Mercurial > repos > ieguinoa > data_manager_salmon_index_builder
changeset 6:d22f69a2e80e draft
Uploaded
author | ieguinoa |
---|---|
date | Tue, 23 Jul 2019 09:25:04 -0400 |
parents | 3888ec1918d0 |
children | 954d617c323d |
files | data_manager/salmon_index_builder.py data_manager/salmon_index_builder.xml data_manager_conf.xml tool-data/all_fasta.loc.sample tool-data/salmon_indexes.loc.sample tool_data_table_conf.xml.sample |
diffstat | 6 files changed, 42 insertions(+), 17 deletions(-) [+] |
line wrap: on
line diff
--- a/data_manager/salmon_index_builder.py Thu Jan 03 10:51:18 2019 -0500 +++ b/data_manager/salmon_index_builder.py Tue Jul 23 09:25:04 2019 -0400 @@ -8,7 +8,7 @@ import sys from json import dumps, loads -DEFAULT_DATA_TABLE_NAME = "salmon_indexes" +DEFAULT_DATA_TABLE_NAME = "salmon_indexes_versioned" def get_id_name( params, dbkey, fasta_description=None): @@ -30,19 +30,17 @@ target_directory = params[ 'output_data' ][0]['extra_files_path'] if not os.path.exists( target_directory ): os.mkdir( target_directory ) - path=sequence_id args = [ 'salmon', 'index' ] if options.kmer_size != '': args.append('-k') args.append(options.kmer_size) - path=path + '_kmer_'+ options.kmer_size - args.extend( [ '-t' , options.fasta_filename, '-i', target_directory ] ) + args.extend( [ '-t', options.fasta_filename, '-i', target_directory ] ) proc = subprocess.Popen( args=args, shell=False) return_code = proc.wait() if return_code: print("Error building index.", file=sys.stderr) sys.exit( return_code ) - data_table_entry = dict( value=sequence_id, dbkey=options.fasta_dbkey, name=sequence_name, path=path ) + data_table_entry = dict( value=sequence_id, dbkey=options.fasta_dbkey, name=sequence_name, path=sequence_id, version=options.index_version ) _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry )
--- a/data_manager/salmon_index_builder.xml Thu Jan 03 10:51:18 2019 -0500 +++ b/data_manager/salmon_index_builder.xml Tue Jul 23 09:25:04 2019 -0400 @@ -1,8 +1,11 @@ <tool id="salmon_index_builder_data_manager" name="Salmon" tool_type="manage_data" version="0.9.1"> <description>index builder</description> <requirements> - <requirement type="package" version="0.9.1">salmon</requirement> + <requirement type="package" version="0.11.2">salmon</requirement> </requirements> + <macros> + <token name="@IDX_VERSION@">q5</token> + </macros> <command detect_errors="exit_code"><![CDATA[ python '$__tool_directory__/salmon_index_builder.py' --output '${out_file}' --fasta_filename '${all_fasta_source.fields.path}' @@ -10,6 +13,7 @@ --fasta_description '${all_fasta_source.fields.name}' --kmer_size "${kmer_size}" --data_table_name salmon_indexes + --index_version @IDX_VERSION@ ]]> </command> <inputs>
--- a/data_manager_conf.xml Thu Jan 03 10:51:18 2019 -0500 +++ b/data_manager_conf.xml Tue Jul 23 09:25:04 2019 -0400 @@ -9,11 +9,12 @@ <column name="path" output_ref="out_file" > <move type="directory" relativize_symlinks="True"> <!-- <source>${path}</source>--> <!-- out_file.extra_files_path is used as base by default --> <!-- if no source, eg for type=directory, then refers to base --> - <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${dbkey}/salmon_index/${path}</target> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${dbkey}/salmon_index/${value}</target> </move> - <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/salmon_index/${path}</value_translation> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/salmon_index/${value}/${path}</value_translation> <value_translation type="function">abspath</value_translation> </column> + <column name="version" /> </output> </data_table> </data_manager>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_fasta.loc.sample Tue Jul 23 09:25:04 2019 -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): +# +#<unique_build_id> <dbkey> <display_name> <file_path> +# +#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. +#
--- a/tool-data/salmon_indexes.loc.sample Thu Jan 03 10:51:18 2019 -0500 +++ b/tool-data/salmon_indexes.loc.sample Tue Jul 23 09:25:04 2019 -0400 @@ -1,28 +1,32 @@ -# salmon_indexes.loc.sample +# salmon_indexes_versioned.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 Salmon. # 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 kallisto_indexes.loc file to use those indexes with tools. +# Then, create a salmon_indexes_versioned.loc.sample 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. # -# <unique_build_id> <dbkey> <display_name> <file_base_path> +# <unique_build_id> <dbkey> <display_name> <file_base_path> <version> # +# The <version> column can be retrieved from the header.json file in the index folder. e.g "IndexVersion": "q5" + + + # So, for example, if you had sacCer3 indexes stored in: # # /depot/data2/galaxy/sacCer3/salmon_indexes/ # # then the salmon_indexes.loc entry could look like this: # -#sacCer3 sacCer3 S. cerevisiae Apr. 2011 (SacCer_Apr2011/sacCer3) (sacCer3) /depot/data2/galaxy/sacCer3/salmon_indexes +#sacCer3 sacCer3 S. cerevisiae Apr. 2011 (SacCer_Apr2011/sacCer3) (sacCer3) /depot/data2/galaxy/sacCer3/salmon_indexes/version_3/ q6 # #More examples: # -#mm10 mm10 Mouse (mm10) /depot/data2/galaxy/salmon_indexes/mm10 -#dm3 dm3 D. melanogaster (dm3) /depot/data2/galaxy/salmon_indexes/dm3 +#mm10 mm10 Mouse (mm10) /depot/data2/galaxy/salmon_indexes/mm10/version_2 q4 +#dm3 dm3 D. melanogaster (dm3) /depot/data2/galaxy/salmon_indexes/dm3/version_1 q5 # #
--- a/tool_data_table_conf.xml.sample Thu Jan 03 10:51:18 2019 -0500 +++ b/tool_data_table_conf.xml.sample Tue Jul 23 09:25:04 2019 -0400 @@ -1,7 +1,7 @@ <tables> <!-- Locations of indexes in salmon mapper format --> - <table name="salmon_indexes" comment_char="#" allow_duplicate_entries="False"> - <columns>value, dbkey, name, path</columns> - <file path="tool-data/salmon_indexes.loc" /> + <table name="salmon_indexes_versioned" comment_char="#" allow_duplicate_entries="False"> + <columns>value, dbkey, name, path, version</columns> + <file path="tool-data/salmon_indexes_versioned.loc" /> </table> </tables>