FP = glob.glob(os.path.join(inputdir, '*.fastq.*'))
if len(FP) == 0:
# single file per-sample
FP = glob.glob(os.path.join(inputdir, '*.fastq'))
file_prefix = FP[fr]
file_split = file_prefix[file_prefix.index('.fastq') + 6:]
file_prefix = file_prefix[file_prefix.rfind('/') +
1:file_prefix.index('.fastq')]
hashobject = Fastq_Reader(inputdir, outputdir)
f = open(hashobject.input_path + file_prefix + '.fastq' + file_split, 'r')
read_type = hashobject.id_type(f)
g = gzip.open(
hashobject.output_path + file_prefix + '.hashq' + file_split + '.gz',
'wb')
hashobject.hpfx = hashobject.hpfx + str(hashobject.kmer_size) + ','
A = []
reads_hashed = 0
while A != None:
try:
A, B = hashobject.generator_to_bins(hashobject.read_generator(
f, max_reads=25000, verbose_ids=True),
rc=do_reverse_compliment)
for b in range(len(B)):
reads_hashed += kmer_bins(B[b], A, hashobject.hpfx, g,
read_type)
except Exception, err:
pass
#print str(err)
f.close()
g.close()
print 'total reads hashed:', reads_hashed
elif opt in ('-o','--outputdir'):
outputdir = arg
if outputdir[-1] != '/':
outputdir += '/'
elif opt in ('-z','--reversecomp'):
do_reverse_compliment = False
FP = glob.glob(os.path.join(inputdir,'*.fastq.*'))
if len(FP) == 0:
# single file per-sample
FP = glob.glob(os.path.join(inputdir,'*.fastq'))
file_prefix = FP[fr]
file_split = file_prefix[file_prefix.index('.fastq')+6:]
file_prefix = file_prefix[file_prefix.rfind('/')+1:file_prefix.index('.fastq')]
hashobject = Fastq_Reader(inputdir,outputdir)
f = open(hashobject.input_path+file_prefix+'.fastq'+file_split,'r')
read_type = hashobject.id_type(f)
g = gzip.open(hashobject.output_path+file_prefix+'.hashq'+file_split+'.gz','wb')
hashobject.hpfx = hashobject.hpfx + str(hashobject.kmer_size)+','
A = []
reads_hashed = 0
while A != None:
try:
A,B = hashobject.generator_to_bins(hashobject.read_generator(f,max_reads=25000,verbose_ids=True),rc=do_reverse_compliment)
for b in range(len(B)):
reads_hashed += kmer_bins(B[b],A,hashobject.hpfx,g,read_type)
except Exception,err:
pass
#print str(err)
f.close()
g.close()
print 'total reads hashed:',reads_hashed
FP = glob.glob(os.path.join(input_dir, '*.fastq.*'))
if len(FP) == 0:
# single file per-sample
FP = glob.glob(os.path.join(input_dir, '*.fastq'))
file_prefix = FP[task_rank]
file_split = file_prefix[file_prefix.index('.fastq') + 6:]
file_prefix = file_prefix[file_prefix.rfind('/') +
1:file_prefix.index('.fastq')]
hashobject = Fastq_Reader(input_dir, output_dir)
reads_file_name = hashobject.input_path + file_prefix + '.fastq' + file_split
with Fq.open_gz(reads_file_name) as f:
hashobject.quality_codes = Fq.set_quality_codes(reads_file_name)
print(reads_file_name)
with gzip.open(
hashobject.output_path + file_prefix + '.hashq' + file_split +
'.gz', 'wt') as g:
IDs = []
reads_hashed = 0
print("[HashFastqReads] Starting to hash the reads.")
IDs, bins = hashobject.generator_to_bins(Fq.fastq_generator(f),
rc=do_reverse_compliment)
print("[HashFastqReads] All k-mers hashed.")
print("[HashFastqReads] Writing hashed reads to file.")
for b in range(len(bins)):
reads_hashed += kmer_bins(bins[b], IDs, g)
print("[HashFastqReads] Total reads hashed: " + str(reads_hashed))
