def map(self):
if self.to_map:
if self.single_end:
if self.gtf != 'blank':
cmd_args = ['tophat', '-p', '6', '-o', self.output,
'-r', self.mean, '--mate-std-dev', self.sd,
'-G', self.gtf, '--library-type', self.library_type,
self.species, self.input1]
else:
cmd_args = ['tophat', '-p', '6', '-o', self.output,
'-r', self.mean, '--mate-std-dev', self.sd,
'--library-type', self.library_type,
self.species, self.input1]
else:
if self.gtf != 'blank':
cmd_args = ['tophat', '-p', '10', '-o', self.output,
'-r', self.mean, '--mate-std-dev', self.sd,
'-G', self.gtf, '--library-type', self.library_type,
self.species, self.input1, self.input2]
else:
cmd_args = ['tophat2',
'-o', self.output,
'-p', '6',
'-r', self.mean,
'--mate-std-dev', self.sd,
'--library-type', self.library_type,
self.species, self.input1, self.input2]
#print self.errorlog
print "Mapping with tophat: " + " ".join(cmd_args[1:])
errorlog = open(self.errorlog, 'w')
tophat = Popen(cmd_args, stderr=errorlog)
tophat.wait()
errorlog.close()
sam.proc([self.output + "/accepted_hits.bam", "False"])
def main(argv):
sam_dir = "/media/storage2/data/sam/"
bam_dir = "/media/storage2/data/bam/"
bed_dir = "/media/storage2/data/bed/"
## take Illmina fastq file
parser = argparse.ArgumentParser(description="Map fastq files.")
parser.add_argument('-i', '--input_fastq', nargs=2, metavar='fastq', required=True,
dest='fastq_files', help='read1 and read3 of library')
parser.add_argument('-n', '--index', dest='index', required=True, help='index number of library')
parser.add_argument('-r', '--mate-inner-dist', metavar='mean', required=True,
dest='mean', help='mean size of library (minus adaptors)')
parser.add_argument('-s', '--mate-std-dev', metavar='sd', required=True, dest='sd', help='standard deviation of library')
parser.add_argument('-g', '--GTF', metavar='gtf', dest='gtf', default='blank',
help='reference gtf file to map reads to')
parser.add_argument('--stranded', action='store_true', required=False, dest='strand', default=False, help="indicate if library contains strand information")
args = parser.parse_args()
input1 = argv[1]
input2 = argv[2]
index = argv[3]
input_prefix = input1.split("_")[0] + "_" + index
print input_prefix
#input_filtered = input_prefix + "_filt.fastq"
#cmd_args = ['fastq_quality_filter', '-q', '20', '-p', '80',
# '-i', input_fastq, '-o', input_filtered]
#filt = Popen(cmd_args)
#filt.wait()
## Run bowtie
samfile = sam_dir + input_prefix + ".sam"
if not os.path.exists(samfile):
cmd_args = ['bowtie', '-S', '-m', '1', '-p', '6', '-I', '100', '-X', '1500', '--chunkmbs', '256',
'mm9', '-1', input1, '-2', input2, samfile]
print "Mapping with bowtie: " + " ".join(cmd_args[1:])
bowtie = Popen(cmd_args)
bowtie.wait()
## SAM to BAM
bamfile = bam_dir + input_prefix + ".bam"
if not os.path.exists(bamfile):
sam.sam2bam(samfile, bamfile)
## Remove unmapped, duplicates, sort, index
sam.proc(bam_dir, input_prefix)
## Output BED
print "Writing BED..."
bam = bam_dir + input_prefix + "_sort.bam"
bed = bed_dir + input_prefix + ".bed"
sam.bam2bed(bam, bed, pe = True)
def sam2bam(self):
if not os.path.exists(self.bamfile):
try:
sam.sam2bam(self.samfile, self.bamfile, self.errorlog)
except IOError:
self.errorlog.write("Can't open SAM for conversion.\n")
return
except:
# pdb.set_trace()
self.errorlog.write("SAM to BAM conversion failed\n")
return
else:
self.errorlog.write("SAM to BAM completed successfully.\n")
self.errorlog.write("Removing SAM...\n")
os.remove(self.samfile)
try:
sam.proc([self.bamfile, "False", self.errorlog])
except IOError:
self.errorlog.write("BAM processing failed: IOError.\n")
else:
self.errorlog.write("BAM processing completed successfully.\n")
def proc(self):
ret = sam.proc([self.bamfile, "False"])
def sam2bam(self):
if not os.path.exists(self.bamfile):
sam.sam2bam(self.samfile, self.bamfile)
sam.proc([self.bamfile, "True"])