def sra2illumina(input_file,
output_file,
tag_read=None,
tag='',
phred_conversion=False,
operation='change',
tmp_dir=None,
size_read_buffer=10**8):
"""
It converts the FASTQ file (PHRED-33 qualities and SRA read names) downloaded
from Short Read Archive (SRA) to Illumina FASTQ file (PHRED-64 Illumina v1.5
and Illumina read names).
"""
temp_file = None
if phred_conversion:
temp_file = give_me_temp_filename(tmp_dir)
else:
temp_file = output_file
read_name = file(input_file, 'r').readline().rstrip('\r\n')
sra = False
e = read_name.partition(" ")[0]
if read_name.startswith('@') and (not (e.endswith('/1')
or e.endswith('/2'))):
sra = True
if operation == 'change' or sra:
fid = open(input_file, 'r')
fod = open(temp_file, 'w')
i = 0
r = 0
while True:
gc.disable()
lines = fid.readlines(size_read_buffer)
gc.enable()
if not lines:
break
n = len(lines)
for j in xrange(n):
r = r + 1
i = i + 1
if i == 1:
if tag_read:
lines[j] = '@%s%s%s\n' % (tag_read, int2str(r,
12), tag)
else: # if there is no tag_read then the original SRA id is left
lines[j] = '%s%s\n' % (lines[j][:-1].partition(" ")[0],
tag)
#lines[j] = lines[j].rstrip('\r\n').upper().split(' ')[1]+tag+'\n'
elif i == 3:
lines[j] = "+\n"
elif i == 4:
i = 0
fod.writelines(lines)
fid.close()
fod.close()
if phred_conversion == '64':
phred.fq2fq(temp_file,
'sanger',
output_file,
'illumina-1.5',
tmp_dir=tmp_dir)
os.remove(temp_file)
elif phred_conversion == '33':
phred.fq2fq(temp_file,
'auto-detect',
output_file,
'sanger',
tmp_dir=tmp_dir)
os.remove(temp_file)
else:
print "No changes are done!"
if os.path.isfile(output_file):
os.remove(output_file)
if operation == 'soft':
if os.path.islink(input_file):
linkto = os.readlink(input_file)
os.symlink(linkto, ooutput_file)
else:
os.symlink(input_file, output_file)
elif operation == 'hard':
linkto = input_file
if os.path.islink(input_file):
linkto = os.readlink(input_file)
try:
os.link(linkto, output_file)
except OSError as er:
print >> sys.stderr, "WARNING: Cannot do hard links ('%s' and '%s')!" % (
linkto, output_file)
shutil.copyfile(linkto, output_file)
# if er.errno == errno.EXDEV:
# # they are on different partitions
# # [Errno 18] Invalid cross-device link
# shutil.copyfile(linkto,output_file)
# else:
# print >>sys.stderr,"ERROR: Cannot do hard links ('%s' and '%s')!" % (linkto,output_file)
# print >>sys.stderr,er
# sys.exit(1)
elif operation == 'copy':
shutil.copyfile(input_file, output_file)
else:
print >> sys.stderr, "ERROR: unknown operation of linking!", operation
sys.exit(1)
def sra2illumina(input_file,
output_file,
tag_read = None,
tag='',
phred_conversion = False,
operation = 'change',
tmp_dir = None,
size_read_buffer = 10**8):
"""
It converts the FASTQ file (PHRED-33 qualities and SRA read names) downloaded
from Short Read Archive (SRA) to Illumina FASTQ file (PHRED-64 Illumina v1.5
and Illumina read names).
"""
temp_file = None
if phred_conversion:
temp_file = give_me_temp_filename(tmp_dir)
else:
temp_file = output_file
read_name = file(input_file,'r').readline().rstrip('\r\n')
sra = False
e = read_name.partition(" ")[0]
if read_name.startswith('@') and ( not(e.endswith('/1') or e.endswith('/2'))):
sra = True
if operation == 'change' or sra:
fid = open(input_file,'r')
fod = open(temp_file,'w')
i = 0
r = 0
while True:
lines = fid.readlines(size_read_buffer)
if not lines:
break
n = len(lines)
for j in xrange(n):
r = r + 1
i = i + 1
if i == 1:
if tag_read:
lines[j] = '@%s%s%s\n' % (tag_read ,int2str(r,12) , tag)
else: # if there is no tag_read then the original SRA id is left
lines[j] = '%s%s\n' % (lines[j][:-1].partition(" ")[0], tag)
#lines[j] = lines[j].rstrip('\r\n').upper().split(' ')[1]+tag+'\n'
elif i == 3:
lines[j] = "+\n"
elif i == 4:
i = 0
fod.writelines(lines)
fid.close()
fod.close()
if phred_conversion == '64':
phred.fq2fq(temp_file,'sanger',output_file,'illumina-1.5',tmp_dir = tmp_dir)
os.remove(temp_file)
elif phred_conversion == '33':
phred.fq2fq(temp_file,'auto-detect',output_file,'sanger',tmp_dir = tmp_dir)
os.remove(temp_file)
else:
print "No changes are done!"
if os.path.isfile(output_file):
os.remove(output_file)
if operation == 'soft':
if os.path.islink(input_file):
linkto = os.readlink(input_file)
os.symlink(linkto,ooutput_file)
else:
os.symlink(input_file,output_file)
elif operation == 'hard':
linkto = input_file
if os.path.islink(input_file):
linkto = os.readlink(input_file)
try:
os.link(linkto,output_file)
except OSError as er:
print >>sys.stderr,"WARNING: Cannot do hard links ('%s' and '%s')!" % (linkto,output_file)
shutil.copyfile(linkto,output_file)
# if er.errno == errno.EXDEV:
# # they are on different partitions
# # [Errno 18] Invalid cross-device link
# shutil.copyfile(linkto,output_file)
# else:
# print >>sys.stderr,"ERROR: Cannot do hard links ('%s' and '%s')!" % (linkto,output_file)
# print >>sys.stderr,er
# sys.exit(1)
elif operation == 'copy':
shutil.copyfile(input_file, output_file)
else:
print >>sys.stderr, "ERROR: unknown operation of linking!", operation
sys.exit(1)