| Next changeset 1:18e2dd472525 (2020-11-22) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_kallisto_index_builder commit 3b54163c4f7daff76fcc589c4a9057bb03904380 |
|
added:
data_manager/kallisto_index_builder.py data_manager/kallisto_index_builder.xml data_manager_conf.xml tool-data/all_fasta.loc.sample tool-data/kallisto_indexes.loc.sample tool_data_table_conf.xml.sample |
| b |
| diff -r 000000000000 -r 6843a0db2da0 data_manager/kallisto_index_builder.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/kallisto_index_builder.py Sat Aug 05 04:02:01 2017 -0400 |
| [ |
| @@ -0,0 +1,82 @@ +#!/usr/bin/env python +# Based heavily on the Bowtie 2 data manager wrapper script by Dan Blankenberg +from __future__ import print_function + +import argparse +import os +import subprocess +import sys +from json import dumps, loads + +DEFAULT_DATA_TABLE_NAME = "kallisto_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_kallisto_index( data_manager_dict, options, params, sequence_id, sequence_name ): + data_table_name = options.data_table_name or DEFAULT_DATA_TABLE_NAME + target_directory = params[ 'output_data' ][0]['extra_files_path'] + if not os.path.exists( target_directory ): + os.mkdir( target_directory ) + fasta_base_name = os.path.split( options.fasta_filename )[-1] + sym_linked_fasta_filename = os.path.join( target_directory, fasta_base_name ) + os.symlink( options.fasta_filename, sym_linked_fasta_filename ) + args = [ 'kallisto', 'index' ] + args.extend( [ sym_linked_fasta_filename, '-i', sequence_id ] ) + proc = subprocess.Popen( args=args, shell=False, cwd=target_directory ) + 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=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 = argparse.ArgumentParser() + parser.add_argument( '--output', dest='output', action='store', type=str, default=None ) + parser.add_argument( '--fasta_filename', dest='fasta_filename', action='store', type=str, default=None ) + parser.add_argument( '--fasta_dbkey', dest='fasta_dbkey', action='store', type=str, default=None ) + parser.add_argument( '--fasta_description', dest='fasta_description', action='store', type=str, default=None ) + parser.add_argument( '--data_table_name', dest='data_table_name', action='store', type=str, default='kallisto_indexes' ) + options = parser.parse_args() + + filename = options.output + + params = loads( open( filename ).read() ) + data_manager_dict = {} + + if options.fasta_dbkey in [ None, '', '?' ]: + raise Exception( '"%s" is not a valid dbkey. You must specify a valid dbkey.' % ( options.fasta_dbkey ) ) + + sequence_id, sequence_name = get_id_name( params, dbkey=options.fasta_dbkey, fasta_description=options.fasta_description ) + + # build the index + build_kallisto_index( data_manager_dict, options, params, sequence_id, sequence_name ) + + # save info to json file + open( filename, 'w' ).write( dumps( data_manager_dict ) ) + + +if __name__ == "__main__": + main() |
| b |
| diff -r 000000000000 -r 6843a0db2da0 data_manager/kallisto_index_builder.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/kallisto_index_builder.xml Sat Aug 05 04:02:01 2017 -0400 |
| [ |
| @@ -0,0 +1,51 @@ +<tool id="kallisto_index_builder_data_manager" name="Kallisto" tool_type="manage_data" version="0.43.1"> + <description>index builder</description> + <requirements> + <requirement type="package" version="0.43.1">kallisto</requirement> + </requirements> + <command detect_errors="exit_code"><![CDATA[ + python '$__tool_directory__/kallisto_index_builder.py' --output '${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 kallisto_indexes + ]]> + </command> + <inputs> + <param label="Source FASTA Sequence" name="all_fasta_source" type="select"> + <options from_data_table="all_fasta" /> + </param> + <param name="sequence_name" type="text" value="" label="Name of sequence" /> + <param name="sequence_id" type="text" value="" label="ID for sequence" /> + </inputs> + <outputs> + <data name="out_file" format="data_manager_json" /> + </outputs> + <help> +<![CDATA[ +.. class:: infomark + +**Notice:** If you leave name, description, or id blank, it will be generated automatically. + +What is Kallisto? +--------------- + +`kallisto <https://pachterlab.github.io/kallisto/about>`__ is a program for +quantifying abundances of transcripts from RNA-Seq data, or more generally of +target sequences using high-throughput sequencing reads. It is based on the +novel idea of pseudoalignment for rapidly determining the compatibility of +reads with targets, without the need for alignment. On benchmarks with standard +RNA-Seq data, kallisto can quantify 30 million human reads in less than 3 +minutes on a Mac desktop computer using only the read sequences and a +transcriptome index that itself takes less than 10 minutes to build. +Pseudoalignment of reads preserves the key information needed for +quantification, and kallisto is therefore not only fast, but also as accurate +as existing quantification tools. In fact, because the pseudoalignment +procedure is robust to errors in the reads, in many benchmarks kallisto +significantly outperforms existing tools. +]]> + </help> + <citations> + <citation type="doi">10.1038/nmeth.3317</citation> + </citations> +</tool> |
| b |
| diff -r 000000000000 -r 6843a0db2da0 data_manager_conf.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager_conf.xml Sat Aug 05 04:02:01 2017 -0400 |
| b |
| @@ -0,0 +1,20 @@ +<?xml version="1.0"?> +<data_managers> + <data_manager tool_file="data_manager/kallisto_index_builder.xml" id="kallisto_index_builder" version="0.43.1"> + <data_table name="kallisto_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}/kallisto_index/${value}</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/kallisto_index/${value}/${path}</value_translation> + <value_translation type="function">abspath</value_translation> + </column> + </output> + </data_table> + </data_manager> +</data_managers> \ No newline at end of file |
| b |
| diff -r 000000000000 -r 6843a0db2da0 tool-data/all_fasta.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_fasta.loc.sample Sat Aug 05 04:02:01 2017 -0400 |
| b |
| @@ -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. +# |
| b |
| diff -r 000000000000 -r 6843a0db2da0 tool-data/kallisto_indexes.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/kallisto_indexes.loc.sample Sat Aug 05 04:02:01 2017 -0400 |
| b |
| @@ -0,0 +1,33 @@ +# kallisto_indexes.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 kallisto. +# 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. +# 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 sacCer3 indexes stored in: +# +# /depot/data2/galaxy/sacCer3/kallisto_indexes/ +# +# containing sacCer3 genome and sacCer3.*.ht2 files, such as: +# +# -rw-rw-r-- 1 dave dave 12M Sep 23 13:57 sacCer3.fa +# -rw-rw-r-- 1 dave dave 2.9M Sep 23 13:57 sacCer3.kallisto +# +# then the kallisto_indexes.loc entry could look like this: +# +#sacCer3 sacCer3 S. cerevisiae Apr. 2011 (SacCer_Apr2011/sacCer3) (sacCer3) /depot/data2/galaxy/sacCer3/kallisto_indexes/sacCer3.kallisto +# +#More examples: +# +#mm10 mm10 Mouse (mm10) /depot/data2/galaxy/kallisto_indexes/mm10 +#dm3 dm3 D. melanogaster (dm3) /depot/data2/galaxy/kallisto_indexes/dm3 +# +# |
| b |
| diff -r 000000000000 -r 6843a0db2da0 tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Sat Aug 05 04:02:01 2017 -0400 |
| b |
| @@ -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="#" allow_duplicate_entries="False"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/all_fasta.loc" /> + </table> + <!-- Locations of indexes in the kallisto mapper format --> + <table name="kallisto_indexes" comment_char="#" allow_duplicate_entries="False"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/kallisto_indexes.loc" /> + </table> +</tables> |