def write_copynumber(vcf_file, sample, vcf_out, cn_list):
#go through the VCF and add the read depth annotations
in_header = True
header = []
vcf = Vcf()
i = 0
s_index = -1
for line in vcf_file:
if in_header:
if line[0] == '#' and line[1] == '#':
header.append(line)
continue
if line[0] == '#' and line[1] != '#':
try:
s_index = line.rstrip().split('\t').index(sample)
except ValueError:
sys.stderr.write(
"Please input valid VCF, format field for " + sample +
" not found in VCF")
sys.exit(1)
line = '\t'.join(
map(str,
line.rstrip().split('\t')[:9] + [sample]))
header.append(line)
continue
else:
in_header = False
vcf.add_header(header)
vcf.add_format('CN', 1, 'Float',
'Copy number of structural variant segment.')
vcf_out.write(vcf.get_header() + '\n')
v = line.rstrip().split('\t')
# XXX Is this second check necessary? Wouldn't this be handled above? Missing header would hit this?
if s_index == -1:
sys.stderr.write("Input a valid sample name: " + sample +
" not found in a provided VCF")
sys.exit(1)
v = v[:9] + [v[s_index]]
if not any("SVTYPE=BND" in s for s in v):
if "CN" not in v[8]:
v[8] = v[8] + ":CN"
v[9] = v[9] + ":" + str(cn_list[i])
else:
cn_index = v[8].rstrip().split(":").index("CN")
gts = v[9].rstrip().split(":")
gts[cn_index] = str(cn_list[i])
v[9] = ":".join(gts)
i += 1
# write the VCF
vcf_out.write('\t'.join(v) + '\n')
vcf_out.close()
return
def write_copynumber(vcf_file, sample, vcf_out, cn_list):
#go through the VCF and add the read depth annotations
in_header = True
header = []
vcf = Vcf()
i = 0
s_index = -1
cn_bad = -1 in cn_list
if cn_bad:
sys.stderr.write(
'cnvnator was unable to produce a copynumber value for one or more chromosomes. All copynumber values will be set to missing.'
)
cn_list = ['.'] * len(cn_list)
for line in vcf_file:
if in_header:
if line[0] == '#' and line[1] == '#':
header.append(line)
continue
if line[0] == '#' and line[1] != '#':
try:
s_index = line.rstrip().split('\t').index(sample)
except ValueError:
sys.stderr.write(
"Please input valid VCF, format field for {0} not found in VCF"
.format(sample))
sys.exit(1)
line = '\t'.join(
map(str,
line.rstrip().split('\t')[:9] + [sample]))
header.append(line)
continue
else:
in_header = False
vcf.add_header(header)
vcf.add_format('CN', 1, 'Float',
'Copy number of structural variant segment.')
vcf_out.write(vcf.get_header() + '\n')
v = line.rstrip().split('\t')
# XXX Is this second check necessary? Wouldn't this be handled above? Missing header would hit this?
if s_index == -1:
sys.stderr.write(
"Input a valid sample name: {0} not found in a provided VCF".
format(sample))
sys.exit(1)
v = v[:9] + [v[s_index]]
if not any("SVTYPE=BND" in s for s in v):
update_line_copynumber(v, cn_list, i)
i += 1
# write the VCF
vcf_out.write('\t'.join(v) + '\n')
vcf_out.close()
return
def write_copynumber(vcf_file, sample, vcf_out, cn_list):
#go through the VCF and add the read depth annotations
in_header = True
header = []
vcf = Vcf()
i = 0
s_index = -1
for line in vcf_file:
if in_header:
if line[0] == '#' and line[1] == '#':
header.append(line)
continue
if line[0] == '#' and line[1] != '#':
try:
s_index = line.rstrip().split('\t').index(sample)
except ValueError:
sys.stderr.write("Please input valid VCF, format field for " + sample + " not found in VCF")
sys.exit(1)
line = '\t'.join(map(str, line.rstrip().split('\t')[:9] + [sample]))
header.append(line)
continue
else:
in_header = False
vcf.add_header(header)
vcf.add_format('CN', 1, 'Float', 'Copy number of structural variant segment.')
vcf_out.write(vcf.get_header() + '\n')
v = line.rstrip().split('\t')
# XXX Is this second check necessary? Wouldn't this be handled above? Missing header would hit this?
if s_index == -1:
sys.stderr.write("Input a valid sample name: " + sample + " not found in a provided VCF")
sys.exit(1)
v = v[:9] + [v[s_index]]
if not any("SVTYPE=BND" in s for s in v):
if "CN" not in v[8]:
v[8] = v[8] + ":CN"
v[9] = v[9] + ":" + str(cn_list[i])
else:
cn_index = v[8].rstrip().split(":").index("CN")
gts = v[9].rstrip().split(":")
gts[cn_index] = str(cn_list[i])
v[9] = ":".join(gts)
i += 1
# write the VCF
vcf_out.write('\t'.join(v) + '\n')
vcf_out.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
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, 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
