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 run_gt_refine(vcf_in, vcf_out, diag_outfile, gender_file):
vcf = Vcf()
header = []
in_header = True
sex = {}
for line in gender_file:
v = line.rstrip().split('\t')
sex[v[0]] = int(v[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('SIL_GT_AVG', '1', 'Float',
'Average silhouette of genotype clusters')
#vcf.add_format('SIL_GT', '1', 'Float', 'Per-sample genotype cluster silhouette')
vcf_out.write(vcf.get_header() + '\n')
var = Variant(line.rstrip().split('\t'), vcf)
df = load_df(var, sex)
df1 = get_silhouette(df)
sil_avg = df1.iloc[0, df1.columns.get_loc('sil_gt_avg')]
#sil_ind=df1.loc[:, 'sil_gt']
var.info['SIL_GT_AVG'] = '%0.2f' % sil_avg
vcf_out.write(var.get_var_string(use_cached_gt_string=True) + '\n')
if ct == 1:
df1.to_csv(outf, header=True)
ct += 1
else:
df1.to_csv(outf, header=False)
vcf_out.close()
vcf_in.close()
outf.close()
gender_file.close()
return
def run_gt_refine(vcf_in, vcf_out, diag_outfile, gender_file):
vcf = Vcf()
header = []
in_header = True
sex={}
for line in gender_file:
v = line.rstrip().split('\t')
sex[v[0]] = int(v[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('SIL_GT_AVG', '1', 'Float', 'Average silhouette of genotype clusters')
#vcf.add_format('SIL_GT', '1', 'Float', 'Per-sample genotype cluster silhouette')
vcf_out.write(vcf.get_header() + '\n')
var = Variant(line.rstrip().split('\t'), vcf)
df=load_df(var, sex)
df1=get_silhouette(df)
sil_avg=df1.iloc[0, df1.columns.get_loc('sil_gt_avg')]
#sil_ind=df1.loc[:, 'sil_gt']
var.info['SIL_GT_AVG'] = '%0.2f' % sil_avg
vcf_out.write(var.get_var_string(use_cached_gt_string=True) + '\n')
if ct==1:
df1.to_csv(outf, header=True)
ct += 1
else:
df1.to_csv(outf, header=False)
vcf_out.close()
vcf_in.close()
outf.close()
gender_file.close()
return
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()
def l_cluster_by_line(file_name,
tempdir,
percent_slop=0,
fixed_slop=0,
use_product=False,
include_genotypes=False,
weighting_scheme='unweighted'):
v_id = 0
in_header = True
header = []
vcf = Vcf()
vcf_out = sys.stdout
with InputStream(file_name, tempdir) as vcf_stream:
BP_l = []
BP_sv_type = ''
BP_max_end_l = -1
BP_chr_l = ''
sample_order = []
for line in vcf_stream:
if in_header:
if line.startswith('##'):
header.append(line)
continue
elif line.startswith('#CHROM'):
v = line.rstrip().split('\t')
for headline in header:
if headline[:8] == '##SAMPLE':
sample_order.append(headline.rstrip()[13:-1])
hline = ''
if include_genotypes:
v.extend(sample_order)
hline = '\t'.join(v)
else:
v = v[:8]
hline = '\t'.join(v)
header.append(hline)
in_header = False
vcf.add_header(header)
vcf.add_info('ALG', '1', 'String',
'Algorithm used to merge this breakpoint')
if include_genotypes:
vcf_out.write(vcf.get_header() + '\n')
else:
vcf_out.write(vcf.get_header(False) + '\n')
continue
b = Breakpoint(l_bp.parse_vcf_record(line),
percent_slop=percent_slop,
fixed_slop=fixed_slop)
if (len(BP_l) == 0) or ((b.left.start <= BP_max_end_l) and
(b.left.chrom == BP_chr_l) and
(b.sv_type == BP_sv_type)):
BP_l.append(b)
BP_max_end_l = max(BP_max_end_l, b.left.end)
BP_chr_l = b.left.chrom
BP_sv_type = b.sv_type
else:
v_id = r_cluster(BP_l, sample_order, v_id, use_product, vcf,
vcf_out, include_genotypes, weighting_scheme)
BP_l = [b]
BP_max_end_l = b.left.end
BP_sv_type = b.sv_type
BP_chr_l = b.left.chrom
if len(BP_l) > 0:
v_id = r_cluster(BP_l, sample_order, v_id, use_product, vcf,
vcf_out, include_genotypes, weighting_scheme)
def varLookup(aFile, bFile, bedpe_out, max_distance, pass_prefix, cohort_name):
# FIXME The following code is heavily duplicated with vcftobedpe and bedpetovcf. Harmonize!!!
bList = list()
headerObj = Vcf() #co-opt the VCF header object
if cohort_name is None:
cohort_name = str(str(bFile).split('/')[-1])
if bFile == "stdin":
bData = sys.stdin
elif bFile.endswith('.gz'):
bData = gzip.open(bFile, 'rb')
else:
bData = open(bFile, 'r')
for bLine in bData:
if bLine.startswith(pass_prefix):
continue
bentry = Bedpe(bLine.rstrip().split('\t'))
if bentry.af is None:
sys.stderr.write(
'No allele frequency for variant found in -b file. This tool requires allele frequency information to function. Please add with svtools afreq and rerun\n'
)
sys.exit(1)
bList.append(bentry)
if aFile == "stdin":
aData = sys.stdin
elif aFile.endswith('.gz'):
aData = gzip.open(aFile, 'rb')
else:
aData = open(aFile, 'r')
in_header = True
header_lines = []
sample_list = None
for aLine in aData:
if pass_prefix is not None and aLine.startswith(pass_prefix):
if aLine[0] == '#' and aLine[1] != '#':
sample_list = aLine.rstrip().split('\t', 14)[-1]
else:
header_lines.append(aLine)
continue
else:
if in_header == True:
headerObj.add_header(header_lines)
headerObj.add_info(
cohort_name + '_AF', '.', 'Float',
'Allele frequency(ies) for matching variants found in the '
+ cohort_name + ' vcf' + ' (' +
str(str(bFile).split('/')[-1]) + ')')
headerObj.add_info(
cohort_name + '_VarID', '.', 'Integer',
'List of Variant ID(s) for matching variants found in the '
+ cohort_name + ' vcf' + ' (' +
str(str(bFile).split('/')[-1]) + ')')
header = headerObj.get_header()
bedpe_out.write(header[:header.rfind('\n')] + '\n')
if len(sample_list) > 0:
bedpe_out.write('\t'.join([
'#CHROM_A', 'START_A', 'END_A', 'CHROM_B', 'START_B',
'END_B', 'ID', 'QUAL', 'STRAND_A', 'STRAND_B', 'TYPE',
'FILTER', 'INFO_A', 'INFO_B', sample_list
]) + '\n')
else:
bedpe_out.write('\t'.join([
'#CHROM_A', 'START_A', 'END_A', 'CHROM_B', 'START_B',
'END_B', 'ID', 'QUAL', 'STRAND_A', 'STRAND_B', 'TYPE',
'FILTER', 'INFO_A', 'INFO_B'
]) + '\n')
in_header = False
a = Bedpe(aLine.rstrip().split('\t'))
if a.af is None:
sys.stderr.write(
'No allele frequency for variant found in -a file. This tool requires allele frequency information to function. Please add with svtools afreq and rerun\n'
)
sys.exit(1)
for b in bList:
add(a, b, max_distance)
bedpe_out.write(get_var_string(a, cohort_name) + '\n')
def varLookup(aFile, bFile, bedpe_out, max_distance, pass_prefix, cohort_name):
# FIXME The following code is heavily duplicated with vcftobedpe and bedpetovcf. Harmonize!!!
bList = list()
headerObj=Vcf() #co-opt the VCF header object
if cohort_name is None:
cohort_name=str(str(bFile).split('/')[-1])
if bFile == "stdin":
bData = sys.stdin
elif bFile.endswith('.gz'):
bData = gzip.open(bFile, 'rb')
else:
bData = open(bFile, 'r')
for bLine in bData:
if bLine.startswith(pass_prefix):
continue
bentry = Bedpe(bLine.rstrip().split('\t'))
if bentry.af is None:
sys.stderr.write('No allele frequency for variant found in -b file. This tool requires allele frequency information to function. Please add with svtools afreq and rerun\n')
sys.exit(1)
bList.append(bentry)
if aFile == "stdin":
aData = sys.stdin
elif aFile.endswith('.gz'):
aData = gzip.open(aFile, 'rb')
else:
aData = open(aFile, 'r')
in_header=True
header_lines = []
sample_list = None
for aLine in aData:
if pass_prefix is not None and aLine.startswith(pass_prefix):
if aLine[0] == '#' and aLine[1] != '#':
sample_list = aLine.rstrip().split('\t', 14)[-1]
else:
header_lines.append(aLine)
continue
else:
if in_header == True:
headerObj.add_header(header_lines)
headerObj.add_info(cohort_name + '_AF', '.', 'Float', 'Allele frequency(ies) for matching variants found in the ' + cohort_name + ' vcf' + ' (' + str(str(bFile).split('/')[-1]) + ')' )
headerObj.add_info(cohort_name + '_VarID', '.', 'Integer', 'List of Variant ID(s) for matching variants found in the ' + cohort_name + ' vcf' + ' (' + str(str(bFile).split('/')[-1]) + ')' )
header = headerObj.get_header()
bedpe_out.write(header[:header.rfind('\n')] + '\n')
if len(sample_list) > 0:
bedpe_out.write('\t'.join(['#CHROM_A',
'START_A',
'END_A',
'CHROM_B',
'START_B',
'END_B',
'ID',
'QUAL',
'STRAND_A',
'STRAND_B',
'TYPE',
'FILTER',
'INFO_A','INFO_B',
sample_list]
) + '\n')
else:
bedpe_out.write('\t'.join(['#CHROM_A',
'START_A',
'END_A',
'CHROM_B',
'START_B',
'END_B',
'ID',
'QUAL',
'STRAND_A',
'STRAND_B',
'TYPE',
'FILTER',
'INFO_A','INFO_B']
) + '\n')
in_header=False
a = Bedpe(aLine.rstrip().split('\t'))
if a.af is None:
sys.stderr.write('No allele frequency for variant found in -a file. This tool requires allele frequency information to function. Please add with svtools afreq and rerun\n')
sys.exit(1)
for b in bList:
add(a,b,max_distance)
bedpe_out.write(get_var_string(a, cohort_name))
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 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()
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_from_args(args):
vcf = Vcf()
vcf_out=sys.stdout
in_header = True
header_lines = list()
with su.InputStream(args.manta_vcf) as input_stream:
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('PRPOS', '1', 'String', 'Breakpoint probability dist')
vcf.add_info('PREND', '1', 'String', 'Breakpoint probability dist')
vcf.add_info('STRANDS', '.', 'String', 'Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--')
vcf.add_info('SU', '.', 'Integer', 'Number of pieces of evidence supporting the variant across all samples')
vcf.add_info('PE', '.', 'Integer', 'Number of paired-end reads supporting the variant across all samples')
vcf.add_info('SR', '.', 'Integer', 'Number of split reads supporting the variant across all samples')
vcf.add_info('INSLEN_ORIG', '.', 'Integer', 'Original insertion length')
vcf.add_info('CIPOS95', '2', 'Integer', 'Confidence interval (95%) around POS for imprecise variants')
vcf.add_info('CIEND95', '2', 'Integer', 'Confidence interval (95%) around END for imprecise variants')
vcf.add_info('SECONDARY', '0', 'Flag', 'Secondary breakend in a multi-line variant')
vcf_out.write(vcf.get_header()+'\n')
else:
v = Variant(line.rstrip().split('\t'), vcf)
convert_variant(v, args.max_ins)
vcf_out.write(v.get_var_string()+"\n")
def l_cluster_by_line(file_name, percent_slop=0, fixed_slop=0, use_product=False, include_genotypes=False, weighting_scheme='unweighted'):
v_id = 0
in_header = True
header = []
vcf = Vcf()
vcf_out=sys.stdout
with InputStream(file_name) as vcf_stream:
BP_l = []
BP_sv_type = ''
BP_max_end_l = -1
BP_chr_l = ''
sample_order = []
for line in vcf_stream:
if in_header:
if line.startswith('##'):
header.append(line)
continue
elif line.startswith('#CHROM'):
v=line.rstrip().split('\t')
for headline in header:
if headline[:8] == '##SAMPLE':
sample_order.append(headline.rstrip()[13:-1])
hline=''
if include_genotypes :
v.extend(sample_order)
hline='\t'.join(v)
else :
v=v[:8]
hline='\t'.join(v)
header.append(hline)
in_header=False
vcf.add_header(header)
vcf.add_info('ALG', '1', 'String', 'Algorithm used to merge this breakpoint')
if include_genotypes:
vcf_out.write(vcf.get_header()+'\n')
else:
vcf_out.write(vcf.get_header(False)+'\n')
continue
b = Breakpoint(l_bp.parse_vcf_record(line), percent_slop=percent_slop, fixed_slop=fixed_slop)
if (len(BP_l) == 0) or ((b.left.start <= BP_max_end_l) and (b.left.chrom == BP_chr_l) and (b.sv_type == BP_sv_type)):
BP_l.append(b)
BP_max_end_l = max(BP_max_end_l, b.left.end)
BP_chr_l = b.left.chrom
BP_sv_type = b.sv_type
else:
v_id = r_cluster(BP_l, sample_order, v_id, use_product, vcf, vcf_out, include_genotypes, weighting_scheme)
BP_l = [b]
BP_max_end_l = b.left.end
BP_sv_type = b.sv_type
BP_chr_l = b.left.chrom
if len(BP_l) > 0:
v_id = r_cluster(BP_l, sample_order, v_id, use_product, vcf, vcf_out, include_genotypes, weighting_scheme)
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, fixed_genotypes=True)
# extract genotypes from VCF
num_alt = len(var.alt.split(','))
alleles = [0] * (num_alt + 1)
num_samp = 0
gt = [var.genotype(s).get_format('GT') for s in var.sample_list]
for gt_string in gt:
if '.' in gt_string:
continue
gt = gt_string.split('/')
if len(gt) == 1:
gt = gt_string.split('|')
gt = map(int, gt)
for i in xrange(len(gt)):
alleles[gt[i]] += 1
# iterate the number of non-reference samples
if sum(gt) > 0:
num_samp += 1
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
var.info['MSQ'] = self.calc_msq(var)
# after all samples have been processed, write
vcf_out.write(var.get_var_string(use_cached_gt_string=True) + '\n')
vcf_out.close()
def l_cluster_by_line(file_name,
tempdir,
percent_slop=0,
fixed_slop=0,
use_product=False,
include_genotypes=False,
weighting_scheme='unweighted'):
v_id = 0
in_header = True
header = []
vcf = Vcf()
vcf_out = sys.stdout
with InputStream(file_name, tempdir) as vcf_stream:
BP_l = []
BP_sv_type = ''
BP_max_end_l = -1
BP_chr_l = ''
sample_order = []
for line in vcf_stream:
if in_header:
if line.startswith('##'):
header.append(line)
continue
elif line.startswith('#CHROM'):
v = line.rstrip().split(
'\t') # #CHROM line split -> list -D
for headline in header:
if headline[:8] == '##SAMPLE' and headline.rstrip(
)[13:-1] != 'VARIOUS':
sample_order.append(
headline.rstrip()[13:-1]
) # maybe add sample name to samplr_order list. -D
hline = '' # Parsed #CHROM line from 'v' -D
if include_genotypes:
v = v[:9] # Remove possible VARIOUS -D
v.extend(sample_order)
hline = '\t'.join(v)
else:
v = v[:8] # No FORMAT field here. -D
hline = '\t'.join(v)
header.append(hline)
in_header = False
vcf.add_header(header)
vcf.add_info('ALG', '1', 'String',
'Algorithm used to merge this breakpoint')
if include_genotypes:
vcf_out.write(vcf.get_header() + '\n')
else:
vcf_out.write(
vcf.get_header(include_samples=False) +
'\n') # Not including samples here. -D
continue
# Header is now parsed, then the main dish. -D
b = Breakpoint(
l_bp.parse_vcf_record(line),
percent_slop=percent_slop,
fixed_slop=fixed_slop) # percent_slop and fixed_slop is 0. -D
if (len(BP_l) == 0) or (
(b.left.start <= BP_max_end_l) and
(b.left.chrom == BP_chr_l) and (b.sv_type == BP_sv_type)
): # Same chrom svtype and start is small than previous end. -D
BP_l.append(b)
BP_max_end_l = max(BP_max_end_l, b.left.end)
BP_chr_l = b.left.chrom
BP_sv_type = b.sv_type
else:
v_id = r_cluster(BP_l, sample_order, v_id, use_product, vcf,
vcf_out, include_genotypes, weighting_scheme)
BP_l = [b]
BP_max_end_l = b.left.end
BP_chr_l = b.left.chrom
BP_sv_type = b.sv_type
if len(BP_l) > 0:
v_id = r_cluster(BP_l, sample_order, v_id, use_product, vcf,
vcf_out, include_genotypes, weighting_scheme)
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
