Merge pull request #3564 from broadinstitute/gregor-metdata-called-va…

…riant-file-filtering

Gregor metadata called variant file filtering

seqr/views/apis/report_api.py

@@ -713,8 +713,9 @@ def _get_sample_airtable_metadata(sample_ids, user, include_collaborator=False):
 READ_RNA_TABLE_COLUMNS.insert(READ_RNA_TABLE_COLUMNS.index('gene_annotation')+1, 'gene_annotation_details')
 READ_RNA_TABLE_COLUMNS.insert(READ_RNA_TABLE_COLUMNS.index('alignment_log_file')+1, 'alignment_postprocessing')
 READ_SET_TABLE_COLUMNS = ['aligned_dna_short_read_set_id', 'aligned_dna_short_read_id']
+CALLED_VARIANT_FILE_COLUMN = 'called_variants_dna_file'
 CALLED_TABLE_COLUMNS = [
-    'called_variants_dna_short_read_id', 'aligned_dna_short_read_set_id', 'called_variants_dna_file', 'md5sum',
+    'called_variants_dna_short_read_id', 'aligned_dna_short_read_set_id', CALLED_VARIANT_FILE_COLUMN, 'md5sum',
     'caller_software', 'variant_types', 'analysis_details',
 ]
 
@@ -912,7 +913,9 @@ def gregor_export(request):
         ('experiment_dna_short_read', EXPERIMENT_TABLE_COLUMNS, airtable_rows),
         ('aligned_dna_short_read', READ_TABLE_COLUMNS, airtable_rows),
         ('aligned_dna_short_read_set', READ_SET_TABLE_COLUMNS, airtable_rows),
-        ('called_variants_dna_short_read', CALLED_TABLE_COLUMNS, airtable_rows),
+        ('called_variants_dna_short_read', CALLED_TABLE_COLUMNS, [
+            row for row in airtable_rows if row.get(CALLED_VARIANT_FILE_COLUMN)
+        ]),
         ('experiment_rna_short_read', EXPERIMENT_RNA_TABLE_COLUMNS, airtable_rna_rows),
         ('aligned_rna_short_read', READ_RNA_TABLE_COLUMNS, airtable_rna_rows),
         ('experiment', EXPERIMENT_LOOKUP_TABLE_COLUMNS, experiment_lookup_rows),

seqr/views/apis/report_api_tests.py

@@ -299,9 +299,9 @@
         'mean_coverage_wes': '42.8',
         'mean_coverage_wgs': '36.1',
         'analysis_details': '',
-        'called_variants_dna_short_read_id': 'NA',
+        'called_variants_dna_short_read_id': '',
         'aligned_dna_short_read_set_id': 'Broad_NA20888_D1',
-        'called_variants_dna_file': 'NA',
+        'called_variants_dna_file': '',
         'caller_software': 'NA',
         'variant_types': 'SNV',
       },
@@ -1031,7 +1031,7 @@ def _assert_expected_gregor_files(self, mock_open, has_second_project=False):
         self.assertIn(['Broad_NA20888_D1', 'Broad_exome_NA20888_1'], read_set_file)
         self.assertEqual(['Broad_NA20888_D1', 'Broad_genome_NA20888_1_1'] in read_set_file, has_second_project)
 
-        self.assertEqual(len(called_file), num_airtable_rows)
+        self.assertEqual(len(called_file), 2)
         self.assertEqual(called_file[0], [
             'called_variants_dna_short_read_id', 'aligned_dna_short_read_set_id', 'called_variants_dna_file', 'md5sum',
             'caller_software', 'variant_types', 'analysis_details',
@@ -1040,9 +1040,6 @@ def _assert_expected_gregor_files(self, mock_open, has_second_project=False):
             'SX2-3', 'BCM_H7YG5DSX2', 'gs://fc-fed09429-e563-44a7-aaeb-776c8336ba02/COL_FAM1_1_D1.SV.vcf',
             '129c28163df082', 'gatk4.1.2', 'SNV', 'DOI:10.5281/zenodo.4469317',
         ], called_file)
-        self.assertIn(['NA', 'Broad_NA20888_D1', 'NA', 'a6f6308866765ce8', 'NA', 'SNV', ''], called_file)
-        self.assertEqual(
-            ['NA', 'Broad_NA20888_D1', 'NA', '2aa33e8c32020b1c', 'NA', 'SNV', ''] in called_file, has_second_project)
 
         self.assertEqual(len(experiment_rna_file), 2)
         self.assertEqual(experiment_rna_file[0], [