Mercurial > repos > greg > data_manager_malt_index_builder

comparison data_manager/malt_index_builder.py @ 1:787f1ca9045a draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Wed, 13 Oct 2021 20:12:48 +0000
parents d69ebf52c233
children
comparison
equal deleted inserted replaced
0:d69ebf52c233 1:787f1ca9045a
3 import json 3 import json
4 import optparse 4 import optparse
5 import os 5 import os
6 import subprocess 6 import subprocess
7 import sys 7 import sys
8
9 DEFAULT_DATA_TABLE_NAME = "malt_indices"
10 8
11 9
12 def get_id_name(params, dbkey, fasta_description=None): 10 def get_id_name(params, dbkey, fasta_description=None):
13 sequence_id = params['param_dict']['sequence_id'] 11 sequence_id = params['param_dict']['sequence_id']
14 if not sequence_id: 12 if not sequence_id:
20 if not sequence_name: 18 if not sequence_name:
21 sequence_name = dbkey 19 sequence_name = dbkey
22 return sequence_id, sequence_name 20 return sequence_id, sequence_name
23 21
24 22
25 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, data_table_name=DEFAULT_DATA_TABLE_NAME): 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.
26 fasta_base_name = os.path.split(fasta_filename)[-1] 27 fasta_base_name = os.path.split(fasta_filename)[-1]
27 sym_linked_fasta_filename = os.path.join(target_directory, fasta_base_name) 28 sym_linked_fasta_filename = os.path.join(target_directory, fasta_base_name)
28 os.symlink(fasta_filename, sym_linked_fasta_filename) 29 os.symlink(fasta_filename, sym_linked_fasta_filename)
29 args = ['malt-build', '--input', sym_linked_fasta_filename, '--sequenceType', sequence_type, '--index', 'index'] 30 args = ['malt-build', '--input', sym_linked_fasta_filename, '--sequenceType', sequence_type, '--index', target_directory]
30 threads = os.environ.get('GALAXY_SLOTS') 31 threads = os.environ.get('GALAXY_SLOTS')
31 if threads: 32 if threads:
32 args.extend(['--threads', threads]) 33 args.extend(['--threads', threads])
33 if shapes is not None: 34 if shapes is not None:
34 args.extend('--shapes', shapes) 35 args.extend(['--shapes', shapes])
35 if max_hits_per_seed is not None: 36 if max_hits_per_seed is not None:
36 args.extend('--maxHitsPerSeed', max_hits_per_seed) 37 args.extend(['--maxHitsPerSeed', max_hits_per_seed])
37 if protein_reduct is not None: 38 if protein_reduct is not None:
38 args.extend('--proteinReduct', protein_reduct) 39 args.extend(['--proteinReduct', protein_reduct])
39 proc = subprocess.Popen(args=args, shell=False, cwd=target_directory) 40 proc = subprocess.Popen(args=args, shell=False, cwd=target_directory)
40 return_code = proc.wait() 41 return_code = proc.wait()
41 if return_code: 42 if return_code:
42 sys.exit('Error building index, return_code: %d' % return_code) 43 sys.exit('Error building index, return_code: %d' % return_code)
43 data_table_entry = dict(value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_name) 44 # Remove unwanted files from the output directory.
44 _add_data_table_entry(data_manager_dict, data_table_name, data_table_entry) 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)
45 53
46 54
47 def _add_data_table_entry(data_manager_dict, data_table_name, data_table_entry): 55 def _add_data_table_entry(data_manager_dict, data_table_entry):
56 data_table_name = "malt_indices"
48 data_manager_dict['data_tables'] = data_manager_dict.get('data_tables', {}) 57 data_manager_dict['data_tables'] = data_manager_dict.get('data_tables', {})
49 data_manager_dict['data_tables'][data_table_name] = data_manager_dict['data_tables'].get(data_table_name, []) 58 data_manager_dict['data_tables'][data_table_name] = data_manager_dict['data_tables'].get(data_table_name, [])
50 data_manager_dict['data_tables'][data_table_name].append(data_table_entry) 59 data_manager_dict['data_tables'][data_table_name].append(data_table_entry)
51 return data_manager_dict 60 return data_manager_dict
52 61
56 parser.add_option('-f', '--fasta_filename', dest='fasta_filename', action='store', type="string", help='fasta filename') 65 parser.add_option('-f', '--fasta_filename', dest='fasta_filename', action='store', type="string", help='fasta filename')
57 parser.add_option('-d', '--fasta_dbkey', dest='fasta_dbkey', action='store', type="string", help='fasta dbkey') 66 parser.add_option('-d', '--fasta_dbkey', dest='fasta_dbkey', action='store', type="string", help='fasta dbkey')
58 parser.add_option('-t', '--fasta_description', dest='fasta_description', action='store', type="string", default=None, help='fasta description') 67 parser.add_option('-t', '--fasta_description', dest='fasta_description', action='store', type="string", default=None, help='fasta description')
59 parser.add_option('-e', '--sequence_type', dest='sequence_type', action='store', type="string", help='DNA or Protein sequences') 68 parser.add_option('-e', '--sequence_type', dest='sequence_type', action='store', type="string", help='DNA or Protein sequences')
60 parser.add_option('-p', '--shapes', dest='shapes', action='store', type="string", default=None, help='Comma-separated list of seed shapes') 69 parser.add_option('-p', '--shapes', dest='shapes', action='store', type="string", default=None, help='Comma-separated list of seed shapes')
61 parser.add_option('-m', '--max_hits_per_seed', dest='max_hits_per_seed', action='store', type="int", default=None, help='Maximum number of hits per seed') 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')
62 parser.add_option('-r', '--protein_reduct', dest='protein_reduct', action='store', type="string", default=None, help='Name or definition of protein alphabet reduction') 71 parser.add_option('-r', '--protein_reduct', dest='protein_reduct', action='store', type="string", default=None, help='Name or definition of protein alphabet reduction')
63 (options, args) = parser.parse_args() 72 (options, args) = parser.parse_args()
64 73
65 filename = args[0] 74 filename = args[0]
66 75
76 raise Exception('"%s" is not a valid dbkey. You must specify a valid dbkey.' % (dbkey)) 85 raise Exception('"%s" is not a valid dbkey. You must specify a valid dbkey.' % (dbkey))
77 86
78 sequence_id, sequence_name = get_id_name(params, dbkey=dbkey, fasta_description=options.fasta_description) 87 sequence_id, sequence_name = get_id_name(params, dbkey=dbkey, fasta_description=options.fasta_description)
79 88
80 # Build the index. 89 # Build the index.
81 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, data_table_name=DEFAULT_DATA_TABLE_NAME) 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)
82 91
83 # Save info to json file. 92 # Save info to json file.
84 with open(filename, 'w') as fh: 93 with open(filename, 'w') as fh:
85 json.dump(data_manager_dict, fh, sort_keys=True) 94 json.dump(data_manager_dict, fh, sort_keys=True)
86 95