def files_data(files_raw):
return {
'config': files_api.parse_config(files_raw['config']),
'sampleinfo': files_api.parse_sampleinfo(files_raw['sampleinfo']),
'qcmetrics': files_api.parse_qcmetrics(files_raw['qcmetrics']),
'sacct': sacct.parse_sacct(files_raw['sacct']),
}
def files_data(files_raw):
return {
'config': files_api.parse_config(files_raw['config']),
'sampleinfo': files_api.parse_sampleinfo(files_raw['sampleinfo']),
'qcmetrics': files_api.parse_qcmetrics(files_raw['qcmetrics']),
'sacct': sacct.parse_sacct(files_raw['sacct']),
}
def test_parse_qcmetrics(files_raw):
"""
Args:
files_raw (dict): With dicts from files
"""
# GIVEN qc metrics input from an analysis
qcmetrics_raw = files_raw['qcmetrics']
# WHEN parsing it
qcmetrics_data = files.parse_qcmetrics(qcmetrics_raw)
# THEN it should work ;-)
assert isinstance(qcmetrics_data, dict)
# Sample data
# Build dict for sample return data
qcmetrics_test_sample_data = {
'at_dropout': '1.716704',
'duplicates': 0.0379523291229131,
'id': 'mother',
'insert_size_standard_deviation': 94.353778,
'gc_dropout': '0.214813',
'mapped': 0.9974176575073073,
'median_insert_size': '409',
'plink_sex': 'female',
'predicted_sex': 'female',
'reads': 600006004,
'strand_balance': 0.50162,
'target_coverage': 28.643247,
}
# Check returns from def
for key, value in qcmetrics_test_sample_data.items():
for sample_data in qcmetrics_data['samples']:
if sample_data['id'] != qcmetrics_test_sample_data['id']:
continue
assert sample_data[key] == value
# Sample coverage data
# Build dict for sample coverage return data
qcmetrics_test_sample_cov_data = {
10: '0.98974',
20: '0.935455',
50: '0.002685',
100: '0.000101',
}
# Check returns from def
for key, value in qcmetrics_test_sample_cov_data.items():
for sample_data in qcmetrics_data['samples']:
if sample_data['id'] != qcmetrics_test_sample_data['id']:
continue
assert sample_data['completeness_target'][key] == value
def files_data(files_raw):
"""Get some data files"""
return {
"config": mip_dna_files_api.parse_config(files_raw["config"]),
"sampleinfo": mip_dna_files_api.parse_sampleinfo(files_raw["sampleinfo"]),
"qcmetrics": mip_dna_files_api.parse_qcmetrics(files_raw["qcmetrics"]),
"rna_config": mip_dna_files_api.parse_config(files_raw["rna_config"]),
"rna_sampleinfo": mip_rna_files_api.parse_sampleinfo_rna(files_raw["rna_sampleinfo"]),
"rna_config_store": store_mip.parse_config(files_raw["rna_config_store"]),
"rna_sampleinfo_store": store_mip.parse_sampleinfo(files_raw["rna_sampleinfo_store"]),
}
def parse_qcmetrics(data: dict) -> dict:
"""Call internal Trailblazer MIP API."""
return files.parse_qcmetrics(data)
def test_parse_qcmetrics(files_raw):
"""
Args:
files_raw (dict): With dicts from files
"""
# GIVEN qc metrics input from an analysis
qcmetrics_raw = files_raw['qcmetrics']
# WHEN parsing it
qcmetrics_data = files.parse_qcmetrics(qcmetrics_raw)
# THEN it should work ;-)
assert isinstance(qcmetrics_data, dict)
## Version data
# Build dict for version return data
qcmetrics_test_version_data = {
'freebayes': 'v1.0.2',
'gatk': 3.6,
'manta': '1.0.3',
'bcftools': '1.3.1+htslib-1.3.1',
'vep': 'v87',
}
# Check returns from def
for key, value in qcmetrics_test_version_data.items():
assert qcmetrics_data['versions'][key] == value
## Sample data
# Build dict for sample return data
qcmetrics_test_sample_data = {
'at_dropout': 0.126963,
'duplicates': 0.132719986683768,
'id': 'sample',
'insert_size_standard_deviation': 89.871783,
'gc_dropout': 3.956909,
'mapped': 0.9850732625744484,
'median_insert_size': 413,
'plink_sex': 'female',
'predicted_sex': 'female',
'reads': 949878168,
'strand_balance': 0.499558,
'target_coverage': 37.428611,
}
# Check returns from def
for key, value in qcmetrics_test_sample_data.items():
for sample_data in qcmetrics_data['samples']:
assert sample_data[key] == value
## Sample coverage data
# Build dict for sample coverage return data
qcmetrics_test_sample_cov_data = {
10: 0.991187,
20: 0.984713,
50: 0.063229,
100: 0.000372,
}
# Check returns from def
for key, value in qcmetrics_test_sample_cov_data.items():
for sample_data in qcmetrics_data['samples']:
assert sample_data['completeness_target'][key] == value
def test_parse_qcmetrics(files_raw):
"""
Args:
files_raw (dict): With dicts from files
"""
# GIVEN qc metrics input from an analysis
qcmetrics_raw = files_raw['qcmetrics']
# WHEN parsing it
qcmetrics_data = files.parse_qcmetrics(qcmetrics_raw)
# THEN it should work ;-)
assert isinstance(qcmetrics_data, dict)
## Version data
# Build dict for version return data
qcmetrics_test_version_data = {
'freebayes': 'v1.0.2',
'gatk': 3.6,
'manta': '1.0.3',
'bcftools': '1.3.1+htslib-1.3.1',
'vep': 'v87',
}
# Check returns from def
for key, value in qcmetrics_test_version_data.items():
assert qcmetrics_data['versions'][key] == value
## Sample data
# Build dict for sample return data
qcmetrics_test_sample_data = {
'at_dropout': 0.126963,
'duplicates': 0.132719986683768,
'id': 'sample',
'insert_size_standard_deviation': 89.871783,
'gc_dropout': 3.956909,
'mapped': 0.9850732625744484,
'median_insert_size': 413,
'plink_sex': 'female',
'predicted_sex': 'female',
'reads': 949878168,
'strand_balance': 0.499558,
'target_coverage': 37.428611,
}
# Check returns from def
for key, value in qcmetrics_test_sample_data.items():
for sample_data in qcmetrics_data['samples']:
assert sample_data[key] == value
## Sample coverage data
# Build dict for sample coverage return data
qcmetrics_test_sample_cov_data = {
10: 0.991187,
20: 0.984713,
50: 0.063229,
100: 0.000372,
}
# Check returns from def
for key, value in qcmetrics_test_sample_cov_data.items():
for sample_data in qcmetrics_data['samples']:
assert sample_data['completeness_target'][key] == value
def check(context: click.Context, family: str):
"""Delete an analysis log from the database."""
analysis_obj = context.obj['store'].analyses(family=family).first()
if analysis_obj is None:
LOG.error('no analysis found')
context.abort()
config_path = Path(analysis_obj.config_path)
if not config_path.exists():
LOG.error(f"analysis config not found: {config_path}")
context.abort()
config_raw = ruamel.yaml.safe_load(config_path.open())
config_data = files.parse_config(config_raw)
sampleinfo_raw = ruamel.yaml.safe_load(
Path(config_data['sampleinfo_path']).open())
sampleinfo_data = files.parse_sampleinfo(sampleinfo_raw)
qcmetrics_path = Path(sampleinfo_data['qcmetrics_path'])
if not qcmetrics_path.exists():
LOG.error(f"qc metrics not found: {str(qcmetrics_path)}")
context.abort()
qcmetrics_raw = ruamel.yaml.safe_load(qcmetrics_path.open())
qcmetrics_data = files.parse_qcmetrics(qcmetrics_raw)
samples = {
'sample': [],
'type': [],
'ped': [],
'chanjo': [],
'peddy': [],
'plink': [],
'duplicates': [],
}
for sample_data in config_data['samples']:
LOG.debug(f"{sample_data['id']}: parse analysis config")
samples['sample'].append(sample_data['id'])
samples['type'].append(sample_data['type'])
for sample_data in sampleinfo_data['samples']:
LOG.debug(f"{sample_data['id']}: parse sample info")
samples['ped'].append(sample_data['sex'])
with Path(sample_data['chanjo_sexcheck']).open() as chanjo_handle:
sexcheck_data = files.parse_chanjo_sexcheck(chanjo_handle)
predicted_sex = sexcheck_data['predicted_sex']
xy_ratio = sexcheck_data['y_coverage'] / sexcheck_data['x_coverage']
samples['chanjo'].append(f"{predicted_sex} ({xy_ratio:.3f})")
for sample_data in qcmetrics_data['samples']:
LOG.debug(f"{sample_data['id']}: parse qc metrics")
samples['plink'].append(sample_data['plink_sex'])
duplicates_percent = sample_data['duplicates'] * 100
samples['duplicates'].append(f"{duplicates_percent:.3f}%")
peddy_path = Path(sampleinfo_data['peddy']['sex_check'])
if peddy_path.exists():
with peddy_path.open() as sexcheck_handle:
peddy_data = files.parse_peddy_sexcheck(sexcheck_handle)
for sample_id in samples['sample']:
LOG.debug(f"{sample_id}: parse peddy")
predicted_sex = peddy_data[sample_id]['predicted_sex']
het_ratio = peddy_data[sample_id]['het_ratio']
samples['peddy'].append(f"{predicted_sex} ({het_ratio})")
else:
LOG.warning(f"missing peddy output: {peddy_path}")
print(tabulate(samples, headers='keys', tablefmt='psql'))
def _parse_qc_metric_file_into_dict(qcmetrics_raw):
qcmetrics_data = files.parse_qcmetrics(qcmetrics_raw)
return qcmetrics_data
def check(context: click.Context, family: str):
"""Delete an analysis log from the database."""
analysis_obj = context.obj['store'].analyses(family=family).first()
if analysis_obj is None:
LOG.error('no analysis found')
context.abort()
config_path = Path(analysis_obj.config_path)
if not config_path.exists():
LOG.error(f"analysis config not found: {config_path}")
context.abort()
config_raw = ruamel.yaml.safe_load(config_path.open())
config_data = files.parse_config(config_raw)
sampleinfo_raw = ruamel.yaml.safe_load(Path(config_data['sampleinfo_path']).open())
sampleinfo_data = files.parse_sampleinfo(sampleinfo_raw)
qcmetrics_path = Path(sampleinfo_data['qcmetrics_path'])
if not qcmetrics_path.exists():
LOG.error(f"qc metrics not found: {str(qcmetrics_path)}")
context.abort()
qcmetrics_raw = ruamel.yaml.safe_load(qcmetrics_path.open())
qcmetrics_data = files.parse_qcmetrics(qcmetrics_raw)
samples = {
'sample': [],
'type': [],
'ped': [],
'chanjo': [],
'peddy': [],
'plink': [],
'duplicates': [],
}
for sample_data in config_data['samples']:
LOG.debug(f"{sample_data['id']}: parse analysis config")
samples['sample'].append(sample_data['id'])
samples['type'].append(sample_data['type'])
for sample_data in sampleinfo_data['samples']:
LOG.debug(f"{sample_data['id']}: parse sample info")
samples['ped'].append(sample_data['sex'])
with Path(sample_data['chanjo_sexcheck']).open() as chanjo_handle:
sexcheck_data = files.parse_chanjo_sexcheck(chanjo_handle)
predicted_sex = sexcheck_data['predicted_sex']
xy_ratio = sexcheck_data['y_coverage'] / sexcheck_data['x_coverage']
samples['chanjo'].append(f"{predicted_sex} ({xy_ratio:.3f})")
for sample_data in qcmetrics_data['samples']:
LOG.debug(f"{sample_data['id']}: parse qc metrics")
samples['plink'].append(sample_data['plink_sex'])
duplicates_percent = sample_data['duplicates'] * 100
samples['duplicates'].append(f"{duplicates_percent:.3f}%")
peddy_path = Path(sampleinfo_data['peddy']['sex_check'])
if peddy_path.exists():
with peddy_path.open() as sexcheck_handle:
peddy_data = files.parse_peddy_sexcheck(sexcheck_handle)
for sample_id in samples['sample']:
LOG.debug(f"{sample_id}: parse peddy")
predicted_sex = peddy_data[sample_id]['predicted_sex']
het_ratio = peddy_data[sample_id]['het_ratio']
samples['peddy'].append(f"{predicted_sex} ({het_ratio})")
else:
LOG.warning(f"missing peddy output: {peddy_path}")
print(tabulate(samples, headers='keys', tablefmt='psql'))
def _parse_qc_metric_file_into_dict(qcmetrics_raw):
qcmetrics_data = files.parse_qcmetrics(qcmetrics_raw)
return qcmetrics_data
