Mercurial > repos > devteam > data_manager_bowtie2_index_builder
changeset 13:8bf75f813413 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_bowtie2_index_builder commit 57d05675396f0b44265fb4dbc8f9f891c6073219
| author | iuc |
|---|---|
| date | Thu, 05 Dec 2024 06:46:58 +0000 |
| parents | 16230154ee87 |
| children | |
| files | data_manager/bowtie2_index_builder.py data_manager/bowtie2_index_builder.xml data_manager_conf.xml test-data/all_fasta.loc test-data/bowtie2_data_manager.1.json test-data/bowtie2_data_manager.2.json test-data/bowtie2_data_manager.json |
| diffstat | 7 files changed, 86 insertions(+), 105 deletions(-) [+] |
line wrap: on
line diff
--- a/data_manager/bowtie2_index_builder.py Sun Apr 16 08:25:58 2023 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,86 +0,0 @@ -#!/usr/bin/env python -# Dan Blankenberg -from __future__ import print_function - -import json -import optparse -import os -import subprocess -import sys - -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 - 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_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) - os.symlink(fasta_filename, sym_linked_fasta_filename) - args = ['bowtie2-build', sym_linked_fasta_filename, sequence_id] - threads = os.environ.get('GALAXY_SLOTS') - if threads: - args.extend(['--threads', threads]) - 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=dbkey, name=sequence_name, path=sequence_id) - 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', {}) - 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(): - 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='append', type="string", default=None, help='data_table_name') - (options, args) = parser.parse_args() - - filename = args[0] - - with open(filename) as fh: - params = json.load(fh) - 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_names=options.data_table_name or DEFAULT_DATA_TABLE_NAMES) - - # save info to json file - with open(filename, 'w') as fh: - json.dump(data_manager_dict, fh, sort_keys=True) - - -if __name__ == "__main__": - main()
--- a/data_manager/bowtie2_index_builder.xml Sun Apr 16 08:25:58 2023 +0000 +++ b/data_manager/bowtie2_index_builder.xml Thu Dec 05 06:46:58 2024 +0000 @@ -1,26 +1,57 @@ -<tool id="bowtie2_index_builder_data_manager" name="Bowtie2 index" tool_type="manage_data" version="@WRAPPER_VERSION@+galaxy0" profile="18.09"> +<tool id="bowtie2_index_builder_data_manager" name="Bowtie2 index" tool_type="manage_data" version="@WRAPPER_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.0"> <description>builder</description> + <macros> + <token name="@WRAPPER_VERSION@">2.5.4</token> + <token name="@VERSION_SUFFIX@">0</token> + </macros> <requirements> <requirement type="package" version="@WRAPPER_VERSION@">bowtie2</requirement> </requirements> - <macros> - <token name="@WRAPPER_VERSION@">2.4.4</token> - </macros> <command detect_errors="exit_code"><![CDATA[ - python '$__tool_directory__/bowtie2_index_builder.py' - '${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} + #set $value = $sequence_id or $all_fasta_source.fields.dbkey + #set $fasta_file_name = str($all_fasta_source.fields.path).split('/')[-1] + mkdir -p '${out_file.extra_files_path}' && + ln -s '${all_fasta_source.fields.path}' '${out_file.extra_files_path}/${fasta_file_name}' && + cd '${out_file.extra_files_path}' && + bowtie2-build --threads \${GALAXY_SLOTS:-1} '${out_file.extra_files_path}/${fasta_file_name}' '${value}' && + cp '$dmjson' '$out_file' ]]></command> + <configfiles> + <configfile name="dmjson"><![CDATA[#slurp +#set $fasta_file_name = str($all_fasta_source.fields.path).split('/')[-1] +#set $value = $sequence_id or $all_fasta_source.fields.dbkey +#set $name = $sequence_name or $all_fasta_source.fields.name +{ + "data_tables":{ + "bowtie2_indexes":[ + { + "value": "${value}", + "dbkey": "${all_fasta_source.fields.dbkey}", + "name": "${name}", + "path": "${fasta_file_name}" + } +#if $tophat2: + ], + "tophat2_indexes":[ + { + "value": "${value}", + "dbkey": "${all_fasta_source.fields.dbkey}", + "name": "${name}", + "path": "${fasta_file_name}" + } +#end if + ] + } +} +]]></configfile> + </configfiles> <inputs> <param name="all_fasta_source" type="select" label="Source FASTA Sequence"> <options from_data_table="all_fasta"/> </param> <param name="sequence_name" type="text" value="" label="Name of sequence" /> <param name="sequence_id" type="text" value="" label="ID for sequence" /> - <param name="tophat2" type="boolean" truevalue="--data_table_name tophat2_indexes" falsevalue="" checked="True" label="Also make available for TopHat" help="Adds values to tophat2_indexes tool data table" /> + <param name="tophat2" type="boolean" checked="True" label="Also make available for TopHat" help="Adds values to tophat2_indexes tool data table" /> </inputs> <outputs> <data name="out_file" format="data_manager_json"/> @@ -28,7 +59,14 @@ <tests> <test> <param name="all_fasta_source" value="phiX174"/> - <output name="out_file" value="bowtie2_data_manager.json"/> + <output name="out_file" value="bowtie2_data_manager.1.json"/> + </test> + <test> + <param name="all_fasta_source" value="phiX174"/> + <param name="sequence_name" value="Galeocerdo cuvier"/> + <param name="sequence_id" value="tigHai1"/> + <param name="tophat2" value="False"/> + <output name="out_file" file="bowtie2_data_manager.2.json"/> </test> </tests>
--- a/data_manager_conf.xml Sun Apr 16 08:25:58 2023 +0000 +++ b/data_manager_conf.xml Thu Dec 05 06:46:58 2024 +0000 @@ -1,6 +1,5 @@ <?xml version="1.0"?> <data_managers> - <data_manager tool_file="data_manager/bowtie2_index_builder.xml" id="bowtie2_index_builder"> <data_table name="bowtie2_indexes"> <output> @@ -10,9 +9,9 @@ <column name="path" output_ref="out_file" > <move type="directory" relativize_symlinks="True"> <!-- <source>${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/${value}</target> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">genomes/${dbkey}/bowtie_index/v2/${value}</target> </move> - <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/bowtie2_index/${value}/${path}</value_translation> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/genomes/${dbkey}/bowtie_index/v2/${value}/${path}</value_translation> <value_translation type="function">abspath</value_translation> </column> </output> @@ -25,11 +24,10 @@ <column name="name" /> <column name="path" output_ref="out_file" > <!-- no move, always happens as part of bowtie2 and uses that path --> - <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/bowtie2_index/${value}/${path}</value_translation> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/genomes/${dbkey}/bowtie_index/v2/${value}/${path}</value_translation> <value_translation type="function">abspath</value_translation> </column> </output> </data_table> </data_manager> - </data_managers>
--- a/test-data/all_fasta.loc Sun Apr 16 08:25:58 2023 +0000 +++ b/test-data/all_fasta.loc Thu Dec 05 06:46:58 2024 +0000 @@ -16,4 +16,4 @@ #fasta file. So there will be multiple fasta files for each build, #such as with hg19 above. # -phiX174 phiX174 phiX174 ${__HERE__}/phiX174.fasta +phiX174 phiX174 phiX 174 ${__HERE__}/phiX174.fasta
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/bowtie2_data_manager.1.json Thu Dec 05 06:46:58 2024 +0000 @@ -0,0 +1,20 @@ +{ + "data_tables":{ + "bowtie2_indexes":[ + { + "value": "phiX174", + "dbkey": "phiX174", + "name": "phiX 174", + "path": "phiX174.fasta" + } + ], + "tophat2_indexes":[ + { + "value": "phiX174", + "dbkey": "phiX174", + "name": "phiX 174", + "path": "phiX174.fasta" + } + ] + } +}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/bowtie2_data_manager.2.json Thu Dec 05 06:46:58 2024 +0000 @@ -0,0 +1,12 @@ +{ + "data_tables":{ + "bowtie2_indexes":[ + { + "value": "tigHai1", + "dbkey": "phiX174", + "name": "Galeocerdo cuvier", + "path": "phiX174.fasta" + } + ] + } +}
--- a/test-data/bowtie2_data_manager.json Sun Apr 16 08:25:58 2023 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -{"data_tables": {"bowtie2_indexes": [{"dbkey": "phiX174", "name": "phiX174", "path": "phiX174", "value": "phiX174"}], "tophat2_indexes": [{"dbkey": "phiX174", "name": "phiX174", "path": "phiX174", "value": "phiX174"}]}} \ No newline at end of file