def runCount(tid, bam, ref, bed, maxLength, minQual, conversionThreshold,
outputDirectory, snpDirectory):
outputCSV = os.path.join(
outputDirectory, replaceExtension(basename(bam), ".tsv", "_tcount"))
outputBedgraphPlus = os.path.join(
outputDirectory,
replaceExtension(basename(bam), ".bedgraph", "_tcount_plus"))
outputBedgraphMinus = os.path.join(
outputDirectory,
replaceExtension(basename(bam), ".bedgraph", "_tcount_mins"))
outputLOG = os.path.join(
outputDirectory, replaceExtension(basename(bam), ".log", "_tcount"))
if (snpDirectory != None):
inputSNP = os.path.join(
snpDirectory, replaceExtension(basename(bam), ".vcf", "_snp"))
else:
inputSNP = None
if (maxLength == None):
maxLength = estimateMaxReadLength(bam)
if (maxLength < 0):
print(
"Difference between minimum and maximum read length is > 10. Please specify --max-read-length parameter."
)
sys.exit(0)
log = getLogFile(outputLOG)
print("Using " + str(maxLength) + " as maximum read length.", file=log)
tcounter.computeTconversions(ref, bed, inputSNP, bam, maxLength, minQual,
outputCSV, outputBedgraphPlus,
outputBedgraphMinus, conversionThreshold, log)
stepFinished()
return outputCSV
def runTcPerUtr(tid, bam, referenceFile, bed, minMQ, maxReadLength,
outputDirectory, snpDirectory, vcfFile):
outputCSV = os.path.join(
outputDirectory, replaceExtension(basename(bam), ".csv", "_tcperutr"))
outputPDF = os.path.join(
outputDirectory, replaceExtension(basename(bam), ".pdf", "_tcperutr"))
outputLOG = os.path.join(
outputDirectory, replaceExtension(basename(bam), ".log", "_tcperutr"))
if (vcfFile != None):
inputSNP = vcfFile
elif (snpDirectory != None):
inputSNP = os.path.join(
snpDirectory, replaceExtension(basename(bam), ".vcf", "_snp"))
else:
inputSNP = None
if (maxReadLength == None):
maxReadLength = estimateMaxReadLength(bam)
if (maxReadLength < 0):
print(
"Could not reliable estimate maximum read length. Please specify --max-read-length parameter."
)
sys.exit(0)
log = getLogFile(outputLOG)
print("Using " + str(maxReadLength) + " as maximum read length.", file=log)
stats.tcPerUtr(referenceFile, bed, bam, minMQ, maxReadLength, outputCSV,
outputPDF, inputSNP, log, False, True, True)
closeLogFile(log)
stepFinished()
def runStatsRatesUTR(tid, bam, referenceFile, minMQ, strictTCs,
outputDirectory, utrFile, maxReadLength):
outputCSV = os.path.join(
outputDirectory,
replaceExtension(basename(bam), ".csv", "_mutationrates_utr"))
outputPDF = os.path.join(
outputDirectory,
replaceExtension(basename(bam), ".pdf", "_mutationrates_utr"))
outputLOG = os.path.join(
outputDirectory,
replaceExtension(basename(bam), ".log", "_mutationrates_utr"))
if (maxReadLength == None):
maxReadLength = estimateMaxReadLength(bam)
if (maxReadLength < 0):
print(
"Could not reliable estimate maximum read length. Please specify --max-read-length parameter."
)
sys.exit(0)
log = getLogFile(outputLOG)
print("Using " + str(maxReadLength) + " as maximum read length.", file=log)
stats.statsComputeOverallRatesPerUTR(referenceFile, bam, minMQ, strictTCs,
outputCSV, outputPDF, utrFile,
maxReadLength, log)
closeLogFile(log)
stepFinished()
def runSNPeval(tid, bam, ref, bed, maxLength, minQual, coverageCutoff,
variantFraction, strictTCs, outputDirectory, snpDirectory):
outputCSV = os.path.join(
outputDirectory, replaceExtension(basename(bam), ".csv", "_SNPeval"))
outputPDF = os.path.join(
outputDirectory, replaceExtension(basename(bam), ".pdf", "_SNPeval"))
outputLOG = os.path.join(
outputDirectory, replaceExtension(basename(bam), ".log", "_SNPeval"))
if (not os.path.isdir(snpDirectory)):
print("SNP directory does not exists. Abort.")
sys.exit(0)
inputSNP = os.path.join(snpDirectory,
replaceExtension(basename(bam), ".vcf", "_snp"))
if (maxLength == None):
maxLength = estimateMaxReadLength(bam)
if (maxLength < 0):
print(
"Could not reliable estimate maximum read length. Please specify --max-read-length parameter."
)
sys.exit(0)
log = getLogFile(outputLOG)
print("Using " + str(maxLength) + " as maximum read length.", file=log)
stats.computeSNPMaskedRates(ref, bed, inputSNP, bam, maxLength, minQual,
coverageCutoff, variantFraction, outputCSV,
outputPDF, strictTCs, log)
stepFinished()
def runCount(
bam,
ref,
bed,
maxLength,
minQual,
conversionThreshold,
is_inverse,
outputDirectory,
snpDirectory,
vcfFile,
):
outputCSV = os.path.join(
outputDirectory, replaceExtension(basename(bam), ".tsv", "_tcount"))
outputBedgraphPlus = os.path.join(
outputDirectory,
replaceExtension(basename(bam), ".bedgraph", "_tcount_plus"))
outputBedgraphMinus = os.path.join(
outputDirectory,
replaceExtension(basename(bam), ".bedgraph", "_tcount_mins"))
outputLOG = os.path.join(
outputDirectory, replaceExtension(basename(bam), ".log", "_tcount"))
if vcfFile is not None:
inputSNP = vcfFile
elif snpDirectory is not None:
inputSNP = os.path.join(
snpDirectory, replaceExtension(basename(bam), ".vcf", "_snp"))
else:
inputSNP = None
if maxLength is None:
maxLength = estimateMaxReadLength(bam)
if maxLength < 0:
print("Difference between minimum and maximum read length is > 10. "
"Please specify --max-read-length parameter.")
sys.exit(0)
log = getLogFile(outputLOG)
print("Using " + str(maxLength) + " as maximum read length.", file=log)
if bed is not None:
message("Bed file detected.")
tcounter.computeTconversions(ref, bed, inputSNP, bam, maxLength,
minQual, outputCSV, outputBedgraphPlus,
outputBedgraphMinus, conversionThreshold,
log)
else:
message("No bed file passed. Count w.r.t. the full genome.")
outputBedgraphPlusNew = os.path.join(
outputDirectory,
replaceExtension(basename(bam), ".bedgraph", "_tcount_plus_new"))
outputBedgraphMinusNew = os.path.join(
outputDirectory,
replaceExtension(basename(bam), ".bedgraph", "_tcount_mins_new"))
tcounter.computeTconversionsAll(ref, inputSNP, bam, outputBedgraphPlus,
outputBedgraphPlusNew,
outputBedgraphMinus,
outputBedgraphMinusNew,
conversionThreshold, minQual,
is_inverse, log)
stepFinished()
return outputCSV
