Skip to content

fix #3246 #3247

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 9, 2023
Merged

fix #3246 #3247

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ad40a15
fix #3246
antgonza Feb 8, 2023
80a0326
fix str cast error
antgonza Feb 9, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 25 additions & 0 deletions qiita_db/metadata_template/base_metadata_template.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,22 @@
# information
QIITA_COLUMN_NAME = 'qiita_sample_column_names'

INSDC_NULL_VALUES = {
'not collected': 'not collected',
'not provided': 'not provided',
'restricted access': 'restricted access',
'not applicable': 'not applicable',
'unspecified': 'not applicable',
'not_collected': 'not collected',
'not_provided': 'not provided',
'restricted_access': 'restricted access',
'not_applicable': 'not applicable',
'missing: not collected': 'not collected',
'missing: not provided': 'not provided',
'missing: restricted access': 'restricted access',
'missing: not applicable': 'not applicable',
}


def _helper_get_categories(table):
"""This is a helper function to avoid duplication of code"""
Expand Down Expand Up @@ -585,6 +601,15 @@ def _clean_validate_template(cls, md_template, study_id,
raise qdb.exceptions.QiitaDBDuplicateHeaderError(
set(duplicates(md_template.columns)))

# validate the INSDC_NULL_VALUES
_df = md_template.fillna("").applymap(str).applymap(str.lower)
_ddf = _df[_df.isin(INSDC_NULL_VALUES.keys()).any(axis=1)]
if _ddf.shape[0] != 0:
for c in _ddf.columns:
if set(INSDC_NULL_VALUES) & set(_ddf[c].values):
for s, v in _ddf[c].to_dict().items():
md_template[c][s] = INSDC_NULL_VALUES[v]

return md_template

@classmethod
Expand Down
38 changes: 28 additions & 10 deletions qiita_db/metadata_template/test/test_prep_template.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -298,6 +298,7 @@ def setUp(self):
'qiita_prep_id': 1000,
'instrument_model': 'Illumina MiSeq',
'library_construction_protocol': 'AAAA',
'insdc_nulls': '3.6',
'experiment_design_description': 'BBBB'},
'SKD8.640184': {'center_name': 'ANL',
'center_project_name': 'Test Project',
Expand All @@ -311,6 +312,7 @@ def setUp(self):
'qiita_prep_id': 1000,
'instrument_model': 'Illumina MiSeq',
'library_construction_protocol': 'AAAA',
'insdc_nulls': 'NoT applicable',
'experiment_design_description': 'BBBB'},
'SKB7.640196': {'center_name': 'ANL',
'center_project_name': 'Test Project',
Expand All @@ -324,6 +326,7 @@ def setUp(self):
'qiita_prep_id': 1000,
'instrument_model': 'Illumina MiSeq',
'library_construction_protocol': 'AAAA',
'insdc_nulls': 'unspecified',
'experiment_design_description': 'BBBB'}
}
self.metadata = pd.DataFrame.from_dict(self.metadata_dict,
Expand All @@ -342,6 +345,7 @@ def setUp(self):
'qiita_prep_id': 1000,
'instrument_model': 'Illumina MiSeq',
'library_construction_protocol': 'AAAA',
'insdc_nulls': '3.6',
'experiment_design_description': 'BBBB'},
'1.SKD8.640184': {'center_name': 'ANL',
'center_project_name': 'Test Project',
Expand All @@ -355,6 +359,7 @@ def setUp(self):
'qiita_prep_id': 1000,
'instrument_model': 'Illumina MiSeq',
'library_construction_protocol': 'AAAA',
'insdc_nulls': 'not applicable',
'experiment_design_description': 'BBBB'},
'1.SKB7.640196': {'center_name': 'ANL',
'center_project_name': 'Test Project',
Expand All @@ -368,6 +373,7 @@ def setUp(self):
'qiita_prep_id': 1000,
'instrument_model': 'Illumina MiSeq',
'library_construction_protocol': 'AAAA',
'insdc_nulls': 'not applicable',
'experiment_design_description': 'BBBB'}
}
self.metadata_prefixed = pd.DataFrame.from_dict(metadata_prefixed_dict,
Expand Down Expand Up @@ -730,6 +736,7 @@ def test_clean_validate_template(self):
'platform': 'Illumina',
'instrument_model': 'Illumina MiSeq',
'library_construction_protocol': 'AAAA',
'insdc_nulls': '3.6',
'experiment_design_description': 'BBBB'},
'2.SKD8.640184': {'center_name': 'ANL',
'center_project_name': 'Test Project',
Expand All @@ -742,6 +749,7 @@ def test_clean_validate_template(self):
'platform': 'Illumina',
'instrument_model': 'Illumina MiSeq',
'library_construction_protocol': 'AAAA',
'insdc_nulls': 'not applicable',
'experiment_design_description': 'BBBB'},
'2.SKB7.640196': {'center_name': 'ANL',
'center_project_name': 'Test Project',
Expand All @@ -754,13 +762,16 @@ def test_clean_validate_template(self):
'platform': 'Illumina',
'instrument_model': 'Illumina MiSeq',
'library_construction_protocol': 'AAAA',
'insdc_nulls': 'not applicable',
'experiment_design_description': 'BBBB'}
}
exp = pd.DataFrame.from_dict(metadata_dict, orient='index', dtype=str)

obs.sort_index(axis=0, inplace=True)
obs.sort_index(axis=1, inplace=True)
exp.sort_index(axis=0, inplace=True)
exp.sort_index(axis=1, inplace=True)

assert_frame_equal(obs, exp, check_like=True)

def test_clean_validate_template_no_forbidden_words1(self):
Expand Down Expand Up @@ -909,7 +920,7 @@ def _common_creation_checks(self, pt, fp_count, name):
'run_prefix', 'barcode', 'primer', 'platform',
'instrument_model', 'experiment_design_description',
'library_construction_protocol', 'center_name',
'center_project_name', 'emp_status'}
'center_project_name', 'insdc_nulls', 'emp_status'}
self.assertCountEqual(pt.categories, exp_categories)
exp_dict = {
'%s.SKB7.640196' % self.test_study.id: {
Expand All @@ -924,6 +935,7 @@ def _common_creation_checks(self, pt, fp_count, name):
'str_column': 'Value for sample 3',
'center_name': 'ANL',
'center_project_name': 'Test Project',
'insdc_nulls': 'not applicable',
'emp_status': 'EMP'},
'%s.SKB8.640193' % self.test_study.id: {
'barcode': 'GTCCGCAAGTTA',
Expand All @@ -937,6 +949,7 @@ def _common_creation_checks(self, pt, fp_count, name):
'str_column': 'Value for sample 1',
'center_name': 'ANL',
'center_project_name': 'Test Project',
'insdc_nulls': '3.6',
'emp_status': 'EMP'},
'%s.SKD8.640184' % self.test_study.id: {
'barcode': 'CGTAGAGCTCTC',
Expand All @@ -950,6 +963,7 @@ def _common_creation_checks(self, pt, fp_count, name):
'str_column': 'Value for sample 2',
'center_name': 'ANL',
'center_project_name': 'Test Project',
'insdc_nulls': 'not applicable',
'emp_status': 'EMP'}
}
for s_id in exp_sample_ids:
Expand Down Expand Up @@ -1068,7 +1082,7 @@ def test_create_warning(self):
self.assertEqual(pt._get_sample_ids(), exp_sample_ids)
self.assertEqual(len(pt), 3)
exp_categories = {'str_column', 'ebi_submission_accession',
'run_prefix', 'primer', 'platform',
'run_prefix', 'primer', 'platform', 'insdc_nulls',
'instrument_model', 'experiment_design_description',
'library_construction_protocol', 'center_name',
'center_project_name', 'emp_status'}
Expand All @@ -1085,6 +1099,7 @@ def test_create_warning(self):
'str_column': 'Value for sample 3',
'center_name': 'ANL',
'center_project_name': 'Test Project',
'insdc_nulls': 'not applicable',
'emp_status': 'EMP'},
'%s.SKB8.640193' % self.test_study.id: {
'ebi_submission_accession': None,
Expand All @@ -1097,6 +1112,7 @@ def test_create_warning(self):
'str_column': 'Value for sample 1',
'center_name': 'ANL',
'center_project_name': 'Test Project',
'insdc_nulls': '3.6',
'emp_status': 'EMP'},
'%s.SKD8.640184' % self.test_study.id: {
'ebi_submission_accession': None,
Expand All @@ -1109,6 +1125,7 @@ def test_create_warning(self):
'str_column': 'Value for sample 2',
'center_name': 'ANL',
'center_project_name': 'Test Project',
'insdc_nulls': 'not applicable',
'emp_status': 'EMP'}
}
for s_id in exp_sample_ids:
Expand Down Expand Up @@ -1217,6 +1234,7 @@ def test_to_file(self):
self._clean_up_files.append(fp)
with open(fp, newline=None) as f:
obs = f.read()

self.assertEqual(obs, EXP_PREP_TEMPLATE.format(pt.id))

# cleaning
Expand Down Expand Up @@ -1803,17 +1821,17 @@ def test_name_setter(self):
EXP_PREP_TEMPLATE = (
'sample_name\tbarcode\tcenter_name\tcenter_project_name\t'
'ebi_submission_accession\temp_status\texperiment_design_description\t'
'instrument_model\tlibrary_construction_protocol\tplatform\tprimer\t'
'qiita_prep_id\trun_prefix\tstr_column\n'
'insdc_nulls\tinstrument_model\tlibrary_construction_protocol\tplatform\t'
'primer\tqiita_prep_id\trun_prefix\tstr_column\n'
'1.SKB7.640196\tCCTCTGAGAGCT\tANL\tTest Project\t\tEMP\tBBBB\t'
'Illumina MiSeq\tAAAA\tIllumina\tGTGCCAGCMGCCGCGGTAA\t{0}\t'
's_G1_L002_sequences\tValue for sample 3\n'
'not applicable\tIllumina MiSeq\tAAAA\tIllumina\tGTGCCAGCMGCCGCGGTAA\t'
'{0}\ts_G1_L002_sequences\tValue for sample 3\n'
'1.SKB8.640193\tGTCCGCAAGTTA\tANL\tTest Project\t\tEMP\tBBBB\t'
'Illumina MiSeq\tAAAA\tIllumina\tGTGCCAGCMGCCGCGGTAA\t{0}\t'
's_G1_L001_sequences\tValue for sample 1\n'
'3.6\tIllumina MiSeq\tAAAA\tIllumina\tGTGCCAGCMGCCGCGGTAA\t'
'{0}\ts_G1_L001_sequences\tValue for sample 1\n'
'1.SKD8.640184\tCGTAGAGCTCTC\tANL\tTest Project\t\tEMP\tBBBB\t'
'Illumina MiSeq\tAAAA\tIllumina\tGTGCCAGCMGCCGCGGTAA\t{0}\t'
's_G1_L001_sequences\tValue for sample 2\n')
'not applicable\tIllumina MiSeq\tAAAA\tIllumina\tGTGCCAGCMGCCGCGGTAA\t'
'{0}\ts_G1_L001_sequences\tValue for sample 2\n')


if __name__ == '__main__':
Expand Down