def get_header(vcf_file_path):
"""Parse the header and return a header object
Args:
vcf_file_path(str): Path to vcf
Returns:
head: A HeaderParser object
"""
logger.info("Parsing header of file {0}".format(vcf_file_path))
head = HeaderParser()
handle = get_vcf_handle(infile=vcf_file_path)
# Parse the header
for line in handle:
line = line.rstrip()
if line.startswith('#'):
if line.startswith('##'):
head.parse_meta_data(line)
else:
head.parse_header_line(line)
else:
break
handle.close()
return head
def export(ctx, outfile):
"""Export the variants of a loqus db
The variants are exported to a vcf file
"""
adapter = ctx.obj['adapter']
logger.info("Export the variants from {0}".format(adapter))
nr_cases = 0
existing_chromosomes = set(adapter.get_chromosomes())
ordered_chromosomes = []
for chrom in CHROMOSOME_ORDER:
if chrom in existing_chromosomes:
ordered_chromosomes.append(chrom)
existing_chromosomes.remove(chrom)
for chrom in existing_chromosomes:
ordered_chromosomes.append(chrom)
nr_cases = adapter.cases().count()
logger.info("Found {0} cases in database".format(nr_cases))
head = HeaderParser()
head.add_fileformat("VCFv4.3")
head.add_meta_line("NrCases", nr_cases)
head.add_info("Obs", '1', 'Integer',
"The number of observations for the variant")
head.add_info("Hom", '1', 'Integer', "The number of observed homozygotes")
head.add_info("Hem", '1', 'Integer', "The number of observed hemizygotes")
head.add_version_tracking("loqusdb", __version__,
datetime.now().strftime("%Y-%m-%d %H:%M"))
for chrom in ordered_chromosomes:
length = adapter.get_max_position(chrom)
head.add_contig(contig_id=chrom, length=str(length))
print_headers(head, outfile=outfile)
for chrom in ordered_chromosomes:
for variant in adapter.get_variants(chromosome=chrom):
chrom = variant['chrom']
pos = variant['start']
ref = variant['ref']
alt = variant['alt']
observations = variant['observations']
homozygotes = variant['homozygote']
hemizygotes = variant['hemizygote']
info = "Obs={0}".format(observations)
if homozygotes:
info += ";Hom={0}".format(homozygotes)
if hemizygotes:
info += ";Hem={0}".format(hemizygotes)
variant_line = "{0}\t{1}\t.\t{2}\t{3}\t.\t.\t{4}\n".format(
chrom, pos, ref, alt, info)
print_variant(variant_line=variant_line, outfile=outfile)
def get_header(vcf_lines):
"""Parse the vcf lines and return a header object"""
head = HeaderParser()
for line in vcf_lines:
if line.startswith('#'):
if line.startswith('##'):
head.parse_meta_data(line)
else:
head.parse_header_line(line)
return head
def export(ctx, outfile):
"""Export the variants of a loqus db
The variants are exported to a vcf file
"""
adapter = ctx.obj['adapter']
logger.info("Export the variants from {0}".format(adapter))
nr_cases = 0
for nr_cases, case in enumerate(adapter.cases()):
nr_cases += 1
logger.info("Found {0} cases in database".format(nr_cases))
head = HeaderParser()
head.add_fileformat("##fileformat=VCFv4.1")
head.add_meta_line("NrCases", nr_cases)
head.add_info("Obs", '1', 'Integer',
"The number of observations for the variant")
head.add_info("Hom", '1', 'Integer', "The number of observed homozygotes")
head.add_version_tracking("loqusdb", __version__,
datetime.now().strftime("%Y-%m-%d %H:%M"))
logger.debug("Create tempfile to print variants from database")
variants = tempfile.TemporaryFile()
logger.debug("Printing headers")
print_headers(head, outfile=outfile)
try:
for variant in adapter.get_variants():
variant_id = variant['_id'].split('_')
chrom = variant_id[0]
pos = variant_id[1]
ref = variant_id[2]
alt = variant_id[3]
observations = variant['observations']
homozygotes = variant['homozygote']
info = "Obs={0};Hom={1}".format(observations, homozygotes)
variant_line = "{0}\t{1}\t.\t{2}\t{3}\t.\t.\t{4}\n".format(
chrom, pos, ref, alt, info)
variants.write(variant_line)
variants.seek(0)
for line in sort_variants(variants):
print_variant(variant_line=line, outfile=outfile)
finally:
variants.close()
def test_parse_vcf_lines():
"""
Test how the header parser behaves with simple vcf lines
"""
header_parser = HeaderParser()
header_lines = [
'##fileformat=VCFv4.2',
'##FILTER=<ID=LowQual,Description="Low quality">',
'##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">',
'##INFO=<ID=CNT,Number=A,Type=Integer,Description="Number of times '\
'this allele was found in external db">',
'##contig=<ID=1,length=249250621,assembly=b37>',
'##INFO=<ID=DP_HIST,Number=R,Type=String,Description="Histogram for '\
'DP; Mids: 2.5|7.5|12.5|17.5|22.5|27.5|32.5|37.5|42.5|47.5|52.5|57.5|'\
'62.5|67.5|72.5|77.5|82.5|87.5|92.5|97.5">',
'##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for'\
' the ref and alt alleles in the order listed">',
'##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">',
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
'##FORMAT=<ID=GQ,Number=1,Type=String,Description="GenotypeQuality">'
'##reference=file:///human_g1k_v37.fasta',
'#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tfather\tmother\tproband'
]
for line in header_lines:
if line.startswith('##'):
header_parser.parse_meta_data(line)
elif line.startswith('#'):
header_parser.parse_header_line(line)
assert header_parser.fileformat == "VCFv4.2"
assert header_parser.individuals == ['father', 'mother', 'proband']
assert header_parser.vep_columns == []
assert "MQ" in header_parser.extra_info
assert header_parser.extra_info["MQ"][
'Description'] == "RMS Mapping Quality"
assert header_parser.extra_info["CNT"]['Number'] == "A"
assert header_parser.extra_info["CNT"]['Type'] == "Integer"
assert "CNT" in header_parser.extra_info
assert "DP_HIST" in header_parser.extra_info
assert "LowQual" in header_parser.filter_dict
assert "1" in header_parser.contig_dict
assert header_parser.header == [
'CHROM', 'POS', 'ID', 'REF', 'ALT', 'QUAL', 'FILTER', 'INFO', 'FORMAT',
'father', 'mother', 'proband'
]
def test_vep_columns():
"""
Test how the vep columns are parsed
"""
header_parser = HeaderParser()
vep_info_line = '##INFO=<ID=CSQ,Number=.,Type=String,Description="Consequence'\
' type as predicted by VEP. Format: Allele|Gene|Feature|Feature_type|Consequence">'
header_parser.parse_meta_data(vep_info_line)
assert header_parser.vep_columns == [
'Allele', 'Gene', 'Feature', 'Feature_type', 'Consequence'
]
def test_malformed_lines():
"""
Test how the header parser behaves with simple vcf lines
"""
header_parser = HeaderParser()
malformed_fileformat = '##fileformat'
malformed_info_line = '##INFO=<ID=MQ,Number=1,Description="RMS Mapping Quality">'
malformed_contig_line = '##contig=<assembly=b37>'
with pytest.raises(SyntaxError):
header_parser.parse_meta_data(malformed_fileformat)
with pytest.raises(SyntaxError):
header_parser.parse_meta_data(malformed_info_line)
with pytest.raises(SyntaxError):
header_parser.parse_meta_data(malformed_contig_line)
def export(ctx, outfile, variant_type):
"""Export the variants of a loqus db
The variants are exported to a vcf file
"""
adapter = ctx.obj['adapter']
version = ctx.obj['version']
LOG.info("Export the variants from {0}".format(adapter))
nr_cases = 0
is_sv = variant_type == 'sv'
existing_chromosomes = set(adapter.get_chromosomes(sv=is_sv))
ordered_chromosomes = []
for chrom in CHROMOSOME_ORDER:
if chrom in existing_chromosomes:
ordered_chromosomes.append(chrom)
existing_chromosomes.remove(chrom)
for chrom in existing_chromosomes:
ordered_chromosomes.append(chrom)
nr_cases = adapter.cases().count()
LOG.info("Found {0} cases in database".format(nr_cases))
head = HeaderParser()
head.add_fileformat("VCFv4.3")
head.add_meta_line("NrCases", nr_cases)
head.add_info("Obs", '1', 'Integer', "The number of observations for the variant")
head.add_info("Hom", '1', 'Integer', "The number of observed homozygotes")
head.add_info("Hem", '1', 'Integer', "The number of observed hemizygotes")
head.add_version_tracking("loqusdb", version, datetime.now().strftime("%Y-%m-%d %H:%M"))
if variant_type == 'sv':
head.add_info("END", '1', 'Integer', "End position of the variant")
head.add_info("SVTYPE", '1', 'String', "Type of structural variant")
head.add_info("SVLEN", '1', 'Integer', "Length of structural variant")
for chrom in ordered_chromosomes:
length = adapter.get_max_position(chrom)
head.add_contig(contig_id=chrom, length=str(length))
print_headers(head, outfile=outfile)
for chrom in ordered_chromosomes:
if variant_type == 'snv':
LOG.info("Collecting all SNV variants")
variants = adapter.get_variants(chromosome=chrom)
else:
LOG.info("Collecting all SV variants")
variants = adapter.get_sv_variants(chromosome=chrom)
LOG.info("{} variants found".format(variants.count()))
for variant in variants:
variant_line = format_variant(variant, variant_type=variant_type)
# chrom = variant['chrom']
# pos = variant['start']
# ref = variant['ref']
# alt = variant['alt']
# observations = variant['observations']
# homozygotes = variant['homozygote']
# hemizygotes = variant['hemizygote']
# info = "Obs={0}".format(observations)
# if homozygotes:
# info += ";Hom={0}".format(homozygotes)
# if hemizygotes:
# info += ";Hem={0}".format(hemizygotes)
# variant_line = "{0}\t{1}\t.\t{2}\t{3}\t.\t.\t{4}\n".format(
# chrom, pos, ref, alt, info)
print_variant(variant_line=variant_line, outfile=outfile)