def sname_filter(input_stream, filter_file, output_stream, complement):
'''
This reads a VCF stream, determines if the line overlaps any from the filter_file by sname and outputs.
'''
filter_list = load_filter_file(filter_file)
vcf = Vcf()
in_header = True
header_lines = list()
sample_list = None
for line in input_stream:
if in_header:
header_lines.append(line)
if line[0:6] == '#CHROM':
in_header = False
vcf.add_header(header_lines)
vcf.add_info('FOUND', '.', 'String',
'Variant id in other file')
output_stream.write(vcf.get_header() + '\n')
else:
v = Variant(line.rstrip().split('\t'), vcf)
sname_set = set_from_string(v.get_info('SNAME'))
found = overlapping_ids(sname_set, filter_list)
if bool(found) != complement:
v.set_info('FOUND', ','.join(found))
output_stream.write(v.get_var_string() + '\n')
def merge_single_bp(BP, sample_order, v_id, use_product, vcf, vcf_out,
include_genotypes):
A = BP[0].l.rstrip().split('\t')
var = Variant(A, vcf)
try:
sname = var.get_info('SNAME')
var.set_info('SNAME', sname + ':' + var.var_id)
except KeyError:
pass
var.var_id = str(v_id)
if use_product:
var.set_info('ALG', 'PROD')
else:
var.set_info('ALG', 'SUM')
GTS = None
if include_genotypes:
null_string = null_format_string(A[8])
gt_dict = {sname: A[9]}
GTS = '\t'.join([gt_dict.get(x, null_string) for x in sample_order])
var.gts = None
var.gts_string = GTS
return var
def merge_single_bp(BP, sample_order, v_id, use_product, vcf, vcf_out, include_genotypes):
A = BP[0].l.rstrip().split('\t')
var = Variant(A,vcf)
try:
sname = var.get_info('SNAME')
var.set_info('SNAME', sname + ':' + var.var_id)
except KeyError:
pass
var.var_id=str(v_id)
if use_product:
var.set_info('ALG', 'PROD')
else:
var.set_info('ALG', 'SUM')
GTS = None
if include_genotypes:
null_string = null_format_string(A[8])
gt_dict = { sname: A[9] }
GTS = '\t'.join([gt_dict.get(x, null_string) for x in sample_order])
var.gts = None
var.gts_string = GTS
return var
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' ]
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'
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(), 'GT:SU')
def test_genotype(self):
self.assertEqual(self.variant.genotype('NA12878').get_gt_string(), '0/0:9')
def test_var_string(self):
self.assertEqual(self.variant.get_var_string(), self.variant_line)
def load_filter_file(filter_file):
'''
Read the file we're going to use as a filter to determine if lines should be output.
This returns a list containing tuples where the first item is the variant id and the second is the set of ids from sname.
'''
filter_list = list()
vcf = Vcf()
header_lines = list()
in_header = True
for line in filter_file:
if in_header:
header_lines.append(line)
if line[0:6] == '#CHROM':
in_header = False
vcf.add_header(header_lines)
else:
v = line.rstrip().split('\t')
var = Variant(v, vcf)
filter_list.append(
(var.var_id, set_from_string(var.get_info('SNAME'))))
return filter_list
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 create_merged_variant(BP,
c,
v_id,
vcf,
use_product,
weighting_scheme='unweighted'):
new_start_L, new_start_R, p_L, p_R, ALG = combine_pdfs(
BP, c, use_product, weighting_scheme)
max_i_L = p_L.index(max(p_L))
max_i_R = p_R.index(max(p_R))
[cipos95, ciend95] = getCI95(p_L, p_R, max_i_L, max_i_R)
new_pos_L = new_start_L + max_i_L
new_pos_R = new_start_R + max_i_R
BP0 = BP[c[0]]
# sometimes after looking at PRs, the left and right can be swapped.
# flip them back so downstream tools don't break.
if new_pos_R < new_pos_L and BP0.sv_type != 'BND':
new_pos_R, new_pos_L = new_pos_L, new_pos_R
cipos95, ciend95 = ciend95, cipos95
p_L, p_R = p_R, p_L
max_i_R, max_i_L = max_i_L, max_i_R
A = BP0.l.rstrip().split('\t', 10)
ALT = ''
if BP0.sv_type == 'BND':
if BP0.strands[:2] == '++':
ALT = 'N]' + BP0.right.chrom + ':' + str(new_pos_R) + ']'
elif BP0.strands[:2] == '-+':
ALT = ']' + BP0.right.chrom + ':' + str(new_pos_R) + ']N'
elif BP0.strands[:2] == '+-':
ALT = 'N[' + BP0.right.chrom + ':' + str(new_pos_R) + '['
elif BP0.strands[:2] == '--':
ALT = '[' + BP0.right.chrom + ':' + str(new_pos_R) + '[N'
else:
ALT = '<' + BP0.sv_type + '>'
var_list = [BP0.left.chrom, new_pos_L,
str(v_id), 'N', ALT, 0.0, '.', ''] + A[8:]
var = Variant(var_list, vcf)
var.set_info('SVTYPE', BP0.sv_type)
var.set_info('ALG', ALG)
if var.get_info('SVTYPE') == 'DEL':
var.set_info('SVLEN', new_pos_L - new_pos_R)
elif BP0.left.chrom == BP0.right.chrom:
var.set_info('SVLEN', new_pos_R - new_pos_L)
else:
SVLEN = None
if var.get_info('SVTYPE') == 'BND':
var.set_info('EVENT', str(v_id))
elif var.get_info('SVTYPE') == 'INS':
var.set_info('END', new_pos_L)
else:
var.set_info('END', new_pos_R)
var.set_info('CIPOS95', cipos95)
var.set_info('CIEND95', ciend95)
var.set_info(
'CIPOS',
','.join([str(x)
for x in [-1 * max_i_L, len(p_L) - max_i_L - 1]]))
var.set_info(
'CIEND',
','.join([str(x)
for x in [-1 * max_i_R, len(p_R) - max_i_R - 1]]))
var.set_info('PRPOS', ','.join([str(x) for x in p_L]))
var.set_info('PREND', ','.join([str(x) for x in p_R]))
return var
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 run_gt_refine(vcf_in, vcf_out, diag_outfile, gender_file, exclude_file):
vcf = Vcf()
header = []
in_header = True
sex = {}
for line in gender_file:
v = line.rstrip().split('\t')
sex[v[0]] = int(v[1])
exclude = []
if exclude_file is not None:
for line in exclude_file:
exclude.append(line.rstrip())
outf = open(diag_outfile, 'w', 4096)
ct = 1
for line in vcf_in:
if in_header:
if line[0] == "#":
header.append(line)
continue
else:
in_header = False
vcf.add_header(header)
vcf.add_info('MEDGQR', '1', 'Float',
'Median quality for refined GT')
vcf.add_info('Q10GQR', '1', 'Float',
'Q10 quality for refined GT')
vcf.add_format('GQR', 1, 'Float',
'Quality of refined genotype.')
vcf.add_format('GTR', 1, 'String', 'Refined genotype.')
vcf_out.write(vcf.get_header() + '\n')
v = line.rstrip().split('\t')
info = v[7].split(';')
svtype = None
for x in info:
if x.startswith('SVTYPE='):
svtype = x.split('=')[1]
break
# bail if not DEL or DUP prior to reclassification
if svtype not in ['DEL']:
vcf_out.write(line)
continue
var = Variant(v, vcf)
sys.stderr.write("%s\n" % var.var_id)
sys.stderr.write("%f\n" % float(var.get_info('AF')))
if float(var.get_info('AF')) < 0.01:
vcf_out.write(line)
else:
df = load_df(var, exclude, sex)
recdf = recluster(df)
if ct == 1:
recdf.to_csv(outf, header=True)
ct += 1
else:
recdf.to_csv(outf, header=False)
var.set_info("MEDGQR",
'{:.2f}'.format(recdf.iloc[0, :].loc['med_gq_re']))
var.set_info("Q10GQR",
'{:.2f}'.format(recdf.iloc[0, :].loc['q10_gq_re']))
recdf.set_index('sample', inplace=True)
for s in var.sample_list:
if s in recdf.index:
var.genotype(s).set_format("GTR", recdf.loc[s, 'GTR'])
var.genotype(s).set_format(
"GQR", '{:.2f}'.format(recdf.loc[s, 'gq_re']))
else:
var.genotype(s).set_format("GTR", "./.")
var.genotype(s).set_format("GQR", 0)
vcf_out.write(
var.get_var_string(use_cached_gt_string=False) + '\n')
vcf_out.close()
vcf_in.close()
gender_file.close()
outf.close()
if exclude_file is not None:
exclude_file.close()
return
def run_gt_refine(vcf_in, vcf_out, diag_outfile, gender_file, exclude_file):
vcf = Vcf()
header = []
in_header = True
sex={}
for line in gender_file:
v = line.rstrip().split('\t')
sex[v[0]] = int(v[1])
exclude = []
if exclude_file is not None:
for line in exclude_file:
exclude.append(line.rstrip())
outf=open(diag_outfile, 'w', 4096)
ct=1
for line in vcf_in:
if in_header:
if line[0] == "#":
header.append(line)
continue
else:
in_header = False
vcf.add_header(header)
vcf.add_info('MEDGQR', '1', 'Float', 'Median quality for refined GT')
vcf.add_info('Q10GQR', '1', 'Float', 'Q10 quality for refined GT')
vcf.add_format('GQR', 1, 'Float', 'Quality of refined genotype.')
vcf.add_format('GTR', 1, 'String', 'Refined genotype.')
vcf_out.write(vcf.get_header() + '\n')
v = line.rstrip().split('\t')
info = v[7].split(';')
svtype = None
for x in info:
if x.startswith('SVTYPE='):
svtype = x.split('=')[1]
break
# bail if not DEL or DUP prior to reclassification
if svtype not in ['DEL']:
vcf_out.write(line)
continue
var = Variant(v, vcf)
sys.stderr.write("%s\n" % var.var_id)
sys.stderr.write("%f\n" % float(var.get_info('AF')))
if float(var.get_info('AF'))<0.01:
vcf_out.write(line)
else:
df=load_df(var, exclude, sex)
recdf=recluster(df)
if ct==1:
recdf.to_csv(outf, header=True)
ct += 1
else:
recdf.to_csv(outf, header=False)
var.set_info("MEDGQR", '{:.2f}'.format(recdf.iloc[0,:].loc['med_gq_re']))
var.set_info("Q10GQR", '{:.2f}'.format(recdf.iloc[0,:].loc['q10_gq_re']))
recdf.set_index('sample', inplace=True)
for s in var.sample_list:
if s in recdf.index:
var.genotype(s).set_format("GTR", recdf.loc[s,'GTR'])
var.genotype(s).set_format("GQR", '{:.2f}'.format(recdf.loc[s,'gq_re']))
else:
var.genotype(s).set_format("GTR", "./.")
var.genotype(s).set_format("GQR", 0)
vcf_out.write(var.get_var_string(use_cached_gt_string=False) + '\n')
vcf_out.close()
vcf_in.close()
gender_file.close()
outf.close()
if exclude_file is not None:
exclude_file.close()
return
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)
def create_merged_variant(BP, c, v_id, vcf, use_product, weighting_scheme='unweighted'):
new_start_L, new_start_R, p_L , p_R, ALG = combine_pdfs(BP, c, use_product, weighting_scheme)
max_i_L = p_L.index(max(p_L))
max_i_R = p_R.index(max(p_R))
[cipos95, ciend95]=getCI95( p_L, p_R, max_i_L, max_i_R)
new_pos_L = new_start_L + max_i_L
new_pos_R = new_start_R + max_i_R
BP0=BP[c[0]]
A=BP0.l.rstrip().split('\t', 10)
ALT = ''
if BP0.sv_type == 'BND':
if BP0.strands[:2] == '++':
ALT = 'N]' + BP0.right.chrom + ':' + str(new_pos_R) + ']'
elif BP0.strands[:2] == '-+':
ALT = ']' + BP0.right.chrom + ':' + str(new_pos_R) + ']N'
elif BP0.strands[:2] == '+-':
ALT = 'N[' + BP0.right.chrom + ':' + str(new_pos_R) + '['
elif BP0.strands[:2] == '--':
ALT = '[' + BP0.right.chrom + ':' + str(new_pos_R) + '[N'
else:
ALT = '<' + BP0.sv_type + '>'
var_list=[ BP0.left.chrom,
new_pos_L,
str(v_id),
'N',
ALT,
0.0,
'.',
''] + A[8:]
var=Variant(var_list, vcf)
var.set_info('SVTYPE', BP0.sv_type)
var.set_info('ALG', ALG)
if var.get_info('SVTYPE')=='DEL':
var.set_info('SVLEN', new_pos_L - new_pos_R)
elif BP0.left.chrom == BP0.right.chrom:
var.set_info('SVLEN', new_pos_R - new_pos_L)
else:
SVLEN = None
if var.get_info('SVTYPE') == 'BND':
var.set_info('EVENT', str(v_id))
else:
var.set_info('END', new_pos_R )
var.set_info('CIPOS95', cipos95)
var.set_info('CIEND95', ciend95)
var.set_info('CIPOS', ','.join([str(x) for x in [-1*max_i_L, len(p_L) - max_i_L - 1]]))
var.set_info('CIEND', ','.join([str(x) for x in [-1*max_i_R, len(p_R) - max_i_R - 1]]))
var.set_info('PRPOS', ','.join([str(x) for x in p_L]))
var.set_info('PREND', ','.join([str(x) for x in p_R]))
return var
def run_gt_refine(vcf_in, vcf_out, diag_outfile, gender_file, exclude_file, batch_file):
vcf = Vcf()
header = []
in_header = True
sex = {}
for line in gender_file:
v = line.rstrip().split('\t')
sex[v[0]] = int(v[1])
exclude = []
if exclude_file is not None:
for line in exclude_file:
exclude.append(line.rstrip())
batch = dict()
if batch_file is not None:
for line in batch_file:
fields = line.rstrip().split('\t')
if fields[1] == 'None':
raise RuntimeError('Batch file contains a batch label of None. This label is reserved.')
batch[fields[0]] = fields[1]
outf = open(diag_outfile, 'w', 4096)
ct = 1
for line in vcf_in:
if in_header:
if line[0] == "#":
header.append(line)
continue
else:
in_header = False
vcf.add_header(header)
vcf.add_info('MEDGQR', '1', 'Float', 'Median quality for refined GT')
vcf.add_info('Q10GQR', '1', 'Float', 'Q10 quality for refined GT')
vcf.add_format('GQO', 1, 'Integer', 'Quality of original genotype')
vcf.add_format('GTO', 1, 'String', 'Genotype before refinement')
vcf_out.write(vcf.get_header() + '\n')
v = line.rstrip().split('\t')
info = v[7].split(';')
svtype = None
for x in info:
if x.startswith('SVTYPE='):
svtype = x.split('=')[1]
break
# bail if not DEL prior to reclassification
# DUPs can be quite complicated in their allelic structure
# and thus less amenable to refinement by clustering in many cases
# INV and BNDs are also unclear.
# See earlier commits for code of previous attempts to refine these.
if svtype not in ['DEL', 'MEI']:
vcf_out.write(line)
continue
var = Variant(v, vcf)
sys.stderr.write("%s\n" % var.var_id)
sys.stderr.write("%f\n" % float(var.get_info('AF')))
if float(var.get_info('AF')) < 0.01:
vcf_out.write(line)
else:
df = load_df(var, exclude, sex, batch)
recdf = recluster(df)
if ct == 1:
recdf.to_csv(outf, header=True)
ct += 1
else:
recdf.to_csv(outf, header=False)
var.set_info("MEDGQR", '{:.2f}'.format(recdf.iloc[0, :].loc['med_gq_re']))
var.set_info("Q10GQR", '{:.2f}'.format(recdf.iloc[0, :].loc['q10_gq_re']))
recdf.set_index('sample', inplace=True)
for s in var.sample_list:
g = var.genotype(s)
g.set_format("GTO", g.get_format("GT"))
g.set_format("GQO", g.get_format("GQ"))
if s in recdf.index:
var.genotype(s).set_format("GT", recdf.loc[s, 'GTR'])
var.genotype(s).set_format("GQ", '{:.0f}'.format(recdf.loc[s, 'gq_re']))
else:
var.genotype(s).set_format("GT", "./.")
var.genotype(s).set_format("GQ", 0)
vcf_out.write(var.get_var_string(use_cached_gt_string=False) + '\n')
vcf_out.close()
vcf_in.close()
gender_file.close()
outf.close()
if exclude_file is not None:
exclude_file.close()
return
