def _get_sample_variant_1(self):
"""Get first sample variant.
Features:
multiple alternates
not phased
multiple names
"""
vcf_line = ('20 1234 rs123;rs2 C A,T 50 PASS AF=0.5,0.1;NS=1 '
'GT:GQ 0/0:48 1/0:20\n')
variant = Variant(reference_name='20',
start=1233,
end=1234,
reference_bases='C',
alternate_bases=['A', 'T'],
names=['rs123', 'rs2'],
quality=50,
filters=['PASS'],
info={
'AF': VariantInfo(data=[0.5, 0.1],
field_count='A'),
'NS': VariantInfo(data=1, field_count='1')
})
variant.calls.append(
VariantCall(name='Sample1', genotype=[0, 0], info={'GQ': 48}))
variant.calls.append(
VariantCall(name='Sample2', genotype=[1, 0], info={'GQ': 20}))
return variant, vcf_line
def test_info_numbers_and_types(self):
info_headers = [
'##INFO=<ID=HA,Number=A,Type=String,Description="StringInfo_A">\n',
'##INFO=<ID=HG,Number=G,Type=Integer,Description="IntInfo_G">\n',
'##INFO=<ID=HR,Number=R,Type=Character,Description="ChrInfo_R">\n',
'##INFO=<ID=HF,Number=0,Type=Flag,Description="FlagInfo">\n',
'##INFO=<ID=HU,Number=.,Type=Float,Description="FloatInfo_variable">\n']
record_lines = [
'19 2 . A T,C . . HA=a1,a2;HG=1,2,3;HR=a,b,c;HF;HU=0.1 GT 1/0 0/1\n',
'19 124 . A T . . HG=3,4,5;HR=d,e;HU=1.1,1.2 GT 0/0 0/1']
variant_1 = Variant(
reference_name='19', start=1, end=2, reference_bases='A',
alternate_bases=['T', 'C'],
info={'HA': VariantInfo(data=['a1', 'a2'], field_count='A'),
'HG': VariantInfo(data=[1, 2, 3], field_count='G'),
'HR': VariantInfo(data=['a', 'b', 'c'], field_count='R'),
'HF': VariantInfo(data=True, field_count='0'),
'HU': VariantInfo(data=[0.1], field_count=None)})
variant_1.calls.append(VariantCall(name='Sample1', genotype=[1, 0]))
variant_1.calls.append(VariantCall(name='Sample2', genotype=[0, 1]))
variant_2 = Variant(
reference_name='19', start=123, end=124, reference_bases='A',
alternate_bases=['T'],
info={'HG': VariantInfo(data=[3, 4, 5], field_count='G'),
'HR': VariantInfo(data=['d', 'e'], field_count='R'),
'HU': VariantInfo(data=[1.1, 1.2], field_count=None)})
variant_2.calls.append(VariantCall(name='Sample1', genotype=[0, 0]))
variant_2.calls.append(VariantCall(name='Sample2', genotype=[0, 1]))
read_data = self._create_temp_file_and_read_records(
info_headers + _SAMPLE_HEADER_LINES[1:] + record_lines)
self.assertEqual(2, len(read_data))
self._assert_variants_equal([variant_1, variant_2], read_data)
def _get_sample_variant_3(self):
"""Get third sample variant.
Features:
symbolic alternate
no calls for sample 2
"""
vcf_line = ('19 12 . C <SYMBOLIC> 49 q10 AF=0.5 GT:GQ 0|1:45 .:.\n')
variant = Variant(
reference_name='19',
start=11,
end=12,
reference_bases='C',
alternate_bases=['<SYMBOLIC>'],
quality=49,
filters=['q10'],
info={'AF': VariantInfo(data=[0.5], field_count='A')})
variant.calls.append(
VariantCall(name='Sample1',
genotype=[0, 1],
phaseset=DEFAULT_PHASESET_VALUE,
info={'GQ': 45}))
variant.calls.append(
VariantCall(name='Sample2',
genotype=[MISSING_GENOTYPE_VALUE],
info={'GQ': None}))
return variant, vcf_line
def _get_sample_variant_2(self):
"""Get second sample variant.
Features:
multiple references
no alternate
phased
multiple filters
missing format field
"""
vcf_line = ('19 123 rs1234 GTC . 40 q10;s50 NS=2 GT:GQ 1|0:48 0/1:.\n')
variant = Variant(reference_name='19',
start=122,
end=125,
reference_bases='GTC',
alternate_bases=[],
names=['rs1234'],
quality=40,
filters=['q10', 's50'],
info={'NS': VariantInfo(data=2, field_count='1')})
variant.calls.append(
VariantCall(name='Sample1',
genotype=[1, 0],
phaseset=DEFAULT_PHASESET_VALUE,
info={'GQ': 48}))
variant.calls.append(
VariantCall(name='Sample2', genotype=[0, 1], info={'GQ': None}))
return variant, vcf_line
def test_no_samples(self):
header_line = '#CHROM POS ID REF ALT QUAL FILTER INFO\n'
record_line = '19 123 . G A . PASS AF=0.2'
expected_variant = Variant(
reference_name='19', start=122, end=123, reference_bases='G',
alternate_bases=['A'], filters=['PASS'],
info={'AF': VariantInfo(data=[0.2], field_count='A')})
read_data = self._create_temp_file_and_read_records(
_SAMPLE_HEADER_LINES[:-1] + [header_line, record_line])
self.assertEqual(1, len(read_data))
self.assertEqual(expected_variant, read_data[0])
