def test_sheet_germline_inconsistent_pedigree(
tsv_sheet_germline_inconsistent_pedigree,
tsv_sheet_germline_trio_plus,
):
"""Tests Germline sheet for sheet with conflict information for joint field and row."""
# Sanity check
shortcuts.GermlineCaseSheet(
sheet=io_tsv.read_germline_tsv_sheet(tsv_sheet_germline_trio_plus),
join_by_field='familyId')
# Expect error as each member of the pedigree has its own `familyId` instead of a common one
with pytest.raises(InconsistentPedigreeException):
shortcuts.GermlineCaseSheet(sheet=io_tsv.read_germline_tsv_sheet(
tsv_sheet_germline_inconsistent_pedigree),
join_by_field='familyId')
def yield_ngs_library_names(sheet,
min_batch=None,
batch_key="batchNo",
pedigree_field=None):
"""Yield DNA NGS library names for indexes.
:param sheet: Sample sheet.
:type sheet: biomedsheets.models.Sheet
:param min_batch: Minimum batch number to be extracted from the sheet. All samples in batches below this values
will be skipped.
:type min_batch: int
:param batch_key: Batch number key in sheet. Default: 'batchNo'.
:type batch_key: str
:param pedigree_field: Field that should be used to define a pedigree. If none is provided pedigree will be defined
based on information in the sample sheets rows alone.
"""
kwargs = {}
if pedigree_field:
kwargs = {"join_by_field": pedigree_field}
shortcut_sheet = shortcuts.GermlineCaseSheet(sheet, **kwargs)
for pedigree in shortcut_sheet.cohort.pedigrees:
max_batch = max(
donor.extra_infos.get(batch_key, 0) for donor in pedigree.donors)
if (min_batch is None
or min_batch <= max_batch) and pedigree.index.dna_ngs_library:
yield pedigree.index.dna_ngs_library.name
def __init__(self, args):
#: Command line arguments.
self.args = args
#: Raw sample sheet.
self.sheets = load_sheets_tsv(self.args)
#: Shortcut sample sheet.
self.shortcut_sheets = [shortcuts.GermlineCaseSheet(sheet) for sheet in self.sheets]
def yield_ngs_library_names(self,
sheet,
min_batch=None,
max_batch=None,
batch_key="batchNo",
family_key="familyId"):
"""Yield index only NGS library names from sheet.
When ``min_batch`` is given then only the donors for which the ``extra_infos[batch_key]`` is greater than
``min_batch`` will be used.
This function can be overloaded, for example to only consider the indexes.
:param sheet: Sample sheet.
:type sheet: biomedsheets.models.Sheet
:param min_batch: Minimum batch number to be extracted from the sheet. All samples in batches below this values
will be skipped.
:type min_batch: int
:param max_batch: Maximum batch number to be extracted from the sheet. All samples in batches above this values
will be skipped.
:type max_batch: int
:param batch_key: Batch number key in sheet. Default: 'batchNo'.
:type batch_key: str
:param family_key: Family identifier key. Default: 'familyId'.
:type family_key: str
"""
family_max_batch = self._build_family_max_batch(
sheet, batch_key, family_key)
shortcut_sheet = shortcuts.GermlineCaseSheet(sheet)
for pedigree in shortcut_sheet.cohort.pedigrees:
donor = pedigree.index
if min_batch is not None:
batch = self._batch_of(donor, family_max_batch, batch_key,
family_key)
if batch < min_batch:
logger.debug(
"Skipping donor %s because %s = %d < min_batch = %d",
donor.name,
batch_key,
donor.extra_infos[batch_key],
min_batch,
)
continue
if max_batch is not None:
if batch > max_batch:
logger.debug(
"Skipping donor %s because %s = %d > max_batch = %d",
donor.name,
batch_key,
donor.extra_infos[batch_key],
max_batch,
)
continue
logger.debug("Processing NGS library for donor %s", donor.name)
yield donor.dna_ngs_library.name
def yield_ngs_library_names(sheet, min_batch=None, batch_key="batchNo"):
shortcut_sheet = shortcuts.GermlineCaseSheet(sheet)
for pedigree in shortcut_sheet.cohort.pedigrees:
donor = pedigree.index
if min_batch is not None and batch_key in donor.extra_infos:
if min_batch > donor.extra_infos[batch_key]:
logger.debug(
"Skipping donor %s because %s = %d < min_batch = %d",
donor.name,
donor.extra_infos[batch_key],
batch_key,
min_batch,
)
continue
yield donor.dna_ngs_library.name
def test_load_sheet_tsv():
"""Tests load_sheet_tsv()"""
# Define expected
expected_ngs_library_name_list = [
"P001-N1-DNA1-WGS1", "P004-N1-DNA1-WGS1", "P007-N1-DNA1-WGS1"
]
# Define input
sheet_path = pathlib.Path(
__file__).resolve().parent / "data" / "germline_sheet.tsv"
# Get actual
sheet = load_sheet_tsv(path_tsv=sheet_path)
assert isinstance(sheet, models.Sheet)
# Convert to manageable format
shortcut_sheet = shortcuts.GermlineCaseSheet(sheet)
for pedigree in shortcut_sheet.cohort.pedigrees:
assert pedigree.index.dna_ngs_library.name in expected_ngs_library_name_list
def yield_ngs_library_names(self,
sheet,
min_batch=None,
batch_key="batchNo",
family_key="familyId"):
family_max_batch = self._build_family_max_batch(
sheet, batch_key, family_key)
shortcut_sheet = shortcuts.GermlineCaseSheet(sheet)
for pedigree in shortcut_sheet.cohort.pedigrees:
donor = pedigree.index
if min_batch is not None:
batch = self._batch_of(donor, family_max_batch, batch_key,
family_key)
if batch < min_batch:
logger.debug(
"Skipping donor %s because %s = %d < min_batch = %d",
donor.name,
batch_key,
donor.extra_infos[batch_key],
min_batch,
)
continue
yield donor.dna_ngs_library.name
def sheet_germline(tsv_sheet_germline):
"""Return ``Sheet`` instance for the germline example"""
return shortcuts.GermlineCaseSheet(
io_tsv.read_germline_tsv_sheet(tsv_sheet_germline))
def test_sheet_germline_trio_plus_exception(tsv_sheet_germline_trio_plus):
"""Tests UndefinedFieldException raise while creating GermlineCaseSheet"""
with pytest.raises(UndefinedFieldException):
shortcuts.GermlineCaseSheet(
sheet=io_tsv.read_germline_tsv_sheet(tsv_sheet_germline_trio_plus),
join_by_field='undefined_field')
def sheet_germline_only_parent_samples(tsv_sheet_germline_only_parent_samples):
"""Return ``Sheet`` instance for the germline example where only parents have samples"""
return shortcuts.GermlineCaseSheet(
io_tsv.read_germline_tsv_sheet(
tsv_sheet_germline_only_parent_samples,
naming_scheme=naming.NAMING_ONLY_SECONDARY_ID))
def sheet_germline_two_test_samples(tsv_sheet_germline_two_test_samples):
"""Return ``Sheet`` instance for the germline example with two test_samples"""
return shortcuts.GermlineCaseSheet(
io_tsv.read_germline_tsv_sheet(
tsv_sheet_germline_two_test_samples,
naming_scheme=naming.NAMING_ONLY_SECONDARY_ID))
def sheet_germline_multiple_trio_plus(tsv_sheet_germline_multiple_trio_plus):
"""Return ``Sheet`` instance for the germline multiple trio plus example"""
return shortcuts.GermlineCaseSheet(sheet=io_tsv.read_germline_tsv_sheet(
tsv_sheet_germline_multiple_trio_plus),
join_by_field='familyId')
