, upgrader, registry, file_28_bam_mapped_props):
+    value = upgrader.upgrade('file', file_28_bam_mapped_props, registry=registry, current_version='28', target_version='29')
+    assert value['schema_version'] == '29'
+    assert 'mapped_run_type' not in value
+    assert 'mapped_read_length' not in value

src/encoded/upgrade/file.py

@@ -680,7 +680,6 @@ def file_20_21(value, system):
     conn = system['registry'][CONNECTION]
     datasetContext = conn.get_by_uuid(value['dataset'])
     assay_type = datasetContext.properties.get('assay_term_name', None)
-
     if assay_type == 'DNase-seq' and output_type == 'enrichment':
         value['output_type'] = 'FDR cut rate'
     return
@@ -751,3 +750,30 @@ def file_27_28(value, system):
     for old_term, new_term in term_pairs:
         if output_type == old_term:
             value['output_type'] = new_term
+
+
+@upgrade_step('file', '28', '29')
+def file_28_29(value, system):
+    # https://encodedcc.atlassian.net/browse/ENCD-5950
+    conn = system['registry'][CONNECTION]
+    if value.get('file_format', '') == 'bam':
+        derived_from = value.get('derived_from', None)
+        checkPlatform = []
+        if derived_from:
+            for item in derived_from:
+                file = conn.get_by_uuid(item)
+                file_format = file.properties.get('file_format', None)
+                if file_format == 'fastq':
+                    checkPlatform.append(file.properties.get('platform', None))
+            if checkPlatform:
+                for platform in checkPlatform:
+                        if platform in ['ced61406-dcc6-43c4-bddd-4c977cc676e8',
+                                        'c7564b38-ab4f-4c42-a401-3de48689a998',
+                                        'e2be5728-5744-4da4-8881-cb9526d0389e',
+                                        '7cc06b8c-5535-4a77-b719-4c23644e767d',
+                                        '8f1a9a8c-3392-4032-92a8-5d196c9d7810',
+                                        '6c275b37-018d-4bf8-85f6-6e3b830524a9',
+                                        '6ce511d5-eeb3-41fc-bea7-8c38301e88c1'
+                                        ]:
+                            value.pop('mapped_read_length', 'None')
+                            value.pop('mapped_run_type', 'None')