Mercurial > repos > iuc > dram_set_database_locations

comparison dram_set_database_locations.py @ 0:6e52f03e612d draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/dram commit 52575ece22fcdbb6fc3aa3582ea377075aaa4db1
author iuc
date Thu, 01 Sep 2022 17:16:35 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:6e52f03e612d
1 #!/usr/bin/env python
2
3 import argparse
4 import os
5 import subprocess
6
7 parser = argparse.ArgumentParser()
8
9 parser.add_argument('--db_version', action='store', dest='db_version', help='Version of DRAM databases')
10 parser.add_argument('--skip_uniref', action='store_true', dest='skip_uniref', default=False, help='Flag to Download and process uniref')
11 parser.add_argument('--galaxy_data_manager_data_path', action='store', dest='galaxy_data_manager_data_path', help='Absolute Galaxy data manager data path')
12 parser.add_argument('--output', action='store', dest='output', help='Output file')
13
14 args = parser.parse_args()
15
16
17 def get_new_dram_config_entry(db_version, old_entry, new_base_path):
18 # Example old_entry:
19 # KOfam db: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/kofam_profiles.hmm
20 base_path, file_name = os.path.split(old_entry)
21 # The new entry must be GALAXY_DATA_MANAGER_DATA_PATH/DRAM/${value}/file_name
22 return os.path.join(new_base_path, 'DRAM', db_version, file_name)
23
24
25 # At this point the DRAM config will look something like this.
26 # Processed search databases
27 # KEGG db: None
28 # KOfam db: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/kofam_profiles.hmm
29 # KOfam KO list: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/kofam_ko_list.tsv
30 # UniRef db: None
31 # Pfam db: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/pfam.mmspro
32 # dbCAN db: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/dbCAN-HMMdb-V10.txt
33 # RefSeq Viral db: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/refseq_viral.20220707.mmsdb
34 # MEROPS peptidase db: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/peptidases.20220707.mmsdb
35 # VOGDB db: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/vog_latest_hmms.txt
36 #
37 # Descriptions of search database entries
38 # Pfam hmm dat: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/Pfam-A.hmm.dat.gz
39 # dbCAN family activities: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/CAZyDB.07292021.fam-activities.txt
40 # VOG annotations: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/vog_annotations_latest.tsv.gz
41 #
42 # Description db: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/description_db.sqlite
43 #
44 # DRAM distillation sheets
45 # Genome summary form: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/genome_summary_form.20220707.tsv
46 # Module step form: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/module_step_form.20220707.tsv
47 # ETC module database: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/etc_mdoule_database.20220707.tsv
48 # Function heatmap form: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/function_heatmap_form.20220707.tsv
49 # AMG database: /home/galaxies/gvk/jwd/003/3045/working/dataset_4268_files/amg_database.20220707.tsv
50
51 # Write the current DRAM CONFIG to a file for processing.
52 cmd = 'DRAM-setup.py print_config > dram_config.txt'
53 subprocess.check_call(cmd, shell=True)
54
55 # Update the database locations that DRAM sets in it's CONFIG
56 # to point to the configured GALAXY_DATA_MANAGER_DATA_PATH location
57 # for the DRAM databases.
58 cmd = 'DRAM-setup.py set_database_locations'
59 with open('dram_config.txt', 'r') as fh:
60 for line in fh:
61 line = line.rstrip('\r\n')
62 if line.startswith('KOfam db:'):
63 cmd = '%s --kofam_hmm_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
64 elif line.startswith('KOfam KO list:'):
65 cmd = '%s --kofam_ko_list_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
66 elif line.startswith('UniRef db:'):
67 if not args.skip_uniref:
68 cmd = '%s --uniref_db_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
69 elif line.startswith('Pfam db:'):
70 cmd = '%s --pfam_db_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
71 elif line.startswith('dbCAN db:'):
72 cmd = '%s --dbcan_db_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
73 elif line.startswith('RefSeq Viral db:'):
74 cmd = '%s --viral_db_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
75 elif line.startswith('MEROPS peptidase db:'):
76 cmd = '%s --peptidase_db_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
77 elif line.startswith('VOGDB db:'):
78 cmd = '%s --vogdb_db_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
79 elif line.startswith('Pfam hmm dat:'):
80 cmd = '%s --pfam_hmm_dat %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
81 elif line.startswith('dbCAN family activities:'):
82 cmd = '%s --dbcan_fam_activities %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
83 elif line.startswith('VOG annotations:'):
84 cmd = '%s --vog_annotations %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
85 elif line.startswith('Description db:'):
86 cmd = '%s --description_db_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
87 elif line.startswith('Genome summary form:'):
88 cmd = '%s --genome_summary_form_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
89 elif line.startswith('Module step form:'):
90 cmd = '%s --module_step_form_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
91 elif line.startswith('ETC module database:'):
92 cmd = '%s --etc_module_database_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
93 elif line.startswith('Function heatmap form:'):
94 cmd = '%s --function_heatmap_form_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
95 elif line.startswith('AMG database:'):
96 cmd = '%s --amg_database_loc %s' % (cmd, get_new_dram_config_entry(args.db_version, line, args.galaxy_data_manager_data_path))
97 cmd = '%s --update_description_db' % cmd
98 subprocess.check_call(cmd, shell=True)
99
100 # Write the new DRAM CONFIG to a file to the output.
101 cmd = 'DRAM-setup.py print_config > %s' % args.output
102 subprocess.check_call(cmd, shell=True)