def parse_smn_file(lines):
"""Parse a SMNCopyNumberCaller TSV file.
Args:
lines(iterable(str))
Returns:
list(sma_info_per_individual(dict))
"""
individuals = []
header = []
for i, line in enumerate(lines):
line = line.rstrip()
if i == 0:
# Header line
header = line.split("\t")
else:
ind_info = dict(zip(header, line.split("\t")))
smn_ind_info = {}
smn_ind_info["sample_id"] = ind_info["Sample"]
smn_ind_info["is_sma"] = make_bool(ind_info["isSMA"])
smn_ind_info["is_sma_carrier"] = make_bool(ind_info["isCarrier"])
smn_ind_info["smn1_cn"] = convert_number(ind_info["SMN1_CN"])
smn_ind_info["smn2_cn"] = convert_number(ind_info["SMN2_CN"])
smn_ind_info["smn2delta78_cn"] = convert_number(
ind_info["SMN2delta7-8_CN"])
smn_ind_info["smn_27134_cn"] = convert_number(
ind_info["g.27134T>G_CN"])
individuals.append(smn_ind_info)
return individuals
def test_make_bool_YES():
## GIVEN a empty string
a = "YES"
## WHEN converting to a boolean
res = make_bool(a)
## THEN assert it is True
assert res is True
def test_make_bool_nonsense():
## GIVEN a nonsense string
a = "nonsense asdlkfjalk"
## WHEN converting to a boolean
res = make_bool(a)
## THEN assert it is False
assert res is False
def test_make_bool_empty():
## GIVEN a empty string
a = ""
## WHEN converting to a boolean
res = make_bool(a)
## THEN assert it is False
assert res is False
def test_make_bool_zero():
## GIVEN a string representing a boolean
a = "0"
## WHEN converting to a boolean
res = make_bool(a)
## THEN assert it is False
assert res is False
def test_make_bool_one():
## GIVEN a string representing a boolean
a = "1"
## WHEN making a boolean
res = make_bool(a)
## THEN assert it is True
assert res is True
def parse_peddy_sex_check(lines):
"""Parse a .ped_check.csv file
Args:
lines(iterable(str))
Returns:
sex_check(list(dict))
"""
sex_check = []
header = []
for i, line in enumerate(lines):
line = line.rstrip()
if i == 0:
# Header line
header = line.lstrip("#").split(",")
else:
ind_info = dict(zip(header, line.split(",")))
# boolean indicating wether there is a mismatch between X
# genotypes and ped sex.
ind_info["error"] = make_bool(ind_info.get("error"))
# number of homozygous-alternate calls
ind_info["hom_alt_count"] = convert_number(
ind_info["hom_alt_count"])
# number of homozygous-reference calls
ind_info["hom_ref_count"] = convert_number(
ind_info["hom_ref_count"])
# number of heterozygote calls
ind_info["het_count"] = convert_number(ind_info["het_count"])
# ratio of het_count / hom_alt_count. Low for males, high for females
ind_info["het_ratio"] = convert_number(ind_info["het_ratio"])
sex_check.append(ind_info)
return sex_check
def parse_peddy_sex_check(lines):
"""Parse a .ped_check.csv file
Args:
lines(iterable(str))
Returns:
sex_check(list(dict))
"""
sex_check = []
header = []
for i,line in enumerate(lines):
line = line.rstrip()
if i == 0:
# Header line
header = line.lstrip('#').split(',')
else:
ind_info = dict(zip(header, line.split(',')))
# boolean indicating wether there is a mismatch between X
# genotypes and ped sex.
ind_info['error'] = make_bool(ind_info.get('error'))
# number of homozygous-alternate calls
ind_info['hom_alt_count'] = convert_number(ind_info['hom_alt_count'])
#number of homozygous-reference calls
ind_info['hom_ref_count'] = convert_number(ind_info['hom_ref_count'])
# number of heterozygote calls
ind_info['het_count'] = convert_number(ind_info['het_count'])
# ratio of het_count / hom_alt_count. Low for males, high for females
ind_info['het_ratio'] = convert_number(ind_info['het_ratio'])
sex_check.append(ind_info)
return sex_check
def parse_peddy_ped_check(lines):
"""Parse a .ped_check.csv file
Args:
lines(iterable(str))
Returns:
ped_check(list(dict))
"""
ped_check = []
header = []
for i,line in enumerate(lines):
line = line.rstrip()
if i == 0:
# Header line
header = line.lstrip('#').split(',')
else:
pair_info = dict(zip(header, line.split(',')))
# the number of sites at which sample_a was heterozygous
pair_info['hets_a'] = convert_number(pair_info['hets_a'])
# the number of sites at which sample_b was heterozygous
pair_info['hets_b'] = convert_number(pair_info['hets_b'])
# the number of sites at which the 2 samples shared no alleles
# (should approach 0 for parent-child pairs).
pair_info['ibs0'] = convert_number(pair_info['ibs0'])
# the number of sites and which the 2 samples where both
# hom-ref, both het, or both hom-alt.
pair_info['ibs2'] = convert_number(pair_info['ibs2'])
# the number of sites that was used to predict the relatedness.
pair_info['n'] = convert_number(pair_info['n'])
# the relatedness reported in the ped file.
pair_info['rel'] = convert_number(pair_info['rel'])
# the relatedness reported in the ped file.
pair_info['pedigree_relatedness'] = convert_number(pair_info['pedigree_relatedness'])
# difference between the preceding 2 colummns.
pair_info['rel_difference'] = convert_number(pair_info['rel_difference'])
# the number of sites at which both samples were hets.
pair_info['shared_hets'] = convert_number(pair_info['shared_hets'])
# boolean indicating that this pair is a parent-child pair
# according to the ped file.
pair_info['pedigree_parents'] = make_bool(pair_info.get('pedigree_parents'))
# boolean indicating that this pair is expected to be a parent-child
# pair according to the ibs0 (< 0.012) calculated from the genotypes.
pair_info['predicted_parents'] = make_bool(pair_info.get('predicted_parents'))
# boolean indicating that the preceding 2 columns do not match
pair_info['parent_error'] = make_bool(pair_info.get('parent_error'))
# boolean indicating that rel > 0.75 and ibs0 < 0.012
pair_info['sample_duplication_error'] = make_bool(pair_info.get('sample_duplication_error'))
ped_check.append(pair_info)
return ped_check
def parse_peddy_ped_check(lines):
"""Parse a .ped_check.csv file
Args:
lines(iterable(str))
Returns:
ped_check(list(dict))
"""
ped_check = []
header = []
for i, line in enumerate(lines):
line = line.rstrip()
if i == 0:
# Header line
header = line.lstrip("#").split(",")
else:
pair_info = dict(zip(header, line.split(",")))
# the number of sites at which sample_a was heterozygous
pair_info["hets_a"] = convert_number(pair_info["hets_a"])
# the number of sites at which sample_b was heterozygous
pair_info["hets_b"] = convert_number(pair_info["hets_b"])
# the number of sites at which the 2 samples shared no alleles
# (should approach 0 for parent-child pairs).
pair_info["ibs0"] = convert_number(pair_info["ibs0"])
# the number of sites and which the 2 samples where both
# hom-ref, both het, or both hom-alt.
pair_info["ibs2"] = convert_number(pair_info["ibs2"])
# the number of sites that was used to predict the relatedness.
pair_info["n"] = convert_number(pair_info["n"])
# the relatedness reported in the ped file.
pair_info["rel"] = convert_number(pair_info["rel"])
# the relatedness reported in the ped file.
pair_info["pedigree_relatedness"] = convert_number(
pair_info["pedigree_relatedness"])
# difference between the preceding 2 colummns.
pair_info["rel_difference"] = convert_number(
pair_info["rel_difference"])
# the number of sites at which both samples were hets.
pair_info["shared_hets"] = convert_number(pair_info["shared_hets"])
# boolean indicating that this pair is a parent-child pair
# according to the ped file.
pair_info["pedigree_parents"] = make_bool(
pair_info.get("pedigree_parents"))
# boolean indicating that this pair is expected to be a parent-child
# pair according to the ibs0 (< 0.012) calculated from the genotypes.
pair_info["predicted_parents"] = make_bool(
pair_info.get("predicted_parents"))
# boolean indicating that the preceding 2 columns do not match
pair_info["parent_error"] = make_bool(
pair_info.get("parent_error"))
# boolean indicating that rel > 0.75 and ibs0 < 0.012
pair_info["sample_duplication_error"] = make_bool(
pair_info.get("sample_duplication_error"))
ped_check.append(pair_info)
return ped_check
