Mercurial > repos > devteam > data_manager_bowtie2_index_builder
changeset 0:9458af1ab90b draft
Uploaded
author | devteam |
---|---|
date | Tue, 14 Apr 2015 12:06:01 -0400 |
parents | |
children | 9bf4eb559ed5 |
files | .shed.yml data_manager/bowtie2_index_builder.py data_manager/bowtie2_index_builder.xml data_manager_conf.xml tool-data/all_fasta.loc.sample tool-data/bowtie2_indices.loc.sample tool_data_table_conf.xml.sample tool_dependencies.xml |
diffstat | 8 files changed, 205 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/.shed.yml Tue Apr 14 12:06:01 2015 -0400 @@ -0,0 +1,4 @@ +# repository published to https://toolshed.g2.bx.psu.edu/repos/devteam/data_manager_bowtie2_index_builder +owner: devteam +name: data_manager_bowtie2_index_builder +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/bowtie2_index_builder.py Tue Apr 14 12:06:01 2015 -0400 @@ -0,0 +1,76 @@ +#!/usr/bin/env python +#Dan Blankenberg + +import sys +import os +import optparse +import subprocess + +from json import loads, dumps + + +DEFAULT_DATA_TABLE_NAME = "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 + sequence_id = params['param_dict']['sequence_id'] + if not sequence_id: + sequence_id = dbkey + + sequence_name = params['param_dict']['sequence_name'] + if not sequence_name: + sequence_name = fasta_description + if not sequence_name: + 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 ): + #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 ) + os.symlink( fasta_filename, sym_linked_fasta_filename ) + args = [ 'bowtie2-build', sym_linked_fasta_filename, sequence_id ] + proc = subprocess.Popen( args=args, shell=False, cwd=target_directory ) + return_code = proc.wait() + if return_code: + 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 ) + +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', {} ) + data_manager_dict['data_tables'][ data_table_name ] = data_manager_dict['data_tables'].get( data_table_name, [] ) + data_manager_dict['data_tables'][ data_table_name ].append( data_table_entry ) + return data_manager_dict + +def main(): + #Parse Command Line + parser = optparse.OptionParser() + 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' ) + (options, args) = parser.parse_args() + + filename = args[0] + + params = loads( open( filename ).read() ) + target_directory = params[ 'output_data' ][0]['extra_files_path'] + os.mkdir( target_directory ) + data_manager_dict = {} + + dbkey = options.fasta_dbkey + + if dbkey in [ None, '', '?' ]: + raise Exception( '"%s" is not a valid dbkey. You must specify a valid dbkey.' % ( dbkey ) ) + + 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 ) + + #save info to json file + open( filename, 'wb' ).write( dumps( data_manager_dict ) ) + +if __name__ == "__main__": main()
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/bowtie2_index_builder.xml Tue Apr 14 12:06:01 2015 -0400 @@ -0,0 +1,29 @@ +<tool id="bowtie2_index_builder_data_manager" name="Bowtie2 index" tool_type="manage_data" version="0.0.1"> + <description>builder</description> + <requirements> + <requirement type="package" version="2.2.4">bowtie2</requirement> + </requirements> + <command interpreter="python">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"</command> + <stdio> + <exit_code range=":-1" /> + <exit_code range="1:" /> + </stdio> + <inputs> + <param name="all_fasta_source" type="select" label="Source FASTA Sequence"> + <options from_data_table="all_fasta"/> + </param> + <param type="text" name="sequence_name" value="" label="Name of sequence" /> + <param type="text" name="sequence_id" value="" label="ID for sequence" /> + </inputs> + <outputs> + <data name="out_file" format="data_manager_json"/> + </outputs> + + <help> + +.. class:: infomark + +**Notice:** If you leave name, description, or id blank, it will be generated automatically. + + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager_conf.xml Tue Apr 14 12:06:01 2015 -0400 @@ -0,0 +1,22 @@ +<?xml version="1.0"?> +<data_managers> + + <data_manager tool_file="data_manager/bowtie2_index_builder.xml" id="bowtie2_index_builder" version="0.0.1"> + <data_table name="bowtie2_indexes"> + <output> + <column name="value" /> + <column name="dbkey" /> + <column name="name" /> + <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}">${dbkey}/bowtie2_index/${value}</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/bowtie2_index/${value}/${path}</value_translation> + <value_translation type="function">abspath</value_translation> + </column> + </output> + </data_table> + </data_manager> + +</data_managers>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_fasta.loc.sample Tue Apr 14 12:06:01 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): +# +#<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. +#
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/bowtie2_indices.loc.sample Tue Apr 14 12:06:01 2015 -0400 @@ -0,0 +1,37 @@ +# bowtie2_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. +# +# <unique_build_id> <dbkey> <display_name> <file_base_path> +# +# 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 +# +#
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Tue Apr 14 12:06:01 2015 -0400 @@ -0,0 +1,13 @@ +<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc--> +<tables> + <!-- Locations of all fasta files under genome directory --> + <table name="all_fasta" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/all_fasta.loc" /> + </table> + <!-- Locations of indexes in the Bowtie2 mapper format --> + <table name="bowtie2_indexes" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/bowtie2_indices.loc" /> + </table> +</tables>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Tue Apr 14 12:06:01 2015 -0400 @@ -0,0 +1,6 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="bowtie2" version="2.2.4"> + <repository changeset_revision="172979b6bf77" name="package_bowtie_2_2_4" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + </package> +</tool_dependency>