Merge pull request #3984 from broadinstitute/dont-skip-gtex

do not allow unneccessary GTEX data in rna upload
broadinstitute · Mar 19, 2024 · 499d67d · 499d67d
2 parents e083b1c + 5d4bf80
commit 499d67d
Show file tree

Hide file tree

Showing 3 changed files with 2 additions and 8 deletions.
diff --git a/seqr/management/tests/load_rna_seq_tests.py b/seqr/management/tests/load_rna_seq_tests.py
@@ -68,9 +68,7 @@ def test_tpm(self, mock_utils_logger):
                 'NA19675_D2\t1kg project nåme with uniçøde\t\tENSG00000240361\t12.6\t\n',
                 'NA19675_D2\t1kg project nåme with uniçøde\t\tENSG00000233750\t1.26\t\n',
                 'NA19678_D1\t1kg project nåme with uniçøde\t\tENSG00000233750\t 6.04\twhole_blood\n',
-                'GTEX-001\t1kg project nåme with uniçøde\t\tENSG00000240361\t3.1\tinvalid\n',
                 'NA19677\t1kg project nåme with uniçøde\t\tENSG00000233750\t5.31\tmuscle\n',
-                'GTEX-001\t1kg project nåme with uniçøde\t\tENSG00000233750\t7.8\tmuscle\n',
                 'NA19678\tTest Reprocessed Project\t\tENSG00000240361\t0.2\twhole_blood\n',
             ],
             unmatched_samples='NA19677, NA19678, NA19678_D1',

diff --git a/seqr/views/apis/data_manager_api_tests.py b/seqr/views/apis/data_manager_api_tests.py
@@ -708,8 +708,6 @@ def test_kibana_proxy(self):
                 ['NA19675_D2', '1kg project nåme with uniçøde', 'ENSG00000233750', 'NA19675_D2', 'muscle', 0.0],
                 # no matched individual NA19675_D3
                 ['NA19675_D3', '1kg project nåme with uniçøde', 'ENSG00000233750', 'NA19675_D3', 'fibroblasts', 0.064],
-                # skip GTEX samples
-                ['GTEX_001', '1kg project nåme with uniçøde', 'ENSG00000233750', 'NA19675_D3', 'whole_blood', 1.95],
                 # a different project sample NA20888
                 ['NA20888', 'Test Reprocessed Project', 'ENSG00000240361', 'NA20888', 'muscle', 0.112],
                 # a project mismatched sample NA20878

diff --git a/seqr/views/utils/dataset_utils.py b/seqr/views/utils/dataset_utils.py
@@ -294,7 +294,7 @@ def _add_splice_rank(sample_data_rows):
     'tpm': {
         'model_class': RnaSeqTpm,
         'columns': TPM_HEADER_COLS,
-        'additional_kwargs': {'should_skip': lambda row: row[SAMPLE_ID_COL].startswith('GTEX')},
+        'additional_kwargs': {},
     },
     'splice_outlier': {
         'model_class': RnaSeqSpliceOutlier,
@@ -331,7 +331,7 @@ def _validate_rna_header(header, column_map):
 def _load_rna_seq_file(
         file_path, user, potential_loaded_samples, update_sample_models, save_sample_data, get_matched_sample,
         column_map, mapping_file=None, allow_missing_gene=False, ignore_extra_samples=False,
-        should_skip=None, format_fields=None,
+        format_fields=None,
 ):
 
     sample_id_to_individual_id_mapping = {}
@@ -349,8 +349,6 @@ def _load_rna_seq_file(
     gene_ids = set()
     for line in tqdm(parsed_f, unit=' rows'):
         row = dict(zip(header, line))
-        if should_skip and should_skip(row):
-            continue
 
         row_dict = {mapped_key: row[col] for mapped_key, col in column_map.items()}
         for mapped_key, format_func in (format_fields or {}).items():