Mercurial > repos > bebatut > compare_humann2_output

comparison compare_humann2_output.py @ 0:9959fa526f1a 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/compare_humann2_output commit c16428041ae3d60b61b6570035c9268726730543-dirty
author bebatut
date Wed, 20 Apr 2016 08:30:08 -0400
parents
children 05766022dfc4
comparison
equal deleted inserted replaced
-1:000000000000 0:9959fa526f1a
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3
4 import sys
5 import os
6 import argparse
7 import re
8
9 def extract_abundances(filepath, nb_charact_to_extract):
10 abundances = {}
11 more_abund_charact = []
12 abund_sum = 0
13 with open(filepath, 'r') as abundance_file:
14 for line in abundance_file.readlines()[1:]:
15 split_line = line[:-1].split('\t')
16 charact_id = split_line[0]
17 abund = float(split_line[1])
18 abundances[charact_id] = 100*abund
19 abund_sum += abundances[charact_id]
20
21 if len(more_abund_charact) < nb_charact_to_extract:
22 more_abund_charact.append(charact_id)
23 else:
24 best_pos = None
25 for i in range(len(more_abund_charact)-1,-1,-1):
26 if abundances[more_abund_charact[i]] < abund:
27 best_pos = i
28 else:
29 break
30 if best_pos != None:
31 tmp_more_abund_charact = more_abund_charact
32 more_abund_charact = tmp_more_abund_charact[:best_pos]
33 more_abund_charact += [charact_id]
34 more_abund_charact += tmp_more_abund_charact[best_pos:-1]
35 return abundances, more_abund_charact
36
37 def format_characteristic_name(all_name):
38 if all_name.find(':') != -1:
39 charact_id = all_name.split(':')[0]
40 charact_name = all_name.split(':')[1][1:]
41 else:
42 charact_id = all_name
43 charact_name = ''
44
45 charact_name = charact_name.replace('/',' ')
46 charact_name = charact_name.replace('-',' ')
47 charact_name = charact_name.replace("'",'')
48 if charact_name.find('(') != -1 and charact_name.find(')') != -1:
49 open_bracket = charact_name.find('(')
50 close_bracket = charact_name.find(')')+1
51 charact_name = charact_name[:open_bracket] + charact_name[close_bracket:]
52 return charact_id,charact_name
53
54 def write_more_abundant_charat(abundances,more_abund_charact, output_filepath):
55 with open(output_filepath,'w') as output_file:
56 output_file.write('id\tname\t')
57 output_file.write('\t'.join(abundances.keys()) + '\n')
58
59 for mac in more_abund_charact:
60 charact_id,charact_name = format_characteristic_name(mac)
61 output_file.write(charact_id + '\t' + charact_name)
62 for sample in abundances:
63 abund = abundances[sample].get(mac, 0)
64 output_file.write('\t' + str(abund))
65 output_file.write('\n')
66
67 def extract_similar_characteristics(abundances, sim_output_filepath,
68 specific_output_files):
69 sim_characteristics = set(abundances[abundances.keys()[0]].keys())
70 for sample in abundances.keys()[1:]:
71 sim_characteristics.intersection_update(abundances[sample].keys())
72 print 'Similar between all samples:', len(sim_characteristics)
73
74 with open(sim_output_filepath, 'w') as sim_output_file:
75 sim_output_file.write('id\tname\t' + '\t'.join(abundances.keys()) + '\n')
76 for charact in list(sim_characteristics):
77 charact_id,charact_name = format_characteristic_name(charact)
78 sim_output_file.write(charact_id + '\t' + charact_name)
79 for sample in abundances.keys():
80 sim_output_file.write('\t' + str(abundances[sample][charact]))
81 sim_output_file.write('\n')
82
83 print 'Specific to samples:'
84 diff_characteristics = {}
85 for i in range(len(abundances.keys())):
86 sample = abundances.keys()[i]
87 print ' ', sample, ""
88 print ' All:', len(abundances[sample].keys())
89 diff_characteristics[sample] = set(abundances[sample].keys())
90 diff_characteristics[sample].difference_update(sim_characteristics)
91 print ' Number of specific characteristics:',
92 print len(diff_characteristics[sample])
93 print ' Percentage of specific characteristics:',
94 print 100*len(diff_characteristics[sample])/(1.*len(abundances[sample].keys()))
95
96 relative_abundance = 0
97 with open(specific_output_files[i], 'w') as output_file:
98 output_file.write('id\tname\tabundances\n')
99 for charact in list(diff_characteristics[sample]):
100 charact_id,charact_name = format_characteristic_name(charact)
101 output_file.write(charact_id + '\t' + charact_name + '\t')
102 output_file.write(str(abundances[sample][charact]) + '\n')
103 relative_abundance += abundances[sample][charact]
104 print ' Relative abundance of specific characteristics(%):', relative_abundance
105
106 return sim_characteristics
107
108 def compare_humann2_output(args):
109 abundances = {}
110 more_abund_charact = []
111
112 for i in range(len(args.sample_name)):
113 abundances[args.sample_name[i]], mac = extract_abundances(args.charact_input_file[i],
114 args.most_abundant_characteristics_to_extract)
115 more_abund_charact += mac
116
117 write_more_abundant_charat(abundances, list(set(more_abund_charact)),
118 args.more_abundant_output_file)
119 sim_characteristics = extract_similar_characteristics(abundances,
120 args.similar_output_file, args.specific_output_file)
121
122 if __name__ == '__main__':
123 parser = argparse.ArgumentParser()
124 parser.add_argument('--sample_name', required=True, action='append')
125 parser.add_argument('--charact_input_file', required=True, action='append')
126 parser.add_argument('--most_abundant_characteristics_to_extract', required=True,
127 type = int)
128 parser.add_argument('--more_abundant_output_file', required=True)
129 parser.add_argument('--similar_output_file', required=True)
130 parser.add_argument('--specific_output_file', required=True,action='append')
131 args = parser.parse_args()
132
133 if len(args.sample_name) != len(args.charact_input_file):
134 raise ValueError("Same number of values (in same order) are expected for --sample_name and --charact_input_file")
135 if len(args.sample_name) != len(args.specific_output_file):
136 raise ValueError("Same number of values (in same order) are expected for --sample_name and --specific_output_file")
137
138 compare_humann2_output(args)