trim = args.cutSite,
minLength = args.minLength
)
# Print trim metrics
print '\nTrim Metrics:\n\t%s\n\t%s\n\t%s\n\t%s' %(
'total: ' + str(trimMetrics['total']),
'too short: ' + str(trimMetrics['short']),
'read1 trim: ' + str(trimMetrics['trim1']),
'read2 trim: ' + str(trimMetrics['trim2'])
)
# Generate align command
alignCommand = fastqAlign.bwaMemAlign(
index = args.bwaFasta,
outFile = args.nameSortBam,
read1 = args.outFastq,
bwaPath = args.bwa,
threads = str(args.threads),
markSecondary = True,
check = True,
nameSort = True
)
# Merge commands and run
subprocess.check_output(alignCommand, shell = True, stderr=subprocess.STDOUT)
###############################################################################
## Extract aligned pairs
###############################################################################
# extract pairs from alignments
alignMetrics, pairMetrics = alignedPair.extractPairs(
inBam = args.nameSortBam,
pairOut = args.outPairs,
minMapQ = args.minMapQ,
itertools.izip_longest(read1List, read2List)):
# Modify and format read group and library id
readgroup = format(readgroup + 1, '03d')
# Create file names for alignment
alignLog = os.path.join(args['<logfolder>'],
'rg{}.align.log'.format(readgroup))
alignBam = args['<outbam>'][:-4] + '.rg{}.sort.bam'.format(readgroup)
# Generate command for alignment
alignCommand = fastqAlign.bwaMemAlign(
index=os.path.abspath(args['<index>']),
outFile=alignBam,
read1=read1,
read2=read2,
bwaPath=pmDict[('bwa', 'path')],
threads=args['<threads>'],
sampleName=args['--samplename'],
libraryID=args['--samplename'],
readGroup=readgroup,
platform=args['--platform'],
markSecondary=True,
check=True,
samtoolsPath=pmDict[('samtools', 'path')],
memory=6,
nameSort=False)
# Add job to queue
alignJobID = jobObject.add(command=alignCommand,
processors=args['<threads>'],
modules=pmDict[('bwa', 'modules')] +
pmDict[('samtools', 'modules')],
memory=7,
stdout=alignLog,
stderr=alignLog)
'dedupbam' : bamPrefix + '_dedup.bam',
'realignbam' : bamPrefix + '_dedup_realign.bam',
'recalbam' : bamPrefix + '_dedup_realign_recal.bam',
'listfile' : logPrefix + '_target.list',
'bsqrfile' : logPrefix + '_bsqr.grp',
'alignlog' : logPrefix + '_align.log',
'deduplog1' : logPrefix + '_dedup_1.log',
'deduplog2' : logPrefix + '_dedup_2.log',
'realignlog' : logPrefix + '_realign.log',
'recallog' : logPrefix + '_recal.log'
}
# Generate command for alignment
alignCommand = fastqAlign.bwaMemAlign(
index = args['<index>'], outFile = outfiles['initialbam'],
read1 = read1[0], read2 = read2[0], bwaPath = paths['bwa'],
threads = args['--threads'], sampleName = args['name'],
libraryID = args['prefix'], readGroup = 1, platform = 'ILLUMINA',
markSecondary = True, check = True, samtoolsPath = paths['samtools'],
memory = 2, nameSort = False
)
# Mark duplicates using picard
dedupCommand = picard.markDuplicates(
inBam = outfiles['initialbam'], outBam = outfiles['dedupbam'],
logFile = outfiles['deduplog1'], picardPath = paths['picard'],
javaPath = paths['java'], removeDuplicates = True, delete = True
)
# Perform local realignment
realignCommand = gatk.gatkRealign(
inBam = outfiles['dedupbam'], outBam = outfiles['realignbam'],
inVcf = args['<indelvcf>'], reference = args['<index>'],
javaPath = paths['java'], gatkPath = paths['gatk'], delete = True,
threads = 4, listFile = outfiles['listfile']
