Mercurial > repos > jjohnson > snpeff
annotate data_manager/data_manager_snpEff_download.py @ 8:aecbd8878923
Uploaded
| author | bgruening |
|---|---|
| date | Fri, 29 Nov 2013 09:29:05 -0500 |
| parents | eb394dd65c98 |
| children |
| rev | line source |
|---|---|
| 0 | 1 #!/usr/bin/env python |
| 2 | |
| 3 import sys | |
| 4 import os | |
| 5 import re | |
| 6 import tempfile | |
| 7 import subprocess | |
| 8 import fileinput | |
| 9 import shutil | |
| 10 import optparse | |
| 11 import urllib2 | |
| 12 from ftplib import FTP | |
| 13 import tarfile | |
| 14 | |
| 15 from galaxy.util.json import from_json_string, to_json_string | |
| 16 | |
| 17 def stop_err(msg): | |
| 18 sys.stderr.write(msg) | |
| 19 sys.exit(1) | |
| 20 | |
| 21 """ | |
| 22 # Download human database 'hg19' | |
| 23 java -jar snpEff.jar download -v hg19 | |
| 24 | |
| 2 | 25 <command>java -jar \$SNPEFF_JAR_PATH/snpEff.jar download -c \$JAVA_JAR_PATH/snpEff.config $genomeVersion > $logfile </command> |
| 0 | 26 |
| 27 snpEffectPredictor.bin | |
| 28 regulation_HeLa-S3.bin | |
| 29 regulation_pattern = 'regulation_(.+).bin' | |
| 30 | |
| 31 | |
| 32 """ | |
| 33 def download_database(data_manager_dict, target_directory, jar_path,config,genome_version,organism): | |
| 34 ## get data_dir from config | |
| 35 ##--- | |
| 36 ## Databases are stored here | |
| 37 ## E.g.: Information for 'hg19' is stored in data_dir/hg19/ | |
| 38 ## | |
| 39 ## Note: Since version 2.1 you can use tilde ('~') as first character to refer to your home directory | |
| 40 ##--- | |
| 41 #data_dir = ~/snpEff/data/ | |
|
5
8952990fcab9
Update to snpEff version 3.4 and add data managers to download snpEff genome reference databases
Jim Johnson <jj@umn.edu>
parents:
2
diff
changeset
|
42 data_dir = target_directory |
| 0 | 43 (snpEff_dir,snpEff_jar) = os.path.split(jar_path) |
| 44 args = [ 'java','-jar' ] | |
| 45 args.append( jar_path ) | |
| 46 args.append( 'download' ) | |
|
5
8952990fcab9
Update to snpEff version 3.4 and add data managers to download snpEff genome reference databases
Jim Johnson <jj@umn.edu>
parents:
2
diff
changeset
|
47 args.append( '-c' ) |
|
8952990fcab9
Update to snpEff version 3.4 and add data managers to download snpEff genome reference databases
Jim Johnson <jj@umn.edu>
parents:
2
diff
changeset
|
48 args.append( config ) |
|
8952990fcab9
Update to snpEff version 3.4 and add data managers to download snpEff genome reference databases
Jim Johnson <jj@umn.edu>
parents:
2
diff
changeset
|
49 args.append( '-dataDir' ) |
|
8952990fcab9
Update to snpEff version 3.4 and add data managers to download snpEff genome reference databases
Jim Johnson <jj@umn.edu>
parents:
2
diff
changeset
|
50 args.append( data_dir ) |
| 0 | 51 args.append( '-v' ) |
| 52 args.append( genome_version ) | |
| 53 proc = subprocess.Popen( args=args, shell=False, cwd=snpEff_dir ) | |
| 54 return_code = proc.wait() | |
| 55 if return_code: | |
| 56 sys.exit( return_code ) | |
| 57 ## search data_dir/genome_version for files | |
| 58 regulation_pattern = 'regulation_(.+).bin' | |
| 2 | 59 # annotation files that are included in snpEff by a flag |
| 60 annotations_dict = {'nextProt.bin' : '-nextprot','motif.bin': '-motif'} | |
| 0 | 61 genome_path = os.path.join(data_dir,genome_version) |
| 62 if os.path.isdir(genome_path): | |
| 63 for root, dirs, files in os.walk(genome_path): | |
| 64 for fname in files: | |
| 65 if fname.startswith('snpEffectPredictor'): | |
| 66 # if snpEffectPredictor.bin download succeeded | |
| 67 name = genome_version + (' : ' + organism if organism else '') | |
|
5
8952990fcab9
Update to snpEff version 3.4 and add data managers to download snpEff genome reference databases
Jim Johnson <jj@umn.edu>
parents:
2
diff
changeset
|
68 data_table_entry = dict(value=genome_version, name=name, path=data_dir) |
| 0 | 69 _add_data_table_entry( data_manager_dict, 'snpeff_genomedb', data_table_entry ) |
| 70 else: | |
| 71 m = re.match(regulation_pattern,fname) | |
| 72 if m: | |
| 73 name = m.groups()[0] | |
| 2 | 74 data_table_entry = dict(genome=genome_version,value=name, name=name) |
| 0 | 75 _add_data_table_entry( data_manager_dict, 'snpeff_regulationdb', data_table_entry ) |
| 2 | 76 elif fname in annotations_dict: |
| 77 value = annotations_dict[fname] | |
| 78 name = value.lstrip('-') | |
| 79 data_table_entry = dict(genome=genome_version,value=value, name=name) | |
| 80 _add_data_table_entry( data_manager_dict, 'snpeff_annotations', data_table_entry ) | |
| 0 | 81 return data_manager_dict |
| 82 | |
| 83 def _add_data_table_entry( data_manager_dict, data_table, data_table_entry ): | |
| 84 data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} ) | |
| 85 data_manager_dict['data_tables'][data_table] = data_manager_dict['data_tables'].get( data_table, [] ) | |
| 86 data_manager_dict['data_tables'][data_table].append( data_table_entry ) | |
| 87 return data_manager_dict | |
| 88 | |
| 89 def main(): | |
| 90 #Parse Command Line | |
| 91 parser = optparse.OptionParser() | |
| 92 parser.add_option( '-j', '--jar_path', dest='jar_path', action='store', type="string", default=None, help='snpEff.jar path' ) | |
| 93 parser.add_option( '-c', '--config', dest='config', action='store', type="string", default=None, help='snpEff.config path' ) | |
| 94 parser.add_option( '-g', '--genome_version', dest='genome_version', action='store', type="string", default=None, help='genome_version' ) | |
| 95 parser.add_option( '-o', '--organism', dest='organism', action='store', type="string", default=None, help='organism name' ) | |
| 96 (options, args) = parser.parse_args() | |
| 97 | |
| 98 filename = args[0] | |
| 99 | |
| 100 params = from_json_string( open( filename ).read() ) | |
| 101 target_directory = params[ 'output_data' ][0]['extra_files_path'] | |
| 102 os.mkdir( target_directory ) | |
| 103 data_manager_dict = {} | |
| 104 | |
| 105 | |
| 106 #Create SnpEff Reference Data | |
|
6
eb394dd65c98
Add mutli-select to data managers from Bjoern, filter unique database options in snpEff_download.xml snpEff.xml
Jim Johnson <jj@umn.edu>
parents:
5
diff
changeset
|
107 for genome_version, organism in zip(options.genome_version.split(','), options.organism.split(',')): |
|
eb394dd65c98
Add mutli-select to data managers from Bjoern, filter unique database options in snpEff_download.xml snpEff.xml
Jim Johnson <jj@umn.edu>
parents:
5
diff
changeset
|
108 download_database( data_manager_dict, target_directory, options.jar_path, options.config, genome_version, organism ) |
| 0 | 109 |
| 110 #save info to json file | |
| 111 open( filename, 'wb' ).write( to_json_string( data_manager_dict ) ) | |
| 112 | |
| 113 if __name__ == "__main__": main() | |
| 114 |