def main(args):
h5file = tables.open_file(args.hdf5PosFile, mode = "r")
table = h5file.root.posCollection.posLs
lookUpSnvs = getSNVInfo(args.exacVcf, table)
useLowCov1KG = True
oneKPopInfo = annotateEVSMajorFreq.get1kInfoAllPop(lookUpSnvs, args.oneKgFile, useLowCov1KG)
tot = 0
with open(args.exacVcf) as f:
for line in f:
if line[0] != '#':
sp = line.strip().split()
chrom = sp[0]
pos = int(sp[1])
resLs = [x['pos'] for x in
table.where('(chrom == b"%s") & (pos == %d)' % (chrom, pos))]
if resLs:
key = chrom + ':' + str(pos)
ref = sp[3]
altLs = sp[4].split(',')
p = 'AC_' + args.pop + '='
if p in sp[7]:
for pZyg in ('Het_' + args.pop + '=', 'Hom_' + args.pop + '='):
countLs = sp[7].split(pZyg)[1].split(';')[0].split(',')
effField = sp[-1]
for count in getCounts(ref, countLs, key, altLs, oneKPopInfo, effField):
tot += int(count)
h5file.close()
with open(args.outFile, 'w') as fout:
print(str(tot), file=fout)
def main(args):
lookUpSnvs = getSNVInfo(args.vcfFile)
useLowCov1KG = True
oneKPopInfo = annotateEVSMajorFreq.get1kInfoAllPop(lookUpSnvs, args.oneKgFile, useLowCov1KG)
with open(args.vcfFile) as f, open(args.outFile, 'w') as fout:
for line in f:
if line[0] != '#':
sp = line.strip().split()
chrom = sp[0]
pos = sp[1]
key = chrom + ':' + pos
ref = sp[3]
altLs = sp[4].split(',')
isRare = checkRare(oneKPopInfo, altLs, ref, key)
if isRare:
print(line.strip(), file=fout)
def main(args):
genes = countTargetSampleTotalVarsForGene.loadGenes(args.geneLsFile)
goodPos = loadPos(args.goodVarPosFile)
h5file = tables.open_file(args.hdf5PosFile, mode = "r")
table = h5file.root.posCollection.posLs
lookUpSnvs = getSNVInfo(args.exacVcf)
useLowCov1KG = True
oneKPopInfo = annotateEVSMajorFreq.get1kInfoAllPop(lookUpSnvs, args.oneKgFile, useLowCov1KG)
tot = defaultdict(int)
with open(args.exacVcf) as f, open(args.varLsOutFile, 'w') as fout:
print('gene\tvarCount\tchrom\tpos\trs\tref\talt\tqual\tfilter\tinfo', file=fout)
for line in f:
if line[0] != '#':
sp = line.strip().split()
chrom = sp[0]
pos = int(sp[1])
resGeneSet = set([x['gene'].decode("utf-8") for x in
table.where('(chrom == b"%s") & (pos == %d)' % (chrom, pos))])
key = chrom + ':' + str(pos)
inGoodPos = key in goodPos
ref = sp[3]
altLs = sp[4].split(',')
p = 'AC_' + args.pop + '='
effField = sp[-1]
if p in sp[7]:
for gene in resGeneSet & genes:
for pZyg in ('Het_' + args.pop + '=', 'Hom_' + args.pop + '='):
countLs = sp[7].split(pZyg)[1].split(';')[0].split(',')
for count in getCounts(ref, countLs, key, altLs, oneKPopInfo, effField, gene, inGoodPos):
tot[gene] += int(count)
if int(count):
print('\t'.join( (gene, count) ) + '\t' + line.strip(), file=fout)
h5file.close()
with open(args.outFile, 'w') as fout:
for gene in tot:
print(gene + '\t' + str(tot[gene]), file=fout)