def process_variant_detail_vcf(self, record, assaytype):
"""Process info file variant detail records
Set up a json-stype document and add it to the
variant buffer
"""
doc = {}
doc["assaytype"] = assaytype
vcfr = VCFrecord(record)
prfx, sfx = vcfr.get_prfx_sfx()
doc["rsid"] = vcfr.get_varid()
# always store chromosome as a 2-digit string
doc["chromosome"] = "%.2d" % (int(vcfr.get_chr()))
alleleA, alleleB = vcfr.get_alleles()
doc["alleleA"] = alleleA
doc["alleleB"] = alleleB
doc["position"] = vcfr.get_posn_as_int()
try:
doc["ref_maf"] = float(vcfr.get_info_value("RefPanelAF"))
except:
pass
try:
doc["info"] = float(vcfr.get_info_value("INFO"))
except:
doc["info"] = 1.0
self.variantbuff.append(doc)
def main(options):
hdr = []
hdrlen = 0
count = 0
try:
fh = open(options.chrommap)
chrom_map = load_chrom_map(fh)
except:
print "Unable to open", options.chrommap
exit()
for line in sys.stdin:
count += 1
line = line.strip()
if (line.startswith('#')):
print line
else:
vcfr = VCFrecord(line)
strchrom = vcfr.get_chr()
try:
vcfr.set_chr(chrom_map[strchrom])
except:
logging.info("Chromosome not found in map %s, %s" % (options.chrommap, strchrom))
exit()
print vcfr.get_record()
return count
def main():
mafh = Mafhelper()
hweh = Hwehelper()
in_count = 0
hdr_count = 0
homr_total = 0
het_total = 0
homa_total = 0
virt_nc_total = 0
miss_total = 0
print "SNPId,AssayType,chr,pos,REF,ALT,Minor,MAF,CallRate,HWE_pval"
for line in sys.stdin:
line = line.strip()
in_count += 1
if line.startswith("#"):
hdr_count += 1
continue
vcfr = VCFrecord(line)
varid = vcfr.get_varid_ukb()
chromosome = vcfr.get_chr()
posn = vcfr.get_posn_as_int()
ref, alt = vcfr.get_alleles()
homref_count, het_count, homalt_count, virt_nc_count, miss_count = vcfr.get_allele_counts()
call_count = homref_count + het_count + homalt_count
#nocall_count = virt_nc_count + miss_count
nocall_count = virt_nc_count
call_rate = float(call_count) / float(call_count + nocall_count)
homr_total += homref_count
het_total += het_count
homa_total += homalt_count
virt_nc_total += virt_nc_count
miss_total += miss_count
try:
hwe = hweh.HWE_exact(het_count, homref_count, homalt_count, call_count)
maf, ma = mafh.maf(het_count, homref_count, ref, homalt_count, alt, virt_nc_count)
except ZeroDivisionError:
logging.info("DIV 0 error at %d (%d), where hom_r=%d, het=%d, home_a=%d, cc=%d", in_count, posn, homref_count, het_count, homalt_count, call_count)
print "%s,combo,%s,%d,%s,%s,%s,%s,%.3f,%s" % (varid, chromosome, posn, ref, alt, ma, maf, call_rate, hwe)
return in_count, hdr_count, homr_total, het_total, homa_total, virt_nc_total, miss_total