def run(self):
AbstractAnalysis.run(self) #Call base method to do some logging
refSequences = getFastaDictionary(self.referenceFastaFile) #Hash of names to sequences
readSequences = getFastqDictionary(self.readFastqFile) #Hash of names to sequences
sam = pysam.Samfile(self.samFile, "r" )
#The data we collect
avgPosteriorMatchProbabilityInCigar = []
alignedPairsInCigar = []
posteriorMatchProbabilities = []
for aR in samIterator(sam): #Iterate on the sam lines
#Exonerate format Cigar string
cigarString = getExonerateCigarFormatString(aR, sam)
#Temporary files
tempCigarFile = os.path.join(self.getLocalTempDir(), "rescoredCigar.cig")
tempRefFile = os.path.join(self.getLocalTempDir(), "ref.fa")
tempReadFile = os.path.join(self.getLocalTempDir(), "read.fa")
tempPosteriorProbsFile = os.path.join(self.getLocalTempDir(), "probs.tsv")
#Write the temporary files.
fastaWrite(tempRefFile, sam.getrname(aR.rname), refSequences[sam.getrname(aR.rname)])
fastaWrite(tempReadFile, aR.qname, aR.query)
#Trained hmm file to use.
hmmFile = os.path.join(pathToBaseNanoporeDir(), "nanopore", "mappers", "blasr_hmm_0.txt")
#Call to cactus_realign
system("echo %s | cactus_realign %s %s --rescoreByPosteriorProbIgnoringGaps --rescoreOriginalAlignment --diagonalExpansion=10 --splitMatrixBiggerThanThis=100 --outputPosteriorProbs=%s --loadHmm=%s > %s" % \
(cigarString, tempRefFile, tempReadFile, tempPosteriorProbsFile, hmmFile, tempCigarFile))
#Load the cigar and get the posterior prob
assert len([ pA for pA in cigarRead(open(tempCigarFile)) ]) > 0
assert len([ pA for pA in cigarRead(open(tempCigarFile)) ]) == 1
pA = [ i for i in cigarRead(open(tempCigarFile)) ][0]
avgPosteriorMatchProbabilityInCigar.append(pA.score)
#Calculate the number of aligned pairs in the cigar
alignedPairsInCigar.append(sum([ op.length for op in pA.operationList if op.type == PairwiseAlignment.PAIRWISE_MATCH ]))
assert alignedPairsInCigar[-1] == len([ readPos for readPos, refPos in aR.aligned_pairs if readPos != None and refPos != None ])
#Get the posterior probs
#posteriorMatchProbabilities += [ float(line.split()[2]) for line in open(tempPosteriorProbsFile) ]
sam.close()
#Write out the substitution info
node = ET.Element("alignmentUncertainty", {
"averagePosteriorMatchProbabilityPerRead":str(self.formatRatio(sum(avgPosteriorMatchProbabilityInCigar), len(avgPosteriorMatchProbabilityInCigar))),
"averagePosteriorMatchProbability":str(self.formatRatio(float(sum([ avgMatchProb*alignedPairs for avgMatchProb, alignedPairs in zip(avgPosteriorMatchProbabilityInCigar, alignedPairsInCigar) ])),sum(alignedPairsInCigar))),
"averagePosteriorMatchProbabilitesPerRead":",".join([ str(i) for i in avgPosteriorMatchProbabilityInCigar ]),
"alignedPairsInCigar":",".join([ str(i) for i in alignedPairsInCigar ]) })
open(os.path.join(self.outputDir, "alignmentUncertainty.xml"), "w").write(prettyXml(node))
if len(avgPosteriorMatchProbabilityInCigar) > 0:
outf = open(os.path.join(self.getLocalTempDir(), "tmp_uncertainty"), "w")
outf.write("\t".join([ str(i) for i in avgPosteriorMatchProbabilityInCigar ])); outf.write("\n")
outf.close()
system("Rscript nanopore/analyses/match_hist.R {} {}".format(os.path.join(self.getLocalTempDir(), "tmp_uncertainty"), os.path.join(self.outputDir, "posterior_prob_hist.pdf")))
#Indicate everything is all done
self.finish()
def realignCigarTargetFn(target, exonerateCigarString, referenceSequenceName, referenceSequence, querySequenceName, querySequence, outputCigarFile, hmmFile, gapGamma, matchGamma):
#Temporary files
tempRefFile = os.path.join(target.getGlobalTempDir(), "ref.fa")
tempReadFile = os.path.join(target.getGlobalTempDir(), "read.fa")
#Write the temporary files.
fastaWrite(tempRefFile, referenceSequenceName, referenceSequence)
fastaWrite(tempReadFile, querySequenceName, querySequence)
#Call to cactus_realign
loadHmm = nameValue("loadHmm", hmmFile)
system("echo %s | cactus_realign %s %s --diagonalExpansion=10 --splitMatrixBiggerThanThis=3000 %s --gapGamma=%s --matchGamma=%s > %s" % (exonerateCigarString, tempRefFile, tempReadFile, loadHmm, gapGamma, matchGamma, outputCigarFile))
assert len([ pA for pA in cigarRead(open(outputCigarFile)) ]) > 0
assert len([ pA for pA in cigarRead(open(outputCigarFile)) ]) == 1
def realignCigarTargetFn(target, exonerateCigarString, referenceSequenceName,
referenceSequence, querySequenceName, querySequence,
outputCigarFile, hmmFile, gapGamma, matchGamma):
#Temporary files
tempRefFile = os.path.join(target.getGlobalTempDir(), "ref.fa")
tempReadFile = os.path.join(target.getGlobalTempDir(), "read.fa")
#Write the temporary files.
fastaWrite(tempRefFile, referenceSequenceName, referenceSequence)
fastaWrite(tempReadFile, querySequenceName, querySequence)
#Call to cactus_realign
loadHmm = nameValue("loadHmm", hmmFile)
system(
"echo %s | cactus_realign %s %s --diagonalExpansion=10 --splitMatrixBiggerThanThis=3000 %s --gapGamma=%s --matchGamma=%s > %s"
% (exonerateCigarString, tempRefFile, tempReadFile, loadHmm, gapGamma,
matchGamma, outputCigarFile))
assert len([pA for pA in cigarRead(open(outputCigarFile))]) > 0
assert len([pA for pA in cigarRead(open(outputCigarFile))]) == 1
def realignSamFile3TargetFn(target, samFile, outputSamFile, tempCigarFiles):
#Setup input and output sam files
sam = pysam.Samfile(samFile, "r" )
#Replace the cigar lines with the realigned cigar lines
outputSam = pysam.Samfile(outputSamFile, "wh", template=sam)
for aR, tempCigarFile in zip(samIterator(sam), tempCigarFiles): #Iterate on the sam lines realigning them in parallel
#Load the cigar
pA = [ i for i in cigarRead(open(tempCigarFile)) ][0]
#Convert to sam line
aR.cigar = tuple([ (op.type, op.length) for op in pA.operationList ])
#Write out
outputSam.write(aR)
#Finish up
sam.close()
outputSam.close()
def realignSamFile3TargetFn(target, samFile, outputSamFile, tempCigarFiles):
#Setup input and output sam files
sam = pysam.Samfile(samFile, "r")
#Replace the cigar lines with the realigned cigar lines
outputSam = pysam.Samfile(outputSamFile, "wh", template=sam)
for aR, tempCigarFile in zip(
samIterator(sam), tempCigarFiles
): #Iterate on the sam lines realigning them in parallel
#Load the cigar
pA = [i for i in cigarRead(open(tempCigarFile))][0]
#Convert to sam line
aR.cigar = tuple([(op.type, op.length) for op in pA.operationList])
#Write out
outputSam.write(aR)
#Finish up
sam.close()
outputSam.close()
def cigarIterator():
#Iterates over all the cigars in the temp files.
for tempCigarFile in tempCigarFiles:
for pA in cigarRead(open(tempCigarFile)):
yield pA
yield None #This is put in to cause an error if there is fewer
def cigarIterator():
#Iterates over all the cigars in the temp files.
for tempCigarFile in tempCigarFiles:
for pA in cigarRead(open(tempCigarFile)):
yield pA
yield None #This is put in to cause an error if there is fewer