def main(inFileName,outFileName,pileupDirL):
inFile = open(inFileName)
outFile = open(outFileName,'w')
outFile.write(inFile.readline())
for line in inFile:
tokL = line[:-1].split('\t')
if tokL[-3]==tokL[-4]=='0':
flag = 0 # Recur
elif tokL[-5]==tokL[-6]=='0':
flag = 1 # Prim
else:
outFile.write(line)
continue
rm = re.match('(chr[^:]*):([0-9]*)~([0-9]*)',tokL[2])
(chrom,chrSta,chrEnd) = rm.groups()
if int(chrEnd)-int(chrEnd)!=0:
outFile.write(line)
continue
refAllele = tokL[3]
altAllele = tokL[4]
#print tokL[1], tokL[2], refAllele, '>', altAllele, tokL[-4:],
sId = tokL[1].split('-')[1-flag]
result = mygenome.lookupPileup(pileupDirL,sId,chrom,chrSta,refAllele,altAllele)
if result:
tokL[-1-flag*2-2] = str(result[1])
tokL[-2-flag*2-2] = str(result[0])
outFile.write('\t'.join(tokL)+'\n')
else:
outFile.write(line)
outFile.close()
def main(inFileName,
outFileName,
pileupDirL=mysetting.wxsPileupProcDirL,
mutectDirL=['/EQL3/pipeline/somatic_mutect']):
inFile = open(inFileName)
if outFileName == '':
outFile = sys.stdout
else:
outFile = open(outFileName, 'w')
header = inFile.readline()
hcolL = header.rstrip().split('\t')
idxH = {}
for i in range(len(hcolL)):
idxH[hcolL[i]] = i
outFile.write(header)
outH = {}
for line in inFile:
tokL = line[:-1].split('\t')
pair = tokL[idxH['sId_pair']]
rm = re.match('(chr[^:]*):([0-9]*)~([0-9]*)', tokL[2])
(chrom, chrSta, chrEnd) = rm.groups()
refAllele = tokL[3]
altAllele = tokL[4]
if pair not in outH:
print_dat(outH, outFile)
outH = {}
if tokL[-3] == tokL[-4] == '0':
flag = 0 # Recur
elif tokL[-5] == tokL[-6] == '0':
flag = 1 # Prim
else:
parse_line(outH, idxH, line)
continue
if int(chrEnd) - int(chrSta) != 0:
parse_line(outH, idxH, line)
continue
#print tokL[1], tokL[2], refAllele, '>', altAllele, tokL[-4:],
sId = tokL[1].split('-')[1 - flag]
if tokL[-1] != '0' or tokL[-2] != '0': ##has matched normal
fileNL = []
for mutDir in mutectDirL:
fileNL += filter(
lambda x: 'backup' not in x,
os.popen('find %s -name *%sT.union_pos.mutect' %
(mutDir, sId[1:])).readlines())
if len(fileNL) > 1:
print 'Mutiple files: %s' % ','.join(fileNL)
sys.exit(1)
fileN = fileNL[0].rstrip()
lines = os.popen(
'grep -w %s %s | grep -w %s | cut -f 1,2,4,5,21,22' %
(chrom, fileN, chrSta)).readlines()
for ln in lines:
colL = ln.rstrip().split('\t')
ref = colL[2]
alt = colL[3]
if ref == refAllele and alt == altAllele:
result = []
result.append(colL[5])
result.append(colL[4])
else:
result = mygenome.lookupPileup(pileupDirL, sId, chrom, chrSta,
refAllele, altAllele)
if result:
tokL[-1 - flag * 2 - 2] = str(result[1])
tokL[-2 - flag * 2 - 2] = str(result[0])
parse_line(outH, idxH, '\t'.join(tokL) + '\n')
else:
parse_line(outH, idxH, line)
print_dat(outH, outFile)
def main(inFileName,outFileName,pileupDirL=mysetting.wxsPileupProcDirL,mutectDirL=['/EQL3/pipeline/somatic_mutect']):
inFile = open(inFileName)
if outFileName == '':
outFile = sys.stdout
else:
outFile = open(outFileName,'w')
header = inFile.readline()
hcolL = header.rstrip().split('\t')
idxH = {}
for i in range(len(hcolL)):
idxH[hcolL[i]] = i
outFile.write(header)
outH = {}
for line in inFile:
tokL = line[:-1].split('\t')
pair = tokL[idxH['sId_pair']]
rm = re.match('(chr[^:]*):([0-9]*)~([0-9]*)',tokL[2])
(chrom,chrSta,chrEnd) = rm.groups()
refAllele = tokL[3]
altAllele = tokL[4]
if pair not in outH:
print_dat(outH, outFile)
outH = {}
if tokL[-3]==tokL[-4]=='0':
flag = 0 # Recur
elif tokL[-5]==tokL[-6]=='0':
flag = 1 # Prim
else:
parse_line(outH, idxH, line)
continue
if int(chrEnd)-int(chrSta)!=0:
parse_line(outH, idxH, line)
continue
#print tokL[1], tokL[2], refAllele, '>', altAllele, tokL[-4:],
sId = tokL[1].split('-')[1-flag]
if tokL[-1] != '0' or tokL[-2] != '0': ##has matched normal
fileNL = []
for mutDir in mutectDirL:
fileNL += filter(lambda x: 'backup' not in x, os.popen('find %s -name *%sT.union_pos.mutect' % (mutDir, sId[1:])).readlines())
if len(fileNL) > 1:
print 'Mutiple files: %s' % ','.join(fileNL)
sys.exit(1)
fileN = fileNL[0].rstrip()
lines = os.popen('grep -w %s %s | grep -w %s | cut -f 1,2,4,5,21,22' % (chrom, fileN, chrSta)).readlines()
for ln in lines:
colL = ln.rstrip().split('\t')
ref = colL[2]
alt = colL[3]
if ref == refAllele and alt == altAllele:
result = []
result.append(colL[5])
result.append(colL[4])
else:
result = mygenome.lookupPileup(pileupDirL,sId,chrom,chrSta,refAllele,altAllele)
if result:
tokL[-1-flag*2-2] = str(result[1])
tokL[-2-flag*2-2] = str(result[0])
parse_line(outH, idxH, '\t'.join(tokL) + '\n')
else:
parse_line(outH, idxH, line)
print_dat(outH, outFile)