Mercurial > repos > jjohnson > data_manager_ucsc_twobit_index_builder
changeset 0:c26087dbccbd draft default tip
Uploaded
author | jjohnson |
---|---|
date | Fri, 05 Jul 2013 15:34:05 -0400 (2013-07-05) |
parents | |
children | |
files | README data_manager/data_manager_ucsc_twobit_index_builder.py data_manager/data_manager_ucsc_twobit_index_builder.xml data_manager_conf.xml tool-data/all_fasta.loc.sample tool-data/twobit.loc.sample tool_data_table_conf.xml.sample tool_dependencies.xml |
diffstat | 8 files changed, 180 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README Fri Jul 05 15:34:05 2013 -0400 @@ -0,0 +1,1 @@ +TODO \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/data_manager_ucsc_twobit_index_builder.py Fri Jul 05 15:34:05 2013 -0400 @@ -0,0 +1,74 @@ +#!/usr/bin/env python +#Dan Blankenberg + +import sys +import os +import tempfile +import optparse +import subprocess + +from galaxy.util.json import from_json_string, to_json_string + +CHUNK_SIZE = 2**20 + +DEFAULT_DATA_TABLE_NAME = "twobit" + +def build_twobit_index( data_manager_dict, fasta_filename, target_directory, dbkey, data_table_name=DEFAULT_DATA_TABLE_NAME ): + #TODO: allow multiple FASTA input files + fasta_base_name = os.path.split( fasta_filename )[-1] + twobit_base_name = os.path.splitext(fasta_base_name)[0] + '.2bit' + twobit_path = os.path.join( target_directory,twobit_base_name ) + sym_linked_fasta_filename = os.path.join( target_directory, fasta_base_name ) + os.symlink( fasta_filename, sym_linked_fasta_filename ) + + args = [ 'faToTwoBit' ] + args.append( sym_linked_fasta_filename ) + args.append( twobit_path ) + tmp_stderr = tempfile.NamedTemporaryFile( prefix = "tmp-data-manager-twobit_builder-stderr" ) + proc = subprocess.Popen( args=args, shell=False, cwd=target_directory, stderr=tmp_stderr.fileno() ) + return_code = proc.wait() + if return_code: + tmp_stderr.flush() + tmp_stderr.seek( 0 ) + sys.stderr.write( "Error building index:\n" ) + while True: + chunk = tmp_stderr.read( CHUNK_SIZE ) + if not chunk: + break + sys.stderr.write( chunk ) + sys.exit( return_code ) + tmp_stderr.close() + data_table_entry = dict( value=dbkey, path=twobit_base_name ) + _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( '-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 = from_json_string( open( filename ).read() ) + target_directory = params[ 'output_data' ][0]['extra_files_path'] + os.mkdir( target_directory ) + data_manager_dict = {} + + if options.fasta_dbkey in [ None, '', '?' ]: + raise Exception( '"%s" is not a valid dbkey. You must specify a valid dbkey.' % ( dbkey ) ) + + #build the index + build_twobit_index( data_manager_dict, options.fasta_filename, target_directory, options.fasta_dbkey, data_table_name=options.data_table_name or DEFAULT_DATA_TABLE_NAME ) + + #save info to json file + open( filename, 'wb' ).write( to_json_string( data_manager_dict ) ) + +if __name__ == "__main__": main()
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/data_manager_ucsc_twobit_index_builder.xml Fri Jul 05 15:34:05 2013 -0400 @@ -0,0 +1,23 @@ +<tool id="data_manager_ucsc_twobit_index_builder" name="UCSC TwoBit index" tool_type="manage_data" version="0.0.1"> + <description>builder</description> + <requirements> + <requirement type="package" version="latest">kent</requirement> + </requirements> + <command interpreter="python">data_manager_ucsc_twobit_index_builder.py "${out_file}" --fasta_filename "${all_fasta_source.fields.path}" --fasta_dbkey "${all_fasta_source.fields.dbkey}" --data_table_name "twobit"</command> + <inputs> + <param name="all_fasta_source" type="select" label="Source FASTA Sequence"> + <options from_data_table="all_fasta"/> + </param> + </inputs> + <outputs> + <data name="out_file" format="data_manager_json"/> + </outputs> + + <help> + +.. class:: infomark + +**Notice:** If you leave name, description, or id blank, it will be generated automatically. + + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager_conf.xml Fri Jul 05 15:34:05 2013 -0400 @@ -0,0 +1,21 @@ +<?xml version="1.0"?> +<data_managers> + + <data_manager tool_file="data_manager/data_manager_ucsc_twobit_index_builder.xml" id="ucsc_towbit_index_builder" version="0.0.1"> + <data_table name="twobit"> + <output> + <column name="line_type" /> + <column name="value" /> + <column name="path" output_ref="out_file" > + <move type="directory" relativize_symlinks="True"> + <!-- <source>${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="${GALAXY_DATA_MANAGER_DATA_PATH}">${value}/twobit/${value}</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${value}/twobit/${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 Fri Jul 05 15:34:05 2013 -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/twobit.loc.sample Fri Jul 05 15:34:05 2013 -0400 @@ -0,0 +1,26 @@ +#This is a sample file distributed with Galaxy that is used by some +#tools. The twobit.loc file has this format (white space characters +#are TAB characters): +# +#<Build> <FullPathToFile> +# +#So, for example, if you had droPer1 twobit files stored in +#/depot/data2/galaxy/droPer1/, then the twobit.loc entry +#would look like this: +# +#droPer1 /depot/data2/galaxy/droPer1/droPer1.2bit +# +#and your /depot/data2/galaxy/droPer1/ directory would +#contain all of your twobit files (e.g.): +# +#-rw-rw-r-- 1 nate galaxy 48972650 2007-05-04 11:27 droPer1.2bit +#...etc... +# +#Your twobit.loc file should include an entry per line for each twobit +#file you have stored. For example: +# +#droPer1 /depot/data2/galaxy/droPer1/droPer1.2bit +#apiMel2 /depot/data2/galaxy/apiMel2/apiMel2.2bit +#droAna1 /depot/data2/galaxy/droAna1/droAna1.2bit +#droAna2 /depot/data2/galaxy/droAna2/droAna2.2bit +#...etc...
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Fri Jul 05 15:34:05 2013 -0400 @@ -0,0 +1,12 @@ +<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 genome reference in the UCSC twobit format --> + <table name="twobit" comment_char="#"> + <columns>value, path</columns> + <file path="tool-data/twobit.loc" /> + </table> +</tables>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Fri Jul 05 15:34:05 2013 -0400 @@ -0,0 +1,5 @@ +<tool_dependency> + <package name="kent" version="latest"> + <repository changeset_revision="b05b788e3989" name="package_kent" owner="jjohnson" toolshed="http://testtoolshed.g2.bx.psu.edu" /> + </package> +</tool_dependency>