def __init__(self, filename):
self.vcf_reader = vcfpy.Reader.from_path(filename)
self.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([
('ID', 'TFX_HGVSBC_G'), ('Number', '.'), ('Type', 'String'),
('Description',
'HGVS genomic reference, as produced by pyhgvs.')
]))
self.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([
('ID', 'TFX_HGVSBC_C'), ('Number', '.'), ('Type', 'String'),
('Description',
'HGVS coding reference, as produced by pyhgvs.')
]))
self.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_HGVSBC_P1'), ('Number', '.'),
('Type', 'String'),
('Description',
'HGVS 1-letter protein reference, as produced '
'by pyhgvs.')]))
self.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_HGVSBC_P3'), ('Number', '.'),
('Type', 'String'),
('Description',
'HGVS 3-letter protein reference, as produced '
'by pyhgvs.')]))
def test_header_pedigree_header_line():
line1 = header.PedigreeHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "child"), ("Father", "father")]))
line2 = header.PedigreeHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "child"), ("Father", "father")]))
line3 = header.PedigreeHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "father")]))
assert line1 == line2
assert line1 != line3
if sys.version_info < (3, 6):
assert str(line1) == (
"PedigreeHeaderLine('PEDIGREE', '<ID=child,Father=father>', "
"OrderedDict([('ID', 'child'), ('Father', 'father')]))")
assert repr(line1) == (
"PedigreeHeaderLine('PEDIGREE', '<ID=child,Father=father>', "
"OrderedDict([('ID', 'child'), ('Father', 'father')]))")
else:
assert str(line1) == (
"PedigreeHeaderLine('PEDIGREE', '<ID=child,Father=father>', {'ID': 'child', 'Father': 'father'})"
)
assert repr(line1) == (
"PedigreeHeaderLine('PEDIGREE', '<ID=child,Father=father>', {'ID': 'child', 'Father': 'father'})"
)
assert line1.value == "<ID=child,Father=father>"
assert line1.serialize() == "##PEDIGREE=<ID=child,Father=father>"
with pytest.raises(TypeError):
hash(line1)
def test_header_filter_header_line():
line1 = header.FilterHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "PASS"),
("Description", "All filters passed")]))
line2 = header.FilterHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "PASS"),
("Description", "All filters passed")]))
line3 = header.FilterHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "q30"), ("Description", "Phred score <30")]))
assert line1 == line2
assert line1 != line3
if sys.version_info < (3, 6):
assert str(line1) == (
"FilterHeaderLine('FILTER', '<ID=PASS,Description=\"All filters passed\">', "
"OrderedDict([('ID', 'PASS'), ('Description', 'All filters passed')]))"
)
assert repr(line1) == (
"FilterHeaderLine('FILTER', '<ID=PASS,Description=\"All filters passed\">', "
"OrderedDict([('ID', 'PASS'), ('Description', 'All filters passed')]))"
)
else:
assert str(line1) == (
"FilterHeaderLine('FILTER', '<ID=PASS,Description=\"All filters passed\">', "
"{'ID': 'PASS', 'Description': 'All filters passed'})")
assert repr(line1) == (
"FilterHeaderLine('FILTER', '<ID=PASS,Description=\"All filters passed\">', "
"{'ID': 'PASS', 'Description': 'All filters passed'})")
assert line1.value == '<ID=PASS,Description="All filters passed">'
assert line1.serialize(
) == '##FILTER=<ID=PASS,Description="All filters passed">'
with pytest.raises(TypeError):
hash(line1)
def test_header_sample_header_line():
line1 = header.SampleHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "sample1")]))
line2 = header.SampleHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "sample1")]))
line3 = header.SampleHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "sample2")]))
assert line1 == line2
assert line1 != line3
if sys.version_info < (3, 6):
assert str(line1) == (
"SampleHeaderLine('SAMPLE', '<ID=sample1>', OrderedDict([('ID', 'sample1')]))"
)
assert repr(line1) == (
"SampleHeaderLine('SAMPLE', '<ID=sample1>', OrderedDict([('ID', 'sample1')]))"
)
else:
assert str(line1) == (
"SampleHeaderLine('SAMPLE', '<ID=sample1>', {'ID': 'sample1'})")
assert repr(line1) == (
"SampleHeaderLine('SAMPLE', '<ID=sample1>', {'ID': 'sample1'})")
assert line1.value == "<ID=sample1>"
assert line1.serialize() == "##SAMPLE=<ID=sample1>"
with pytest.raises(TypeError):
hash(line1)
def test_header_info_header_line():
line1 = header.InfoHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "SVTYPE"), ("Number", 1),
("Type", "String")]))
line2 = header.InfoHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "SVTYPE"), ("Number", 1),
("Type", "String")]))
line3 = header.InfoHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "END"), ("Number", 1), ("Type", "Integer")]))
assert line1 == line2
assert line1 != line3
if sys.version_info < (3, 6):
assert str(line1) == (
"InfoHeaderLine('INFO', '<ID=SVTYPE,Number=1,Type=String>', "
"OrderedDict([('ID', 'SVTYPE'), ('Number', 1), ('Type', 'String')]))"
)
assert repr(line1) == (
"InfoHeaderLine('INFO', '<ID=SVTYPE,Number=1,Type=String>', "
"OrderedDict([('ID', 'SVTYPE'), ('Number', 1), ('Type', 'String')]))"
)
else:
assert str(line1) == (
"InfoHeaderLine('INFO', '<ID=SVTYPE,Number=1,Type=String>', "
"{'ID': 'SVTYPE', 'Number': 1, 'Type': 'String'})")
assert repr(line1) == (
"InfoHeaderLine('INFO', '<ID=SVTYPE,Number=1,Type=String>', "
"{'ID': 'SVTYPE', 'Number': 1, 'Type': 'String'})")
assert line1.value == "<ID=SVTYPE,Number=1,Type=String>"
assert line1.serialize() == "##INFO=<ID=SVTYPE,Number=1,Type=String>"
with pytest.raises(TypeError):
hash(line1)
def test_header_format_header_line():
line1 = header.FormatHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "AD"), ("Number", "R"),
("Type", "Integer")]))
line2 = header.FormatHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "AD"), ("Number", "R"),
("Type", "Integer")]))
line3 = header.FormatHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "DP"), ("Number", 1), ("Type", "Integer")]))
assert line1 == line2
assert line1 != line3
if sys.version_info < (3, 6):
assert str(line1) == (
"FormatHeaderLine('FORMAT', '<ID=AD,Number=R,Type=Integer>', "
"OrderedDict([('ID', 'AD'), ('Number', 'R'), ('Type', 'Integer')]))"
)
assert repr(line1) == (
"FormatHeaderLine('FORMAT', '<ID=AD,Number=R,Type=Integer>', "
"OrderedDict([('ID', 'AD'), ('Number', 'R'), ('Type', 'Integer')]))"
)
else:
assert str(line1) == (
"FormatHeaderLine('FORMAT', '<ID=AD,Number=R,Type=Integer>', "
"{'ID': 'AD', 'Number': 'R', 'Type': 'Integer'})")
assert repr(line1) == (
"FormatHeaderLine('FORMAT', '<ID=AD,Number=R,Type=Integer>', "
"{'ID': 'AD', 'Number': 'R', 'Type': 'Integer'})")
assert line1.value == "<ID=AD,Number=R,Type=Integer>"
assert line1.serialize() == "##FORMAT=<ID=AD,Number=R,Type=Integer>"
with pytest.raises(TypeError):
hash(line1)
def test_header_alt_allele_header_line():
line1 = header.AltAlleleHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "DEL"), ("Description", "deletion")]))
line2 = header.AltAlleleHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "DEL"), ("Description", "deletion")]))
line3 = header.AltAlleleHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "DUP"), ("Description", "duplication")]))
assert line1 == line2
assert line1 != line3
if sys.version_info < (3, 6):
assert str(line1) == (
"""AltAlleleHeaderLine('ALT', '<ID=DEL,Description="deletion">', """
"""OrderedDict([('ID', 'DEL'), ('Description', 'deletion')]))""")
assert repr(line1) == (
"""AltAlleleHeaderLine('ALT', '<ID=DEL,Description="deletion">', """
"""OrderedDict([('ID', 'DEL'), ('Description', 'deletion')]))""")
else:
assert str(line1) == (
"AltAlleleHeaderLine('ALT', '<ID=DEL,Description=\"deletion\">', "
"{'ID': 'DEL', 'Description': 'deletion'})")
assert repr(line1) == (
"AltAlleleHeaderLine('ALT', '<ID=DEL,Description=\"deletion\">', "
"{'ID': 'DEL', 'Description': 'deletion'})")
assert line1.value == '<ID=DEL,Description="deletion">'
assert line1.serialize() == '##ALT=<ID=DEL,Description="deletion">'
with pytest.raises(TypeError):
hash(line1)
def test_header_contig_header_line():
line1 = header.ContigHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "1"), ("length", 234)]))
line2 = header.ContigHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "1"), ("length", 234)]))
line3 = header.ContigHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "2"), ("length", 123)]))
assert line1 == line2
assert line1 != line3
if sys.version_info < (3, 6):
assert str(line1) == (
"ContigHeaderLine('contig', '<ID=1,length=234>', OrderedDict([('ID', '1'), ('length', 234)]))"
)
assert repr(line1) == (
"ContigHeaderLine('contig', '<ID=1,length=234>', OrderedDict([('ID', '1'), ('length', 234)]))"
)
else:
assert str(line1) == (
"ContigHeaderLine('contig', '<ID=1,length=234>', {'ID': '1', 'length': 234})"
)
assert repr(line1) == (
"ContigHeaderLine('contig', '<ID=1,length=234>', {'ID': '1', 'length': 234})"
)
assert line1.value == "<ID=1,length=234>"
assert line1.serialize() == "##contig=<ID=1,length=234>"
with pytest.raises(TypeError):
hash(line1)
def run(vi, vo, mmc, mmf, mmfs, mff):
"""
Filter VCF based on given parameter
"""
mff = 0.99
if not vi:
exit("VCF file path not given. Exiting . . . . . .")
if not path.isfile(vi):
exit(
"Given file path doesn't exist or it is not a file. Exiting . . . . ."
)
try:
reader = vcfpy.Reader.from_path(vi)
reader.header.add_filter_line(
vcfpy.OrderedDict([('ID', 'min_alt_count'),
('Description',
f'Minimum {mmc} from each atrand')]))
reader.header.add_filter_line(
vcfpy.OrderedDict([('ID', 'min_alt_frac'),
('Description', f'Minimum {mmf} of total DP4')
]))
reader.header.add_filter_line(
vcfpy.OrderedDict([('ID', 'min_alt_fication_frac'),
('Description', f'Minimum {mff} of total DP4')
]))
writer = vcfpy.Writer.from_path(
'/dev/stdout',
reader.header) if not vo else vcfpy.Writer.from_path(
vo, reader.header)
for record in reader:
base_sum = sum(record.INFO["DP4"])
if ((record.INFO["DP4"][2] >= mmc) &
(record.INFO["DP4"][2] >= mmfs *
(record.INFO["DP4"][2] + record.INFO["DP4"][3])) &
(record.INFO["DP4"][3] >= mmc) &
(record.INFO["DP4"][3] >= mmfs *
(record.INFO["DP4"][2] + record.INFO["DP4"][3])) &
(record.INFO["DP4"][2] + record.INFO["DP4"][3] >=
mmf * base_sum)):
if record.INFO["DP4"][2] + record.INFO["DP4"][
3] >= mff * base_sum:
record.INFO["DP4"][0] = 0
record.INFO["DP4"][1] = 0
record.INFO["AF"] = 1.0
writer.write_record(record)
except:
exit(
"Please check given file. Is it in proper format??. Exiting . . . . ."
)
def test_header_without_lines():
lines = [
header.HeaderLine("foo", "bar"),
header.HeaderLine("foo2", "bar2")
]
samples = header.SamplesInfos(["one", "two", "three"])
hdr = header.Header(lines, samples)
hdr.add_filter_line(vcfpy.OrderedDict([("ID", "PASS")]))
hdr.add_filter_line(vcfpy.OrderedDict([("ID", "q30")]))
assert len(hdr.lines) == 4
hdr2 = header.header_without_lines(hdr, [("foo", "bar"),
("FILTER", "q30")])
assert len(hdr2.lines) == 2
assert hdr2.samples == hdr.samples
def test_add_format_line(vcf_header):
# check header before adding
assert len(vcf_header.lines) == 18
# add header line
VALUE = '<ID=GTa,Number=1,Type=String,Description="Genotype">'
line = header.FormatHeaderLine(
"FORMAT",
VALUE,
vcfpy.OrderedDict([("ID", "GTa"), ("Number", 1), ("Type", "String"),
("Description", "Genotype")]),
)
vcf_header.add_line(line)
# check header after adding
assert len(vcf_header.lines) == 19
assert "GTa" in vcf_header._indices["FORMAT"]
assert vcf_header._indices["FORMAT"]["GTa"] is vcf_header.lines[-1]
# Check resulting added header line
assert vcf_header.lines[-1].key == "FORMAT"
assert vcf_header.lines[-1].value == VALUE
assert len(vcf_header.lines[-1].mapping) == 4
assert vcf_header.lines[-1].mapping["ID"] == "GTa"
assert vcf_header.lines[-1].mapping["Number"] == 1
assert vcf_header.lines[-1].mapping["Type"] == "String"
assert vcf_header.lines[-1].mapping["Description"] == "Genotype"
def test_add_contig_line_shortcut(vcf_header):
# check header before adding
assert len(vcf_header.lines) == 18
assert "20a" not in vcf_header._indices["contig"]
# add header line
mapping = vcfpy.OrderedDict([
("ID", "20a"),
("length", 62435964),
("assembly", "B36"),
("md5", "f126cdf8a6e0c7f379d618ff66beb2da"),
("species", "H**o sapiens"),
("taxonomy", "x"),
])
vcf_header.add_contig_line(mapping)
# check header after adding
assert len(vcf_header.lines) == 19
assert "20a" in vcf_header._indices["contig"]
assert vcf_header._indices["contig"]["20a"] is vcf_header.lines[-1]
# Check resulting added header line
assert vcf_header.lines[-1].key == "contig"
VALUE = ("<ID=20a,length=62435964,assembly=B36,"
"md5=f126cdf8a6e0c7f379d618ff66beb2da,"
'species="H**o sapiens",taxonomy=x>')
assert vcf_header.lines[-1].value == VALUE
assert len(vcf_header.lines[-1].mapping) == 6
assert vcf_header.lines[-1].mapping["ID"] == "20a"
assert vcf_header.lines[-1].mapping["length"] == 62435964
assert vcf_header.lines[-1].mapping["assembly"] == "B36"
assert vcf_header.lines[-1].mapping[
"md5"] == "f126cdf8a6e0c7f379d618ff66beb2da"
assert vcf_header.lines[-1].mapping["species"] == "H**o sapiens"
assert vcf_header.lines[-1].mapping["taxonomy"] == "x"
def test_add_info_line_shortcut(vcf_header):
# check header before adding
assert len(vcf_header.lines) == 18
# add header line
VALUE = '<ID=DPa,Number=1,Type=Integer,Description="Total Depth">'
mapping = vcfpy.OrderedDict([("ID", "DPa"), ("Number", 1),
("Type", "Integer"),
("Description", "Total Depth")])
vcf_header.add_info_line(mapping)
assert len(vcf_header.lines) == 19
# check header after adding
assert len(vcf_header.lines) == 19
assert "DPa" in vcf_header._indices["INFO"]
assert vcf_header._indices["INFO"]["DPa"] is vcf_header.lines[-1]
# Check resulting added header line
assert vcf_header.lines[-1].key == "INFO"
assert vcf_header.lines[-1].value == VALUE
assert len(vcf_header.lines[-1].mapping) == 4
assert vcf_header.lines[-1].mapping["ID"] == "DPa"
assert vcf_header.lines[-1].mapping["Number"] == 1
assert vcf_header.lines[-1].mapping["Type"] == "Integer"
assert vcf_header.lines[-1].mapping["Description"] == "Total Depth"
def merge_contig_header(self):
for contig in self.readers[0].header.get_lines('contig'):
self.merge_header.add_contig_line(
vcfpy.OrderedDict(
[('ID', contig.id),
('length', contig.length)]
)
)
def add_caller_filter_header(self):
"""
Add caller info as FILTER to writer header
"""
for reader, caller in zip(self.readers, self.callers):
reader.header.add_filter_line(
vcfpy.OrderedDict(
[('ID', caller),
('Description', 'Variant caller label.')])
)
def merge_filter_header(self):
exclude = ['PASS']
exclude.extend(self.callers)
seen = []
for reader, caller in zip(self.readers, self.callers):
for filter in reader.header.get_lines('FILTER'):
if filter.id not in seen:
seen.append(filter.id)
if filter.id not in exclude:
self.merge_header.add_filter_line(
vcfpy.OrderedDict(
[('ID', '{}_{}'.format(caller, filter.id)),
('Description', '{} {}'.format(caller, filter.description))]
)
)
else:
self.merge_header.add_filter_line(
vcfpy.OrderedDict([('ID', filter.id), ('Description', filter.description)])
)
def merge_info_header(self):
for reader, caller in zip(self.readers, self.callers):
for info in reader.header.get_lines('INFO'):
self.merge_header.add_info_line(
vcfpy.OrderedDict(
[('ID', '{}_{}'.format(caller, info.id)),
('Number', info.number),
('Type', info.type),
('Description', '{} {}'.format(caller, info.description))]
)
)
def merge_format_header(self):
for reader, caller in zip(self.readers, self.callers):
for format in reader.header.get_lines('FORMAT'):
self.merge_header.add_format_line(
vcfpy.OrderedDict(
[('ID', '{}_{}'.format(caller, format.id)),
('Number', format.number),
('Type', format.type),
('Description', '{} {}'.format(caller, format.description))]
)
)
def test_header_has_header_line_positive():
lines = [
header.FormatHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "DP"), ("Number", "R"),
("Type", "Integer")])),
header.InfoHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "AD"), ("Number", "R"),
("Type", "Integer")])),
header.FilterHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "PASS"),
("Description", "All filters passed")])),
header.ContigHeaderLine.from_mapping(
vcfpy.OrderedDict([("ID", "1"), ("length", 234)])),
]
samples = header.SamplesInfos(["one", "two", "three"])
hdr = header.Header(lines, samples)
assert hdr.has_header_line("FORMAT", "DP")
assert hdr.has_header_line("INFO", "AD")
assert hdr.has_header_line("FILTER", "PASS")
assert hdr.has_header_line("contig", "1")
def collect_all_vcf(
dirs: str,
vcf_filename: str = "phased.partial.vcf",
output: str = "IsoSeq_IsoPhase.vcf",
) -> None:
no_snp_found_filename = Path(f"{Path(vcf_filename).stem}.NO_SNPS_FOUND")
snps_by_chrom = defaultdict(lambda: [])
reader = None
for d in dirs:
filename = Path(d, vcf_filename)
if not filename.exists():
if not no_snp_found_filename.exists():
logger.info("VCF file {filename} does not exist. Skipping.")
continue
with open(filename) as rf:
reader = vcfpy.Reader(rf)
for r in reader:
c = Counter() # genotype -> count
for x in r.samples:
if x.data.GT.count("|") == 0:
c[x.data.GT] += x.data.HQ
else:
for i, gt in enumerate(x.data.GT.split("|")):
c[gt] += x.data.HQ[i]
c_keys = c.keys()
genotype = "|".join(str(k) for k in c_keys)
counts = ",".join(str(c[k]) for k in c_keys)
r.samples = [
vcfpy.Call(
r,
"SAMPLE",
vcfpy.OrderedDict([("GT", genotype), ("HQ", counts)]),
)
]
snps_by_chrom[r.CHROM].append((r.POS, r))
keys = list(snps_by_chrom.keys())
keys.sort()
if reader is not None:
reader.samples = ["SAMPLE"]
with open(output, "w") as f:
f = vcfpy.Writer(f, reader)
for k in keys:
v = snps_by_chrom[k]
v.sort(key=lambda x: x[0])
for _, rec in v:
f.write_record(rec)
print("Output written to:", output)
def main():
# read from stdin
reader = vcfpy.Reader.from_path('/dev/stdin')
# add 'nhomalt' to header
reader.header.add_info_line(
vcfpy.OrderedDict([
('ID', 'nhomalt'), ('Number', 'A'), ('Type', 'Integer'),
('Description',
'The number of individuals that are called homozygous for the alternate allele.'
)
]))
# write to stdout with modified header
with vcfpy.Writer.from_path('/dev/stdout', reader.header) as writer:
for record in reader:
record.INFO['nhomalt'] = [nhomalt(record)]
writer.write_record(record)
def build_rec(calls=None, format_extras=None):
calls = calls or []
format_extras = format_extras or []
alt1 = record.Substitution(vcfpy.SNV, "T")
alt2 = record.Substitution(vcfpy.SNV, "A")
return record.Record(
"2",
100,
[],
"C",
[alt1, alt2],
None,
[],
vcfpy.OrderedDict(),
["GT"] + format_extras,
calls,
)
def generate_sv_record(records, comparison_result, sample_names):
"""
This method generates a single SV record after a call has been made over a set of input records
:param records: the input records involved in the SV call
:param comparison_result:
:param sample_names:
:return:
"""
# Build a map to easily find the records by the sample name. It can be multi-valued
sample_names_to_records = group_by(records,
lambda record: get_sample_name(record))
# Generate calls for each sample in this group
calls = [
get_sample_call(sample_name,
sample_names_to_records.get(sample_name, None))
for sample_name in sample_names
]
first_record_of_the_group = records[0]
chrom = first_record_of_the_group.CHROM
id_of_new_record = generate_id(chrom, comparison_result.initial_position)
info = vcfpy.OrderedDict()
info["SVTYPE"] = comparison_result.svtype
info["END"] = comparison_result.final_position
if comparison_result.insseq is not None:
info["INSSEQ"] = comparison_result.insseq
return vcfpy.Record(
CHROM=chrom, # by construction, all the grouped records have the same
POS=comparison_result.
initial_position, # by construction, all the grouped records have the same
ID=[id_of_new_record],
REF=first_record_of_the_group.
REF, # by construction, all the grouped records have the same
ALT=[
vcfpy.Substitution(type_=comparison_result.svtype,
value='<{}>'.format(comparison_result.svtype))
],
QUAL=maximum_qual(records),
FILTER=["PASS"],
INFO=info,
FORMAT=["GT", "TRANCHE2", "VAF"],
calls=calls)
def test_add_filter_line_shortcut(vcf_header):
# check header before adding
assert len(vcf_header.lines) == 18
# add header line
mapping = vcfpy.OrderedDict([("ID", "q10a"),
("Description", "Quality below 10")])
vcf_header.add_filter_line(mapping)
# check header after adding
assert len(vcf_header.lines) == 19
assert "q10a" in vcf_header._indices["FILTER"]
assert vcf_header._indices["FILTER"]["q10a"] is vcf_header.lines[-1]
# Check resulting added header line
assert vcf_header.lines[-1].key == "FILTER"
VALUE = '<ID=q10a,Description="Quality below 10">'
assert vcf_header.lines[-1].value == VALUE
assert len(vcf_header.lines[-1].mapping) == 2
assert vcf_header.lines[-1].mapping["ID"] == "q10a"
assert vcf_header.lines[-1].mapping["Description"] == "Quality below 10"
def select_info_header(self):
for info_field in self.info_fields:
for caller in self.caller_priority:
id = '{}_{}'.format(caller, info_field)
if id in self.reader.header.info_ids():
info = self.reader.header.get_info_field_info(id)
self.write_header.add_info_line(
vcfpy.OrderedDict([('ID', info.id.split('_', 1)[1]),
('Number', info.number),
('Type', info.type),
('Description',
info.description.split(' ',
1)[1])]))
break
else:
print('{} not found for {} in INFO column.'.format(
info_field, caller))
not_found = list(
set(list(self.info_fields)) - set(self.write_header.info_ids()))
if len(not_found) > 0:
raise Exception(', '.join(not_found) +
' INFO field(s) not found in VCF')
def modify_outheader(outheader):
info_lines={'CALLER':vcfpy.OrderedDict([('ID','CALLER'),('Number','1'),('Type','String'),('Description','Variant Call method')]),
'SS':vcfpy.OrderedDict([('ID','SS'),('Number','1'),('Type','String'),('Description','Somatic Status from respective Call Method')]),
'OFS':vcfpy.OrderedDict([('ID','OFS'),('Number','.'),('Type','String'),('Description','Original FILTER State')])}
#
format_lines={'GT':vcfpy.OrderedDict([('ID','GT'),('Number','1'),('Type','String'),('Description','Genotype')]),
'AD':vcfpy.OrderedDict([('ID','AD'),('Number','R'),('Type','Integer'),('Description','Alt Allele Depth')]),
'AAF':vcfpy.OrderedDict([('ID','AAF'),('Number','1'),('Type','Float'),('Description','Alt Allele Frequency')])}
#
for i in info_lines.keys():
if i not in outheader.info_ids():
outheader.add_info_line(info_lines[i])
else:
outheader.get_info_field_info(i).mapping.update(info_lines[i])
for f in format_lines.keys():
if f not in outheader.format_ids():
outheader.add_format_line(format_lines[f])
else:
outheader.get_format_field_info(f).mapping.update(format_lines[f])
return outheader
def main():
args = supply_args()
myvcf = VcfReader(args.infile)
vrnts = myvcf.get_vrnts()
coll = CollectMetrics()
# Set VCF header.
# 'AAP': hgvs_aap,
# 'BASEP': hgvs_basep,
# 'EXON': exon,
# 'HGNC': hgnc,
# 'HGVSC': hgvs_c,
# 'HGVSP1': hgvs_p,
# 'HGVSP3': hgvs_three,
# 'SOURCE': self.tfx_type,
# 'SPLICE': None,
# 'TXC': tx,
# 'VFX': self.veff,
# 'PVT': None
myvcf.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_AAP'), ('Number', '.'),
('Type', 'String'),
('Description', 'Amino acid start position.')]))
myvcf.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_BASEP'), ('Number', '.'),
('Type', 'String'),
('Description', 'Coding sequence start position.')
]))
myvcf.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_EXON'), ('Number', '.'),
('Type', 'String'),
('Description', 'Exon number associated with given '
'transcript.')]))
myvcf.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_HGNC'), ('Number', '.'),
('Type', 'String'),
('Description', 'HGNC gene symbol.')]))
myvcf.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_HGVSC'), ('Number', '.'),
('Type', 'String'),
('Description', 'HGVS cdot nomenclature.')]))
myvcf.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_HGVSP1'), ('Number', '.'),
('Type', 'String'),
('Description',
'HGVS pdot nomenclature, single letter '
'amino acids.')]))
myvcf.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_HGVSP3'), ('Number', '.'),
('Type', 'String'),
('Description',
'HGVS pdot nomenclature, three letter '
'amino acids.')]))
myvcf.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_SOURCE'), ('Number', '.'),
('Type', 'String'),
('Description', 'Annotation source.')]))
myvcf.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_SPLICE'), ('Number', '.'),
('Type', 'String'),
('Description', 'Splice site annotation.')]))
myvcf.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_TXC'), ('Number', '.'),
('Type', 'String'),
('Description', 'Transcript identifier.')]))
myvcf.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_VFX'), ('Number', '.'),
('Type', 'String'),
('Description', 'Variant effect annotation.')]))
myvcf.vcf_reader.header.add_info_line(
vcfpy.OrderedDict([('ID', 'TFX_PVT'), ('Number', '.'),
('Type', 'String'),
('Description',
'Variant type or location annotation.')]))
if args.evf:
my_evf = AnnovarExonVrntFunc(args.evf).read_annovar()
coll.metrics_push(my_evf)
if args.vf:
my_vf = AnnovarVrntFunc(args.vf).read_annovar()
coll.metrics_push(my_vf)
if args.ccds_evf:
my_ccds_evf = AnnovarExonVrntFunc(args.ccds_evf).read_annovar()
coll.metrics_push(my_ccds_evf)
if args.ccds_vf:
my_ccds_vf = AnnovarVrntFunc(args.ccds_vf).read_annovar()
coll.metrics_push(my_ccds_vf)
to_write = {}
for coord, txs in coll.metrics.items():
comb = defaultdict(list)
dict_items = map(methodcaller('items'), (txs.values()))
for k, v in chain.from_iterable(dict_items):
comb[k].append(v)
to_write[coord] = comb
# Look for any instances where the number of TFX fields do not match.
num_vals = len(set([len(x) for x in comb.values()]))
assert num_vals == 1 or not num_vals, "%s" % comb
writer = VcfWriter(args.outfile, myvcf.vcf_reader)
writer.write_metrics(vrnts, to_write)
def get_header(sample_name_to_header, chromosome_set):
"""
Returns the header of the output VCF file
:param sample_name_to_header: a dictionary from the sample names to the headers
:param chromosome_set: the set of chromosomes selected for analysis
:return: a vcfpy.Header
"""
header = vcfpy.Header()
header.add_line(vcfpy.HeaderLine(key="fileformat", value="VCFv4.2"))
# CONTIG headers
first_sample_header = next(iter(sample_name_to_header.values()))
for input_header_line in first_sample_header.lines:
if isinstance(input_header_line, vcfpy.ContigHeaderLine):
if chromosome_set is None or input_header_line.mapping[
"ID"] in chromosome_set:
header.add_line(input_header_line)
# INFO fields
header.add_info_line(
vcfpy.OrderedDict(ID="END",
Number=1,
Type="Integer",
Description="Stop position of the interval"))
header.add_info_line(
vcfpy.OrderedDict(ID="SVTYPE",
Number=1,
Type="String",
Description="Type of structural variant"))
header.add_info_line(
vcfpy.OrderedDict(
ID="INSSEQ",
Number=1,
Type="String",
Description=
"Insertion sequence of structural variant, not including sequence marked as duplication"
))
header.add_info_line(
vcfpy.OrderedDict(
ID="TRANCHE2",
Number=1,
Type="String",
Description=
"Quality category of GRIDSS structural variant calls determined using FILTER,SRQ,AS,RAS. Values are LOW INTERMEDIATE HIGH"
))
header.add_info_line(
vcfpy.OrderedDict(
ID="BNDVAF",
Number=1,
Type="Float",
Description=
"VAF of this gridss-called BND calculated as (SR+RP+IC+AS)/(REF+SR+RP+IC+AS)"
))
# FORMAT fields
header.add_format_line(
vcfpy.OrderedDict(ID="GT",
Number=1,
Type="String",
Description="Genotype"))
header.add_format_line(
vcfpy.OrderedDict(
ID="TRANCHE2",
Number=1,
Type="String",
Description=
"Quality category of GRIDSS structural variant calls determined using FILTER,SRQ,AS,RAS. Values are LOW INTERMEDIATE HIGH"
))
header.add_format_line(
vcfpy.OrderedDict(
ID="BNDVAF",
Number=1,
Type="Float",
Description=
"VAF of this gridss-called BND calculated as (SR+RP+IC+AS)/(REFPAIR+SR+RP+IC+AS)"
))
header.add_format_line(
vcfpy.OrderedDict(
ID="VAF",
Number=1,
Type="Float",
Description=
"VAF of this SV call, derived from BNDVAF values of BND calls used to call this SV"
))
header.add_format_line(
vcfpy.OrderedDict(
ID="INSSEQ",
Number=1,
Type="String",
Description=
"Insertion sequence of structural variant, not including sequence marked as duplication"
))
# Samples, sorted to ensure determinism
sample_names = sample_name_to_header.keys()
header.samples = vcfpy.SamplesInfos(sorted(sample_names))
return header
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import vcfpy
# Open input, add FILTER header, and open output file
reader = vcfpy.Reader.from_path("input.vcf")
reader.header.add_filter_line(
vcfpy.OrderedDict([("ID", "DP10"), ("Description", "total DP < 10")]))
writer = vcfpy.Writer.from_path("/dev/stdout", reader.header)
# Add "DP10" filter to records having less than 10 reads
for record in reader:
ad = sum(c.data.get("DP", 0) for c in record.calls)
if ad < 10:
record.add_filter("DP10")
writer.write_record(record)
# Variant calling score (QUAL) field
dico_vcf[var_id]["features"][caller_name]["QUAL"] = record.QUAL
# Filter field
dico_vcf[var_id]["features"][caller_name]["FILTER"] = record.FILTER
# Genotype (GT) field
dico_vcf[var_id]["features"][caller_name]["GT"] = record.calls[0].data.get('GT').replace("|","/")
# Read Depth (DP) field
dico_vcf[var_id]["features"][caller_name]["DP"] = record.calls[0].data.get('DP')
# Allele Frequency (AF) field
if caller_name in ["strelka","deepvariant"]: dico_vcf[var_id]["features"][caller_name]["AF"] = round((float(record.calls[0].data['AD'][1])/(float(record.calls[0].data['AD'][0])+float(record.calls[0].data['AD'][1]))),2) # for strelka and deepvariant AD for ref and alt is in FORMAT
else: dico_vcf[var_id]["features"][caller_name]["AF"] = round(float(record.INFO['AF'][0]),2)
#***** CREATE new vcf header *****#
# Callers list
new_header.add_line(vcfpy.HeaderLine("Nk_calls","|".join(lst_caller_name)))
# Filters list
for filter_id in dico_filter_line: new_header.add_filter_line(vcfpy.OrderedDict([('ID', filter_id),('Description', dico_filter_line[filter_id])]))
new_header.add_filter_line(vcfpy.OrderedDict([('ID', "FILTER"),('Description', "All callers filtered")]))
# INFO
dico_line_info_CALLNB = collections.OrderedDict([("ID","CALLNB"),("Number","A"),("Type","Integer"),("Description","Number of PASS calls")])
new_header.add_info_line(dico_line_info_CALLNB)
dico_line_info_CALLAF = collections.OrderedDict([("ID","CALLAF"),("Number","A"),("Type","String"),("Description","Allele frequency per caller")])
new_header.add_info_line(dico_line_info_CALLAF)
dico_line_info_CALLFILTER = collections.OrderedDict([("ID","CALLFILTER"),("Number","A"),("Type","String"),("Description","Filters per caller")])
new_header.add_info_line(dico_line_info_CALLFILTER)
dico_line_info_CALLQUAL = collections.OrderedDict([("ID","CALLQUAL"),("Number","A"),("Type","String"),("Description","Variant quality per caller")])
new_header.add_info_line(dico_line_info_CALLQUAL)
# FORMAT
dico_line_info_GT = collections.OrderedDict([("ID","GT"),("Number","1"),("Type","String"),("Description","Genotype")])
new_header.add_format_line(dico_line_info_GT)
dico_line_info_DP = collections.OrderedDict([("ID","DP"),("Number","1"),("Type","Integer"),("Description","Read depth (median if multiple calls)")])
new_header.add_format_line(dico_line_info_DP)
