def test_generate_header_fields_from_schema(self):
sample_schema = bigquery_schema_util.get_sample_table_schema()
header = bigquery_vcf_schema_converter.generate_header_fields_from_schema(
sample_schema)
infos = OrderedDict([
('AF', Info('AF', field_counts['A'], 'Float', 'desc', None, None)),
('AA', Info('AA', 1, 'String', 'desc', None, None)),
('IFR', Info('IFR', field_counts['.'], 'Float', 'desc', None,
None)),
('IS', Info('IS', 1, 'String', 'desc', None, None))
])
formats = OrderedDict([('FB', parser._Format('FB', 0, 'Flag', 'desc')),
('GQ', parser._Format('GQ', 1, 'Integer',
'desc'))])
expected_header = vcf_header_io.VcfHeader(infos=infos, formats=formats)
self.assertEqual(header, expected_header)
def main(args):
# Load VCF file
if not os.path.exists(args.vcf):
common.WARNING("%s does not exist" % args.vcf)
return 1
invcf = vcf.Reader(filename=args.vcf)
# Set up record harmonizer and infer VCF type
vcftype = trh.InferVCFType(invcf)
# Check filters all make sense
if not CheckFilters(invcf, args, vcftype): return 1
# Set up locus-level filter list
try:
filter_list = BuildLocusFilters(args, vcftype)
except ValueError:
return 1
invcf.filters = {}
for f in filter_list:
short_doc = f.__doc__ or ''
short_doc = short_doc.split('\n')[0].lstrip()
invcf.filters[f.filter_name()] = _Filter(f.filter_name(), short_doc)
# Set up call-level filters
call_filters = BuildCallFilters(args)
# Add new FORMAT fields
if "FILTER" not in invcf.formats:
invcf.formats["FILTER"] = _Format("FILTER", 1, "String",
"Call-level filter")
# Add new INFO fields
invcf.infos["AC"] = _Info("AC",
-1,
"Integer",
"Alternate allele counts",
source=None,
version=None)
invcf.infos["REFAC"] = _Info("REFAC",
1,
"Integer",
"Reference allele count",
source=None,
version=None)
invcf.infos["HET"] = _Info("HET",
1,
"Float",
"Heterozygosity",
source=None,
version=None)
invcf.infos["HWEP"] = _Info("HWEP",
1,
"Float",
"HWE p-value for obs. vs. exp het rate",
source=None,
version=None)
invcf.infos["HRUN"] = _Info("HRUN",
1,
"Integer",
"Length of longest homopolymer run",
source=None,
version=None)
# Set up output files
if not os.path.exists(os.path.dirname(os.path.abspath(args.out))):
common.WARNING("Output directory does not exist")
return 1
outvcf = MakeWriter(args.out + ".vcf", invcf, " ".join(sys.argv))
if outvcf is None: return 1
# Set up sample info
all_reasons = GetAllCallFilters(call_filters)
sample_info = {}
for s in invcf.samples:
sample_info[s] = {"numcalls": 0, "totaldp": 0}
for r in all_reasons:
sample_info[s][r] = 0
# Set up locus info
loc_info = {"totalcalls": 0, "PASS": 0}
for filt in filter_list:
loc_info[filt.filter_name()] = 0
# Go through each record
record_counter = 0
while True:
try:
record = next(invcf)
except IndexError:
common.WARNING(
"Skipping TR that couldn't be parsed by PyVCF. Check VCF format"
)
if args.die_on_warning: return 1
except StopIteration:
break
if args.verbose:
common.MSG("Processing %s:%s" % (record.CHROM, record.POS))
record_counter += 1
if args.num_records is not None and record_counter > args.num_records:
break
# Call-level filters
record = ApplyCallFilters(record, invcf, call_filters, sample_info)
# Locus-level filters
record.FILTER = None
output_record = True
for filt in filter_list:
if filt(record) == None: continue
if args.drop_filtered:
output_record = False
break
record.add_filter(filt.filter_name())
loc_info[filt.filter_name()] += 1
if args.drop_filtered:
if record.call_rate == 0: output_record = False
if output_record:
trrecord = trh.HarmonizeRecord(vcftype, record)
# Recalculate locus-level INFO fields
record.INFO["HRUN"] = utils.GetHomopolymerRun(record.REF)
if record.num_called > 0:
allele_freqs = trrecord.GetAlleleFreqs(
uselength=args.use_length)
genotype_counts = trrecord.GetGenotypeCounts(
uselength=args.use_length)
record.INFO["HET"] = utils.GetHeterozygosity(allele_freqs)
record.INFO["HWEP"] = utils.GetHardyWeinbergBinomialTest(
allele_freqs, genotype_counts)
record.INFO["AC"] = [
int(item * (3 * record.num_called)) for item in record.aaf
]
record.INFO["REFAC"] = int(
(1 - sum(record.aaf)) * (2 * record.num_called))
else:
record.INFO["HET"] = -1
record.INFO["HWEP"] = -1
record.INFO["AC"] = [0] * len(record.ALT)
record.INFO["REFAC"] = 0
# Recalc filter
if record.FILTER is None and not args.drop_filtered:
record.FILTER = "PASS"
loc_info["PASS"] += 1
loc_info["totalcalls"] += record.num_called
# Output the record
outvcf.write_record(record)
# Output log info
WriteSampLog(sample_info, all_reasons, args.out + ".samplog.tab")
WriteLocLog(loc_info, args.out + ".loclog.tab")
return 0
def get_format_obj():
# arguments should be: ['id', 'num', 'type', 'desc']
return _Format(BAlleleFreqFormat.get_id(), 1, "Float",
BAlleleFreqFormat.get_description())
def get_format_obj():
return _Format(GencallFormat.get_id(), 1, "Integer",
GencallFormat.get_description())
def get_format_obj():
return _Format(GenotypeFormat.get_id(), 1, "String", GenotypeFormat.get_description())
def get_format_obj():
# arguments should be: ['id', 'num', 'type', 'desc']
return _Format(LogRRatioFormat.get_id(), 1, "Float", LogRRatioFormat.get_description())