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 convert(self, bedpe):
'''
Convert a bedpe object to Vcf object(s). Returns a list of entries.
'''
adjust_tag1, adjust_tag2 = 'CIPOS', 'CIEND'
if bedpe.malformedFlag == 1:
adjust_tag2, adjust_tag1 = adjust_tag1, adjust_tag2
b1 = self.adjust_by_tag(bedpe, adjust_tag1, bedpe.o1, bedpe.s1)
primary_bedpe_list = [
bedpe.c1, b1, bedpe.orig_name1, bedpe.orig_ref1, bedpe.orig_alt1,
bedpe.score, bedpe.filter, bedpe.info1
] + bedpe.misc
var = Variant(primary_bedpe_list, self.vcf_header)
to_return = [var]
if bedpe.svtype == 'BND':
b2 = self.adjust_by_tag(bedpe, adjust_tag2, bedpe.o2, bedpe.s2)
secondary_bedpe_list = [
bedpe.c2, b2, bedpe.orig_name2, bedpe.orig_ref2,
bedpe.orig_alt2, bedpe.score, bedpe.filter, bedpe.info2
] + bedpe.misc
var2 = Variant(secondary_bedpe_list, self.vcf_header)
if bedpe.malformedFlag == 0:
to_return += [var2]
elif bedpe.malformedFlag == 1:
#Only returning one of our entries
to_return[0] = var2
return to_return
def test_bnd_breakpoints(self):
vcf_array1 = [
'1', '20000', '235', 'T', 'A[1:6[', '0.00', '.', '.', 'GT', '0/0'
]
v1 = Variant(vcf_array1, self.vcf)
self.assertEqual(self.converter.bnd_breakpoints(v1),
('1', 20000, 20000, '1', 5, 5, '+', '-'))
vcf_array2 = [
'1', '20000', '235', 'T', ']1:6]N', '0.00', '.', '.', 'GT', '0/0'
]
v2 = Variant(vcf_array2, self.vcf)
self.assertEqual(self.converter.bnd_breakpoints(v2),
('1', 19999, 19999, '1', 6, 6, '-', '+'))
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 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_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):
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 calc_ld(vcf_in, exclude_file, ld_outfile, winsz, minpos):
vcf = Vcf()
header = []
in_header = True
maxwin = 100
exclude = []
keep = []
if exclude_file is not None:
for line in exclude_file:
exclude.append(line.rstrip())
if ld_outfile is not None:
outf = open(ld_outfile, 'w', 4096)
outf.write("id1\tid2\tnp1\tnp2\tr2\n")
curlist = []
curchr = -1
for line in vcf_in:
if in_header:
if line[0] == '#':
header.append(line)
continue
else:
in_header = False
vcf.add_header(header)
v = line.rstrip().split('\t')
var = Variant(v, vcf)
for s in var.sample_list:
if s in exclude:
continue
keep.append(s)
if var.info['NSAMP'] > minpos:
if curchr != -1 and var.chr is not curchr:
ld_calc(curlist, keep, ld_outfile, winsz)
curlist = [var]
curchr = var.chr
elif len(curlist) > maxwin:
ld_calc(curlist, keep, ld_outfile, winsz)
curlist = curlist[(maxwin - 1 - winsz):]
curlist.append(var)
else:
curlist.append(var)
ld_calc(curlist, keep, ld_outfile, winsz)
if ld_outfile is not None:
outf.close()
vcf_in.close()
if exclude_file is not None:
exclude_file.close()
return
def test_adjust_coordinate(self):
vcf_array1 = [
'1', '20000', '235', 'T', '<DEL>', '0.00', '.', 'CIEND=-50,50',
'GT', '0/0'
]
v1 = Variant(vcf_array1, self.vcf)
self.assertEqual(
self.converter.adjust_coordinate(v1, 'CIEND', 500, 1000),
(450, 1050))
self.assertEqual(
self.converter.adjust_coordinate(v1, 'CIPOS', 500, 1000),
(500, 1000))
vcf_array2 = [
'1', '20000', '235', 'T', '<DEL>', '0.00', '.', 'CIEND=50', 'GT',
'0/0'
]
v2 = Variant(vcf_array2, self.vcf)
with self.assertRaises(ValueError):
self.converter.adjust_coordinate(v2, 'CIEND', 500, 1000)
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 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 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
def test_simple_breakpoints(self):
vcf_array1 = [
'1', '20000', '235', 'T', '<DEL>', '0.00', '.', 'END=20500', 'GT',
'0/0'
]
v1 = Variant(vcf_array1, self.vcf)
self.assertEqual(self.converter.simple_breakpoints(v1),
('1', 20000, 20000, '1', 20500, 20500, '+', '-'))
vcf_array2 = [
'1', '20000', '235', 'T', '<DEL>', '0.00', '.',
'END=20500;STRANDS=-+:2', 'GT', '0/0'
]
v2 = Variant(vcf_array2, self.vcf)
self.assertEqual(self.converter.simple_breakpoints(v2),
('1', 20000, 20000, '1', 20500, 20500, '-', '+'))
vcf_array3 = [
'1', '20000', '235', 'T', '<DEL>', '0.00', '.', 'STRANDS=--:2',
'GT', '0/0'
]
v3 = Variant(vcf_array3, self.vcf)
with self.assertRaises(ValueError):
self.converter.simple_breakpoints(v3)
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 sv_classify(vcf_in, gender_file, exclude_file, ae_dict, f_overlap, slope_threshold, rsquared_threshold, het_del_fit, hom_del_fit, params, diag_outfile):
vcf_out = sys.stdout
vcf = Vcf()
header = []
in_header = True
min_pos_samps_for_regression = 10
sex = {}
# read sample genders
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())
if diag_outfile is not None:
outf=open(diag_outfile, 'w', 4096)
for line in vcf_in:
if in_header:
if line[0] == '#':
header.append(line)
continue
else:
in_header = False
vcf.add_header(header)
vcf_out.write(vcf.get_header() + '\n')
# split variant line, quick pre-check if the SVTYPE is BND, and skip if so
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', 'DUP']:
vcf_out.write(line)
continue
# parse the VCF line
var = Variant(v, vcf, True)
# check intersection with mobile elements
if ae_dict is not None and var.info['SVTYPE'] in ['DEL']:
ae = annotation_intersect(var, ae_dict, f_overlap)
if ae is not None:
if ae.startswith('SINE') or ae.startswith('LINE') or ae.split('|')[2].startswith('SVA'):
ae = 'ME:' + ae
var.alt = '<DEL:%s>' % ae
var.info['SVTYPE'] = 'MEI'
vcf_out.write(var.get_var_string(True) + '\n')
continue
# for now, don't worry about sex chromosomes
if (var.chrom == 'X' or var.chrom == 'Y'):
vcf_out.write(line)
continue
#count positively genotyped samples
num_pos_samps = 0;
for s in var.sample_list:
if s in exclude:
continue
if var.genotype(s).get_format('GT') not in ["./.", "0/0"]:
num_pos_samps += 1
high_freq_support = False
low_freq_support = False
nb_support = False
if num_pos_samps == 0:
vcf_out.write(line)
else:
df=load_df(var, exclude, sex)
if has_rd_support_by_nb(df, het_del_fit, hom_del_fit, params):
nb_support = True
if num_pos_samps < min_pos_samps_for_regression:
if has_low_freq_depth_support(df):
low_freq_support = True
vcf_out.write(line)
else:
for m_var in to_bnd_strings(var, True ):
vcf_out.write(m_var + '\n')
else:
if has_high_freq_depth_support(df, slope_threshold, rsquared_threshold):
high_freq_support = True
vcf_out.write(line)
else:
for m_var in to_bnd_strings(var, True):
vcf_out.write(m_var + '\n')
if diag_outfile is not None:
svlen=df['svlen'][0]
outf.write(var.var_id+"\t"+svtype+"\t"+str(svlen)+"\t"+str(num_pos_samps)+"\t"+str(nb_support)+"\t"+str(high_freq_support)+"\t"+str(low_freq_support)+"\n")
vcf_out.close()
if diag_outfile is not None:
outf.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 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 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()
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')
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 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
def calc_params(vcf_path):
tSet = list()
epsilon=0.1
header=[]
in_header = True
vcf = Vcf()
if vcf_path.endswith('.gz'):
vcf_file = gzip.open(vcf_path, 'rb')
else:
vcf_file = open(vcf_path, 'r')
for line in vcf_file:
if in_header:
if line[0] == '#':
header.append(line)
if line[1] != '#':
vcf_samples = line.rstrip().split('\t')[9:]
in_header = False
vcf.add_header(header)
continue
else:
v = line.rstrip().split('\t')
info = v[7].split(';')
svtype = None
for x in info:
if x.startswith('SVTYPE='):
svtype = x.split('=')[1]
break
if svtype not in ['DEL', 'DUP'] or v[0]=="X" or v[0]=="Y":
continue
var = Variant(v, vcf)
for sample in vcf_samples:
sample_genotype = var.genotype(sample)
if sample_genotype.get_format('GT') != './.':
log2r = math.log((float(sample_genotype.get_format('CN'))+ epsilon)/2,2) #to avoid log(0)
tSet.append(CN_rec(var.var_id, sample, var.info['SVTYPE'], abs(float(var.info['SVLEN'])), var.info['AF'],
sample_genotype.get_format('GT'), sample_genotype.get_format('CN'), sample_genotype.get_format('AB'), math.log(abs(float(var.info['SVLEN']))), log2r))
df=pd.DataFrame(tSet, columns=CN_rec._fields)
#exclude from training data, DELs and DUPs with CN in the tails of the distribution
df['q_low']=df.groupby(['sample', 'svtype', 'GT'])['log2r'].transform(lowQuantile)
df['q_high']=df.groupby(['sample', 'svtype', 'GT'])['log2r'].transform(highQuantile)
df=df[(df.log2r>=df.q_low) & (df.log2r<=df.q_high)]
#df.to_csv('./train.csv')
#adjust copy number for small deletions (<1kb), no strong relationship b/w cn and size for dups evident so far
small_het_dels = df[(df.svtype=="DEL") & (df.GT=="0/1") & (df.svlen<1000) & (df.svlen>=50)]
small_hom_dels = df[(df.svtype=="DEL") & (df.GT=="1/1") & (df.svlen<1000) & (df.svlen>=50)]
het_del_mean=np.mean(df[(df.svlen>1000) & (df.GT=="0/1") & (df.svtype=="DEL")]['log2r'])
hom_del_mean=np.mean(df[(df.svlen>1000) & (df.GT=="1/1") & (df.svtype=="DEL")]['log2r'])
small_het_dels['offset']=small_het_dels['log2r']-het_del_mean
small_hom_dels['offset']=small_hom_dels['log2r']-hom_del_mean
with warnings.catch_warnings():
warnings.filterwarnings("ignore")
hom_del_fit=smf.ols('offset~log_len',small_hom_dels).fit()
het_del_fit=smf.ols('offset~log_len',small_het_dels).fit()
#print hom_del_fit.summary()
#print het_del_fit.summary()
small_hom_dels['log2r_adj'] = small_hom_dels['log2r'] - hom_del_fit.predict(small_hom_dels)
small_het_dels['log2r_adj'] = small_het_dels['log2r'] - het_del_fit.predict(small_het_dels)
small_dels=small_hom_dels.append(small_het_dels)
small_dels=small_dels[['var_id', 'sample', 'svtype', 'svlen', 'AF', 'GT', 'CN', 'log_len', 'log2r', 'q_low', 'q_high', 'log2r_adj']]
# dels of length<100 bp are excluded here
df1=df[(df.svtype!="DEL") | (df.GT=="0/0") | (df.svlen>=1000)]
df1['log2r_adj']=df1['log2r']
df1=df1.append(small_dels)
params=df1.groupby(['sample', 'svtype', 'GT'])['log2r_adj'].aggregate([np.mean,np.var, len]).reset_index()
params=pd.pivot_table(params, index=['sample', 'svtype'], columns='GT', values=['mean', 'var', 'len']).reset_index()
params.columns=['sample', 'svtype', 'mean0', 'mean1', 'mean2', 'var0', 'var1', 'var2', 'len0', 'len1', 'len2']
params['std_pooled']=np.sqrt((params['var0']*params['len0']+params['var1']*params['len1']+params['var2']*params['len2'])/(params['len0']+params['len1']+params['len2']))
#params.to_csv('./params.csv')
return (params, het_del_fit, hom_del_fit)
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 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 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 __iter__(self):
for line in self.stream:
yield Variant(line.rstrip().split('\t'), self.vcf_obj)
def calc_params(vcf_path, sex_chrom_names):
tSet = list()
epsilon=0.1
header=[]
in_header = True
vcf = Vcf()
if vcf_path.endswith('.gz'):
vcf_file = gzip.open(vcf_path, 'rb')
else:
vcf_file = open(vcf_path, 'r')
for line in vcf_file:
if in_header:
if line[0] == '#':
header.append(line)
if line[1] != '#':
vcf_samples = line.rstrip().split('\t')[9:]
in_header = False
vcf.add_header(header)
continue
else:
v = line.rstrip().split('\t')
info = v[7].split(';')
svtype = None
for x in info:
if x.startswith('SVTYPE='):
svtype = x.split('=')[1]
break
if svtype not in ['DEL', 'DUP'] or v[0] in sex_chrom_names:
continue
var = Variant(v, vcf)
for sample in vcf_samples:
sample_genotype = var.genotype(sample)
if sample_genotype.get_format('GT') != './.':
log2r = math.log((float(sample_genotype.get_format('CN'))+ epsilon)/2,2) #to avoid log(0)
tSet.append(
CN_rec(
var.var_id,
sample,
var.info['SVTYPE'],
abs(float(var.info['SVLEN'])),
var.info['AF'],
sample_genotype.get_format('GT'),
sample_genotype.get_format('CN'),
sample_genotype.get_format('AB'),
math.log(abs(float(var.info['SVLEN']))), log2r
)
)
df=pd.DataFrame(tSet, columns=CN_rec._fields)
#exclude from training data, DELs and DUPs with CN in the tails of the distribution
df.loc[:,'q_low']=df.groupby(['sample', 'svtype', 'GT'])['log2r'].transform(lowQuantile)
df.loc[:,'q_high']=df.groupby(['sample', 'svtype', 'GT'])['log2r'].transform(highQuantile)
df=df[(df.log2r>=df.q_low) & (df.log2r<=df.q_high)]
#df.to_csv('./train.csv')
#adjust copy number for small deletions (<1kb), no strong relationship b/w cn and size for dups evident so far
small_het_dels = df[(df.svtype=="DEL") & (df.GT=="0/1") & (df.svlen<1000) & (df.svlen>=50)].copy()
small_hom_dels = df[(df.svtype=="DEL") & (df.GT=="1/1") & (df.svlen<1000) & (df.svlen>=50)].copy()
het_del_mean=np.mean(df[(df.svlen>1000) & (df.GT=="0/1") & (df.svtype=="DEL")]['log2r'])
hom_del_mean=np.mean(df[(df.svlen>1000) & (df.GT=="1/1") & (df.svtype=="DEL")]['log2r'])
small_het_dels.loc[:,'offset']=small_het_dels.loc[:,'log2r']-het_del_mean
small_hom_dels.loc[:,'offset']=small_hom_dels.loc[:,'log2r']-hom_del_mean
with warnings.catch_warnings():
warnings.filterwarnings("ignore")
hom_del_fit=smf.ols('offset~log_len',small_hom_dels).fit()
het_del_fit=smf.ols('offset~log_len',small_het_dels).fit()
#print hom_del_fit.summary()
#print het_del_fit.summary()
small_hom_dels.loc[:,'log2r_adj'] = small_hom_dels.loc[:,'log2r'] - hom_del_fit.predict(small_hom_dels)
small_het_dels.loc[:,'log2r_adj'] = small_het_dels.loc[:,'log2r'] - het_del_fit.predict(small_het_dels)
small_dels=small_hom_dels.append(small_het_dels)
small_dels=small_dels[['var_id', 'sample', 'svtype', 'svlen', 'AF', 'GT', 'CN', 'log_len', 'log2r', 'q_low', 'q_high', 'log2r_adj']]
# dels of length<100 bp are excluded here
df1=df.loc[(df.svtype!="DEL") | (df.GT=="0/0") | (df.svlen>=1000), :].copy()
df1.loc[:,'log2r_adj']=df1.loc[:,'log2r']
df1=df1.append(small_dels)
params=df1.groupby(['sample', 'svtype', 'GT'])['log2r_adj'].aggregate([np.mean,np.var, len]).reset_index()
params=pd.pivot_table(params, index=['sample', 'svtype'], columns='GT', values=['mean', 'var', 'len']).reset_index()
params.columns=['sample', 'svtype', 'mean0', 'mean1', 'mean2', 'var0', 'var1', 'var2', 'len0', 'len1', 'len2']
params['std_pooled'] = np.sqrt((params['var0']*params['len0']+params['var1']*params['len1']+params['var2']*params['len2'])/(params['len0']+params['len1']+params['len2']))
#params.to_csv('./params.csv')
return (params, het_del_fit, hom_del_fit)
def sv_classify(vcf_in, gender_file, exclude_file, ae_dict, f_overlap, slope_threshold, rsquared_threshold):
vcf_out = sys.stdout
vcf = Vcf()
header = []
in_header = True
min_pos_samps_for_regression = 10
gender = {}
# read sample genders
for line in gender_file:
v = line.rstrip().split('\t')
gender[v[0]] = int(v[1])
exclude = []
if exclude_file is not None:
for line in exclude_file:
exclude.append(line.rstrip())
for line in vcf_in:
if in_header:
if line[0] == '#':
header.append(line)
continue
else:
in_header = False
vcf.add_header(header)
# write the output header
vcf_out.write(vcf.get_header() + '\n')
# split variant line, quick pre-check if the SVTYPE is BND, and skip if so
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', 'DUP']:
vcf_out.write(line)
continue
# parse the VCF line
var = Variant(v, vcf, True)
# check intersection with mobile elements
if ae_dict is not None and var.info['SVTYPE'] in ['DEL']:
ae = annotation_intersect(var, ae_dict, f_overlap)
if ae is not None:
if ae.startswith('SINE') or ae.startswith('LINE') or ae.split('|')[2].startswith('SVA'):
ae = 'ME:' + ae
var.alt = '<DEL:%s>' % ae
var.info['SVTYPE'] = 'MEI'
vcf_out.write(var.get_var_string(True) + '\n')
continue
# # write to directory
# writedir = 'data/r11.100kb.dup'
# annotate based on read depth
if var.info['SVTYPE'] in ['DEL', 'DUP']:
# count the number of positively genotyped samples
num_pos_samps = 0;
for s in var.sample_list:
if s in exclude:
continue
if var.genotype(s).get_format('GT') not in ["./.", "0/0"]:
num_pos_samps += 1
if num_pos_samps < min_pos_samps_for_regression:
if has_low_freq_depth_support(var, gender, exclude):
# has_low_freq_depth_support(var, gender, exclude, writedir + '/low_freq_rd')
# has_high_freq_depth_support(var, gender, exclude, slope_threshold, rsquared_threshold, writedir + '/low_freq_rd')
# write variant
#vcf_out.write(var.get_var_string(True) + '\n')
vcf_out.write(line)
else:
# has_low_freq_depth_support(var, gender, exclude, writedir + '/low_freq_no_rd')
# has_high_freq_depth_support(var, gender, exclude, slope_threshold, rsquared_threshold, writedir + '/low_freq_no_rd')
for m_var in to_bnd_strings(var):
vcf_out.write(m_var + '\n')
else:
if has_high_freq_depth_support(var, gender, exclude, slope_threshold, rsquared_threshold):
# has_high_freq_depth_support(var, gender, exclude, slope_threshold, rsquared_threshold, writedir + '/high_freq_rd')
# has_low_freq_depth_support(var, gender, exclude, writedir + '/high_freq_rd')
# write variant
#vcf_out.write(var.get_var_string(True) + '\n')
vcf_out.write(line)
else:
# has_high_freq_depth_support(var, gender, exclude, slope_threshold, rsquared_threshold, writedir + '/high_freq_no_rd')
# has_low_freq_depth_support(var, gender, exclude, writedir + '/high_freq_no_rd')
for m_var in to_bnd_strings(var):
vcf_out.write(m_var + '\n')
vcf_out.close()
return
def sv_classify(vcf_in, vcf_out, gender_file, exclude_file, ae_dict, f_overlap, slope_threshold, rsquared_threshold, p_cnv, het_del_fit, hom_del_fit, params, diag_outfile, method):
vcf = Vcf()
header = []
in_header = True
sex = {}
# read sample genders
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())
if diag_outfile is not None:
outf=open(diag_outfile, 'w', 4096)
outf.write("varid\torig_svtype\tsvlen\tnum_pos_samps\tnb_support\tls_support\thybrid_support\thas_rd_support\n")
for line in vcf_in:
if in_header:
if line[0] == '#':
header.append(line)
continue
else:
in_header = False
vcf.add_header(header)
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', 'DUP']:
vcf_out.write(line)
continue
var = Variant(v, vcf)
# check intersection with mobile elements
if ae_dict is not None and var.info['SVTYPE'] in ['DEL']:
ae = annotation_intersect(var, ae_dict, f_overlap)
if ae is not None:
if ae.startswith('SINE') or ae.startswith('LINE') or ae.split('|')[2].startswith('SVA'):
ae = 'ME:' + ae
var.alt = '<DEL:%s>' % ae
var.info['SVTYPE'] = 'MEI'
vcf_out.write(var.get_var_string(True) + '\n')
continue
#count positively genotyped samples
num_pos_samps = 0
num_total_samps=len(var.sample_list)
for s in var.sample_list:
if var.genotype(s).get_format('GT') not in ["./.", "0/0"]:
num_pos_samps += 1
nb_support = False
ls_support = False
hybrid_support = False
has_rd_support = False
if num_pos_samps == 0:
vcf_out.write(line)
else:
df=load_df(var, exclude, sex)
if method=='large_sample':
ls_support = has_rd_support_by_ls(df, slope_threshold, rsquared_threshold, num_pos_samps)
has_rd_support=ls_support
elif method=='naive_bayes':
nb_support = has_rd_support_by_nb(df, het_del_fit, hom_del_fit, params, p_cnv)
has_rd_support=nb_support
elif method=='hybrid':
ls_support, nb_support, hybrid_support = has_rd_support_hybrid(df, het_del_fit, hom_del_fit, params, p_cnv, slope_threshold, rsquared_threshold, num_pos_samps)
has_rd_support=hybrid_support
if has_rd_support:
vcf_out.write(line)
else:
for m_var in to_bnd_strings(var, True):
vcf_out.write(m_var + '\n')
if diag_outfile is not None:
svlen=df['svlen'][0]
outf.write(var.var_id+"\t"+svtype+"\t"+str(svlen)+"\t"+str(num_pos_samps)+"\t"+str(nb_support)+"\t"+str(ls_support)+"\t"+str(hybrid_support)+"\t"+str(has_rd_support)+"\n")
vcf_out.close()
if diag_outfile is not None:
outf.close()
vcf_in.close()
vcf_out.close()
gender_file.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_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 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 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
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 sv_classify(vcf_in, vcf_out, gender_file, sex_chrom_names, exclude_file, ae_dict, f_overlap, slope_threshold, rsquared_threshold, p_cnv, het_del_fit, hom_del_fit, params, diag_outfile, method):
vcf = Vcf()
header = []
in_header = True
sex = {}
# read sample genders
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())
if diag_outfile is not None:
outf=open(diag_outfile, 'w', 4096)
outf.write("varid\torig_svtype\tsvlen\tnum_pos_samps\tnb_support\tls_support\thybrid_support\thas_rd_support\n")
for line in vcf_in:
if in_header:
if line[0] == '#':
header.append(line)
continue
else:
in_header = False
vcf.add_header(header)
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', 'DUP']:
vcf_out.write(line)
continue
var = Variant(v, vcf)
# check intersection with mobile elements
if ae_dict is not None and var.info['SVTYPE'] in ['DEL']:
ae = annotation_intersect(var, ae_dict, f_overlap)
if ae is not None:
if ae.startswith('SINE') or ae.startswith('LINE') or ae.split('|')[2].startswith('SVA'):
ae = 'ME:' + ae
var.alt = '<DEL:%s>' % ae
var.info['SVTYPE'] = 'MEI'
vcf_out.write(var.get_var_string(True) + '\n')
continue
#count positively genotyped samples
num_pos_samps = 0
num_total_samps=len(var.sample_list)
for s in var.sample_list:
if var.genotype(s).get_format('GT') not in ["./.", "0/0"]:
num_pos_samps += 1
nb_support = False
ls_support = False
hybrid_support = False
has_rd_support = False
if num_pos_samps == 0:
vcf_out.write(line)
else:
df = load_df(var, exclude, sex, sex_chrom_names)
if method == 'large_sample':
ls_support = has_rd_support_by_ls(df, slope_threshold, rsquared_threshold, num_pos_samps)
has_rd_support = ls_support
elif method == 'naive_bayes':
nb_support = has_rd_support_by_nb(df, het_del_fit, hom_del_fit, params, p_cnv)
has_rd_support = nb_support
elif method == 'hybrid':
ls_support, nb_support, hybrid_support = has_rd_support_hybrid(
df,
het_del_fit,
hom_del_fit,
params, p_cnv,
slope_threshold,
rsquared_threshold,
num_pos_samps
)
has_rd_support=hybrid_support
if has_rd_support:
vcf_out.write(line)
else:
for m_var in to_bnd_strings(var, True):
vcf_out.write(m_var + '\n')
if diag_outfile is not None:
svlen=df['svlen'][0]
outf.write(
'\t'.join((
var.var_id,
svtype,
str(svlen),
str(num_pos_samps),
str(nb_support),
str(ls_support),
str(hybrid_support),
str(has_rd_support)
)) + "\n"
)
vcf_out.close()
if diag_outfile is not None:
outf.close()
vcf_in.close()
vcf_out.close()
gender_file.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 bedpeToVcf(bedpe_file, vcf_out):
myvcf = Vcf()
in_header = True
# parse the bedpe data
header = list()
for line in bedpe_file:
if in_header:
if line[0:2] == '##':
header.append(line)
continue
elif line[0] == '#' and line[1] != '#':
sample_list_str = line.rstrip().split('\t', 14)[-1]
header.append('\t'.join([
'#CHROM',
'POS',
'ID',
'REF',
'ALT',
'QUAL',
'FILTER',
'INFO',
sample_list_str
] ))
continue
else:
in_header = False
myvcf.add_header(header)
myvcf.file_format='VCFv4.2'
vcf_out.write(myvcf.get_header() + '\n')
#
bedpe = Bedpe(line.rstrip().split('\t'))
if bedpe.svtype == 'BND':
bedpe1_list = [
bedpe.c1,
bedpe.b1 + 1,
bedpe.name + '_1', #ID
'N',
'<' + str(bedpe.svtype) + '>', #ALT
bedpe.score,
bedpe.filter
]
bedpe1_list.extend(bedpe.misc)
var1 = Variant(bedpe1_list, myvcf)
if bedpe.o1 == '+':
if bedpe.o2 == '-':
var1.alt = '%s[%s:%s[' % (var1.ref, bedpe.c2, bedpe.b2 + 1)
elif bedpe.o2 == '+':
var1.alt = '%s]%s:%s]' % (var1.ref, bedpe.c2, bedpe.b2 + 1)
elif bedpe.o1 == '-':
if bedpe.o2 == '+':
var1.alt = ']%s:%s]%s' % (bedpe.c2, bedpe.b2 + 1, var1.ref)
elif bedpe.o2 == '-':
var1.alt = '[%s:%s[%s' % (bedpe.c2, bedpe.b2 + 1, var1.ref)
misc = copy.deepcopy(bedpe.misc)
strands = re.split('=|:',''.join(filter(lambda x: 'STRANDS=' in x, bedpe.misc[0].split(";"))))
strands_str = str(strands[0]) + '=' + str(strands[1][::-1]) + ':' + str(strands[2])
misc[0]=misc[0].replace(''.join(filter(lambda x: 'STRANDS=' in x, bedpe.misc[0].split(";"))), strands_str)
#add the cipos ciend,cipos95 and ciend95 variables
misc[0]=misc[0].replace(''.join(filter(lambda x: 'CIPOS=' in x, bedpe.misc[0].split(";"))),'CIPOS='+ re.split('=',''.join(filter(lambda x: 'CIEND=' in x, bedpe.misc[0].split(";"))))[1])
misc[0]=misc[0].replace(''.join(filter(lambda x: 'CIEND=' in x, bedpe.misc[0].split(";"))),'CIEND='+ re.split('=',''.join(filter(lambda x: 'CIPOS=' in x, bedpe.misc[0].split(";"))))[1])
misc[0]=misc[0].replace(''.join(filter(lambda x: 'CIPOS95=' in x, bedpe.misc[0].split(";"))),'CIPOS95='+ re.split('=',''.join(filter(lambda x: 'CIEND95=' in x, bedpe.misc[0].split(";"))))[1])
misc[0]=misc[0].replace(''.join(filter(lambda x: 'CIEND95=' in x, bedpe.misc[0].split(";"))),'CIEND95='+ re.split('=',''.join(filter(lambda x: 'CIPOS95=' in x, bedpe.misc[0].split(";"))))[1])
#Change MATEID
misc[0]= misc[0].replace(''.join(filter(lambda x: 'MATEID=' in x, bedpe.misc[0].split(";"))),'MATEID=' + bedpe.name + '_2')
#ADD IDENTIFIER FOR SECONDARY BREAKEND MATE
misc[0]=misc[0].replace(''.join(filter(lambda x: 'EVENT=' in x, bedpe.misc[0].split(";"))),''.join(filter(lambda x: 'EVENT=' in x, bedpe.misc[0].split(";"))) + ';SECONDARY;')
bedpe2_list = [
bedpe.c2, #chrom1
bedpe.b2 + 1,
bedpe.name + '_2', #ID
'N',
'<' + str(bedpe.svtype) + '>', #ALT
bedpe.score,
bedpe.filter
]
bedpe2_list.extend(misc)
var2 = Variant(bedpe2_list, myvcf)
# add the strands field. For variant 2 must switch the order
if bedpe.o2 == '+':
if bedpe.o1 == '-':
var2.alt = '%s[%s:%s[' % (var2.ref, bedpe.c1, bedpe.b1 + 1)
elif bedpe.o1 == '+':
var2.alt = '%s]%s:%s]' % (var2.ref, bedpe.c1, bedpe.b1 + 1)
elif bedpe.o2 == '-':
if bedpe.o1 == '+':
var2.alt = ']%s:%s]%s' % (bedpe.c1, bedpe.b1 + 1, var2.ref)
elif bedpe.o1 == '-':
var2.alt = '[%s:%s[%s' % (bedpe.c1, bedpe.b1 + 1, var2.ref)
if bedpe.malformedFlag == 0:
vcf_out.write(var1.get_var_string() + '\n')
vcf_out.write(var2.get_var_string() + '\n')
elif bedpe.malformedFlag == 1:
vcf_out.write(var2.get_var_string() + '\n')
elif bedpe.malformedFlag == 2:
vcf_out.write(var1.get_var_string() + '\n')
else:
# set VCF info elements for simple events
bedpe_list = [
bedpe.c1, #chrom1
bedpe.b1 + 1,
bedpe.name, #ID
'N',
'<' + str(bedpe.svtype) + '>', #ALT
bedpe.score,
bedpe.filter
]
bedpe_list.extend(bedpe.misc)
var = Variant(bedpe_list, myvcf)
# write the record to the VCF output file
vcf_out.write(var.get_var_string() + '\n')
# close the VCF output file
vcf_out.close()
return
