#!/bin/bash
#$ -N mapping
#$ -cwd
#$ -V
#$ -e """+outputTrashDir+"""
#$ -o """+outputTrashDir+"""
#$ -q long.q
#$ -pe parallel_smp """+str(nbThreads)+"""
#$ -t 1-"""+str(count-1)+"""
#$ -tc """+str(args.nbJobValue)+"""
#$ -S /bin/bash
/bin/bash """+outputSHDir+"""${SGE_TASK_ID}_mapping.sh"""
with open(SGENameFile, "w") as SGEFile:
SGEFile.write(headerSGE)
print("\n - Execution summary:")
print("\n You want run MutilmappingX for %s fasta,\
The script are created all fasta-MutilmappingX.sh for all fasta into %s,\n\
For run all sub-script in qsub, %s was created.\n\
It lunch programm with job array and run %s job max:\n" %(count-1,outputSHDir,SGENameFile, args.nbJobValue))
printCol.green("\tqsub %s" % SGENameFile)
print("\nStop time: ", strftime("%d-%m-%Y_%H:%M:%S", localtime()))
print("#################################################################")
print("# End of execution #")
print("#################################################################")
else: raise IOError, 'invalid file'
header = ''.join(cache)
# Ouvre le header avec le parseur egglib from_header il sert à comprendre que c'est un fichier vcf
vcf = egglib.io.VcfParser.from_header(header)
else:
# Ouvre le vcf avec le parseur egglib
vcfFileOpen = egglib.io.VcfParser(str(vcfFile))
vcf = vcfFileOpen
samples = [vcf.get_sample(i) for i in xrange(vcf.num_samples)] # liste des individus
print 'number of samples: %s\n' % vcf.num_samples
printCol.green('samples: %s' % "\t".join(samples))
if compress:
if ".gz" not in outFileName:
outputFile = gzip.open(outFileName+'.gz', 'wb')
else:
outputFile = open(outFileName,"w")
txtout = 'Chromosome\tPosition\tReference\t%s\n' % "\t".join(samples)
outputFile.write(txtout)
dicoAlreadyFind = {}
reset = 0
for line in vcfFileOpen:
if extention == "gz": # Parcours des positions du vcf si compresser
chrom, pos, nall = vcf.read_line(line)