else:
bar_pattern_non_quality_counts += 1
else:
non_bar_pattern_counts += 1
print('The total counts of reads is ' + str(total_counts))
print('The barcode pattern matching reads is ' + str(bar_pattern_counts))
print('The non barcode pattern matching reads is ' +
str(non_bar_pattern_counts))
print('The barcode pattern matching and quality reads is ' +
str(bar_pattern_quality_counts))
print('The barcode pattern matching and non quality reads is ' +
str(bar_pattern_non_quality_counts))
print(
'The barcode pattern matching, quality, and multitag matching reads is ' +
str(bar_pattern_quality_multitag_counts))
#Close the files
for i in multitag:
vars()[i + '_multitag'].close()
vars()[i + '_lintag1'].close()
vars()[i + '_lintag2'].close()
f_file.close()
r_file.close()
# run bartender to cluster the barcodes
#for i in multitag:
# os.system("bartender_single_com -f " + i + "_lintag1_umi.txt -c 2 -t 8 -d 2 -o " + i + "_bartender_lintag1" )
# os.system("bartender_single_com -f " + i + "_lintag2_umi.txt -c 2 -t 8 -d 2 -o " + i + "_bartender_lintag2")
break
if not found:
with gzip.open(
output_dir + 'discarded.fq.gz',
'at') as out_handle:
[
out_handle.write(field + '\n')
for read in g[bc] for field in read
]
global_counter['discarded'] += len(g[bc])
local_counter['discarded'] += len(g[bc])
if verbose:
print(
os.path.basename(input_file) + ':',
'processed', processed, 'reads')
file_iterator.close()
out_stats = re.sub('(fq|fastq).*$', 'stats.txt',
os.path.basename(input_file))
with open(output_dir + out_stats, 'wt') as out_handle:
for key in barcode_files.keys():
out_handle.write('\t'.join([
'Barcode', key,
str(local_counter[key] - 1),
str((local_counter[key] - 1) / processed)
]) + '\n')
out_handle.write('\t'.join([
'Barcode', 'Discarded',
str(local_counter['discarded'] - 1),
str((local_counter['discarded'] - 1) / processed)
]) + '\n')
if len(inFile) > 1:
