###############################################################################
# Generate file names
args['tempSam'] = os.path.join(args['tophatSampleDir'],
args['name'] + '_sample.sam')
args['nsortBam'] = os.path.join(args['tophatSampleDir'],
args['name'] + '_sample_nsort.bam')
args['tophatLog'] = os.path.join(args['tophatSampleDir'],
args['name'] + '_Tophat2.log')
# Generate command for single-end samples
if args['--singleend']:
# Generate command to perform tophat2 alignment
tophat2Complete = fastqAlign.tophat2Align(
read1=args['trimRead1'],
genomeIndex=args['<bwt2genindex>'],
transcriptIndex=args['<bwt2tranindex>'],
outDir=args['tophatSampleDir'],
path=paths['tophat2'],
forProb=args['--forprob'],
threads=args['--threads'],
readGroup='1',
sampleName=args['name'])
# Generate command for paired-end samples
else:
# Generate command to align first 1e6 reads to transcriptome
alignSampleCommand = fastqAlign.bowtie2Align(
read1=args['trimRead1'],
read2=args['trimRead2'],
index=args['<bwt2tranindex>'],
bowtie2Path=paths['bowtie2'],
samtoolsPath=paths['samtools'],
outFile=args['nsortBam'],
threads=args['--threads'],
modules = pmDict[('rsem', 'modules')]
)
###############################################################################
## Generate Tophat2 Alignment Command
###############################################################################
# Generate file names
args['tophatLog'] = os.path.join(args['tophatSampleDir'],
args['name'] + '_tophat2.log')
# Generate tophat command
tophat2AlignCommand = fastqAlign.tophat2Align(
read1 = args['trimRead1'],
read2 = args['trimRead2'],
genomeIndex = args['<bwt2genindex>'],
transcriptIndex = args['<bwt2tranindex>'],
outDir = args['tophatSampleDir'],
path = pmDict[('tophat2', 'path')],
forProb = args['--forprob'],
threads = args['--threads'],
readGroup = '1',
sampleName = args['name']
)
# Submit tophat2 commands
tophat2AlignJobID = slurmJobs.add(
command = tophat2AlignCommand,
processors = args['--threads'],
stdout = args['tophatLog'],
stderr = args['tophatLog'],
depend = [trimReadsJobID],
modules = pmDict[('tophat2', 'modules')]
)
# Generate file names
args['tempSam'] = os.path.join(args['tophatSampleDir'],
args['name'] + '_sample.sam')
args['nsortBam'] = os.path.join(args['tophatSampleDir'],
args['name'] + '_sample_nsort.bam')
args['tophatLog'] = os.path.join(args['tophatSampleDir'],
args['name'] + '_Tophat2.log')
# Generate command for single-end samples
if args['--singleend']:
# Generate command to perform tophat2 alignment
tophat2Complete = fastqAlign.tophat2Align(
read1 = args['trimRead1'],
genomeIndex = args['<bwt2genindex>'],
transcriptIndex = args['<bwt2tranindex>'],
outDir = args['tophatSampleDir'],
path = paths['tophat2'],
forProb = args['--forprob'],
threads = args['--threads'],
readGroup = '1',
sampleName = args['name']
)
# Generate command for paired-end samples
else:
# Generate command to align first 1e6 reads to transcriptome
alignSampleCommand = fastqAlign.bowtie2Align(
read1 = args['trimRead1'],
read2 = args['trimRead2'],
index = args['<bwt2tranindex>'],
bowtie2Path = paths['bowtie2'],
samtoolsPath = paths['samtools'],
outFile = args['nsortBam'],
modules = pmDict[('rsem', 'modules')]
)
###############################################################################
## Generate Tophat2 Alignment Command
###############################################################################
# Generate file names
args['tophatLog'] = os.path.join(args['tophatSampleDir'],
args['name'] + '_tophat2.log')
# Generate tophat command
tophat2AlignCommand = fastqAlign.tophat2Align(
read1 = args['trimRead1'],
read2 = args['trimRead2'],
genomeIndex = args['<bwt2genindex>'],
transcriptIndex = args['<bwt2tranindex>'],
outDir = args['tophatSampleDir'],
path = pmDict[('tophat2', 'path')],
forProb = args['--forprob'],
threads = args['--threads'],
readGroup = '1',
sampleName = args['name']
)
# Submit tophat2 commands
tophat2AlignJobID = slurmJobs.add(
command = tophat2AlignCommand,
processors = args['--threads'],
stdout = args['tophatLog'],
stderr = args['tophatLog'],
depend = [trimReadsJobID],
modules = pmDict[('tophat2', 'modules')]
)
