| Next changeset 1:561c4b181bfa (2025-03-27) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_mmseqs2_database commit 1400593429eb4e9c6e307df3621825a8b84a6fa7 |
|
added:
data_manager/data_manager_mmseqs2_download.xml data_manager_conf.xml test-data/mmseqs2_databases.loc.test tool-data/mmseqs2_databases.loc.sample tool_data_table_conf.xml.sample tool_data_table_conf.xml.test |
| b |
| diff -r 000000000000 -r 75cc3fb4c10f data_manager/data_manager_mmseqs2_download.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager/data_manager_mmseqs2_download.xml Thu Mar 27 14:37:32 2025 +0000 |
| [ |
| b'@@ -0,0 +1,160 @@\n+<tool id="data_manager_mmseqs2_download" name="Download MMseqs2 databases" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" tool_type="manage_data" profile="22.05">\n+ <description></description>\n+ <macros>\n+ <token name="@TOOL_VERSION@">15.6f452</token>\n+ <token name="@VERSION_SUFFIX@">0</token>\n+ </macros>\n+ <requirements>\n+ <requirement type="package" version="@TOOL_VERSION@">mmseqs2</requirement>\n+ </requirements>\n+ <command detect_errors="exit_code"><![CDATA[\n+#set $database_name = str($database).split(\'/\')[-1] if \'/\' in str($database) else str($database)\n+\n+mkdir -p \'$out_file.extra_files_path\'/\'$database_name\' &&\n+mmseqs databases \n+ \'$database\' \'$out_file.extra_files_path\'/\'$database_name\'/database\n+ \'tmp\'\n+ --threads "\\${GALAXY_SLOTS:-1}" &&\n+cp \'$dmjson\' \'$out_file\'\n+ ]]></command>\n+ <configfiles>\n+ <configfile name="dmjson"><![CDATA[\n+#from datetime import date\n+#set $database_name = str($database).split(\'/\')[-1] if \'/\' in str($database) else str($database)\n+{\n+ "data_tables":{\n+ "mmseqs2_databases":[\n+ {\n+ "value": "${database}-@TOOL_VERSION@-#echo date.today().strftime(\'%d%m%Y\')#",\n+ "name": "${database} #echo date.today().strftime(\'%d%m%Y\')#",\n+ "type": "${db_type}",\n+ "taxonomy": "${db_taxonomy}",\n+ "path": "$database_name",\n+ "version": "@TOOL_VERSION@"\n+ }\n+ ]\n+ }\n+}]]>\n+ </configfile>\n+ </configfiles>\n+ <inputs>\n+ <conditional name="db_name">\n+ <param argument="type" type="select" label="Type of Databases">\n+ <option value="aminoacid">Aminoacid databases</option>\n+ <option value="aminoacid_taxonomy">Aminoacid databases that can be used for taxonomy</option>\n+ <option value="nucleotide">Nucleotide databases</option>\n+ <option value="nucleotide_taxonomy">Nucleotide databases that can be used for taxonomy</option>\n+ <option value="profile">Profile databases</option>\n+ </param>\n+ <when value="aminoacid">\n+ <param name="db_type" value="aminoacid" type="hidden"/>\n+ <param name="db_taxonomy" value="no" type="hidden"/>\n+ <param name="database" type="select" label="MMseqs2 aminoacid databases">\n+ <option value="UniRef100" selected="true">UniRef100</option>\n+ <option value="UniRef90">UniRef90</option>\n+ <option value="UniRef50">UniRef50</option>\n+ <option value="UniProtKB">UniProtKB</option>\n+ <option value="UniProtKB/TrEMBL">TrEMBL (UniProtKB)</option>\n+ <option value="UniProtKB/Swiss-Prot">Swiss-Prot (UniProtKB)</option>\n+ <option value="NR">NR (Non-redundant protein sequences from GenPept, Swissprot, PIR, PDF, PDB, and NCBI RefSeq)</option>\n+ <option value="GTDB">GTDB (Genome Taxonomy Database)</option>\n+ <option value="PDB">PDB (The Protein Data Bank)</option> \n+ </param>\n+ </when>\n+ <when value="aminoacid_taxonomy">\n+ <param name="db_type" value="aminoacid" type="hidden"/>\n+ <param name="db_taxonomy" value="yes" type="hidden"/>\n+ <param name="database" type="select" label="MMseqs2 aminoacid databases that can be used for taxonomy">\n+ <option value="UniRef100" selected="true">UniRef100</option>\n+ <option value="UniRef90">UniRef90</option>\n+ <option value="UniRef50">UniRef50</option>\n+ <option value="UniProtKB">UniProtKB</option>\n+ <option value="UniProtKB/TrEMBL">TrEMBL (UniProtKB)</option>\n+ <option value="UniProtKB/Swiss-Prot">Swiss-Prot (UniProtKB)</option>\n+ <option value="NR">NR (Non-redundant protein '..b'leotide sequences from all traditional divisions of GenBank, EMBL, and DDBJ excluding GSS, STS, PAT, EST, HTG, and WGS)</option>\n+ <option value="Resfinder">Resfinder</option>\n+ </param>\n+ </when>\n+ <when value="nucleotide_taxonomy">\n+ <param name="db_type" value="nucleotide" type="hidden"/>\n+ <param name="db_taxonomy" value="yes" type="hidden"/>\n+ <param name="database" type="select" label="MMseqs2 nucleotide databases that can be used for taxonomy">\n+ <option value="SILVA">SILVA</option>\n+ <option value="Kalamari">Kalamari</option>\n+ </param>\n+ </when>\n+ <when value="profile">\n+ <param name="db_type" value="profile" type="hidden"/>\n+ <param name="db_taxonomy" value="no" type="hidden"/>\n+ <param name="database" type="select" label="MMseqs2 profile databases">\n+ <option value="PDB70">PDB70 (PDB clustered to 70% sequence identity)</option>\n+ <option value="Pfam-A.full">Pfam-A.full</option>\n+ <option value="Pfam-A.seed">Pfam-A.seed</option>\n+ <option value="Pfam-B">Pfam-B</option>\n+ <option value="CDD">CDD (Conserved Domain Database)</option>\n+ <option value="VOGDB">VOGDB (Virus Orthologous Groups)</option>\n+ <option value="dbCAN2">dbCAN2 (database of carbohydrate-active enzymes)</option>\n+ </param>\n+ </when>\n+ </conditional>\n+ </inputs>\n+ <outputs>\n+ <data name="out_file" format="data_manager_json" label="${tool.name}"/>\n+ </outputs>\n+ <tests>\n+ <test expect_num_outputs="1">\n+ <conditional name="db_name">\n+ <param name="type" value="nucleotide_taxonomy" />\n+ <param name="db_type" value="nucleotide" />\n+ <param name="db_taxonomy" value="yes" />\n+ <param name="database" value="SILVA" />\n+ </conditional>\n+ <output name="out_file">\n+ <assert_contents>\n+ <has_text text=\'"mmseqs2_databases":\'/>\n+ <has_text text=\'"version": "15.6f452"\'/>\n+ <has_text_matching expression=\'"value": "SILVA-15.6f452-[0-9]{8}"\'/>\n+ <has_text_matching expression=\'"name": "SILVA [0-9]{8}"\'/>\n+ <has_text text=\'"type": "nucleotide"\'/>\n+ <has_text text=\'"taxonomy": "yes"\'/>\n+ <has_text text=\'"path": "SILVA"\'/>\n+ </assert_contents>\n+ </output>\n+ </test>\n+ <test expect_num_outputs="1">\n+ <conditional name="db_name">\n+ <param name="type" value="aminoacid_taxonomy" />\n+ <param name="db_type" value="aminoacid" />\n+ <param name="db_taxonomy" value="yes" />\n+ <param name="database" value="UniProtKB/Swiss-Prot" />\n+ </conditional>\n+ <output name="out_file">\n+ <assert_contents>\n+ <has_text text=\'"mmseqs2_databases":\'/>\n+ <has_text text=\'"version": "15.6f452"\'/>\n+ <has_text_matching expression=\'"value": "UniProtKB/Swiss-Prot-15.6f452-[0-9]{8}"\'/>\n+ <has_text_matching expression=\'"name": "UniProtKB/Swiss-Prot [0-9]{8}"\'/>\n+ <has_text text=\'"type": "aminoacid"\'/>\n+ <has_text text=\'"taxonomy": "yes"\'/>\n+ <has_text text=\'"path": "Swiss-Prot"\'/>\n+ </assert_contents>\n+ </output>\n+ </test>\n+ </tests>\n+ <help><![CDATA[\n+This tool downloads databases that can be used with MMseqs2.\n+ ]]></help>\n+ <citations>\n+ <citation type="doi">10.1038/nbt.3988</citation>\n+ </citations>\n+</tool>\n\\ No newline at end of file\n' |
| b |
| diff -r 000000000000 -r 75cc3fb4c10f data_manager_conf.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data_manager_conf.xml Thu Mar 27 14:37:32 2025 +0000 |
| b |
| @@ -0,0 +1,21 @@ +<data_managers> + <data_manager tool_file="data_manager/data_manager_mmseqs2_download.xml" id="mmseqs2_download_databases"> + <data_table name="mmseqs2_databases"> + <output> + <column name="value"/> + <column name="name"/> + <column name="type"/> + <column name="taxonomy"/> + <column name="path" output_ref="out_file"> + <move type="directory"> + <source>${path}</source> + <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">mmseqs2/${path}</target> + </move> + <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/mmseqs2/${path}</value_translation> + <value_translation type="function">abspath</value_translation> + </column> + <column name="version"/> + </output> + </data_table> + </data_manager> +</data_managers> \ No newline at end of file |
| b |
| diff -r 000000000000 -r 75cc3fb4c10f test-data/mmseqs2_databases.loc.test --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/mmseqs2_databases.loc.test Thu Mar 27 14:37:32 2025 +0000 |
| b |
| @@ -0,0 +1,2 @@ +SILVA-15.6f452-10022025 SILVA 10022025 nucleotide yes /tmp/tmpepbr4_rb/galaxy-dev/tool-data/mmseqs2/SILVA 15.6f452 +UniProtKB/Swiss-Prot-15.6f452-10022025 UniProtKB/Swiss-Prot 10022025 aminoacid yes /tmp/tmpepbr4_rb/galaxy-dev/tool-data/mmseqs2/Swiss-Prot 15.6f452 |
| b |
| diff -r 000000000000 -r 75cc3fb4c10f tool-data/mmseqs2_databases.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/mmseqs2_databases.loc.sample Thu Mar 27 14:37:32 2025 +0000 |
| b |
| @@ -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) +#UniRef100-16102024 UniRef100 (MMseqs2) UniRef100.15.6f452 /path/to/data 15.6f452 \ No newline at end of file |
| b |
| diff -r 000000000000 -r 75cc3fb4c10f tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Thu Mar 27 14:37:32 2025 +0000 |
| b |
| @@ -0,0 +1,6 @@ +<tables> + <table name="mmseqs2_databases" comment_char="#"> + <columns>value, name, type, taxonomy, path, version</columns> + <file path="tool-data/mmseqs2_databases.loc"/> + </table> +</tables> \ No newline at end of file |
| b |
| diff -r 000000000000 -r 75cc3fb4c10f tool_data_table_conf.xml.test --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.test Thu Mar 27 14:37:32 2025 +0000 |
| b |
| @@ -0,0 +1,6 @@ +<tables> + <table name="mmseqs2_databases" comment_char="#"> + <columns>value, name, type, taxonomy, path, version</columns> + <file path="${__HERE__}/test-data/mmseqs2_databases.loc.test"/> + </table> +</tables> \ No newline at end of file |