Mercurial > repos > greg > data_manager_malt_index_builder
changeset 1:787f1ca9045a draft default tip
Uploaded
| author | greg |
|---|---|
| date | Wed, 13 Oct 2021 20:12:48 +0000 |
| parents | d69ebf52c233 |
| children | |
| files | data_manager/malt_index_builder.py data_manager/malt_index_builder.xml data_manager_conf.xml test-data/malt_index_builder.json test-data/malt_index_builder1.json test-data/malt_index_builder2.json tool_data_table_conf.xml.sample |
| diffstat | 7 files changed, 83 insertions(+), 43 deletions(-) [+] |
line wrap: on
line diff
--- a/data_manager/malt_index_builder.py Tue Oct 12 14:15:35 2021 +0000 +++ b/data_manager/malt_index_builder.py Wed Oct 13 20:12:48 2021 +0000 @@ -6,8 +6,6 @@ import subprocess import sys -DEFAULT_DATA_TABLE_NAME = "malt_indices" - def get_id_name(params, dbkey, fasta_description=None): sequence_id = params['param_dict']['sequence_id'] @@ -22,29 +20,40 @@ return sequence_id, sequence_name -def build_malt_index(data_manager_dict, fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, sequence_type, shapes, max_hits_per_seed, protein_reduct, data_table_name=DEFAULT_DATA_TABLE_NAME): +def build_malt_index(data_manager_dict, fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, sequence_type, shapes, max_hits_per_seed, protein_reduct): + # The malt-build program produces a directory of files, + # so the data table path entry will be a directory and + # not an index file. 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 = ['malt-build', '--input', sym_linked_fasta_filename, '--sequenceType', sequence_type, '--index', 'index'] + args = ['malt-build', '--input', sym_linked_fasta_filename, '--sequenceType', sequence_type, '--index', target_directory] threads = os.environ.get('GALAXY_SLOTS') if threads: args.extend(['--threads', threads]) if shapes is not None: - args.extend('--shapes', shapes) + args.extend(['--shapes', shapes]) if max_hits_per_seed is not None: - args.extend('--maxHitsPerSeed', max_hits_per_seed) + args.extend(['--maxHitsPerSeed', max_hits_per_seed]) if protein_reduct is not None: - args.extend('--proteinReduct', protein_reduct) + args.extend(['--proteinReduct', protein_reduct]) proc = subprocess.Popen(args=args, shell=False, cwd=target_directory) return_code = proc.wait() if return_code: sys.exit('Error building index, return_code: %d' % 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) + # Remove unwanted files from the output directory. + os.remove(sym_linked_fasta_filename) + # The path entry here is the directory + # where the index files will be located, + # not a single index file (malt-build + # produces a directory if files, which + # is considered an index.. + data_table_entry = dict(value=sequence_id, dbkey=dbkey, name=sequence_name, path=None) + _add_data_table_entry(data_manager_dict, data_table_entry) -def _add_data_table_entry(data_manager_dict, data_table_name, data_table_entry): +def _add_data_table_entry(data_manager_dict, data_table_entry): + data_table_name = "malt_indices" 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) @@ -58,7 +67,7 @@ parser.add_option('-t', '--fasta_description', dest='fasta_description', action='store', type="string", default=None, help='fasta description') parser.add_option('-e', '--sequence_type', dest='sequence_type', action='store', type="string", help='DNA or Protein sequences') parser.add_option('-p', '--shapes', dest='shapes', action='store', type="string", default=None, help='Comma-separated list of seed shapes') - parser.add_option('-m', '--max_hits_per_seed', dest='max_hits_per_seed', action='store', type="int", default=None, help='Maximum number of hits per seed') + parser.add_option('-m', '--max_hits_per_seed', dest='max_hits_per_seed', action='store', type="string", default=None, help='Maximum number of hits per seed') parser.add_option('-r', '--protein_reduct', dest='protein_reduct', action='store', type="string", default=None, help='Name or definition of protein alphabet reduction') (options, args) = parser.parse_args() @@ -78,7 +87,7 @@ sequence_id, sequence_name = get_id_name(params, dbkey=dbkey, fasta_description=options.fasta_description) # Build the index. - build_malt_index(data_manager_dict, options.fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, options.sequence_type, options.shapes, options.max_hits_per_seed, options.protein_reduct, data_table_name=DEFAULT_DATA_TABLE_NAME) + build_malt_index(data_manager_dict, options.fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, options.sequence_type, options.shapes, options.max_hits_per_seed, options.protein_reduct) # Save info to json file. with open(filename, 'w') as fh:
--- a/data_manager/malt_index_builder.xml Tue Oct 12 14:15:35 2021 +0000 +++ b/data_manager/malt_index_builder.xml Wed Oct 13 20:12:48 2021 +0000 @@ -10,40 +10,32 @@ --fasta_dbkey '${all_fasta_source.fields.dbkey}' --fasta_description '${all_fasta_source.fields.name}' --sequence_type '${sequence_type}' +#if str($protein_reduct_setting_cond.protein_reduct_setting) == 'yes': + --protein_reduct '${protein_reduct_setting_cond.protein_reduct}' +#end if #if str($seed_setting_cond.seed_setting) == 'yes': --shapes '${seed_setting_cond.shapes}' - --max_hits_per_seed $seed_setting_cond.max_hits_per_seed - --protein_reduct '${seed_setting_cond.protein_reduct}' + ## malt-build requires a string here. + --max_hits_per_seed '${seed_setting_cond.max_hits_per_seed}' #end if ]]></command> <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="sequence_type" type="select" label="Specify whether the reference sequences are DNA or Protein sequences" help="Use the DNA setting For RNA sequences"> + <param name="sequence_name" type="text" value="" label="Name of sequence"/> + <param name="sequence_id" type="text" value="" label="ID for sequence"/> + <param name="sequence_type" type="select" label="Reference sequences type" help="Use the DNA setting For RNA sequences"> <option value="DNA" selected="true">DNA</option> <option value="Protein">Protein</option> </param> - <conditional name="seed_setting_cond"> - <param name="seed_setting" type="select" label="Specify seed settings?"> + <conditional name="protein_reduct_setting_cond"> + <param name="protein_reduct_setting" type="select" label="Specify protein alphabet resuction?" help="Used only if the reference sequences are Protein sequences"> <option selected="true" value="no">No</option> <option value="yes">Yes</option> </param> <when value="no"/> <when value="yes"> - <param name="shapes" type="text" value="" label="Comma-separated list of seed shapes" help="See help text below"> - <sanitizer invalid_char=""> - <valid initial="string.printable"> - <remove value="'" /> - </valid> - <mapping initial="none"> - <add source="'" target="'"'"'" /> - </mapping> - </sanitizer> - </param> - <param name="max_hits_per_seed" type="integer" value="1" min="1" label="Maximum number of hits per seed"/> <param name="protein_reduct" type="select" label="Name or definition of protein alphabet reduction"> <option selected="true" value="DIAMOND_11">DIAMOND_11</option> <option value="BLOSUM50_10">BLOSUM50_10</option> @@ -59,20 +51,59 @@ </param> </when> </conditional> + <conditional name="seed_setting_cond"> + <param name="seed_setting" type="select" label="Specify seed settings?"> + <option selected="true" value="no">No</option> + <option value="yes">Yes</option> + </param> + <when value="no"/> + <when value="yes"> + <param name="shapes" type="text" value="" label="Comma-separated list of seed shapes" help="See help text below"> + <sanitizer invalid_char=""> + <valid initial="string.printable"> + <remove value="'"/> + </valid> + <mapping initial="none"> + <add source="'" target="'"'"'"/> + </mapping> + </sanitizer> + </param> + <param name="max_hits_per_seed" type="integer" value="1" min="1" label="Maximum number of hits per seed"/> + </when> + </conditional> </inputs> <outputs> - <data name="out_file" format="data_manager_json" /> + <data name="out_file" format="data_manager_json"/> </outputs> <tests> <test> <param name="all_fasta_source" value="phiX174"/> - <output name="out_file" value="malt_index_builder.json"/> + <param name="sequence_name" value="Pretty name for phiX174"/> + <param name="sequence_id" value="phiX174-1"/> + <output name="out_file" value="malt_index_builder1.json"/> + </test> + <test> + <param name="all_fasta_source" value="phiX174"/> + <param name="sequence_name" value="Pretty name for phiX174"/> + <param name="sequence_id" value="phiX174-1"/> + <param name="seed_setting" value="yes"/> + <param name="shapes" value="111110111011110110111111"/> + <output name="out_file" value="malt_index_builder1.json"/> + </test> + <test> + <param name="all_fasta_source" value="phiX174"/> + <param name="sequence_name" value="Pretty name for phiX174"/> + <param name="sequence_id" value="phiX174-2"/> + <param name="sequence_type" value="Protein"/> + <param name="protein_reduct_setting" value="yes"/> + <param name="protein_reduct" value="BLOSUM50_10"/> + <output name="out_file" value="malt_index_builder2.json"/> </test> </tests> <help> .. class:: infomark -**Notice:** Values for name, description, and id will be generated automatically if left blank. +**Notice:** Values for Name and ID of sequence will be generated automatically if left blank. **What it does**
--- a/data_manager_conf.xml Tue Oct 12 14:15:35 2021 +0000 +++ b/data_manager_conf.xml Wed Oct 13 20:12:48 2021 +0000 @@ -1,16 +1,15 @@ <data_managers> - <data_manager tool_file="data_manager/malt_index_builder.xml" id="malt_index_builder" version="0.5.3"> + <data_manager tool_file="data_manager/malt_index_builder.xml" id="data_manager_malt_index_builder"> <data_table name="malt_indices"> <output> - <column name="value" /> - <column name="dbkey" /> - <column name="name" /> - <column name="path" output_ref="out_file" > + <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}/malt_index/${value}</target> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">malt_index/${value}</target> </move> - <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${dbkey}/malt_index/${value}/${path}</value_translation> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/malt_index/${value}</value_translation> <value_translation type="function">abspath</value_translation> </column> </output>
--- a/test-data/malt_index_builder.json Tue Oct 12 14:15:35 2021 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -{"data_tables": {"malt_indices": [{"dbkey": "phiX174", "name": "phiX174", "path": "phiX174.fasta", "value": "phiX174"}]}} \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/malt_index_builder1.json Wed Oct 13 20:12:48 2021 +0000 @@ -0,0 +1,1 @@ +{"data_tables": {"malt_indices": [{"dbkey": "phiX174", "name": "Pretty name for phiX174", "path": null, "value": "phiX174-1"}]}} \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/malt_index_builder2.json Wed Oct 13 20:12:48 2021 +0000 @@ -0,0 +1,1 @@ +{"data_tables": {"malt_indices": [{"dbkey": "phiX174", "name": "Pretty name for phiX174", "path": null, "value": "phiX174-2"}]}} \ No newline at end of file
--- a/tool_data_table_conf.xml.sample Tue Oct 12 14:15:35 2021 +0000 +++ b/tool_data_table_conf.xml.sample Wed Oct 13 20:12:48 2021 +0000 @@ -1,7 +1,7 @@ <tables> <!-- Locations of indices MALT versions 0.5.3 and higher --> <table name="malt_indices" comment_char="#"> - <columns>value, name, path, description</columns> + <columns>value, dbkey, name, path</columns> <file path="tool-data/malt_indices.loc" /> </table> </tables>