Mercurial > repos > bebatut > format_metaphlan2_output

comparison format_metaphlan2_output.py @ 0:2bfa9b200600 draft

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/format_metaphlan2_output/ commit 36388cac89e4ffa55fe317d10cbf97346ab00a71-dirty
author bebatut
date Wed, 20 Apr 2016 07:52:41 -0400
parents
children 1e74cb2c8e67
comparison
equal deleted inserted replaced
-1:000000000000 0:2bfa9b200600
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3
4 import sys
5 import os
6 import argparse
7 import re
8
9 taxo_level_correspondance = {}
10 taxo_level_correspondance['k'] = 'kingdom'
11 taxo_level_correspondance['p'] = 'phylum'
12 taxo_level_correspondance['c'] = 'class'
13 taxo_level_correspondance['o'] = 'order'
14 taxo_level_correspondance['f'] = 'family'
15 taxo_level_correspondance['g'] = 'genus'
16 taxo_level_correspondance['s'] = 'species'
17 taxo_level_correspondance['t'] = 'strains'
18
19 def write_taxo_abundance(output_files, level, taxo, abundance):
20 if not taxo_level_correspondance.has_key(level):
21 raise ValueError(level + ' is not a know taxonomic level')
22 output_files[taxo_level_correspondance[level]].write(taxo + '\t')
23 output_files[taxo_level_correspondance[level]].write(abundance + '\n')
24
25 def format_metaphlan2_output(args):
26 taxo_levels_abundance_files = {}
27 taxo_levels_abundance_files['kingdom'] = open(args.kingdom_abundance_file, 'w')
28 taxo_levels_abundance_files['phylum'] = open(args.phylum_abundance_file, 'w')
29 taxo_levels_abundance_files['class'] = open(args.class_abundance_file, 'w')
30 taxo_levels_abundance_files['order'] = open(args.order_abundance_file, 'w')
31 taxo_levels_abundance_files['family'] = open(args.family_abundance_file, 'w')
32 taxo_levels_abundance_files['genus'] = open(args.genus_abundance_file, 'w')
33 taxo_levels_abundance_files['species'] = open(args.species_abundance_file, 'w')
34 taxo_levels_abundance_files['strains'] = open(args.strains_abundance_file, 'w')
35
36 for taxo_level_file in taxo_levels_abundance_files:
37 taxo_levels_abundance_files[taxo_level_file].write(taxo_level_file + '\t')
38 taxo_levels_abundance_files[taxo_level_file].write('abundance\n')
39
40 with open(args.metaphlan2_output, 'r') as input_file:
41 with open(args.all_taxo_level_abundance_file, 'w') as output_file:
42 output_file.write("kingdom\t")
43 output_file.write("phylum\t")
44 output_file.write("class\t")
45 output_file.write("order\t")
46 output_file.write("family\t")
47 output_file.write("genus\t")
48 output_file.write("species\t")
49 output_file.write("strains\t")
50 output_file.write("abundance\n")
51 levels_number = 8
52
53 for line in input_file.readlines():
54 if line.startswith("#"):
55 continue
56
57 split_line = line[:-1].split('\t')
58 all_taxo = split_line[0]
59 abundance = split_line[1]
60
61 split_taxo = all_taxo.split('|')
62 for level in split_taxo:
63 taxo = level.split('__')[1]
64 taxo = taxo.replace("_"," ")
65 output_file.write(taxo + '\t')
66
67 for i in range(len(split_taxo), levels_number):
68 output_file.write('\t')
69
70 output_file.write(abundance + "\n")
71
72
73 last_taxo_level = split_taxo[-1].split('__')
74 taxo = last_taxo_level[1].replace("_"," ")
75 level = last_taxo_level[0]
76 write_taxo_abundance(taxo_levels_abundance_files, level, taxo,
77 abundance)
78
79 for taxo_level_file in taxo_levels_abundance_files:
80 taxo_levels_abundance_files[taxo_level_file].close()
81
82 if __name__ == '__main__':
83 parser = argparse.ArgumentParser()
84 parser.add_argument('--metaphlan2_output', required=True)
85 parser.add_argument('--all_taxo_level_abundance_file', required=True)
86 parser.add_argument('--kingdom_abundance_file', required=True)
87 parser.add_argument('--phylum_abundance_file', required=True)
88 parser.add_argument('--class_abundance_file', required=True)
89 parser.add_argument('--order_abundance_file', required=True)
90 parser.add_argument('--family_abundance_file', required=True)
91 parser.add_argument('--genus_abundance_file', required=True)
92 parser.add_argument('--species_abundance_file', required=True)
93 parser.add_argument('--strains_abundance_file', required=True)
94
95 args = parser.parse_args()
96
97 format_metaphlan2_output(args)