Add MMseqs2 clustering and taxonomy

data_managers/data_manager_mmseqs2_database/.shed.yml

@@ -0,0 +1,14 @@
+name: data_manager_mmseqs2_database
+owner: iuc
+description: "MMseqs2 is an ultra fast and sensitive sequence search and clustering suite"
+homepage_url: "https://github.com/soedinglab/MMseqs2"
+long_description: |
+  MMseqs2 (Many-against-Many sequence searching) is a software suite to search and cluster huge protein and nucleotide sequence sets. 
+  MMseqs2 is open source GPL-licensed software implemented in C++ for Linux, MacOS, and (as beta version, via cygwin) Windows. 
+  The software is designed to run on multiple cores and servers and exhibits very good scalability. 
+  MMseqs2 can run 10000 times faster than BLAST. At 100 times its speed it achieves almost the same sensitivity. 
+  It can perform profile searches with the same sensitivity as PSI-BLAST at over 400 times its speed.
+remote_repository_url: "https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_mmseqs2_database"
+type: unrestricted
+categories:
+- Data Managers

data_managers/data_manager_mmseqs2_database/data_manager/data_manager_mmseqs2_download.xml

@@ -0,0 +1,161 @@
+<tool id="data_manager_mmseqs2_download" name="Download MMseqs2 databases" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" tool_type="manage_data" profile="22.05">
+    <description></description>
+    <macros>
+        <token name="@TOOL_VERSION@">15</token>
+        <token name="@VERSION_SUFFIX@">0</token>
+        <token name="@COMMIT@">6f452</token>
+        <token name="@FULL_TOOL_VERSION@">@TOOL_VERSION@.@COMMIT@</token>
+    </macros>
+    <requirements>
+        <requirement type="package" version="@FULL_TOOL_VERSION@">mmseqs2</requirement>
+    </requirements>
+    <stdio>
+        <exit_code range=":-1" level="fatal" description="Error: Cannot open file"/>
+        <exit_code range="1:" level="fatal" description="Error"/>
+    </stdio>
+    <command><![CDATA[
+#set $database_name = str($database).split('/')[-1] if '/' in str($database) else str($database)
+        mmseqs databases 
+        '$database' '$database_name'
+        '$data_table'
+        --threads "\${GALAXY_SLOTS:-1}" &&
+        cp '$dmjson' '$out_file'
+    ]]></command>
+     <configfiles>
+        <configfile name="dmjson"><![CDATA[
+#from datetime import date
+#set $database_name = str($database).split('/')[-1] if '/' in str($database) else str($database)
+{
+  "data_tables":{
+    "$data_table":[
+      {
+        "value": "${database}-@FULL_TOOL_VERSION@-#echo date.today().strftime('%d%m%Y')#",
+        "name": "${database} #echo date.today().strftime('%d%m%Y')#",
+        "path": "$database_name",
+        "version": "@FULL_TOOL_VERSION@"
+      }
+    ]
+  }
+}]]>
+        </configfile>
+    </configfiles>
+    <inputs>
+        <conditional name="db_name">
+            <param argument="type" type="select" label="Type of Databases">
+                <option value="aminoacid" selected="true">Aminoacid databases</option>
+                <option value="aminoacid_taxonomy">Aminoacid databases that can be used for taxonomy</option>
+                <option value="nucleotide">Nucleotide databases</option>
+                <option value="nucleotide_taxonomy">Nucleotide databases that can be used for taxonomy</option>
+                <option value="profile">Profile databases</option>
+            </param>
+            <when value="aminoacid">
+                <param name="database" type="select" label="MMseqs2 aminoacid databases">
+                    <option value="UniRef100" selected="true">UniRef100</option>
+                    <option value="UniRef90">UniRef90</option>
+                    <option value="UniRef50">UniRef50</option>
+                    <option value="UniProtKB">UniProtKB</option>
+                    <option value="UniProtKB/TrEMBL">TrEMBL (UniProtKB)</option>
+                    <option value="UniProtKB/Swiss-Prot">Swiss-Prot (UniProtKB)</option>
+                    <option value="NR">NR (Non-redundant protein sequences from GenPept, Swissprot, PIR, PDF, PDB, and NCBI RefSeq)</option>
+                    <option value="GTDB">GTDB (Genome Taxonomy Database)</option>
+                    <option value="PDB">PDB (The Protein Data Bank)</option>            
+                </param>
+                <param name="data_table" type="select" label="Select datatable">
+                    <option value="mmseqs2_aminoacid_databases" selected="true">Aminoacid Databases</option>            
+                </param>
+            </when>
+            <when value="aminoacid_taxonomy">
+                <param name="database" type="select" label="MMseqs2 aminoacid databases that can be used for taxonomy">
+                    <option value="UniRef100" selected="true">UniRef100</option>
+                    <option value="UniRef90">UniRef90</option>
+                    <option value="UniRef50">UniRef50</option>
+                    <option value="UniProtKB">UniProtKB</option>
+                    <option value="UniProtKB/TrEMBL">TrEMBL (UniProtKB)</option>
+                    <option value="UniProtKB/Swiss-Prot">Swiss-Prot (UniProtKB)</option>
+                    <option value="NR">NR (Non-redundant protein sequences from GenPept, Swissprot, PIR, PDF, PDB, and NCBI RefSeq)</option>
+                    <option value="GTDB">GTDB (Genome Taxonomy Database)</option>
+                </param>
+                <param name="data_table" type="select" label="Select datatable">
+                    <option value="mmseqs2_aminoacid_taxonomy_databases" selected="true">Aminoacid Databases that can be used for taxonomy</option>            
+                </param>
+            </when>
+            <when value="nucleotide">
+                <param name="database" type="select" label="MMseqs2 nucleotide databases">
+                    <option value="SILVA">SILVA</option>
+                    <option value="Kalamari">Kalamari</option>
+                    <option value="NT">NT (Partially non-redundant nucleotide sequences from all traditional divisions of GenBank, EMBL, and DDBJ excluding GSS, STS, PAT, EST, HTG, and WGS)</option>
+                    <option value="Resfinder">Resfinder</option>
+                </param>
+                <param name="data_table" type="select" label="Select datatable">
+                    <option value="mmseqs2_nucleotide_databases" selected="true">Nucleotide Databases</option>            
+                </param>
+            </when>
+            <when value="nucleotide_taxonomy">
+                <param name="database" type="select" label="MMseqs2 nucleotide databases that can be used for taxonomy">
+                    <option value="SILVA">SILVA</option>
+                    <option value="Kalamari">Kalamari</option>
+                </param>
+                <param name="data_table" type="select" label="Select datatable">
+                    <option value="mmseqs2_nucleotide_taxonomy_databases" selected="true">Nucleotide Databases that can be used for taxonomy</option>            
+                </param>
+            </when>
+            <when value="profile">
+                <param name="database" type="select" label="MMseqs2 profile databases">
+                    <option value="PDB70">PDB70 (PDB clustered to 70% sequence identity)</option>
+                    <option value="Pfam-A.full">Pfam-A.full</option>
+                    <option value="Pfam-A.seed">Pfam-A.seed</option>
+                    <option value="Pfam-B">Pfam-B</option>
+                    <option value="CDD">CDD (Conserved Domain Database)</option>
+                    <option value="VOGDB">VOGDB (Virus Orthologous Groups)</option>
+                    <option value="dbCAN2">dbCAN2 (database of carbohydrate-active enzymes)</option>
+                </param>
+                <param name="data_table" type="select" label="Select datatable">
+                    <option value="mmseqs2_profile_databases" selected="true">Profile Databases</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_name">
+                <param name="type" value="nucleotide_taxonomy" />
+                <param name="database" value="SILVA" />
+                <param name="data_table" value="mmseqs2_nucleotide_taxonomy_databases" />
+            </conditional>
+            <output name="out_file">
+                <assert_contents>
+                    <has_text text='"mmseqs2_nucleotide_taxonomy_databases":'/>
+                    <has_text text='"version": "15.6f452"'/>
+                    <has_text_matching expression='"value": "SILVA-15.6f452-[0-9]{8}"'/>
+                    <has_text_matching expression='"name": "SILVA [0-9]{8}"'/>
+                    <has_text text='"path": "SILVA"'/>
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="1">
+            <conditional name="db_name">
+                <param name="type" value="aminoacid_taxonomy" />
+                <param name="database" value="UniProtKB/Swiss-Prot" />
+                <param name="data_table" value="mmseqs2_aminoacid_taxonomy_databases" />
+            </conditional>
+            <output name="out_file">
+                <assert_contents>
+                    <has_text text='"mmseqs2_aminoacid_taxonomy_databases":'/>
+                    <has_text text='"version": "15.6f452"'/>
+                    <has_text_matching expression='"value": "UniProtKB/Swiss-Prot-15.6f452-[0-9]{8}"'/>
+                    <has_text_matching expression='"name": "UniProtKB/Swiss-Prot [0-9]{8}"'/>
+                    <has_text text='"path": "Swiss-Prot"'/>
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+    <help><![CDATA[
+This tool downloads databases that can be used with MMseqs2.
+    ]]></help>
+    <citations>
+        <citation type="doi">10.1038/nbt.3988</citation>
+    </citations>
+</tool>

data_managers/data_manager_mmseqs2_database/data_manager_conf.xml

@@ -0,0 +1,79 @@
+<data_managers>
+    <data_manager tool_file="data_manager/data_manager_mmseqs2_download.xml" id="mmseqs2_download_databases">
+        <data_table name="mmseqs2_aminoacid_databases">
+            <output>
+                <column name="value"/>
+                <column name="name"/>
+                <column name="path" output_ref="out_file">
+                    <move type="directory">
+                        <source>${path}</source>
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${path}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${path}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+                <column name="version"/>
+            </output>
+        </data_table>
+        <data_table name="mmseqs2_aminoacid_taxonomy_databases">
+            <output>
+                <column name="value"/>
+                <column name="name"/>
+                <column name="path" output_ref="out_file">
+                    <move type="directory">
+                        <source>${path}</source>
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${path}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${path}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+                <column name="version"/>
+            </output>
+        </data_table>
+        <data_table name="mmseqs2_nucleotide_databases">
+            <output>
+                <column name="value"/>
+                <column name="name"/>
+                <column name="path" output_ref="out_file">
+                    <move type="directory">
+                        <source>${path}</source>
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${path}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${path}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+                <column name="version"/>
+            </output>
+        </data_table>
+        <data_table name="mmseqs2_nucleotide_taxonomy_databases">
+            <output>
+                <column name="value"/>
+                <column name="name"/>
+                <column name="path" output_ref="out_file">
+                    <move type="directory">
+                        <source>${path}</source>
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${path}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${path}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+                <column name="version"/>
+            </output>
+        </data_table>
+        <data_table name="mmseqs2_profile_databases">
+            <output>
+                <column name="value"/>
+                <column name="name"/>
+                <column name="path" output_ref="out_file">
+                    <move type="directory">
+                        <source>${path}</source>
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">${path}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/${path}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+                <column name="version"/>
+            </output>
+        </data_table>
+    </data_manager>
+</data_managers>

data_managers/data_manager_mmseqs2_database/test-data/mmseqs2_aminoacid_taxonomy_databases.loc.test

@@ -0,0 +1,3 @@
+UniProtKB/Swiss-Prot-15.6f452-15112024	UniProtKB/Swiss-Prot 15112024		/tmp/tmp5_ppo41w/galaxy-dev/tool-data/Swiss-Prot	15.6f452
+UniProtKB/Swiss-Prot-15.6f452-18112024	UniProtKB/Swiss-Prot 18112024		/tmp/tmpm3q21te0/galaxy-dev/tool-data/Swiss-Prot	15.6f452
+UniProtKB/Swiss-Prot-15.6f452-19112024	UniProtKB/Swiss-Prot 19112024		/tmp/tmprct41jv5/galaxy-dev/tool-data/Swiss-Prot	15.6f452

data_managers/data_manager_mmseqs2_database/test-data/mmseqs2_nucleotide_taxonomy_databases.loc.test

@@ -0,0 +1,2 @@
+SILVA-15.6f452-18112024	SILVA 18112024		/tmp/tmpm3q21te0/galaxy-dev/tool-data/SILVA	15.6f452
+SILVA-15.6f452-19112024	SILVA 19112024		/tmp/tmprct41jv5/galaxy-dev/tool-data/SILVA	15.6f452

data_managers/data_manager_mmseqs2_database/tool-data/mmseqs2_databases.loc.sample

@@ -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	

data_managers/data_manager_mmseqs2_database/tool_data_table_conf.xml.sample

@@ -0,0 +1,22 @@
+<tables>
+    <table name="mmseqs2_aminoacid_databases" comment_char="#">
+        <columns>value, name, dbkey, path, version</columns>
+        <file path="tool-data/mmseqs2_aminoacid_databases.loc"/>
+    </table>
+    <table name="mmseqs2_aminoacid_taxonomy_databases" comment_char="#">
+        <columns>value, name, dbkey, path, version</columns>
+        <file path="tool-data/mmseqs2_aminoacid_taxonomy_databases.loc"/>
+    </table>
+    <table name="mmseqs2_nucleotide_databases" comment_char="#">
+        <columns>value, name, dbkey, path, version</columns>
+        <file path="tool-data/mmseqs2_nucleotide_databases.loc"/>
+    </table>
+    <table name="mmseqs2_nucleotide_taxonomy_databases" comment_char="#">
+        <columns>value, name, dbkey, path, version</columns>
+        <file path="tool-data/mmseqs2_nucleotide_taxonomy_databases.loc"/>
+    </table>
+    <table name="mmseqs2_profile_databases" comment_char="#">
+        <columns>value, name, dbkey, path, version</columns>
+        <file path="tool-data/mmseqs2_profile_databases.loc"/>
+    </table>
+</tables>

data_managers/data_manager_mmseqs2_database/tool_data_table_conf.xml.test

@@ -0,0 +1,22 @@
+<tables>
+    <table name="mmseqs2_aminoacid_databases" comment_char="#">
+        <columns>value, name, dbkey, path, version</columns>
+        <file path="${__HERE__}/test-data/mmseqs2_aminoacid_databases.loc.test"/>
+    </table>
+    <table name="mmseqs2_aminoacid_taxonomy_databases" comment_char="#">
+        <columns>value, name, dbkey, path, version</columns>
+        <file path="${__HERE__}/test-data/mmseqs2_aminoacid_taxonomy_databases.loc.test"/>
+    </table>
+    <table name="mmseqs2_nucleotide_databases" comment_char="#">
+        <columns>value, name, dbkey, path, version</columns>
+        <file path="${__HERE__}/test-data/mmseqs2_nucleotide_databases.loc.test"/>
+    </table>
+    <table name="mmseqs2_nucleotide_taxonomy_databases" comment_char="#">
+        <columns>value, name, dbkey, path, version</columns>
+        <file path="${__HERE__}/test-data/mmseqs2_nucleotide_taxonomy_databases.loc.test"/>
+    </table>
+    <table name="mmseqs2_profile_databases" comment_char="#">
+        <columns>value, name, dbkey, path, version</columns>
+        <file path="${__HERE__}/test-data/mmseqs2_profile_databases.loc.test"/>
+    </table>
+</tables>

tools/mmseqs2/.shed.yml

@@ -0,0 +1,21 @@
+name: mmseqs2
+owner: iuc
+description: MMseqs2 is an ultra fast and sensitive sequence search and clustering suite
+long_description: |
+  MMseqs2 (Many-against-Many sequence searching) is a software suite to search and cluster huge protein and nucleotide sequence sets. 
+  MMseqs2 is open source GPL-licensed software implemented in C++ for Linux, MacOS, and (as beta version, via cygwin) Windows. 
+  The software is designed to run on multiple cores and servers and exhibits very good scalability. 
+  MMseqs2 can run 10000 times faster than BLAST. At 100 times its speed it achieves almost the same sensitivity. 
+  It can perform profile searches with the same sensitivity as PSI-BLAST at over 400 times its speed.
+categories:
+- Sequence Analysis
+- Metagenomics
+homepage_url: https://github.com/soedinglab/MMseqs2
+remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/master/tools/mmsesq2
+type: unrestricted
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "Wrapper for the MMseqs2 tool suite: {{ tool_name }}"
+suite:
+  name: "suite_mmseqs2"
+  description: "MMseqs2 is an ultra fast and sensitive sequence search and clustering suite"

tools/mmseqs2/macro.xml

@@ -0,0 +1,33 @@
+<?xml version="1.0"?>
+<macros>
+    <token name="@TOOL_VERSION@">15</token>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <!-- Remove token COMMIT and FULL_TOOL_VERSION if bioconda version fixed like 16 instead of 15.6f452 -->
+    <token name="@COMMIT@">6f452</token>
+    <token name="@FULL_TOOL_VERSION@">@TOOL_VERSION@.@COMMIT@</token>
+    <token name="@PROFILE@">22.05</token>
+    <xml name="version_command">
+        <version_command><![CDATA[mmseqs version]]></version_command>
+    </xml>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">mmseqs2</requirement>
+            <yield/>
+        </requirements>
+    </xml>
+    <xml name="biotools">
+        <xrefs>
+            <xref type="bio.tools">MMseqs2</xref>
+        </xrefs>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1038/nbt.3988</citation>
+            <citation type="doi">10.1101/079681</citation>
+            <citation type="doi">10.1038/s41467-018-04964-5</citation>
+            <citation type="doi">10.1093/bioinformatics/bty1057</citation>
+            <citation type="doi">10.1101/2020.11.27.401018</citation>
+            <citation type="doi">10.1093/bioinformatics/btab184</citation>
+        </citations>
+    </xml>
+</macros>