| Previous changeset 0:9ac823a8b328 (2015-01-22) Next changeset 2:984733fcab49 (2016-06-07) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/data_managers/data_manager_snpeff commit 88c982c5adcd32b11d98428fc554a4fdfcc19584 |
|
modified:
data_manager/data_manager_snpEff_databases.py data_manager/data_manager_snpEff_databases.xml data_manager/data_manager_snpEff_download.py data_manager/data_manager_snpEff_download.xml tool_dependencies.xml |
|
removed:
repository_dependencies.xml |
| b |
| diff -r 9ac823a8b328 -r 85a23e2dd92b data_manager/data_manager_snpEff_databases.py --- a/data_manager/data_manager_snpEff_databases.py Thu Jan 22 09:14:50 2015 -0500 +++ b/data_manager/data_manager_snpEff_databases.py Tue Jun 07 10:11:50 2016 -0400 |
| [ |
| @@ -1,30 +1,23 @@ #!/usr/bin/env python - -import sys +import json +import optparse import os -import re -import tempfile import subprocess -import fileinput -import shutil -import optparse -import urllib2 -from ftplib import FTP -import tarfile +import sys -from galaxy.util.json import from_json_string, to_json_string def stop_err(msg): sys.stderr.write(msg) sys.exit(1) + def fetch_databases(data_manager_dict, target_directory, jar_path): - (snpEff_dir,snpEff_jar) = os.path.split(jar_path) + (snpEff_dir, snpEff_jar) = os.path.split(jar_path) if not os.path.exists(target_directory): os.makedirs(target_directory) databases_path = os.path.join( target_directory, 'databases.out' ) - databases_output = open(databases_path,'w') - args = [ 'java','-jar', ] + databases_output = open(databases_path, 'w') + args = [ 'java', '-jar' ] args.append( snpEff_jar ) args.append( 'databases' ) # tmp_stderr = tempfile.NamedTemporaryFile( prefix = "tmp-data-manager-snpEff-stderr" ) @@ -35,48 +28,48 @@ if return_code: sys.exit( return_code ) databases_output.close() + data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} ) + data_manager_dict['data_tables']['snpeff4_databases'] = data_manager_dict['data_tables'].get( 'snpeff4_databases', [] ) + data_table_entries = [] try: - data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} ) - data_manager_dict['data_tables']['snpeff4_databases'] = data_manager_dict['data_tables'].get( 'snpeff4_databases', [] ) - data_table_entries = [] - fh = open(databases_path,'r') - for i,line in enumerate(fh): + fh = open(databases_path, 'r') + for i, line in enumerate(fh): fields = line.split('\t') if len(fields) >= 2: genome_version = fields[0].strip() if genome_version.startswith("Genome") or genome_version.startswith("-"): continue - #snpeff test genome + # snpeff test genome if genome_version == '30c2c903' or fields[1].strip() == 'TestCase' or fields[1].strip().startswith('Test_'): continue description = fields[1].strip() + ' : ' + genome_version data_table_entries.append(dict(value=genome_version, name=description)) data_manager_dict['data_tables']['snpeff4_databases'] = data_table_entries - except Exception, e: - stop_err( 'Error parsing %s %s\n' % (config,str( e )) ) + except Exception as e: + stop_err( 'Error parsing %s %s\n' % (databases_path, str( e )) ) else: fh.close() return data_manager_dict + def main(): - #Parse Command Line + # Parse Command Line parser = optparse.OptionParser() parser.add_option( '-j', '--jar_path', dest='jar_path', action='store', type="string", default=None, help='snpEff.jar path' ) (options, args) = parser.parse_args() filename = args[0] - params = from_json_string( open( filename ).read() ) + params = json.loads( open( filename ).read() ) target_directory = params[ 'output_data' ][0]['extra_files_path'] os.mkdir( target_directory ) data_manager_dict = {} - - #Create Defuse Reference Data + # Create Defuse Reference Data data_manager_dict = fetch_databases( data_manager_dict, target_directory, options.jar_path) - #save info to json file - open( filename, 'wb' ).write( to_json_string( data_manager_dict ) ) + # save info to json file + open( filename, 'wb' ).write( json.dumps( data_manager_dict ) ) -if __name__ == "__main__": main() - +if __name__ == "__main__": + main() |
| b |
| diff -r 9ac823a8b328 -r 85a23e2dd92b data_manager/data_manager_snpEff_databases.xml --- a/data_manager/data_manager_snpEff_databases.xml Thu Jan 22 09:14:50 2015 -0500 +++ b/data_manager/data_manager_snpEff_databases.xml Tue Jun 07 10:11:50 2016 -0400 |
| [ |
| @@ -1,20 +1,20 @@ -<tool id="data_manager_snpeff_databases" name="SnpEff Databases" version="4.0.0" tool_type="manage_data"> +<tool id="data_manager_snpeff_databases" name="SnpEff Databases" version="4.1.0" tool_type="manage_data"> <description>Read the list of available snpEff databases</description> <requirements> - <requirement type="package" version="4.0">snpEff</requirement> + <requirement type="package" version="4.1">snpEff</requirement> </requirements> + <stdio> + <exit_code range=":-1" level="fatal" description="Error: Cannot open file" /> + <exit_code range="1:" level="fatal" description="Error" /> + </stdio> <command interpreter="python"> - data_manager_snpEff_databases.py --jar_path \$SNPEFF_JAR_PATH/snpEff.jar "$out_file" + data_manager_snpEff_databases.py --jar_path "\$SNPEFF_JAR_PATH/snpEff.jar" "$out_file" </command> <inputs> </inputs> <outputs> <data name="out_file" format="data_manager_json"/> </outputs> - <stdio> - <exit_code range=":-1" level="fatal" description="Error: Cannot open file" /> - <exit_code range="1:" level="fatal" description="Error" /> - </stdio> <tests> <test> <output name="out_file"> @@ -37,5 +37,8 @@ "A program for annotating and predicting the effects of single nucleotide polymorphisms, SnpEff: SNPs in the genome of Drosophila melanogaster strain w1118; iso-2; iso-3.", Cingolani P, Platts A, Wang le L, Coon M, Nguyen T, Wang L, Land SJ, Lu X, Ruden DM. Fly (Austin). 2012 Apr-Jun;6(2):80-92. PMID: 22728672 [PubMed - in process] </help> + <citations> + <citation type="doi">10.4161/fly.19695</citation> + </citations> </tool> |
| b |
| diff -r 9ac823a8b328 -r 85a23e2dd92b data_manager/data_manager_snpEff_download.py --- a/data_manager/data_manager_snpEff_download.py Thu Jan 22 09:14:50 2015 -0500 +++ b/data_manager/data_manager_snpEff_download.py Tue Jun 07 10:11:50 2016 -0400 |
| [ |
| b'@@ -1,31 +1,24 @@\n #!/usr/bin/env python\n-\n-import sys\n+import gzip\n+import json\n+import optparse\n import os\n import re\n-import tempfile\n import subprocess\n-import fileinput\n-import shutil\n-import optparse\n-import urllib2\n-import gzip\n-from ftplib import FTP\n-import tarfile\n+import sys\n \n-from galaxy.util.json import from_json_string, to_json_string\n \n def stop_err(msg):\n sys.stderr.write(msg)\n sys.exit(1)\n \n \n-def fetch_databases(jar_path,genome_list=None):\n+def fetch_databases(jar_path, genome_list=None):\n snpDBs = dict()\n- (snpEff_dir,snpEff_jar) = os.path.split(jar_path)\n- databases_path = \'databases.out\' \n- databases_output = open(databases_path,\'w\')\n- args = [ \'java\',\'-jar\', ]\n+ (snpEff_dir, snpEff_jar) = os.path.split(jar_path)\n+ databases_path = \'databases.out\'\n+ databases_output = open(databases_path, \'w\')\n+ args = [ \'java\', \'-jar\' ]\n args.append( snpEff_jar )\n args.append( \'databases\' )\n # tmp_stderr = tempfile.NamedTemporaryFile( prefix = "tmp-data-manager-snpEff-stderr" )\n@@ -37,8 +30,8 @@\n sys.exit( return_code )\n databases_output.close()\n try:\n- fh = open(databases_path,\'r\')\n- for i,line in enumerate(fh):\n+ fh = open(databases_path, \'r\')\n+ for i, line in enumerate(fh):\n fields = line.split(\'\\t\')\n if len(fields) >= 2:\n genome_version = fields[0].strip()\n@@ -47,30 +40,32 @@\n if genome_version.startswith("Genome") or genome_version.startswith("-"):\n continue\n description = fields[1].strip()\n- snpDBs[genome_version] = description;\n- except Exception, e:\n- stop_err( \'Error parsing %s %s\\n\' % (config,str( e )) )\n+ snpDBs[genome_version] = description\n+ except Exception as e:\n+ stop_err( \'Error parsing %s %s\\n\' % (databases_path, str( e )) )\n else:\n fh.close()\n return snpDBs\n \n-def getOrganismNames(jar_path,genomes,organisms) :\n+\n+def getOrganismNames(jar_path, genomes, organisms):\n genome_list = genomes.split(\',\')\n organism_list = organisms.split(\',\') if organisms else []\n if len(genome_list) != len(organism_list):\n descriptions = []\n- snpDBdict = fetch_databases(jar_path,genome_list=genome_list); \n+ snpDBdict = fetch_databases(jar_path, genome_list=genome_list)\n for genome in snpDBdict:\n descriptions.append(snpDBdict[genome] if genome in snpDBdict else genome)\n return \',\'.join(descriptions)\n- return organisms \n+ return organisms\n+\n \n def getSnpeffVersion(jar_path):\n snpeff_version = \'SnpEff ?.?\'\n- (snpEff_dir,snpEff_jar) = os.path.split(jar_path)\n+ (snpEff_dir, snpEff_jar) = os.path.split(jar_path)\n stderr_path = \'snpeff.err\'\n- stderr_fh = open(stderr_path,\'w\')\n- args = [ \'java\',\'-jar\', ]\n+ stderr_fh = open(stderr_path, \'w\')\n+ args = [ \'java\', \'-jar\' ]\n args.append( snpEff_jar )\n args.append( \'-h\' )\n proc = subprocess.Popen( args=args, shell=False, cwd=snpEff_dir, stderr=stderr_fh.fileno() )\n@@ -78,58 +73,57 @@\n if return_code != 255:\n sys.exit( return_code )\n stderr_fh.close()\n- fh = open(stderr_path,\'r\')\n+ fh = open(stderr_path, \'r\')\n for line in fh:\n- m = re.match(\'^[Ss]npEff version (SnpEff)\\s*(\\d+\\.\\d+).*$\',line)\n+ m = re.match(\'^[Ss]npEff version (SnpEff)\\s*(\\d+\\.\\d+).*$\', line)\n if m:\n snpeff_version = m.groups()[0] + m.groups()[1]\n break\n fh.close()\n return snpeff_version\n \n+\n # Starting with SnpEff 4.1 the .bin files contain the SnpEff version:\n # Example - the first 3 line of GRCh37.75/snpEffectPredictor.bin (uncompressed):\n-"""\n-SnpEff 4.1\n-CHROMOSOME 2 1 0 179197 GL000219.1 false\n-CHROMOSOME 3 1 0 81347269 HSCHR17_1 false\n-"""\n+#\n+# SnpEff 4.1\n+# CHROMOSOME 2 1 0 179197 GL000219.1 '..b'ion)\n snpeff_version = getSnpeffVersion(jar_path)\n- key = snpeff_version + \'_\' + genome_version \n+ key = snpeff_version + \'_\' + genome_version\n if os.path.isdir(genome_path):\n for root, dirs, files in os.walk(genome_path):\n for fname in files:\n if fname.startswith(\'snpEffectPredictor\'):\n # if snpEffectPredictor.bin download succeeded\n- name = genome_version + (\' : \' + organism if organism else \'\') \n+ name = genome_version + (\' : \' + organism if organism else \'\')\n # version = getSnpeffVersionFromFile(os.path.join(root,fname))\n- data_table_entry = dict(key=key,version=snpeff_version,value=genome_version, name=name, path=data_dir)\n+ data_table_entry = dict(key=key, version=snpeff_version, value=genome_version, name=name, path=data_dir)\n _add_data_table_entry( data_manager_dict, \'snpeffv_genomedb\', data_table_entry )\n else:\n- m = re.match(regulation_pattern,fname)\n+ m = re.match(regulation_pattern, fname)\n if m:\n name = m.groups()[0]\n- data_table_entry = dict(key=key,version=snpeff_version,genome=genome_version,value=name, name=name)\n+ data_table_entry = dict(key=key, version=snpeff_version, genome=genome_version, value=name, name=name)\n _add_data_table_entry( data_manager_dict, \'snpeffv_regulationdb\', data_table_entry )\n elif fname in annotations_dict:\n value = annotations_dict[fname]\n name = value.lstrip(\'-\')\n- data_table_entry = dict(key=key,version=snpeff_version,genome=genome_version,value=value, name=name)\n+ data_table_entry = dict(key=key, version=snpeff_version, genome=genome_version, value=value, name=name)\n _add_data_table_entry( data_manager_dict, \'snpeffv_annotations\', data_table_entry )\n return data_manager_dict\n \n+\n def _add_data_table_entry( data_manager_dict, data_table, data_table_entry ):\n data_manager_dict[\'data_tables\'] = data_manager_dict.get( \'data_tables\', {} )\n data_manager_dict[\'data_tables\'][data_table] = data_manager_dict[\'data_tables\'].get( data_table, [] )\n data_manager_dict[\'data_tables\'][data_table].append( data_table_entry )\n return data_manager_dict\n \n+\n def main():\n- #Parse Command Line\n+ # Parse Command Line\n parser = optparse.OptionParser()\n parser.add_option( \'-j\', \'--jar_path\', dest=\'jar_path\', action=\'store\', type="string", default=None, help=\'snpEff.jar path\' )\n parser.add_option( \'-c\', \'--config\', dest=\'config\', action=\'store\', type="string", default=None, help=\'snpEff.config path\' )\n@@ -188,18 +184,17 @@\n \n filename = args[0]\n \n- params = from_json_string( open( filename ).read() )\n+ params = json.loads( open( filename ).read() )\n target_directory = params[ \'output_data\' ][0][\'extra_files_path\']\n os.mkdir( target_directory )\n data_manager_dict = {}\n \n-\n- #Create SnpEff Reference Data\n- for genome_version, organism in zip(options.genome_version.split(\',\'), getOrganismNames(options.jar_path,options.genome_version,options.organism).split(\',\')):\n+ # Create SnpEff Reference Data\n+ for genome_version, organism in zip(options.genome_version.split(\',\'), getOrganismNames(options.jar_path, options.genome_version, options.organism).split(\',\')):\n download_database( data_manager_dict, target_directory, options.jar_path, options.config, genome_version, organism )\n \n- #save info to json file\n- open( filename, \'wb\' ).write( to_json_string( data_manager_dict ) )\n+ # save info to json file\n+ open( filename, \'wb\' ).write( json.dumps( data_manager_dict ) )\n \n-if __name__ == "__main__": main()\n-\n+if __name__ == "__main__":\n+ main()\n' |
| b |
| diff -r 9ac823a8b328 -r 85a23e2dd92b data_manager/data_manager_snpEff_download.xml --- a/data_manager/data_manager_snpEff_download.xml Thu Jan 22 09:14:50 2015 -0500 +++ b/data_manager/data_manager_snpEff_download.xml Tue Jun 07 10:11:50 2016 -0400 |
| [ |
| @@ -1,14 +1,18 @@ -<tool id="data_manager_snpeff_download" name="SnpEff Download" version="4.0.0" tool_type="manage_data"> +<tool id="data_manager_snpeff_download" name="SnpEff Download" version="4.1.0" tool_type="manage_data"> <description>Download a new database</description> <requirements> - <requirement type="package" version="4.0">snpEff</requirement> + <requirement type="package" version="4.1">snpEff</requirement> </requirements> + <stdio> + <exit_code range=":-1" level="fatal" description="Error: Cannot open file" /> + <exit_code range="1:" level="fatal" description="Error" /> + </stdio> <command interpreter="python"> - data_manager_snpEff_download.py --jar_path \$SNPEFF_JAR_PATH/snpEff.jar --config \$SNPEFF_JAR_PATH/snpEff.config + data_manager_snpEff_download.py --jar_path "\$SNPEFF_JAR_PATH/snpEff.jar" --config "\$SNPEFF_JAR_PATH/snpEff.config" --genome_version "$genome_version" "$out_file" </command> <inputs> - <param name="genome_version" type="text" size="40" value="" label="Snpff Genome Version Name (e.g. GRCh38.76)"> + <param name="genome_version" type="text" value="" label="Snpff Genome Version Name (e.g. GRCh38.76)"> <help>https://snpeff-data.galaxyproject.org/databases/</help> <validator type="regex" message="A genome version name is required">\S+</validator> </param> @@ -17,10 +21,6 @@ <outputs> <data name="out_file" format="data_manager_json" label="${tool.name}"/> </outputs> - <stdio> - <exit_code range=":-1" level="fatal" description="Error: Cannot open file" /> - <exit_code range="1:" level="fatal" description="Error" /> - </stdio> <tests> <test> <param name="genome_version" value="GRCh38.76"/> @@ -38,7 +38,7 @@ This tool downloads a SnpEff database and populates data tables: snpeffv_genomedb, snpeffv_regulationdb, and snpeffv_annotations. -To see the list of available SnpEff genomes run the "SnpEff Databases" data manager which records the available genome databases in data table: snpeff4_databases +To see the list of available SnpEff genomes run the "SnpEff Databases" data manager which records the available genome databases in data table: snpeff4_databases The SnpEff genome databases are at: http://sourceforge.net/projects/snpeff/files/databases/ @@ -49,5 +49,8 @@ "A program for annotating and predicting the effects of single nucleotide polymorphisms, SnpEff: SNPs in the genome of Drosophila melanogaster strain w1118; iso-2; iso-3.", Cingolani P, Platts A, Wang le L, Coon M, Nguyen T, Wang L, Land SJ, Lu X, Ruden DM. Fly (Austin). 2012 Apr-Jun;6(2):80-92. PMID: 22728672 [PubMed - in process] </help> + <citations> + <citation type="doi">10.4161/fly.19695</citation> + </citations> </tool> |
| b |
| diff -r 9ac823a8b328 -r 85a23e2dd92b repository_dependencies.xml --- a/repository_dependencies.xml Thu Jan 22 09:14:50 2015 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,4 +0,0 @@ -<?xml version="1.0"?> -<repositories description="This requires the SnpEff datatype definitions."> - <repository changeset_revision="d78b2b2a3388" name="snpeff_datatypes" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" /> -</repositories> |
| b |
| diff -r 9ac823a8b328 -r 85a23e2dd92b tool_dependencies.xml --- a/tool_dependencies.xml Thu Jan 22 09:14:50 2015 -0500 +++ b/tool_dependencies.xml Tue Jun 07 10:11:50 2016 -0400 |
| b |
| @@ -1,6 +1,6 @@ <?xml version="1.0"?> <tool_dependency> - <package name="snpEff" version="4.0"> - <repository changeset_revision="6bc55957927b" name="package_snpeff_4_0" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" /> + <package name="snpEff" version="4.1"> + <repository changeset_revision="374c7f8421fb" name="package_snpeff_4_1" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" /> </package> </tool_dependency> |