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 test_yield_ngs_library_names():
"""Tests yield_ngs_library_names()"""
# Define expected
expected_batch_one = ["P001-N1-DNA1-WGS1"]
expected_batch_two = ["P004-N1-DNA1-WGS1"]
expected_batch_three = ["P007-N1-DNA1-WGS1"]
expected_ped_field_defined = expected_batch_one + expected_batch_two
expected_ped_field_none = expected_batch_one + expected_batch_two + expected_batch_three
# Define input
sheet_path = pathlib.Path(__file__).resolve().parent / "data" / "germline_sheet.tsv"
with open(sheet_path, "rt") as f_sheet:
sheet = read_germline_tsv_sheet(f=f_sheet, naming_scheme=NAMING_ONLY_SECONDARY_ID)
# Test `pedigree_field` = 'familyId'
actual = yield_ngs_library_names(sheet=sheet, pedigree_field="familyId")
for name_ in actual:
assert name_ in expected_ped_field_defined
# Test `pedigree_field` is None
actual = yield_ngs_library_names(sheet=sheet, pedigree_field=None)
for name_ in actual:
assert name_ in expected_ped_field_none
# Test `pedigree_field` is None and min batch = 2
actual = yield_ngs_library_names(sheet=sheet, pedigree_field=None, min_batch=2)
for name_ in actual:
expected_list = expected_batch_two + expected_batch_three
assert name_ in expected_list
# Test `pedigree_field` is None and min batch = 3
actual = yield_ngs_library_names(sheet=sheet, pedigree_field=None, min_batch=3)
for name_ in actual:
assert name_ in expected_batch_three
def test_read_germline_sheet_platform_name(tsv_sheet_germline_platform_name):
sheet = io_tsv.read_germline_tsv_sheet(tsv_sheet_germline_platform_name)
assert EXPECTED_GERMLINE_SHEET_JSON_PLATFORM_NAME == json.dumps(
sheet.json_data, indent=' ')
def test_read_germline_sheet_no_header_hyphened_identifiers(
tsv_sheet_germline_no_header_hyphened_identifier):
sheet = io_tsv.read_germline_tsv_sheet(
tsv_sheet_germline_no_header_hyphened_identifier)
assert EXPECTED_GERMLINE_SHEET_JSON_NO_HEADER_HYPHEN == json.dumps(
sheet.json_data, indent=' ')
def test_read_germline_sheet_no_header(tsv_sheet_germline_no_header):
sheet = io_tsv.read_germline_tsv_sheet(tsv_sheet_germline_no_header)
assert EXPECTED_GERMLINE_SHEET_JSON_NO_HEADER == json.dumps(
sheet.json_data, indent=' ')
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')
def test_yield_ngs_library_names(snappy_itransfer_command_base):
"""Tests varfish_upload.yield_ngs_library_names()"""
# Define expected
expected_batch_one = [
"P001-N1-DNA1-WGS1", "P002-N1-DNA1-WGS1", "P003-N1-DNA1-WGS1"
]
expected_batch_two = [
"P004-N1-DNA1-WGS1", "P005-N1-DNA1-WGS1", "P006-N1-DNA1-WGS1"
]
expected_batch_three = [
"P007-N1-DNA1-WGS1", "P008-N1-DNA1-WGS1", "P009-N1-DNA1-WGS1"
]
expected_batch_four = [
"P010-N1-DNA1-WGS1", "P011-N1-DNA1-WGS1", "P012-N1-DNA1-WGS1"
]
expected_batch_five = ["P013-N1-DNA1-WGS1", "P014-N1-DNA1-WGS1"]
expected_batch_six = ["P015-N1-DNA1-WGS1"]
# Define input
sheet_path = pathlib.Path(
__file__).resolve().parent / "data" / "germline_sheet_multi_batch.tsv"
with open(sheet_path, "rt") as f_sheet:
sheet = read_germline_tsv_sheet(f=f_sheet,
naming_scheme=NAMING_ONLY_SECONDARY_ID)
# Sanity test - no constraints
actual = snappy_itransfer_command_base.yield_ngs_library_names(
sheet=sheet, min_batch=None, max_batch=None)
expected_list = (expected_batch_one + expected_batch_two +
expected_batch_three + expected_batch_four +
expected_batch_five + expected_batch_six)
for name_ in actual:
assert name_ in expected_list
# Test min batch = 2, max batch = None
actual = snappy_itransfer_command_base.yield_ngs_library_names(
sheet=sheet, min_batch=2, max_batch=None)
expected_list = (expected_batch_two + expected_batch_three +
expected_batch_four + expected_batch_five +
expected_batch_six)
for name_ in actual:
assert name_ in expected_list
# Test min batch = 2, max batch = 3
actual = snappy_itransfer_command_base.yield_ngs_library_names(sheet=sheet,
min_batch=2,
max_batch=3)
expected_list = expected_batch_two + expected_batch_three
for name_ in actual:
assert name_ in expected_list
# Test min batch = 3, max batch = 5
actual = snappy_itransfer_command_base.yield_ngs_library_names(sheet=sheet,
min_batch=3,
max_batch=5)
expected_list = expected_batch_three + expected_batch_four + expected_batch_five
for name_ in actual:
assert name_ in expected_list
# Test min batch = 5, max batch = 5
actual = snappy_itransfer_command_base.yield_ngs_library_names(sheet=sheet,
min_batch=5,
max_batch=5)
expected_list = expected_batch_five
for name_ in actual:
assert name_ in expected_list
# Test min batch = 6, max batch = 6
actual = snappy_itransfer_command_base.yield_ngs_library_names(sheet=sheet,
min_batch=6,
max_batch=6)
expected_list = expected_batch_six
for name_ in actual:
assert name_ in expected_list