# HG changeset patch # User devteam # Date 1444745847 14400 # Node ID 8de13c28d92ef818d16adaf8037b38f5d8a7e134 # Parent e0839cffd0093b40faeeb8ef98072745c36603f4 planemo upload commit 33927a87ba2eee9bf0ecdd376a66241b17b3d734 diff -r e0839cffd009 -r 8de13c28d92e .shed.yml --- a/.shed.yml Thu Mar 19 10:24:37 2015 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,4 +0,0 @@ -# repository published to https://toolshed.g2.bx.psu.edu/repos/devteam/data_manager_bowtie2_index_builder -owner: devteam -name: data_manager_bowtie2_index_builder - diff -r e0839cffd009 -r 8de13c28d92e data_manager/bowtie2_index_builder.py --- a/data_manager/bowtie2_index_builder.py Thu Mar 19 10:24:37 2015 -0400 +++ b/data_manager/bowtie2_index_builder.py Tue Oct 13 10:17:27 2015 -0400 @@ -9,7 +9,7 @@ from json import loads, dumps -DEFAULT_DATA_TABLE_NAME = "bowtie2_indexes" +DEFAULT_DATA_TABLE_NAMES = ["bowtie2_indexes"] def get_id_name( params, dbkey, fasta_description=None): #TODO: ensure sequence_id is unique and does not already appear in location file @@ -24,7 +24,7 @@ sequence_name = dbkey return sequence_id, sequence_name -def build_bowtie2_index( data_manager_dict, fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, data_table_name=DEFAULT_DATA_TABLE_NAME ): +def build_bowtie2_index( data_manager_dict, fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, data_table_names=DEFAULT_DATA_TABLE_NAMES ): #TODO: allow multiple FASTA input files fasta_base_name = os.path.split( fasta_filename )[-1] sym_linked_fasta_filename = os.path.join( target_directory, fasta_base_name ) @@ -36,7 +36,8 @@ print >> sys.stderr, "Error building index." sys.exit( return_code ) data_table_entry = dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=sequence_id ) - _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry ) + for data_table_name in data_table_names: + _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry ) def _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry ): data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} ) @@ -50,7 +51,7 @@ parser.add_option( '-f', '--fasta_filename', dest='fasta_filename', action='store', type="string", default=None, help='fasta_filename' ) parser.add_option( '-d', '--fasta_dbkey', dest='fasta_dbkey', action='store', type="string", default=None, help='fasta_dbkey' ) parser.add_option( '-t', '--fasta_description', dest='fasta_description', action='store', type="string", default=None, help='fasta_description' ) - parser.add_option( '-n', '--data_table_name', dest='data_table_name', action='store', type="string", default=None, help='data_table_name' ) + parser.add_option( '-n', '--data_table_name', dest='data_table_name', action='append', type="string", default=None, help='data_table_name' ) (options, args) = parser.parse_args() filename = args[0] @@ -68,7 +69,7 @@ sequence_id, sequence_name = get_id_name( params, dbkey=dbkey, fasta_description=options.fasta_description ) #build the index - build_bowtie2_index( data_manager_dict, options.fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, data_table_name=options.data_table_name or DEFAULT_DATA_TABLE_NAME ) + build_bowtie2_index( data_manager_dict, options.fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, data_table_names=options.data_table_name or DEFAULT_DATA_TABLE_NAMES ) #save info to json file open( filename, 'wb' ).write( dumps( data_manager_dict ) ) diff -r e0839cffd009 -r 8de13c28d92e data_manager/bowtie2_index_builder.xml --- a/data_manager/bowtie2_index_builder.xml Thu Mar 19 10:24:37 2015 -0400 +++ b/data_manager/bowtie2_index_builder.xml Tue Oct 13 10:17:27 2015 -0400 @@ -1,9 +1,9 @@ - + builder bowtie2 - bowtie2_index_builder.py "${out_file}" --fasta_filename "${all_fasta_source.fields.path}" --fasta_dbkey "${all_fasta_source.fields.dbkey}" --fasta_description "${all_fasta_source.fields.name}" --data_table_name "bowtie2_indexes" + bowtie2_index_builder.py "${out_file}" --fasta_filename "${all_fasta_source.fields.path}" --fasta_dbkey "${all_fasta_source.fields.dbkey}" --fasta_description "${all_fasta_source.fields.name}" --data_table_name "bowtie2_indexes" ${tophat2} @@ -14,6 +14,7 @@ + diff -r e0839cffd009 -r 8de13c28d92e data_manager_conf.xml --- a/data_manager_conf.xml Thu Mar 19 10:24:37 2015 -0400 +++ b/data_manager_conf.xml Tue Oct 13 10:17:27 2015 -0400 @@ -1,7 +1,7 @@ - + @@ -17,6 +17,19 @@ + + + + + + + + + ${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/bowtie2_index/${value}/${path} + abspath + + + - + diff -r e0839cffd009 -r 8de13c28d92e tool-data/all_fasta.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_fasta.loc.sample Tue Oct 13 10:17:27 2015 -0400 @@ -0,0 +1,18 @@ +#This file lists the locations and dbkeys of all the fasta files +#under the "genome" directory (a directory that contains a directory +#for each build). The script extract_fasta.py will generate the file +#all_fasta.loc. This file has the format (white space characters are +#TAB characters): +# +# +# +#So, all_fasta.loc could look something like this: +# +#apiMel3 apiMel3 Honeybee (Apis mellifera): apiMel3 /path/to/genome/apiMel3/apiMel3.fa +#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /path/to/genome/hg19/hg19canon.fa +#hg19full hg19 Human (Homo sapiens): hg19 Full /path/to/genome/hg19/hg19full.fa +# +#Your all_fasta.loc file should contain an entry for each individual +#fasta file. So there will be multiple fasta files for each build, +#such as with hg19 above. +# diff -r e0839cffd009 -r 8de13c28d92e tool-data/tophat2_indices.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/tophat2_indices.loc.sample Tue Oct 13 10:17:27 2015 -0400 @@ -0,0 +1,37 @@ +# tophat2_indices.loc.sample +# This is a *.loc.sample file distributed with Galaxy that enables tools +# to use a directory of indexed data files. This one is for Bowtie2 and Tophat2. +# See the wiki: http://wiki.galaxyproject.org/Admin/NGS%20Local%20Setup +# First create these data files and save them in your own data directory structure. +# Then, create a bowtie_indices.loc file to use those indexes with tools. +# Copy this file, save it with the same name (minus the .sample), +# follow the format examples, and store the result in this directory. +# The file should include an one line entry for each index set. +# The path points to the "basename" for the set, not a specific file. +# It has four text columns seperated by TABS. +# +# +# +# So, for example, if you had hg18 indexes stored in: +# +# /depot/data2/galaxy/hg19/bowtie2/ +# +# containing hg19 genome and hg19.*.bt2 files, such as: +# -rw-rw-r-- 1 james james 914M Feb 10 18:56 hg19canon.fa +# -rw-rw-r-- 1 james james 914M Feb 10 18:56 hg19canon.1.bt2 +# -rw-rw-r-- 1 james james 683M Feb 10 18:56 hg19canon.2.bt2 +# -rw-rw-r-- 1 james james 3.3K Feb 10 16:54 hg19canon.3.bt2 +# -rw-rw-r-- 1 james james 683M Feb 10 16:54 hg19canon.4.bt2 +# -rw-rw-r-- 1 james james 914M Feb 10 20:45 hg19canon.rev.1.bt2 +# -rw-rw-r-- 1 james james 683M Feb 10 20:45 hg19canon.rev.2.bt2 +# +# then the bowtie2_indices.loc entry could look like this: +# +#hg19 hg19 Human (hg19) /depot/data2/galaxy/hg19/bowtie2/hg19canon +# +#More examples: +# +#mm10 mm10 Mouse (mm10) /depot/data2/galaxy/mm10/bowtie2/mm10 +#dm3 dm3 D. melanogaster (dm3) /depot/data2/galaxy/mm10/bowtie2/dm3 +# +# diff -r e0839cffd009 -r 8de13c28d92e tool_data_table_conf.xml.sample --- a/tool_data_table_conf.xml.sample Thu Mar 19 10:24:37 2015 -0400 +++ b/tool_data_table_conf.xml.sample Tue Oct 13 10:17:27 2015 -0400 @@ -1,8 +1,18 @@ + + + value, dbkey, name, path + +
value, dbkey, name, path
+ + + value, dbkey, name, path + +