def main(args, options):
""" Run the main functionality of the module (see module docstring for more information), excluding testing.
The options argument should be generated by an optparse parser.
"""
try:
infile, outfile_base = args
except ValueError:
parser.print_help()
sys.exit("\nError: one infile and one outfile base name are required! Got %s"%args)
indexes = options.index_list.split(',')
index_OUTFILES = {index: open("%s_%s.fq"%(outfile_base, index), 'w') for index in indexes}
unmatched_OUTFILE = open("%s_unmatched.fq"%outfile_base, 'w')
index_counts = {index: 0 for index in indexes}
unmatched_count = 0
if options.index_in_sequence:
index_len = set(len(x) for x in indexes)
if len(index_len) > 1:
raise Exception("Indexes need to all have the same lengths! Found lengths %s from indexes %s"%(index_len, indexes))
index_len = index_len.pop()
get_index = lambda name,seq: seq[:index_len]
make_output = lambda name, seq, qual, index: ("%s:%s"%(name,index), seq[index_len:], qual[index_len:])
else:
get_index = lambda name, seq: name.split(':')[-1]
make_output = lambda name, seq, qual, index: (name, seq, qual)
for (name,seq,qual) in basic_seq_utilities.parse_fastq(infile):
index = get_index(name, seq)
try:
OUTFILE = index_OUTFILES[index]
index_counts[index] += 1
except KeyError:
OUTFILE = unmatched_OUTFILE
unmatched_count += 1
basic_seq_utilities.write_fastq_line(*make_output(name, seq, qual, index), OUTFILE=OUTFILE)
if not options.quiet:
total = unmatched_count + sum(index_counts.values())
print "%s reads:\n%s unmatched\n%s"%(total, value_and_percentages(unmatched_count, [total]),
'\n'.join("%s %s"%(value_and_percentages(count, [total]), index) for (index,count) in index_counts.items()) )
(options, args) = parser.parse_args()
try:
[infile,outfile] = args
except ValueError:
parser.print_help()
sys.exit("\nError: exactly one input and output file required!")
max_values_kept = 10
if options.remove_first_header_field: first_field_values = set()
if options.remove_last_header_field: last_field_values = set()
# go over all sequences, remove bases as required, print all the sequences
with open(outfile,'w') as OUTFILE:
for (header,sequence,quality) in parse_fastq(infile):
if options.remove_first_header_field:
first_field,header = header.split(':',1)
if len(first_field_values)<max_values_kept:
first_field_values.add(first_field)
if options.remove_last_header_field:
header,last_field = header.rsplit('#',1)
if len(last_field_values)<max_values_kept:
last_field_values.add(last_field)
OUTFILE.write( "@%s\n"%header)
OUTFILE.write(sequence + '\n')
OUTFILE.write( "+\n")
OUTFILE.write(quality + '\n')
def print_info_line(field_name, field_values):
global max_values_kept
