Mercurial > repos > galaxyp > maxquant

comparison mqwrapper.py @ 0:4ce8694766e3 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/maxquant commit ab4e4f1817080cbe8a031a82cb180610ff140847
author galaxyp
date Fri, 19 Jul 2019 19:13:15 -0400
parents
children 461ba35a313f
comparison
equal deleted inserted replaced
-1:000000000000 0:4ce8694766e3
1 """
2 Run MaxQuant on a modified mqpar.xml.
3 Use maxquant conda package.
4 TODO: add support for parameter groups
5
6 Authors: Damian Glaetzer <d.glaetzer@mailbox.org>
7
8 based on the maxquant galaxy tool by John Chilton:
9 https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/maxquant
10 """
11
12 import argparse
13 import os
14 import shutil
15 import subprocess
16
17 import mqparam
18
19 # build parser
20 parser = argparse.ArgumentParser()
21
22 # input, special outputs and others
23 other_args = ('raw_files', 'mzxml_files', 'fasta_files',
24 'description_parse_rule', 'identifier_parse_rule',
25 'exp_design', 'output_all',
26 'mqpar_out', 'infile_names', 'mzTab',
27 'version', 'substitution_rx')
28
29 # txt result files
30 txt_output = ('evidence', 'msms', 'parameters',
31 'peptides', 'proteinGroups', 'allPeptides',
32 'libraryMatch', 'matchedFeatures',
33 'modificationSpecificPeptides', 'ms3Scans',
34 'msmsScans', 'mzRange', 'peptideSection',
35 'summary')
36
37 # arguments for mqparam
38 ## global
39 global_flags = ('calc_peak_properties',
40 'write_mztab',
41 'ibaq',
42 'ibaq_log_fit',
43 'separate_lfq',
44 'lfq_stabilize_large_ratios',
45 'lfq_require_msms',
46 'advanced_site_intensities',
47 'match_between_runs')
48
49 global_simple_args = ('min_unique_pep',
50 'num_threads',
51 'min_peptide_len',
52 'max_peptide_mass')
53
54 ## parameter group specific
55 param_group_flags = ('lfq_skip_norm',)
56
57 param_group_simple_args = ('missed_cleavages',
58 'lfq_mode',
59 'lfq_min_edges_per_node',
60 'lfq_avg_edges_per_node',
61 'lfq_min_ratio_count')
62
63 param_group_silac_args = ('light_mods', 'medium_mods', 'heavy_mods')
64
65 list_args = ('fixed_mods', 'var_mods', 'proteases')
66
67 arguments = ['--' + el for el in (txt_output
68 + global_simple_args
69 + param_group_simple_args
70 + list_args
71 + param_group_silac_args
72 + other_args)]
73
74 flags = ['--' + el for el in global_flags + param_group_flags]
75
76 for arg in arguments:
77 parser.add_argument(arg)
78 for flag in flags:
79 parser.add_argument(flag, action="store_true")
80
81 args = vars(parser.parse_args())
82
83 # link infile datasets to names with correct extension
84 # for maxquant to accept them
85 files = (args['raw_files'] if args['raw_files']
86 else args['mzxml_files']).split(',')
87 ftype = ".thermo.raw" if args['raw_files'] else ".mzXML"
88 filenames = args['infile_names'].split(',')
89 fnames_with_ext = [(a if a.endswith(ftype)
90 else os.path.splitext(a)[0] + ftype)
91 for a in filenames]
92
93 for f, l in zip(files, fnames_with_ext):
94 os.link(f, l)
95
96 # build mqpar.xml
97 mqpar_in = os.path.join(os.getcwd(), 'mqpar.xml')
98 subprocess.run(('maxquant', '-c', mqpar_in))
99 mqpar_out = args['mqpar_out'] if args['mqpar_out'] != 'None' else mqpar_in
100
101
102 exp_design = args['exp_design'] if args['exp_design'] != 'None' else None
103 m = mqparam.MQParam(mqpar_out, mqpar_in, exp_design,
104 substitution_rx=args['substitution_rx'])
105 if m.version != args['version']:
106 raise Exception('mqpar version is ' + m.version +
107 '. Tool uses version {}.'.format(args['version']))
108
109 # modify parameters, interactive mode if no mqpar_in was specified
110 m.add_infiles([os.path.join(os.getcwd(), name) for name in fnames_with_ext], True)
111 m.add_fasta_files(args['fasta_files'].split(','),
112 identifier=args['identifier_parse_rule'],
113 description=args['description_parse_rule'])
114
115 for e in (global_simple_args
116 + param_group_simple_args
117 + global_flags
118 + param_group_flags):
119 if args[e]:
120 m.set_simple_param(e, args[e])
121
122 for e in list_args:
123 if args[e]:
124 m.set_list_params(e, args[e].split(','))
125
126 if args['light_mods'] or args['medium_mods'] or args['heavy_mods']:
127 m.set_silac(args['light_mods'].split(',') if args['light_mods'] else None,
128 args['medium_mods'].split(',') if args['medium_mods'] else None,
129 args['heavy_mods'].split(',') if args['heavy_mods'] else None)
130
131 m.write()
132
133 # build and run MaxQuant command
134 cmd = ['maxquant', mqpar_out]
135
136 subprocess.run(cmd, check=True, cwd='./')
137
138 # copy results to galaxy database
139 for el in txt_output:
140 destination = args[el]
141 source = os.path.join(os.getcwd(), "combined", "txt", "{}.txt".format(el))
142 if destination != 'None' and os.path.isfile(source):
143 shutil.copy(source, destination)
144
145 if args['mzTab'] != 'None':
146 source = os.path.join(os.getcwd(), "combined", "txt", "mzTab.mzTab")
147 if os.path.isfile(source):
148 shutil.copy(source, args['mzTab'])