Mercurial > repos > iuc > data_manager_humann_database_downloader
changeset 0:60eb2512c5a0 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_humann_database_downloader commit 077b8f34e081e6c427acb0fde0fbb97d1b241e0b"
| author | iuc |
|---|---|
| date | Wed, 12 May 2021 08:58:50 +0000 |
| parents | |
| children | 87febc68b45b |
| files | data_manager/data_manager_humann_download.py data_manager/data_manager_humann_download.xml data_manager_conf.xml test-data/humann_nucleotide_database.loc test-data/humann_protein_database.loc test-data/humann_utility_mapping.loc tool-data/humann_nucleotide_database.loc.sample tool-data/humann_protein_database.loc.sample tool-data/humann_utility_mapping.loc.sample tool_data_table_conf.xml.sample tool_data_table_conf.xml.test |
| diffstat | 11 files changed, 431 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/data_manager_humann_download.py Wed May 12 08:58:50 2021 +0000 @@ -0,0 +1,212 @@ +#!/usr/bin/env python +# +# Data manager for reference data for the 'humann' Galaxy tools +import argparse +import json +import subprocess +from datetime import date +from pathlib import Path + +HUMANN_REFERENCE_DATA = { + "chocophlan": { + "full": "Full ChocoPhlAn for HUManN", + "DEMO": "Demo ChocoPhlAn for HUManN" + }, + "uniref": { + "uniref50_diamond": "Full UniRef50 for HUManN", + "uniref50_ec_filtered_diamond": "EC-filtered UniRef50 for HUManN", + "uniref90_diamond": "Full UniRef90 for HUManN", + "uniref90_ec_filtered_diamond": "EC-filtered UniRef90 for HUManN", + "DEMO_diamond": "Demo UniRef for HUManN" + }, + "utility_mapping": { + "full": { + "map_uniref50_uniref90": "Mapping (full) for UniRef50 from UniRef90", + "map_ko_uniref90": "Mapping (full) for KEGG Orthogroups (KOs) from UniRef90", + "map_eggnog_name": "Mapping (full) between EggNOG (including COGs) ids and names", + "map_uniref90_name": "Mapping (full) between UniRef90 ids and names", + "map_go_uniref90": "Mapping (full) for Gene Ontology (GO) from UniRef90", + "uniref90-tol-lca": "Mapping (full) for LCA for UniRef90", + "uniref50-tol-lca": "Mapping (full) for LCA for UniRef50", + "map_eggnog_uniref50": "Mapping (full) for EggNOG (including COGs) from UniRef50", + "map_pfam_uniref90": "Mapping (full) for Pfam domains from UniRef90", + "map_go_uniref50": "Mapping (full) for Gene Ontology (GO) from UniRef50", + "map_ko_name": "Mapping (full) between KEGG Orthogroups (KOs) ids and names", + "map_level4ec_uniref90": "Mapping (full) for Level-4 enzyme commission (EC) categories from UniRef90", + "map_go_name": "Mapping (full) between Gene Ontology (GO) ids and names", + "map_ko_uniref50": "Mapping (full) for KEGG Orthogroups (KOs) from UniRef50", + "map_level4ec_uniref50": "Mapping (full) for Level-4 enzyme commission (EC) categories from UniRef90", + "map_pfam_uniref50": "Mapping (full) for Pfam domains from UniRef50", + "map_eggnog_uniref90": "Mapping (full) for EggNOG (including COGs) from UniRef90", + "map_uniref50_name": "Mapping (full) between UniRef50 ids and names", + "map_ec_name": "Mapping (full) between Level-4 enzyme commission (EC) categories ids and names", + "map_pfam_name": "Mapping (full) between Pfam domains ids and names" + } + } +} + + +# Utility functions for interacting with Galaxy JSON +def read_input_json(json_fp): + """Read the JSON supplied from the data manager tool + Returns a tuple (param_dict,extra_files_path) + 'param_dict' is an arbitrary dictionary of parameters + input into the tool; 'extra_files_path' is the path + to a directory where output files must be put for the + receiving data manager to pick them up. + NB the directory pointed to by 'extra_files_path' + doesn't exist initially, it is the job of the script + to create it if necessary. + """ + with open(json_fp) as fh: + params = json.load(fh) + return (params['param_dict'], + Path(params['output_data'][0]['extra_files_path'])) + + +# Utility functions for creating data table dictionaries +# +# Example usage: +# >>> d = create_data_tables_dict() +# >>> add_data_table(d,'my_data') +# >>> add_data_table_entry(dict(dbkey='hg19',value='human')) +# >>> add_data_table_entry(dict(dbkey='mm9',value='mouse')) +# >>> print(json.dumps(d)) +def create_data_tables_dict(): + """Return a dictionary for storing data table information + + Returns a dictionary that can be used with 'add_data_table' + and 'add_data_table_entry' to store information about a + data table. It can be converted to JSON to be sent back to + the data manager. + + """ + d = { + 'data_tables': {} + } + return d + + +def add_data_table(d, table): + """Add a data table to the data tables dictionary + + Creates a placeholder for a data table called 'table'. + + """ + d['data_tables'][table] = [] + + +def add_data_table_entry(d, table, entry): + """Add an entry to a data table + + Appends an entry to the data table 'table'. 'entry' + should be a dictionary where the keys are the names of + columns in the data table. + + Raises an exception if the named data table doesn't + exist. + + """ + try: + d['data_tables'][table].append(entry) + except KeyError: + raise Exception("add_data_table_entry: no table '%s'" % table) + + +def download_humann_db(data_tables, table_name, database, build, version, target_dp): + """Download HUMAnN database + + Creates references to the specified file(s) on the Galaxy + server in the appropriate data table (determined from the + file extension). + + The 'data_tables' dictionary should have been created using + the 'create_data_tables_dict' and 'add_data_table' functions. + + Arguments: + data_tables: a dictionary containing the data table info + table_name: name of the table + database: database to download (chocophlan or uniref) + build: build of the database to download + version: tool version + target_dp: directory to put copy or link to the data file + """ + db_target_dp = target_dp / Path(database) + db_dp = db_target_dp / Path(database) + build_target_dp = db_target_dp / Path(build) + # launch tool to get db + cmd = "humann_databases --download %s %s %s --update-config no" % ( + database, + build, + db_target_dp) + subprocess.check_call(cmd, shell=True) + # move db + db_dp.rename(build_target_dp) + # add details to data table + if database != "utility_mapping": + add_data_table_entry( + data_tables, + table_name, + dict( + value="%s-%s-%s-%s" % (database, build, version, date.today().strftime("%d%m%Y")), + name=HUMANN_REFERENCE_DATA[database][build], + dbkey=version, + path=str(build_target_dp))) + elif args.database == "utility_mapping": + for x in build_target_dp.iterdir(): + name = str(x.stem).split('.')[0] + add_data_table_entry( + data_tables, + table_name, + dict( + value="%s-%s-%s-%s-%s" % (database, build, name, version, date.today().strftime("%d%m%Y")), + name=HUMANN_REFERENCE_DATA["utility_mapping"][build][name], + dbkey=version, + path=str(x))) + + +if __name__ == "__main__": + print("Starting...") + + # Read command line + parser = argparse.ArgumentParser(description='Download HUMAnN database') + parser.add_argument('--database', help="Database name") + parser.add_argument('--build', help="Build of the database") + parser.add_argument('--version', help="HUMAnN version") + parser.add_argument('--json', help="Path to JSON file") + args = parser.parse_args() + print("args : %s" % args) + + # Read the input JSON + json_fp = Path(args.json) + params, target_dp = read_input_json(json_fp) + + # Make the target directory + print("Making %s" % target_dp) + target_dp.mkdir(parents=True, exist_ok=True) + + # Set up data tables dictionary + data_tables = create_data_tables_dict() + if args.database == "chocophlan": + table_name = 'humann_nucleotide_database' + elif args.database == "uniref": + table_name = 'humann_protein_database' + elif args.database == "utility_mapping": + table_name = 'humann_utility_mapping' + add_data_table(data_tables, table_name) + + # Fetch data from specified data sources + print("Download and build database") + download_humann_db( + data_tables, + table_name, + args.database, + args.build, + args.version, + target_dp) + + # Write output JSON + print("Outputting JSON") + with open(json_fp, 'w') as fh: + json.dump(data_tables, fh, sort_keys=True) + print("Done.")
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/data_manager_humann_download.xml Wed May 12 08:58:50 2021 +0000 @@ -0,0 +1,120 @@ +<tool id="data_manager_humann_download" name="HUMAnN download" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" tool_type="manage_data" profile="20.01"> + <description>Download HUMAnN database</description> + <macros> + <token name="@TOOL_VERSION@">3.0.0</token> + <token name="@VERSION_SUFFIX@">0</token> + </macros> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">humann</requirement> + </requirements> + <command detect_errors="exit_code"><![CDATA[ +python '$__tool_directory__/data_manager_humann_download.py' + --database '$db.database' + --build '$db.build' + --json '$out_file' + --version '@TOOL_VERSION@' + ]]></command> + <inputs> + <conditional name="db"> + <param name="database" type="select" label="Type of database to download"> + <option value="chocophlan" selected="true">Nucleotide database</option> + <option value="uniref">Protein database</option> + <option value="utility_mapping">Mapping files</option> + </param> + <when value="chocophlan"> + <param name="build" type="select" label="Build for nucleotide database"> + <option value="full" selected="true">Full</option> + <option value="DEMO">Demo</option> + </param> + </when> + <when value="uniref"> + <param name="build" type="select" label="Build for protein database"> + <option value="uniref50_diamond">Full UniRef50</option> + <option value="uniref50_ec_filtered_diamond">EC-filtered UniRef50</option> + <option value="uniref90_diamond" selected="true">Full UniRef90</option> + <option value="uniref90_ec_filtered_diamond">EC-filtered UniRef90</option> + <option value="DEMO_diamond">Demo</option> + </param> + </when> + <when value="utility_mapping"> + <param name="build" type="select" label="Build for mapping files"> + <option value="full" selected="true">Full</option> + </param> + </when> + </conditional> + </inputs> + <outputs> + <data name="out_file" format="data_manager_json" label="${tool.name}" /> + </outputs> + <tests> + <test expect_num_outputs="1"> + <conditional name="db"> + <param name="database" value="chocophlan"/> + <param name="build" value="DEMO"/> + </conditional> + <output name="out_file"> + <assert_contents> + <has_text text="humann_nucleotide_database"/> + <has_text text="Demo ChocoPhlAn for HUManN"/> + <has_text text="chocophlan/DEMO"/> + <has_text text="chocophlan-DEMO-"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <conditional name="db"> + <param name="database" value="uniref"/> + <param name="build" value="DEMO_diamond"/> + </conditional> + <output name="out_file"> + <assert_contents> + <has_text text="DEMO_diamond"/> + <has_text text="Demo UniRef for HUManN"/> + <has_text text="uniref/DEMO_diamond"/> + <has_text text="uniref-DEMO_diamond-"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <conditional name="db"> + <param name="database" value="utility_mapping"/> + <param name="build" value="full"/> + </conditional> + <output name="out_file"> + <assert_contents> + <has_text text="utility_mapping"/> + <has_text text="Mapping (full)"/> + <has_text text="utility_mapping/full"/> + <has_text text="map_uniref50_uniref90"/> + <has_text text="map_ko_uniref90"/> + <has_text text="map_eggnog_name"/> + <has_text text="map_uniref90_name"/> + <has_text text="map_go_uniref90"/> + <has_text text="uniref90-tol-lca"/> + <has_text text="uniref50-tol-lca"/> + <has_text text="map_eggnog_uniref50"/> + <has_text text="map_pfam_uniref90"/> + <has_text text="map_go_uniref50"/> + <has_text text="map_ko_name"/> + <has_text text="map_level4ec_uniref90"/> + <has_text text="map_go_name"/> + <has_text text="map_ko_uniref50"/> + <has_text text="map_level4ec_uniref50"/> + <has_text text="map_pfam_uniref50"/> + <has_text text="map_eggnog_uniref90"/> + <has_text text="map_uniref50_name"/> + <has_text text="map_ec_name"/> + <has_text text="map_pfam_name"/> + </assert_contents> + </output> + </test> + </tests> + <help> +This tool downloads the HUMAnN databases. + +Read more about the tool at http://huttenhower.sph.harvard.edu/humann . + </help> + <citations> + <citation type="doi">10.1371/journal.pcbi.1003153</citation> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager_conf.xml Wed May 12 08:58:50 2021 +0000 @@ -0,0 +1,47 @@ +<data_managers> + <data_manager tool_file="data_manager/data_manager_humann_download.xml" id="data_manager_humann_download" > + <data_table name="humann_nucleotide_database"> <!-- Defines a Data Table to be modified. --> + <output> <!-- Handle the output of the Data Manager Tool --> + <column name="value" /> <!-- columns that are going to be specified by the Data Manager Tool --> + <column name="name" /> <!-- columns that are going to be specified by the Data Manager Tool --> + <column name="dbkey" /> <!-- columns that are going to be specified by the Data Manager Tool --> + <column name="path" output_ref="out_file" > + <move type="directory"> + <source>${path}</source> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">humann/data/nucleotide_database/${value}</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/humann/data/nucleotide_database/${value}</value_translation> + </column> + </output> + </data_table> + <data_table name="humann_protein_database"> <!-- Defines a Data Table to be modified. --> + <output> <!-- Handle the output of the Data Manager Tool --> + <column name="value" /> <!-- columns that are going to be specified by the Data Manager Tool --> + <column name="name" /> <!-- columns that are going to be specified by the Data Manager Tool --> + <column name="dbkey" /> <!-- columns that are going to be specified by the Data Manager Tool --> + <column name="path" output_ref="out_file" > + <move type="directory"> + <source>${path}</source> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">humann/data/protein_database/${value}</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/humann/data/protein_database/${value}</value_translation> + </column> + </output> + </data_table> + <data_table name="humann_utility_mapping"> <!-- Defines a Data Table to be modified. --> + <output> <!-- Handle the output of the Data Manager Tool --> + <column name="value" /> <!-- columns that are going to be specified by the Data Manager Tool --> + <column name="name" /> <!-- columns that are going to be specified by the Data Manager Tool --> + <column name="dbkey" /> <!-- columns that are going to be specified by the Data Manager Tool --> + <column name="path" output_ref="out_file" > + <move type="file" relativize_symlinks="False"> + <source>${path}</source> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">humann/data/utility_mapping/${value}</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/humann/data/utility_mapping/${value}</value_translation> + </column> + </output> + </data_table> + </data_manager> +</data_managers> +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/humann_nucleotide_database.loc Wed May 12 08:58:50 2021 +0000 @@ -0,0 +1,4 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of metagenomics files. +#file has this format (white space characters are TAB characters) +#db-build-version-date db-name build /path/to/data \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/humann_protein_database.loc Wed May 12 08:58:50 2021 +0000 @@ -0,0 +1,4 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of metagenomics files. +#file has this format (white space characters are TAB characters) +#db-build-version-date db-name build /path/to/data \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/humann_utility_mapping.loc Wed May 12 08:58:50 2021 +0000 @@ -0,0 +1,4 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of metagenomics files. +#file has this format (white space characters are TAB characters) +#db-build-version-date db-name build /path/to/data \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/humann_nucleotide_database.loc.sample Wed May 12 08:58:50 2021 +0000 @@ -0,0 +1,4 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of metagenomics files. +#file has this format (white space characters are TAB characters) +#db-build-version-date db-name build /path/to/data \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/humann_protein_database.loc.sample Wed May 12 08:58:50 2021 +0000 @@ -0,0 +1,4 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of metagenomics files. +#file has this format (white space characters are TAB characters) +#db-build-version-date db-name build /path/to/data \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/humann_utility_mapping.loc.sample Wed May 12 08:58:50 2021 +0000 @@ -0,0 +1,4 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of metagenomics files. +#file has this format (white space characters are TAB characters) +#db-build-version-date db-name build /path/to/data \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Wed May 12 08:58:50 2021 +0000 @@ -0,0 +1,14 @@ +<tables> + <table name="humann_nucleotide_database" comment_char="#"> + <columns>value, name, dbkey, path</columns> + <file path="tool-data/humann_nucleotide_database.loc" /> + </table> + <table name="humann_protein_database" comment_char="#"> + <columns>value, name, dbkey, path</columns> + <file path="tool-data/humann_protein_database.loc" /> + </table> + <table name="humann_utility_mapping" comment_char="#"> + <columns>value, name, dbkey, path</columns> + <file path="tool-data/humann_utility_mapping.loc" /> + </table> +</tables>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.test Wed May 12 08:58:50 2021 +0000 @@ -0,0 +1,14 @@ +<tables> + <table name="humann_nucleotide_database" comment_char="#"> + <columns>value, name, dbkey, path</columns> + <file path="${__HERE__}/test-data/humann_nucleotide_database.loc" /> + </table> + <table name="humann_protein_database" comment_char="#"> + <columns>value, name, dbkey, path</columns> + <file path="${__HERE__}/test-data/humann_protein_database.loc" /> + </table> + <table name="humann_utility_mapping" comment_char="#"> + <columns>value, name, dbkey, path</columns> + <file path="${__HERE__}/test-data/humann_utility_mapping.loc" /> + </table> +</tables> \ No newline at end of file