def readFile(inFile, afCutoff, aoCutoff):
target = open(inFile, 'r')
print 'Chrom-Loc\tAO\t\tDP\t\tAF'
for line in target:
if '#' not in line and 'chr' in line: # skip vcf info
lineObj = seqRead(line)
if (lineObj.af() >= afCutoff) and (lineObj.ao() >= aoCutoff):
print '%s-%s\t%f\t%f\t%f' % (lineObj.chrom(), lineObj.loc(),
lineObj.ao(), lineObj.dp(),
lineObj.af())
def elimBadAligns(inFile, outFile):
from parseLine import seqRead
inTarget = open(inFile, 'r')
outTarget = open(outFile, 'w')
targetLocs = {'chr1':['1152278','1152279','1152564','1152565','1152566','1152587','1152588'],'chr2':['254572','254573','2091130','2091131','2091132','1982668','1982669','2231906','2231907','2231908','2290411','2290412'],'chr4':['1061972','1061973','1061974','1061551','1061552','1105411','1105412','1105413','1129972','1129973','1211677','1211678','1235477','1235478','1235479','1244286','1244287'],'chr9':['50737','50738'],'chr11':['21262','21263','21264','23899','2390','2593','2594','114865','114866','114867','5342','5343'],'chr12':['253982','253983','253984','253802','253803'],'chr15':['925270','925271','906318','906319'],'chr16':['733796','733797','733798','824550','824551','859491','859492'],'chr17':['75775','75776','75783','75784','75785','75770','75771','75772'],'chrX':['486496','486497','486498']}
for line in inTarget:
if '#' not in line and 'chr' in line: # skip the damn info
lineObj = seqRead(line)
if lineObj.chrom() in targetLocs: # is this chrom probed?
goodLoc = False
for i in targetLocs[lineObj.chrom()]:
if i in lineObj.loc(): # is location probed?
goodLoc = True
if goodLoc == True:
outTarget.write(line)
elif '#' in line:
outTarget.write(line)
inTarget.close()
outTarget.close()
def mutationsPerProbe(inFile, outputDir):
from parseLine import seqRead
target = open(inFile, 'r')
# Number of unique variants found within a particular capture region
uniqVars = {
'TIIIa': 0,
'NRAS-1': 0,
'NRAS-2': 0,
'DNMT3a': 0,
'IDH1': 0,
'SF3B1': 0,
'TIIIb': 0,
'TIIIc': 0,
'TET2-1': 0,
'TET2-2': 0,
'TIIId': 0,
'TIIIe': 0,
'TIIIf': 0,
'TIIIg': 0,
'TIIIh': 0,
'JAK2': 0,
'TIIIj': 0,
'TIIIk': 0,
'TIIIl': 0,
'TIIIm': 0,
'HRAS': 0,
'KRAS-1': 0,
'KRAS-2': 0,
'TIIIn': 0,
'IDH2': 0,
'TIIIo': 0,
'TIIIp': 0,
'TIIIq': 0,
'p53-1': 0,
'p53-2': 0,
'p53-3': 0,
'GATA1': 0
}
# Number of total variants found within a particular capture region
totalVars = {
'TIIIa': 0,
'NRAS-1': 0,
'NRAS-2': 0,
'DNMT3a': 0,
'IDH1': 0,
'SF3B1': 0,
'TIIIb': 0,
'TIIIc': 0,
'TET2-1': 0,
'TET2-2': 0,
'TIIId': 0,
'TIIIe': 0,
'TIIIf': 0,
'TIIIg': 0,
'TIIIh': 0,
'JAK2': 0,
'TIIIj': 0,
'TIIIk': 0,
'TIIIl': 0,
'TIIIm': 0,
'HRAS': 0,
'KRAS-1': 0,
'KRAS-2': 0,
'TIIIn': 0,
'IDH2': 0,
'TIIIo': 0,
'TIIIp': 0,
'TIIIq': 0,
'p53-1': 0,
'p53-2': 0,
'p53-3': 0,
'GATA1': 0
}
# Number of total probes capturing a particular region
totalCoverage = {
'TIIIa': [],
'NRAS-1': [],
'NRAS-2': [],
'DNMT3a': [],
'IDH1': [],
'SF3B1': [],
'TIIIb': [],
'TIIIc': [],
'TET2-1': [],
'TET2-2': [],
'TIIId': [],
'TIIIe': [],
'TIIIf': [],
'TIIIg': [],
'TIIIh': [],
'JAK2': [],
'TIIIj': [],
'TIIIk': [],
'TIIIl': [],
'TIIIm': [],
'HRAS': [],
'KRAS-1': [],
'KRAS-2': [],
'TIIIn': [],
'IDH2': [],
'TIIIo': [],
'TIIIp': [],
'TIIIq': [],
'p53-1': [],
'p53-2': [],
'p53-3': [],
'GATA1': []
}
for line in target:
if '#' not in line and 'chr' in line:
lineObj = seqRead(line)
probeNum = identifyProbe(lineObj.loc())
if probeNum:
uniqVars[probeNum] += 1
if lineObj.af() < 0.4: # Don't want germline bias
totalVars[probeNum] += lineObj.ao()
totalCoverage[probeNum].append(lineObj.dp())
print totalCoverage
from matplotlib.backends.backend_pdf import PdfPages
pdf = PdfPages(outputDir + '/probeBias.pdf')
totalCoverage = getMeanCoverage(totalCoverage)
pdf = plotTally(outputDir, totalCoverage, pdf, 'Probe Bias',
'Avg Num of Captures')
uniqVars = normalizeCounts(uniqVars, totalCoverage)
#displayTally(uniqVars)
pdf = plotTally(outputDir, uniqVars, pdf,
'Normalized Unique Variants Per Probe',
'Number of Variants')
totalVars = normalizeCounts(totalVars, totalCoverage)
#displayTally(totalVars)
pdf = plotTally(outputDir, totalVars, pdf,
'Normalized Total Variants Per Probe',
'Number of Variants')
pdf.close()
#!/usr/bin/python from parseLine import seqRead line = 'chr18\t22343095\t.\tG\tA\t13777\t.\tAB=0;ABP=0;AC=2;AF=1;AN=2;AO=636;CIGAR=1X;DP=637;DPB=637;DPRA=0;EPP=1384.07;EPPR=5.18177;GTI=0;LEN=1;MEANALT=1;MQM=60;MQMR=60;NS=1;NUMALT=1;ODDS=875.012;PAIRED=0;PAIREDR=0;PAO=0;PQA=0;PQR=0;PRO=0;QA=21725;QR=36;RO=1;RPL=636;RPP=1384.07;RPPR=5.18177;RPR=0;RUN=1;SAF=636;SAP=1384.07;SAR=0;SRF=1;SRP=5.18177;SRR=0;TYPE=snp\tGT:DP:DPR:RO:QR:AO:QA:GL\t1/1:637:637,636:1:36:636:21725:-1951.16,-188.158,0\n' x = seqRead(line) print x.chrom() print x.loc() print x.wt() print x.var() print x.ao() print x.dp() print x.af()