def calcCarriage(vcfLine, vcfIndices, kgpLine, kgpIndices, alleles):
if len(vcfIndices) > 0:
vcfLine.extractAlleles()
vcfLine.extractGenotypes(vcfIndices)
if len(kgpIndices) > 0:
kgpLine.extractAlleles()
kgpLine.extractGenotypes(kgpIndices)
counts = countingDict()
for i in vcfIndices:
allele0 = vcfLine.genotypes[i][0]
allele1 = vcfLine.genotypes[i][1]
if allele0 != None:
if allele0 == allele1:
counts[allele0] += 1
else:
counts[allele0] += 1
counts[allele1] += 1
for i in kgpIndices:
allele0 = kgpLine.genotypes[i][0]
allele1 = kgpLine.genotypes[i][1]
if allele0 != None:
if allele0 == allele1:
counts[allele0] += 1
else:
counts[allele0] += 1
counts[allele1] += 1
return [counts.get(i, 0) for i, a in enumerate(alleles)]
def calcAF(vcfLine, vcfIndices, kgpLine, kgpIndices, alleles):
if len(vcfIndices) > 0:
vcfLine.extractAlleles()
vcfLine.extractGenotypes(vcfIndices)
if len(kgpIndices) > 0:
kgpLine.extractAlleles()
kgpLine.extractGenotypes(kgpIndices)
count = 0.0
matches = countingDict()
for i in vcfIndices:
allele0 = vcfLine.genotypes[i][0]
allele1 = vcfLine.genotypes[i][1]
if allele0 != None:
count += 2.0
matches[allele0] += 1
matches[allele1] += 1
for i in kgpIndices:
allele0 = kgpLine.genotypes[i][0]
allele1 = kgpLine.genotypes[i][1]
if allele0 != None:
count += 2.0
matches[allele0] += 1
matches[allele1] += 1
if count == 0.0:
return [float('Inf') for a in alleles]
else:
return [matches.get(i, 0) / count for i, a in enumerate(alleles)]
def calcCarriage(vcfLine,vcfIndices,kgpLine,kgpIndices,alleles):
if len(vcfIndices) > 0:
vcfLine.extractAlleles()
vcfLine.extractGenotypes(vcfIndices)
if len(kgpIndices) > 0:
kgpLine.extractAlleles()
kgpLine.extractGenotypes(kgpIndices)
counts = countingDict()
for i in vcfIndices:
allele0 = vcfLine.genotypes[i][0]
allele1 = vcfLine.genotypes[i][1]
if allele0 != None:
if allele0 == allele1:
counts[allele0] += 1
else:
counts[allele0] += 1
counts[allele1] += 1
for i in kgpIndices:
allele0 = kgpLine.genotypes[i][0]
allele1 = kgpLine.genotypes[i][1]
if allele0 != None:
if allele0 == allele1:
counts[allele0] += 1
else:
counts[allele0] += 1
counts[allele1] += 1
return [counts.get(i,0) for i,a in enumerate(alleles)]
def calcAF(vcfLine,vcfIndices,kgpLine,kgpIndices,alleles):
if len(vcfIndices) > 0:
vcfLine.extractAlleles()
vcfLine.extractGenotypes(vcfIndices)
if len(kgpIndices) > 0:
kgpLine.extractAlleles()
kgpLine.extractGenotypes(kgpIndices)
count = 0.0
matches = countingDict()
for i in vcfIndices:
allele0 = vcfLine.genotypes[i][0]
allele1 = vcfLine.genotypes[i][1]
if allele0 != None:
count += 2.0
matches[allele0] += 1
matches[allele1] += 1
for i in kgpIndices:
allele0 = kgpLine.genotypes[i][0]
allele1 = kgpLine.genotypes[i][1]
if allele0 != None:
count += 2.0
matches[allele0] += 1
matches[allele1] += 1
if count == 0.0:
return [float('Inf') for a in alleles]
else:
return [matches.get(i,0)/count for i,a in enumerate(alleles)]
def run(args):
kgp = kgpInterface(args.data, sys.path[0] + "/KGP_populations.txt")
outfile = open(args.outfile, 'wb')
freqOnly = args.frequencies_only.lower().startswith('t')
wroteHeader = False
for line in kgp.iterate():
if not wroteHeader:
outfile.write('CHROM\tPOS\tID')
if not freqOnly:
for p in kgp.populations[args.pop]:
outfile.write('\t%s_1\t%s_2' % (p, p))
outfile.write('\n')
wroteHeader = True
line.extractChrAndPos()
line.extractAlleles()
line.extractGenotypes()
outfile.write('\t'.join(
[line.chromosome, str(line.position), line.name]))
if freqOnly:
counts = countingDict()
total = 0.0
for p in kgp.populations[args.pop]:
i = kgp.individualIndices[p]
if line.genotypes[i][0] != None:
counts[line.genotypes[i][0]] += 1
total += 1.0
if line.genotypes[i][1] != None:
counts[line.genotypes[i][1]] += 1
total += 1.0
for i, c in counts.iteritems():
outfile.write('\t%s:\t%f' % (line.alleles[i], c / total))
else:
for p in kgp.populations[args.pop]:
i = kgp.individualIndices[p]
a1 = line.genotypes[i][0]
if a1 == None:
a1 = '.'
else:
a1 = line.alleles[a1]
a2 = line.genotypes[i][1]
if a2 == None:
a2 = '.'
else:
a2 = line.alleles[a2]
outfile.write('\t%s\t%s' % (a1, a2))
outfile.write('\n')
outfile.close()
def run(args):
kgp = kgpInterface(args.data,sys.path[0] + "/KGP_populations.txt")
outfile = open(args.outfile,'wb')
freqOnly = args.frequencies_only.lower().startswith('t')
wroteHeader = False
for line in kgp.iterate():
if not wroteHeader:
outfile.write('CHROM\tPOS\tID')
if not freqOnly:
for p in kgp.populations[args.pop]:
outfile.write('\t%s_1\t%s_2' % (p,p))
outfile.write('\n')
wroteHeader = True
line.extractChrAndPos()
line.extractAlleles()
line.extractGenotypes()
outfile.write('\t'.join([line.chromosome,str(line.position),line.name]))
if freqOnly:
counts = countingDict()
total = 0.0
for p in kgp.populations[args.pop]:
i = kgp.individualIndices[p]
if line.genotypes[i][0] != None:
counts[line.genotypes[i][0]] += 1
total += 1.0
if line.genotypes[i][1] != None:
counts[line.genotypes[i][1]] += 1
total += 1.0
for i,c in counts.iteritems():
outfile.write('\t%s:\t%f' % (line.alleles[i],c/total))
else:
for p in kgp.populations[args.pop]:
i = kgp.individualIndices[p]
a1 = line.genotypes[i][0]
if a1 == None:
a1 = '.'
else:
a1 = line.alleles[a1]
a2 = line.genotypes[i][1]
if a2 == None:
a2 = '.'
else:
a2 = line.alleles[a2]
outfile.write('\t%s\t%s' % (a1,a2))
outfile.write('\n')
outfile.close()
