def augment_header(header: VariantHeader, contigs: List[str], formats: List[str], infos: List[str]):
"""
Add contigs, formats and infos to a VariantHeader.
formats and infos are given as a list of strings, where each item is the ID of the header
line to add. The full header info (Number, Type, Description) is taken from the PREDEFINED_*
constants above. Any other FORMATs or INFOs that are not predefined will raise a VcfError.
The header is modified in place.
"""
for contig in contigs:
header.contigs.add(contig)
for fmt in formats:
if fmt in header.formats:
header.formats[fmt].remove_header()
try:
h = PREDEFINED_FORMATS[fmt]
except KeyError:
raise VcfError("FORMAT {!r} not defined in VCF header".format(fmt)) from None
header.add_line(h.line())
for info in infos:
try:
h = PREDEFINED_INFOS[info]
except KeyError:
raise VcfError("INFO {!r} not defined in VCF header".format(info)) from None
header.add_line(h.line())
def setup_header(self, header: VariantHeader):
"""Called by baseclass constructor"""
# FreeBayes adds phasing=none to its VCF output - remove that.
for hr in header.records:
if hr.key == "phasing":
hr.remove()
break
header.add_line(PREDEFINED_FORMATS[self.tag].line())
def format_header():
header_info = [
'##fileformat=VCFv4.2',
'##assembly=hg19',
'##FILTER=<ID=PASS,Description="All filters passed">',
'##INFO=<ID=AAChange_refGene,Number=.,Type=String,Description="AAChange_refGene annotation">',
# '##FORMAT=<ID=None,Number=R,Type=Integer,Description="None">',
'#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO',
]
header = VariantHeader()
for line in header_info:
header.add_line(line)
return header
def _get_vcf_header(contigs: List[str]) -> VariantHeader:
header: VariantHeader = VariantHeader()
header.add_meta('source', value='valiant')
for contig in contigs:
header.add_meta('contig', items=[('ID', contig)])
# TODO: add contig lengths?
for info_items in VCF_HEADER_INFO_ITEMS:
header.add_meta('INFO', items=info_items)
return header
def setup_header(self, header: VariantHeader):
"""Called by baseclass constructor"""
header.add_line(
'##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype computed by WhatsHap genotyping algorithm">'
)
header.add_line(
'##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Phred-scaled genotype quality computed by WhatsHap genotyping algorithm">'
)
header.add_line(
'##FORMAT=<ID=GL,Number=G,Type=Float,Description="Log10-scaled likelihoods for genotypes: 0/0, 0/1, 1/1, computed by WhatsHap genotyping algorithm">'
)
def generate_header(reference_fa: str, tag: str) -> VariantHeader:
"""
Generates the header for the minimal VCF.
:param reference_fa: Path to reference fasta file.
:param tag: The filter tag to use.
"""
header = VariantHeader()
header.filters.add(tag, None, None, "Failed dToxoG")
fasta = FastaFile(reference_fa)
try:
for contig in fasta.references:
header.contigs.add(contig,
length=fasta.get_reference_length(contig))
finally:
fasta.close()
return header
def get_vcf_header(self, sample_name, contigs):
header = VariantHeader()
items = [('ID', "PASS"), ('Description', "All filters passed")]
header.add_meta(key='FILTER', items=items)
items = [('ID', "refCall"), ('Description', "Call is homozygous")]
header.add_meta(key='FILTER', items=items)
items = [('ID', "lowGQ"), ('Description', "Low genotype quality")]
header.add_meta(key='FILTER', items=items)
items = [('ID', "lowQUAL"),
('Description', "Low variant call quality")]
header.add_meta(key='FILTER', items=items)
items = [('ID', "conflictPos"), ('Description', "Overlapping record")]
header.add_meta(key='FILTER', items=items)
items = [('ID', "GT"), ('Number', 1), ('Type', 'String'),
('Description', "Genotype")]
header.add_meta(key='FORMAT', items=items)
items = [('ID', "GQ"), ('Number', 1), ('Type', 'Float'),
('Description', "Genotype Quality")]
header.add_meta(key='FORMAT', items=items)
sqs = self.fasta_handler.get_chromosome_names()
for sq in sqs:
if sq not in contigs:
continue
sq_id = sq
ln = self.fasta_handler.get_chromosome_sequence_length(sq)
header.contigs.add(sq_id, length=ln)
header.add_sample(sample_name)
return header
def get_vcf_header(self, sample_name):
header = VariantHeader()
items = [('ID', "PASS"), ('Description', "All filters passed")]
header.add_meta(key='FILTER', items=items)
items = [('ID', "refCall"), ('Description', "Call is homozygous")]
header.add_meta(key='FILTER', items=items)
items = [('ID', "lowGQ"), ('Description', "Low genotype quality")]
header.add_meta(key='FILTER', items=items)
items = [('ID', "lowQUAL"),
('Description', "Low variant call quality")]
header.add_meta(key='FILTER', items=items)
items = [('ID', "conflictPos"), ('Description', "Overlapping record")]
header.add_meta(key='FILTER', items=items)
items = [('ID', "GT"), ('Number', 1), ('Type', 'String'),
('Description', "Genotype")]
header.add_meta(key='FORMAT', items=items)
items = [('ID', "GQ"), ('Number', 1), ('Type', 'Float'),
('Description', "Genotype Quality")]
header.add_meta(key='FORMAT', items=items)
bam_sqs = self.bam_handler.get_header_sq()
for sq in bam_sqs:
id = sq['SN']
ln = sq['LN']
items = [('ID', id), ('length', ln)]
header.add_meta(key='contig', items=items)
header.add_sample(sample_name)
return header