Mercurial > repos > bebatut > fasta_add_barcode

comparison fasta_add_barcode.py @ 0:04699558a38a draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/fasta_add_barcode commit e857f7126443e115f11954085423f8999bc870aa-dirty
author bebatut
date Fri, 15 Apr 2016 06:04:56 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:04699558a38a
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3
4 import sys
5 import os
6 import argparse
7 import copy
8 import operator
9
10
11 def write_seq_fasta_format(seq, output_file):
12 split_seq = [seq[i:i+60] for i in xrange(0,len(seq),60)]
13 for split in split_seq:
14 output_file.write(split + '\n')
15
16 def fasta_add_barcode(args):
17 mapping = {}
18 with open(args.input_mapping_file,'r') as input_mapping_file:
19 for line in input_mapping_file:
20 split_line = line[:-1].split('\t')
21
22 if len(split_line) != 2:
23 string = 'Incorrect number of column in mapping file.'
24 string += '\nTwo tabular separated columns are expected'
25 raise ValueError(string)
26
27 mapping[split_line[0]] = split_line[1]
28
29 seq_id = ''
30 seq = ''
31 with open(args.input_sequence_file,'r') as input_sequence_file:
32 with open(args.output_sequence_file, 'w') as output_sequence_file:
33 for line in input_sequence_file:
34 if line.startswith('>'):
35 if seq != '':
36 if not mapping.has_key(seq_id):
37 string = 'A sequence identifier (' + seq_id + ') is'
38 string += ' not found in mapping file'
39 raise ValueError(string)
40
41 output_sequence_file.write('>' + seq_id + '\n')
42
43 barcode = mapping[seq_id]
44 seq = barcode + seq
45 write_seq_fasta_format(seq, output_sequence_file)
46 seq_id = line[1:-1].split( )[0]
47 seq = ''
48 else:
49 seq += line[:-1]
50
51 ########
52 # Main #
53 ########
54 if __name__ == "__main__":
55 parser = argparse.ArgumentParser()
56 parser.add_argument('--input_sequence_file', required=True)
57 parser.add_argument('--input_mapping_file', required=True)
58 parser.add_argument('--output_sequence_file', required=True)
59 args = parser.parse_args()
60
61 fasta_add_barcode(args)