def test_var_string_format_caching(self):
header_lines = [
'##fileformat=VCFv4.2',
'##fileDate=20151202',
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=AS,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
'#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA12878' ]
vcf = Vcf()
vcf.add_header(header_lines)
variant_line = '1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG GT:AS:SU 0/0:1:9'
uncached_line = '1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG GT:SU:AS 0/0:9:1'
variant = Variant(variant_line.split('\t'), vcf)
gt = variant.genotypes() #force parsing
self.assertEqual(variant.get_var_string(), uncached_line)
self.assertEqual(variant.get_var_string(use_cached_gt_string=True), variant_line)
def test_var_string_format_caching(self):
header_lines = [
'##fileformat=VCFv4.2', '##fileDate=20151202',
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=AS,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
'#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA12878'
]
vcf = Vcf()
vcf.add_header(header_lines)
variant_line = '1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG GT:AS:SU 0/0:1:9'
uncached_line = '1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG GT:SU:AS 0/0:9:1'
variant = Variant(variant_line.split('\t'), vcf)
gt = variant.genotypes() #force parsing
self.assertEqual(variant.get_var_string(), uncached_line)
self.assertEqual(variant.get_var_string(use_cached_gt_string=True),
variant_line)
def execute(self, output_handle=sys.stdout):
in_header = True
header = []
vcf = Vcf()
vcf_out = output_handle
# read input VCF
for line in self.vcf_stream:
if in_header:
if line.startswith('##'):
header.append(line)
continue
elif line.startswith('#CHROM'):
v = line.rstrip().split('\t')
header.append('\t'.join(v))
in_header = False
vcf.add_header(header)
vcf.add_info('AF', 'A', 'Float', 'Allele Frequency, for each ALT allele, in the same order as listed')
vcf.add_info('NSAMP', '1', 'Integer', 'Number of samples with non-reference genotypes')
vcf.add_info('MSQ', '1', 'Float', 'Mean sample quality of positively genotyped samples')
# write header
vcf_out.write(vcf.get_header() + '\n')
#vcf_out.write('\t' + '\t'.join(v[8:]) + '\n')
continue
v = line.rstrip().split('\t')
var = Variant(v, vcf)
# extract genotypes from VCF
num_alt = len(var.alt.split(','))
alleles = [0] * (num_alt + 1)
num_samp = 0
sum_sq = 0.0
for gt in var.genotypes():
gt_string = gt.get_format('GT')
if '.' not in gt_string:
indexes = self.numeric_alleles(gt_string)
for i in indexes:
alleles[i] += 1
# iterate the number of non-reference samples
if sum(indexes) > 0:
num_samp += 1
try:
sum_sq += float(gt.get_format('SQ'))
except KeyError:
pass
allele_sum = float(sum(alleles))
allele_freq = ['.'] * len(alleles)
# populate AF
if allele_sum > 0:
for i in xrange(len(alleles)):
allele_freq[i] = alleles[i] / allele_sum
var.info['AF'] = ','.join(map(str, ['%.4g' % a for a in allele_freq[1:]]))
else:
var.info['AF'] = ','.join(map(str, allele_freq[1:]))
# populate NSAMP
var.info['NSAMP'] = num_samp
if num_samp > 0:
msq = '%0.2f' % (sum_sq / num_samp)
else:
msq = '.'
var.info['MSQ'] = msq
# after all samples have been processed, write
vcf_out.write(var.get_var_string(use_cached_gt_string=True) + '\n')
vcf_out.close()
class TestVariant(TestCase):
def setUp(self):
header_lines = [
'##fileformat=VCFv4.2', '##fileDate=20151202',
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
'#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA12878 NA0001'
]
self.vcf = Vcf()
self.vcf.add_header(header_lines)
self.variant_line = '1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG GT:SU 0/0:9 1/1:15'
self.variant = Variant(self.variant_line.split('\t'), self.vcf)
def test_parse_genotypes(self):
genotype_field_strings = ['0/1:20', '0/0:15']
parsed_dict = self.variant._parse_genotypes(genotype_field_strings)
na12878_gt = Genotype(self.variant,
genotype_field_strings[0].split(':'))
na0001_gt = Genotype(self.variant,
genotype_field_strings[1].split(':'))
expected_genotype_dict = {'NA12878': na12878_gt, 'NA0001': na0001_gt}
self.assertEqual(parsed_dict, expected_genotype_dict)
def test_set_info(self):
self.variant.set_info('SVTYPE', 'INV')
self.assertEqual(self.variant.info['SVTYPE'], 'INV')
self.variant.set_info('IMAFLAG', False)
self.assertEqual(self.variant.info['IMAFLAG'], False)
with self.assertRaises(SystemExit) as cm:
self.variant.set_info('SUPER', True)
def test_get_info(self):
self.assertEqual(self.variant.get_info('IMAFLAG'), True)
self.assertEqual(self.variant.get_info('SVTYPE'), 'BND')
with self.assertRaises(KeyError) as cm:
self.variant.get_info('CALI')
def test_get_info_string(self):
self.assertEqual(self.variant.get_info_string(),
'SVTYPE=BND;STRANDS=-+:9;IMAFLAG')
self.variant.set_info('IMAFLAG', False)
self.assertEqual(self.variant.get_info_string(),
'SVTYPE=BND;STRANDS=-+:9')
def test_get_format_string(self):
self.assertEqual(self.variant.get_format_string(), 'GT:SU')
def test_get_gt_string(self):
self.assertEqual(self.variant.get_gt_string(), '0/0:9 1/1:15')
def test_genotype(self):
self.assertEqual(
self.variant.genotype('NA12878').get_gt_string(), '0/0:9')
def test_genotypes(self):
self.assertEqual([x.get_gt_string() for x in self.variant.genotypes()],
['0/0:9', '1/1:15'])
def test_var_string(self):
self.assertEqual(self.variant.get_var_string(), self.variant_line)
self.variant.genotype('NA12878').set_format('GT', './.')
self.assertEqual(
self.variant.get_var_string(use_cached_gt_string=True),
self.variant_line)
self.assertNotEqual(self.variant.get_var_string(), self.variant_line)
class TestVariant(TestCase):
def setUp(self):
header_lines = [
"##fileformat=VCFv4.2",
"##fileDate=20151202",
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
"#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA12878 NA0001",
]
self.vcf = Vcf()
self.vcf.add_header(header_lines)
self.variant_line = (
"1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG GT:SU 0/0:9 1/1:15"
)
self.variant = Variant(self.variant_line.split("\t"), self.vcf)
def test_parse_genotypes(self):
genotype_field_strings = ["0/1:20", "0/0:15"]
parsed_dict = self.variant._parse_genotypes(genotype_field_strings)
na12878_gt = Genotype(self.variant, genotype_field_strings[0].split(":"))
na0001_gt = Genotype(self.variant, genotype_field_strings[1].split(":"))
expected_genotype_dict = {"NA12878": na12878_gt, "NA0001": na0001_gt}
self.assertEqual(parsed_dict, expected_genotype_dict)
def test_set_info(self):
self.variant.set_info("SVTYPE", "INV")
self.assertEqual(self.variant.info["SVTYPE"], "INV")
self.variant.set_info("IMAFLAG", False)
self.assertEqual(self.variant.info["IMAFLAG"], False)
with self.assertRaises(SystemExit) as cm:
self.variant.set_info("SUPER", True)
def test_get_info(self):
self.assertEqual(self.variant.get_info("IMAFLAG"), True)
self.assertEqual(self.variant.get_info("SVTYPE"), "BND")
with self.assertRaises(KeyError) as cm:
self.variant.get_info("CALI")
def test_get_info_string(self):
self.assertEqual(self.variant.get_info_string(), "SVTYPE=BND;STRANDS=-+:9;IMAFLAG")
self.variant.set_info("IMAFLAG", False)
self.assertEqual(self.variant.get_info_string(), "SVTYPE=BND;STRANDS=-+:9")
def test_get_format_string(self):
self.assertEqual(self.variant.get_format_string(), "GT:SU")
def test_get_format_string_caching(self):
header_lines = [
"##fileformat=VCFv4.2",
"##fileDate=20151202",
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=AS,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
"#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA12878",
]
vcf = Vcf()
vcf.add_header(header_lines)
variant_line = "1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG GT:AS:SU 0/0:1:9"
variant = Variant(variant_line.split("\t"), vcf)
self.assertEqual(variant.get_format_string(), "GT:AS:SU")
gts = variant.genotypes()
self.assertEqual(variant.get_format_string(), "GT:SU:AS")
self.assertEqual(variant.get_format_string(True), "GT:AS:SU")
def test_get_gt_string(self):
self.assertEqual(self.variant.get_gt_string(), "0/0:9 1/1:15")
def test_genotype(self):
self.assertEqual(self.variant.genotype("NA12878").get_gt_string(), "0/0:9")
def test_set_genotype(self):
new_genotype = Genotype(self.variant, ["0/1", "9"])
self.variant.set_genotype("NA12878", new_genotype)
self.assertEqual(self.variant.genotype("NA12878").get_gt_string(), "0/1:9")
def test_genotypes(self):
self.assertEqual([x.get_gt_string() for x in self.variant.genotypes()], ["0/0:9", "1/1:15"])
def test_var_string(self):
self.assertEqual(self.variant.get_var_string(), self.variant_line)
self.variant.genotype("NA12878").set_format("GT", "./.")
self.assertEqual(self.variant.get_var_string(use_cached_gt_string=True), self.variant_line)
self.assertNotEqual(self.variant.get_var_string(), self.variant_line)
def test_var_string_format_caching(self):
header_lines = [
"##fileformat=VCFv4.2",
"##fileDate=20151202",
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=AS,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
"#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA12878",
]
vcf = Vcf()
vcf.add_header(header_lines)
variant_line = "1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG GT:AS:SU 0/0:1:9"
uncached_line = "1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG GT:SU:AS 0/0:9:1"
variant = Variant(variant_line.split("\t"), vcf)
gt = variant.genotypes() # force parsing
self.assertEqual(variant.get_var_string(), uncached_line)
self.assertEqual(variant.get_var_string(use_cached_gt_string=True), variant_line)
def test_add_genotype(self):
header_lines = [
"##fileformat=VCFv4.2",
"##fileDate=20151202",
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
"#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA12878",
]
vcf = Vcf()
vcf.add_header(header_lines)
variant_line = "1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG SU 9"
variant = Variant(variant_line.split("\t"), vcf)
self.assertEqual(variant.get_gt_string(), "./.:9")
def execute(self, output_handle=sys.stdout):
in_header = True
header = []
vcf = Vcf()
vcf_out = output_handle
# read input VCF
for line in self.vcf_stream:
if in_header:
if line.startswith('##'):
header.append(line)
continue
elif line.startswith('#CHROM'):
v = line.rstrip().split('\t')
header.append('\t'.join(v))
in_header = False
vcf.add_header(header)
vcf.add_info('AF', 'A', 'Float', 'Allele Frequency, for each ALT allele, in the same order as listed')
vcf.add_info('NSAMP', '1', 'Integer', 'Number of samples with non-reference genotypes')
vcf.add_info('MSQ', '1', 'Float', 'Mean sample quality of positively genotyped samples')
# write header
vcf_out.write(vcf.get_header() + '\n')
#vcf_out.write('\t' + '\t'.join(v[8:]) + '\n')
continue
v = line.rstrip().split('\t')
var = Variant(v, vcf)
# extract genotypes from VCF
num_alt = len(var.alt.split(','))
alleles = [0] * (num_alt + 1)
num_samp = 0
sum_sq = 0.0
for gt in var.genotypes():
gt_string = gt.get_format('GT')
if '.' not in gt_string:
indexes = self.numeric_alleles(gt_string)
for i in indexes:
alleles[i] += 1
# iterate the number of non-reference samples
if sum(indexes) > 0:
num_samp += 1
try:
sum_sq += float(gt.get_format('SQ'))
except KeyError:
pass
allele_sum = float(sum(alleles))
allele_freq = ['.'] * len(alleles)
# populate AF
if allele_sum > 0:
for i in xrange(len(alleles)):
allele_freq[i] = alleles[i] / allele_sum
var.info['AF'] = ','.join(map(str, ['%.4g' % a for a in allele_freq[1:]]))
else:
var.info['AF'] = ','.join(map(str, allele_freq[1:]))
# populate NSAMP
var.info['NSAMP'] = num_samp
if num_samp > 0:
msq = '%0.2f' % (sum_sq / num_samp)
else:
msq = '.'
var.info['MSQ'] = msq
# after all samples have been processed, write
vcf_out.write(var.get_var_string(use_cached_gt_string=True) + '\n')
vcf_out.close()
class TestVariant(TestCase):
def setUp(self):
header_lines = [
'##fileformat=VCFv4.2',
'##fileDate=20151202',
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
'#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA12878 NA0001' ]
self.vcf = Vcf()
self.vcf.add_header(header_lines)
self.variant_line = '1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG GT:SU 0/0:9 1/1:15'
self.variant = Variant(self.variant_line.split('\t'), self.vcf)
def test_parse_genotypes(self):
genotype_field_strings = ['0/1:20', '0/0:15']
parsed_dict = self.variant._parse_genotypes(genotype_field_strings)
na12878_gt = Genotype(self.variant, genotype_field_strings[0].split(':'))
na0001_gt = Genotype(self.variant, genotype_field_strings[1].split(':'))
expected_genotype_dict = { 'NA12878': na12878_gt, 'NA0001': na0001_gt }
self.assertEqual(parsed_dict, expected_genotype_dict)
def test_set_info(self):
self.variant.set_info('SVTYPE', 'INV')
self.assertEqual(self.variant.info['SVTYPE'], 'INV')
self.variant.set_info('IMAFLAG', False)
self.assertEqual(self.variant.info['IMAFLAG'], False)
with self.assertRaises(SystemExit) as cm:
self.variant.set_info('SUPER', True)
def test_get_info(self):
self.assertEqual(self.variant.get_info('IMAFLAG'), True)
self.assertEqual(self.variant.get_info('SVTYPE'), 'BND')
with self.assertRaises(KeyError) as cm:
self.variant.get_info('CALI')
def test_get_info_string(self):
self.assertEqual(self.variant.get_info_string(), 'SVTYPE=BND;STRANDS=-+:9;IMAFLAG')
self.variant.set_info('IMAFLAG', False)
self.assertEqual(self.variant.get_info_string(), 'SVTYPE=BND;STRANDS=-+:9')
def test_get_format_string(self):
self.assertEqual(self.variant.get_format_string(), 'GT:SU')
def test_get_gt_string(self):
self.assertEqual(self.variant.get_gt_string(), '0/0:9 1/1:15')
def test_genotype(self):
self.assertEqual(self.variant.genotype('NA12878').get_gt_string(), '0/0:9')
def test_genotypes(self):
self.assertEqual([ x.get_gt_string() for x in self.variant.genotypes() ], ['0/0:9', '1/1:15'])
def test_var_string(self):
self.assertEqual(self.variant.get_var_string(), self.variant_line)
self.variant.genotype('NA12878').set_format('GT', './.')
self.assertEqual(self.variant.get_var_string(use_cached_gt_string=True), self.variant_line)
self.assertNotEqual(self.variant.get_var_string(), self.variant_line)
def test_add_genotype(self):
header_lines = [
'##fileformat=VCFv4.2',
'##fileDate=20151202',
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
'#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA12878' ]
vcf = Vcf()
vcf.add_header(header_lines)
variant_line = '1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG SU 9'
variant = Variant(variant_line.split('\t'), vcf)
self.assertEqual(variant.get_gt_string(), './.:9')
class TestVariant8Col(TestCase):
def setUp(self):
header_lines = [
'##fileformat=VCFv4.2', '##fileDate=20151202',
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
'#CHROM POS ID REF ALT QUAL FILTER INFO'
]
self.vcf = Vcf()
self.vcf.add_header(header_lines)
self.variant_line = '1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG'
self.variant = Variant(self.variant_line.split('\t'), self.vcf)
def test_set_info(self):
self.variant.set_info('SVTYPE', 'INV')
self.assertEqual(self.variant.info['SVTYPE'], 'INV')
self.variant.set_info('IMAFLAG', False)
self.assertEqual(self.variant.info['IMAFLAG'], False)
with self.assertRaises(SystemExit) as cm:
self.variant.set_info('SUPER', True)
def test_get_info(self):
self.assertEqual(self.variant.get_info('IMAFLAG'), True)
self.assertEqual(self.variant.get_info('SVTYPE'), 'BND')
with self.assertRaises(KeyError) as cm:
self.variant.get_info('CALI')
def test_get_info_string(self):
self.assertEqual(self.variant.get_info_string(),
'SVTYPE=BND;STRANDS=-+:9;IMAFLAG')
self.variant.set_info('IMAFLAG', False)
self.assertEqual(self.variant.get_info_string(),
'SVTYPE=BND;STRANDS=-+:9')
def test_get_format_string(self):
self.assertEqual(self.variant.get_format_string(), None)
def test_get_format_string_caching(self):
header_lines = [
'##fileformat=VCFv4.2', '##fileDate=20151202',
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=AS,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
'#CHROM POS ID REF ALT QUAL FILTER INFO'
]
vcf = Vcf()
vcf.add_header(header_lines)
variant_line = '1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG'
variant = Variant(variant_line.split('\t'), vcf)
self.assertEqual(variant.get_format_string(), None)
gts = variant.genotypes()
self.assertEqual(variant.get_format_string(), None)
self.assertEqual(variant.get_format_string(True), None)
def test_get_gt_string(self):
self.assertEqual(self.variant.get_gt_string(), None)
def test_genotypes(self):
self.assertEqual(self.variant.genotypes(), [])
def test_var_string(self):
self.assertEqual(self.variant.get_var_string(), self.variant_line)
class TestVariant8Col(TestCase):
def setUp(self):
header_lines = [
'##fileformat=VCFv4.2',
'##fileDate=20151202',
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
'#CHROM POS ID REF ALT QUAL FILTER INFO' ]
self.vcf = Vcf()
self.vcf.add_header(header_lines)
self.variant_line = '1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG'
self.variant = Variant(self.variant_line.split('\t'), self.vcf)
def test_set_info(self):
self.variant.set_info('SVTYPE', 'INV')
self.assertEqual(self.variant.info['SVTYPE'], 'INV')
self.variant.set_info('IMAFLAG', False)
self.assertEqual(self.variant.info['IMAFLAG'], False)
with self.assertRaises(SystemExit) as cm:
self.variant.set_info('SUPER', True)
def test_get_info(self):
self.assertEqual(self.variant.get_info('IMAFLAG'), True)
self.assertEqual(self.variant.get_info('SVTYPE'), 'BND')
with self.assertRaises(KeyError) as cm:
self.variant.get_info('CALI')
def test_get_info_string(self):
self.assertEqual(self.variant.get_info_string(), 'SVTYPE=BND;STRANDS=-+:9;IMAFLAG')
self.variant.set_info('IMAFLAG', False)
self.assertEqual(self.variant.get_info_string(), 'SVTYPE=BND;STRANDS=-+:9')
def test_get_format_string(self):
self.assertEqual(self.variant.get_format_string(), None)
def test_get_format_string_caching(self):
header_lines = [
'##fileformat=VCFv4.2',
'##fileDate=20151202',
'##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">',
'##INFO=<ID=STRANDS,Number=.,Type=String,Description="Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--)">',
'##INFO=<ID=IMAFLAG,Number=.,Type=Flag,Description="Test Flag code">',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
'##FORMAT=<ID=SU,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=AS,Number=1,Type=Integer,Description="Number of pieces of evidence supporting the variant">',
'##FORMAT=<ID=INACTIVE,Number=1,Type=Integer,Description="A format not in use">',
'#CHROM POS ID REF ALT QUAL FILTER INFO' ]
vcf = Vcf()
vcf.add_header(header_lines)
variant_line = '1 820915 5838_1 N ]GL000232.1:20940]N 0.00 . SVTYPE=BND;STRANDS=-+:9;IMAFLAG'
variant = Variant(variant_line.split('\t'), vcf)
self.assertEqual(variant.get_format_string(), None)
gts = variant.genotypes()
self.assertEqual(variant.get_format_string(), None)
self.assertEqual(variant.get_format_string(True), None)
def test_get_gt_string(self):
self.assertEqual(self.variant.get_gt_string(), None)
def test_genotypes(self):
self.assertEqual(self.variant.genotypes(), [])
def test_var_string(self):
self.assertEqual(self.variant.get_var_string(), self.variant_line)
