Mercurial > repos > iuc > data_manager_malt_index_builder
comparison data_manager/malt_index_builder.py @ 0:5f9d6aee2256 draft default tip
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_malt_index_builder commit 710e56e0e522b0ed060dab2fecf05ed1c79c928f"
author | iuc |
---|---|
date | Wed, 17 Nov 2021 08:22:56 +0000 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:5f9d6aee2256 |
---|---|
1 #!/usr/bin/env python | |
2 | |
3 import json | |
4 import optparse | |
5 import os | |
6 import subprocess | |
7 import sys | |
8 | |
9 | |
10 def get_id_name(params, dbkey, fasta_description=None): | |
11 sequence_id = params['param_dict']['sequence_id'] | |
12 if not sequence_id: | |
13 sequence_id = dbkey | |
14 | |
15 sequence_name = params['param_dict']['sequence_name'] | |
16 if not sequence_name: | |
17 sequence_name = fasta_description | |
18 if not sequence_name: | |
19 sequence_name = dbkey | |
20 return sequence_id, sequence_name | |
21 | |
22 | |
23 def build_malt_index(data_manager_dict, fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, sequence_type, shapes, max_hits_per_seed, protein_reduct): | |
24 # The malt-build program produces a directory of files, | |
25 # so the data table path entry will be a directory and | |
26 # not an index file. | |
27 fasta_base_name = os.path.split(fasta_filename)[-1] | |
28 sym_linked_fasta_filename = os.path.join(target_directory, fasta_base_name) | |
29 os.symlink(fasta_filename, sym_linked_fasta_filename) | |
30 args = ['malt-build', '--input', sym_linked_fasta_filename, '--sequenceType', sequence_type, '--index', target_directory] | |
31 threads = os.environ.get('GALAXY_SLOTS') | |
32 if threads: | |
33 args.extend(['--threads', threads]) | |
34 if shapes is not None: | |
35 args.extend(['--shapes', shapes]) | |
36 if max_hits_per_seed is not None: | |
37 args.extend(['--maxHitsPerSeed', max_hits_per_seed]) | |
38 if protein_reduct is not None: | |
39 args.extend(['--proteinReduct', protein_reduct]) | |
40 proc = subprocess.Popen(args=args, shell=False, cwd=target_directory) | |
41 return_code = proc.wait() | |
42 if return_code: | |
43 sys.exit('Error building index, return_code: %d' % return_code) | |
44 # Remove unwanted files from the output directory. | |
45 os.remove(sym_linked_fasta_filename) | |
46 # The path entry here is the directory | |
47 # where the index files will be located, | |
48 # not a single index file (malt-build | |
49 # produces a directory if files, which | |
50 # is considered an index.. | |
51 data_table_entry = dict(value=sequence_id, dbkey=dbkey, name=sequence_name, path=None) | |
52 _add_data_table_entry(data_manager_dict, data_table_entry) | |
53 | |
54 | |
55 def _add_data_table_entry(data_manager_dict, data_table_entry): | |
56 data_table_name = "malt_indices" | |
57 data_manager_dict['data_tables'] = data_manager_dict.get('data_tables', {}) | |
58 data_manager_dict['data_tables'][data_table_name] = data_manager_dict['data_tables'].get(data_table_name, []) | |
59 data_manager_dict['data_tables'][data_table_name].append(data_table_entry) | |
60 return data_manager_dict | |
61 | |
62 | |
63 def main(): | |
64 parser = optparse.OptionParser() | |
65 parser.add_option('-f', '--fasta_filename', dest='fasta_filename', action='store', type="string", help='fasta filename') | |
66 parser.add_option('-d', '--fasta_dbkey', dest='fasta_dbkey', action='store', type="string", help='fasta dbkey') | |
67 parser.add_option('-t', '--fasta_description', dest='fasta_description', action='store', type="string", default=None, help='fasta description') | |
68 parser.add_option('-e', '--sequence_type', dest='sequence_type', action='store', type="string", help='DNA or Protein sequences') | |
69 parser.add_option('-p', '--shapes', dest='shapes', action='store', type="string", default=None, help='Comma-separated list of seed shapes') | |
70 parser.add_option('-m', '--max_hits_per_seed', dest='max_hits_per_seed', action='store', type="string", default=None, help='Maximum number of hits per seed') | |
71 parser.add_option('-r', '--protein_reduct', dest='protein_reduct', action='store', type="string", default=None, help='Name or definition of protein alphabet reduction') | |
72 (options, args) = parser.parse_args() | |
73 | |
74 filename = args[0] | |
75 | |
76 with open(filename) as fh: | |
77 params = json.load(fh) | |
78 target_directory = params['output_data'][0]['extra_files_path'] | |
79 os.mkdir(target_directory) | |
80 data_manager_dict = {} | |
81 | |
82 dbkey = options.fasta_dbkey | |
83 | |
84 if dbkey in [None, '', '?']: | |
85 raise Exception('"%s" is not a valid dbkey. You must specify a valid dbkey.' % (dbkey)) | |
86 | |
87 sequence_id, sequence_name = get_id_name(params, dbkey=dbkey, fasta_description=options.fasta_description) | |
88 | |
89 # Build the index. | |
90 build_malt_index(data_manager_dict, options.fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, options.sequence_type, options.shapes, options.max_hits_per_seed, options.protein_reduct) | |
91 | |
92 # Save info to json file. | |
93 with open(filename, 'w') as fh: | |
94 json.dump(data_manager_dict, fh, sort_keys=True) | |
95 | |
96 | |
97 if __name__ == "__main__": | |
98 main() |