--quality=<quality> Trimming quality [default: 20]
--adapter=<adapter> Adapter sequence [default: AGATCGGAAGAGC]
--path=<path> Path to cutadapt [default: cutadapt]
--help Output this message
"""
# Import required modules
import os
from ngs_python.fastq import fastqFind, fastqTrim
from general_python import docopt, toolbox, moab
# Extract and process arguments
args = docopt.docopt(__doc__,version = 'v1')
args['--quality'] = int(args['--quality'])
inDir, inPrefix = os.path.split(args['<inprefix>'])
toolbox.checkArg(args['--path'], 'exc')
# Extract fastq files and generate output file names
read1In, read2In = fastqFind.findFastq(prefix = inPrefix, dirList = [inDir],
pair = True, gzip = True)
read1Out = args['<outprefix>'] + '.R1.fastq.gz'
read2Out = args['<outprefix>'] + '.R2.fastq.gz'
trimLog = args['<outprefix>'] + '.log'
# Generate and submit trim command
trimCommand = fastqTrim.cutadaptTrimPaired(read1In = read1In,
read2In = read2In, read1Out = read1Out, read2Out = read2Out,
quality = args['--quality'], adapter = 'AGATCGGAAGAGC', length = 25,
path = args['--path']
)
jobID = moab.submitJob(trimCommand, stdout = trimLog, stderr = trimLog)
print jobID
"""
# Import required modules
import os
from ngs_python.fastq import fastqFind, fastqTrim
from general_python import docopt, toolbox, moab
# Extract and process arguments
args = docopt.docopt(__doc__, version='v1')
args['--quality'] = int(args['--quality'])
inDir, inPrefix = os.path.split(args['<inprefix>'])
toolbox.checkArg(args['--path'], 'exc')
# Extract fastq files and generate output file names
read1In, read2In = fastqFind.findFastq(prefix=inPrefix,
dirList=[inDir],
pair=True,
gzip=True)
read1Out = args['<outprefix>'] + '.R1.fastq.gz'
read2Out = args['<outprefix>'] + '.R2.fastq.gz'
trimLog = args['<outprefix>'] + '.log'
# Generate and submit trim command
trimCommand = fastqTrim.cutadaptTrimPaired(read1In=read1In,
read2In=read2In,
read1Out=read1Out,
read2Out=read2Out,
quality=args['--quality'],
adapter='AGATCGGAAGAGC',
length=25,
path=args['--path'])
jobID = moab.submitJob(trimCommand, stdout=trimLog, stderr=trimLog)
print jobID
# Find FASTQ files by prefix
if args['prefix']:
indir, prefix = os.path.split(args['<prefix>'])
print indir, prefix
args['<infastq>'] = fastqFind.findFastq(prefix = prefix,
dirList = [indir], pair = False)
args['<infastq>'].sort()
# Check number of FASTQ files
if len(args['<infastq>']) < 2:
sys.exit('\nCannot concatenate %s files\n' %(len(args['<infastq>'])))
# Check output file doesnt exist
if os.path.isfile(args['<outfastq>']):
sys.exit('\nOutput file exists. No command submitted\n')
# Print input and out files
print '\nInput files:\n%s\n\nOutput file:\n%s\n' %(
'\n'.join(args['<infastq>']), args['<outfastq>'])
# Get user response before concatenation
print "Enter 'concat' to concatenate: "
response = raw_input()
# Submit command
if response == 'concat':
# Create and submit command
command = 'zcat %s | gzip > %s' %(
' '.join(args['<infastq>']),
args['<outfastq>']
)
moabID = moab.submitJob(command)
print '\n%s\n' %(moabID)
else:
print '\nNo command submitted\n'
inDir, inPrefix = os.path.split(args['<inprefix>'])
outDir = os.path.join(args['<outdir>'], args['<samplename>'])
if not os.path.isdir(outDir):
os.mkdir(outDir)
outPrefix = os.path.join(outDir, args['<samplename>'])
outLog = outPrefix + '.rsem.log'
# Create job dictionary
# Extract fastq files and generate output file names
read1, read2 = fastqFind.findFastq(prefix=inPrefix,
dirList=[inDir],
pair=True,
gzip=True)
rsemCommand = fastqAlign.rsemBowtie2Align(index=args['<index>'],
outPrefix=outPrefix,
read1=read1,
read2=read2,
rsemPath=args['--rsem'],
bowtie2Path=args['--bowtie2'],
threads=args['--threads'],
forProb=args['--forprob'],
genomeBam=args['--genomebam'],
estimateRspd=False,
check=True)
print rsemCommand
jobID = moab.submitJob(rsemCommand,
processor=args['--threads'],
stdout=outLog,
stderr=outLog)
print args['<samplename>'], jobID
"""
# Import required modules
import os
from ngs_python.fastq import fastqFind, fastqAlign
from general_python import docopt, toolbox, moab
# Extract and process arguments
args = docopt.docopt(__doc__,version = 'v1')
args['--threads'] = int(args['--threads'])
args['--forprob'] = float(args['--forprob'])
toolbox.check_var(args['--forprob'], 'num', mn = 0, mx = 1)
inDir, inPrefix = os.path.split(args['<inprefix>'])
outDir = os.path.join(args['<outdir>'], args['<samplename>'])
if not os.path.isdir(outDir):
os.mkdir(outDir)
outPrefix = os.path.join(outDir, args['<samplename>'])
outLog = outPrefix + '.rsem.log'
# Create job dictionary
# Extract fastq files and generate output file names
read1, read2 = fastqFind.findFastq(prefix = inPrefix, dirList = [inDir],
pair = True, gzip = True)
rsemCommand = fastqAlign.rsemBowtie2Align(index = args['<index>'],
outPrefix = outPrefix, read1 = read1, read2 = read2,
rsemPath = args['--rsem'], bowtie2Path = args['--bowtie2'],
threads = args['--threads'], forProb = args['--forprob'],
genomeBam = args['--genomebam'], estimateRspd = False, check = True)
print rsemCommand
jobID = moab.submitJob(rsemCommand, processor = args['--threads'],
stdout = outLog, stderr = outLog)
print args['<samplename>'], jobID
