Mercurial > repos > devteam > data_manager_bwa_mem_index_builder
changeset 10:74dbe9e6c888 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_bwa_mem_index_builder commit 57d05675396f0b44265fb4dbc8f9f891c6073219
| author | iuc |
|---|---|
| date | Thu, 05 Dec 2024 06:47:18 +0000 |
| parents | 0429479e3821 |
| children | |
| files | data_manager/bwa_mem_index_builder.py data_manager/bwa_mem_index_builder.xml data_manager_conf.xml test-data/all_fasta.loc test-data/bwa_mem_data_manager.1.json test-data/bwa_mem_data_manager.2.json test-data/bwa_mem_data_manager.json |
| diffstat | 7 files changed, 70 insertions(+), 118 deletions(-) [+] |
line wrap: on
line diff
--- a/data_manager/bwa_mem_index_builder.py Sun Apr 16 08:27:00 2023 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,102 +0,0 @@ -#!/usr/bin/env python -# Dan Blankenberg -from __future__ import print_function - -import json -import optparse -import os -import subprocess -import sys - -CHUNK_SIZE = 2**20 -TWO_GB = 2**30 * 2 -DEFAULT_DATA_TABLE_NAME = "bwa_mem_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_bwa_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) - if params['param_dict']['index_algorithm'] == 'automatic': - if os.stat(fasta_filename).st_size < TWO_GB: # use 2 GB as cut off for memory vs. max of 2gb database size; this is somewhat arbitrary - index_algorithm = 'is' - else: - index_algorithm = 'bwtsw' - else: - index_algorithm = params['param_dict']['index_algorithm'] - - args = ['bwa', 'index', '-a', index_algorithm] - args.append(sym_linked_fasta_filename) - 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=fasta_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(): - 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] - - 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_bwa_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 - with open(filename, 'w') as fh: - json.dump(data_manager_dict, fh, sort_keys=True) - - -if __name__ == "__main__": - main()
--- a/data_manager/bwa_mem_index_builder.xml Sun Apr 16 08:27:00 2023 +0000 +++ b/data_manager/bwa_mem_index_builder.xml Thu Dec 05 06:47:18 2024 +0000 @@ -1,17 +1,42 @@ -<tool id="bwa_mem_index_builder_data_manager" name="BWA-MEM index" tool_type="manage_data" version="0.0.5" profile="19.05"> +<tool id="bwa_mem_index_builder_data_manager" name="BWA-MEM index" tool_type="manage_data" version="@WRAPPER_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.0"> <description>builder</description> + <macros> + <token name="@WRAPPER_VERSION@">0.7.18</token> + <token name="@VERSION_SUFFIX@">0</token> + </macros> <requirements> - <requirement type="package" version="0.7.17">bwa</requirement> - <requirement type="package" version="3.7">python</requirement> + <requirement type="package" version="@WRAPPER_VERSION@">bwa</requirement> </requirements> <command detect_errors="exit_code"><![CDATA[ - python '$__tool_directory__/bwa_mem_index_builder.py' - '${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 bwa_mem_indexes + #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}' && + bwa index + #if $index_algorithm != 'automatic': + -a '$index_algorithm' + #end if + '${out_file.extra_files_path}/${fasta_file_name}' && + 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 $all_fasta_source.fields.name +{ + "data_tables":{ + "bwa_mem_indexes":[ + { + "value": "${value}", + "dbkey": "${all_fasta_source.fields.dbkey}", + "name": "${name}", + "path": "${fasta_file_name}" + } + ] + } +} +]]></configfile> + </configfiles> <inputs> <param name="all_fasta_source" type="select" label="Source FASTA Sequence"> <options from_data_table="all_fasta"/> @@ -23,6 +48,7 @@ <option value="automatic" selected="true">Guess automatically (2GB cut-off)</option> <option value="is">IS linear-time algorithm (for small genomes)</option> <option value="bwtsw">BWT-SW (for large genomes)</option> + <option value="rb2">RB2</option> </param> </inputs> <outputs> @@ -31,7 +57,14 @@ <tests> <test> <param name="all_fasta_source" value="phiX174"/> - <output name="out_file" value="bwa_mem_data_manager.json"/> + <output name="out_file" value="bwa_mem_data_manager.1.json"/> + </test> + <test> + <param name="all_fasta_source" value="phiX174"/> + <param name="sequence_name" value="Galeocerdo cuvier"/> + <param name="sequence_id" value="tigHai1"/> + <param name="index_algorithm" value="bwtsw"/> + <output name="out_file" file="bwa_mem_data_manager.2.json"/> </test> </tests> <help>
--- a/data_manager_conf.xml Sun Apr 16 08:27:00 2023 +0000 +++ b/data_manager_conf.xml Thu Dec 05 06:47:18 2024 +0000 @@ -1,6 +1,5 @@ <?xml version="1.0"?> <data_managers> - <data_manager tool_file="data_manager/bwa_mem_index_builder.xml" id="bwa_mem_index_builder"> <data_table name="bwa_mem_indexes"> <output> @@ -10,13 +9,12 @@ <column name="path" output_ref="out_file" > <move type="directory" relativize_symlinks="True"> <!-- <source>${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}/bwa_mem_index/${value}</target> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">genomes/${dbkey}/bwa_mem_index/v1/${value}</target> </move> - <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/bwa_mem_index/${value}/${path}</value_translation> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/genomes/${dbkey}/bwa_mem_index/v1/${value}/${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 08:27:00 2023 +0000 +++ b/test-data/all_fasta.loc Thu Dec 05 06:47:18 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/bwa_mem_data_manager.1.json Thu Dec 05 06:47:18 2024 +0000 @@ -0,0 +1,12 @@ +{ + "data_tables":{ + "bwa_mem_indexes":[ + { + "value": "phiX174", + "dbkey": "phiX174", + "name": "phiX 174", + "path": "phiX174.fasta" + } + ] + } +}