Add kMetaShot and DM for kMetaShot

data_managers/data_manager_kmetashot/.shed.yml

@@ -0,0 +1,10 @@
+categories:
+- Data Managers
+- Metagenomics
+homepage_url: https://github.com/gdefazio/kMetaShot
+description: Data manager for kMetaShot reference data
+long_description: Data manager for kMetaShot reference data
+name: kmetashot_build_database
+owner: iuc
+remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/main/data_managers/data_manager_kmetashot
+type: unrestricted

data_managers/data_manager_kmetashot/data_manager/kmetashot_datamanager.xml

@@ -0,0 +1,83 @@
+<tool id="kmetashot_build_database" name="kMetaShot" tool_type="manage_data" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>database builder</description>
+    <macros>
+        <token name="@TOOL_VERSION@">2.0</token>
+        <token name="@VERSION_SUFFIX@">0</token>
+        <token name="@PROFILE@">24.1</token>
+    </macros>
+    <requirements>
+        <requirement type="package" version="@TOOL_VERSION@">kmetashot</requirement>
+    </requirements>
+    <command><![CDATA[ 
+        mkdir -p "$out_file.extra_files_path" &&
+        #if $test != "true":
+            #if $release == "1":
+                wget "https://zenodo.org/records/17591095/files/kMetaShot_reference.h5" &&
+                mv "kMetaShot_reference.h5" "$out_file.extra_files_path" &&
+            #else:
+                wget "https://zenodo.org/records/17375120/files/kMetaShot_bacteria_archaea_2025-05-22.h5" &&
+                mv "kMetaShot_bacteria_archaea_2025-05-22.h5" "$out_file.extra_files_path" &&
+            #end if
+        #else:
+            touch '$out_file.extra_files_path'/kMetaShot_bacteria_archaea_2025-05-22.h5 &&
+        #end if
+        cp "$dmjson" "$out_file"
+    ]]></command>
+    <configfiles>
+        <configfile name="dmjson"><![CDATA[
+{
+  "data_tables":{
+    "kmetashot":[
+      {
+        "dbkey":"kmetashot",
+        "version":"${release}",
+        #if $test == "true":
+            "path":"${out_file.extra_files_path}/kMetaShot_bacteria_archaea_2025-05-22.h5",
+            "name":"kMetaShot reference data 2025-05-22 - TEST",
+            "value":"2025-05-22"
+        #else:
+            #if $release == "1":
+                "path":"${out_file.extra_files_path}/kMetaShot_reference.h5",
+                "name":"kMetaShot reference data 2022-07-31",
+                "value":"2022-07-31"
+            #else:
+                "path":"${out_file.extra_files_path}/kMetaShot_bacteria_archaea_2025-05-22.h5",
+                "name":"kMetaShot reference data 2025-05-22",
+                "value":"2025-05-22"
+            #end if
+        #end if
+      }
+    ]
+  }
+}]]>
+        </configfile>
+    </configfiles>
+    <inputs>
+        <param name="release" type="select" multiple="false" label="kMetaShot reference data release">
+            <option value="1">First release</option>
+            <option value="2">Second release</option>
+        </param>
+        <param name="test" type="hidden" value="" checked="false" label="Run test"/>
+    </inputs>
+    <outputs>
+        <data name="out_file" format="data_manager_json" />
+    </outputs>
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="release" value="2"/>
+            <param name="test" value="true"/>
+            <output name="out_file">
+                <assert_contents>
+                    <has_text text="25-05-22"/>
+                    <has_text text="kMetaShot reference data 2025-05-22 - TEST"/>
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+    <help><![CDATA[
+Download and extract kMetaShot reference data.
+    ]]></help>
+    <citations>
+        <citation type="doi">10.1038/s41592-023-01940-w</citation>
+    </citations>
+</tool>

data_managers/data_manager_kmetashot/data_manager_conf.xml

@@ -0,0 +1,20 @@
+<data_managers>
+    <data_manager tool_file="data_manager/kmetashot_datamanager.xml" id="kmetashot_build_database">
+        <data_table name="kmetashot">
+            <output>
+                <column name="value"/>
+                <column name="dbkey"/>
+                <column name="name"/>
+                <column name="version"/>
+                <column name="path" output_ref="out_file">
+                    <move type="file">
+                        <source>${path}</source>
+                        <target base="${GALAXY_DATA_MANAGER_DATA_PATH}">kmetashot/${value}/${path}</target>
+                    </move>
+                    <value_translation>${GALAXY_DATA_MANAGER_DATA_PATH}/kmetashot/${value}/${path}</value_translation>
+                    <value_translation type="function">abspath</value_translation>
+                </column>
+            </output>
+        </data_table>
+    </data_manager>
+</data_managers>

data_managers/data_manager_kmetashot/test-data/kmetashot.loc

@@ -0,0 +1,3 @@
+
+25-05-22	kMetaShot-25-05-22	kMetaShot reference data 2025-05-22	2	/tmp/tmpf_hplx2a/galaxy-dev/tool-data/kmetashot/2/kMetaShot_bacteria_archaea_2025-05-22.h5
+2025-05-22	kmetashot	kMetaShot reference data 2025-05-22 - TEST	2	/home/sf373/sf373/galaxy/tool-data/kmetashot/2025-05-22/tmp/tmpt500ppxr/job_working_directory/000/1/outputs/dataset_46c18f80-8c8e-416d-ad88-f91119feab82_files/kMetaShot_bacteria_archaea_2025-05-22.h5

data_managers/data_manager_kmetashot/tool-data/kmetashot.loc.sample

@@ -0,0 +1,9 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a the kMetaShot database.
+#You will need to create these data files using the following command
+
+#wget [selected version] [url_from_donwlaod]
+
+#The <version> column indicates the version from the kMetaShot ref data was downloaded
+
+#25-05-22	kMetaShot-25-05-22	kMetaShot reference data 2025-05-22	2	/mnt/galaxyIndices/kMetaShot_database/kMetaShot_bacteria_archaea_2025-05-22.h5

data_managers/data_manager_kmetashot/tool_data_table_conf.xml.sample

@@ -0,0 +1,6 @@
+<tables>
+    <table name="kmetashot" comment_char="#" allow_duplicate_entries="False">
+        <columns>value, dbkey, name, version, path</columns>
+        <file path="tool-data/kmetashot.loc" />
+    </table>
+</tables>

data_managers/data_manager_kmetashot/tool_data_table_conf.xml.test

@@ -0,0 +1,7 @@
+<tables>
+    <!-- Location of kmetashot indexes for testing -->
+    <table name="kmetashot" comment_char="#" allow_duplicate_entries="False">
+        <columns>value, dbkey, name, version, path</columns>
+        <file path="${__HERE__}/test-data/kmetashot.loc" />
+    </table>
+</tables>

tools/kmetashot/.shed.yml

@@ -0,0 +1,13 @@
+name: kmetashot
+owner: iuc
+description: an alignment-free taxonomic classifier based on k-mer/minimizer counting
+long_description: |
+  kMetaShot, a bioinformatic approach relying on k-mer/minimizer profiling 
+  from the reference prokaryotic genomes, in order to build a concise 
+  representation of genomic diversity and perform MAG taxonomic 
+  classification up to the strain level
+homepage_url: https://github.com/gdefazio/kMetaShot
+remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/main/tools/kmetashot
+categories:
+  - Metagenomics
+type: unrestricted

tools/kmetashot/kmetashot.xml

@@ -0,0 +1,92 @@
+<tool id="kmetashot" name="kMetaShot" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>an alignment-free taxonomic classifier based on k-mer/minimizer counting</description>
+    <macros>
+        <token name="@TOOL_VERSION@">2.0</token>
+        <token name="@VERSION_SUFFIX@">0</token>
+        <token name="@PROFILE@">24.1</token>
+    </macros>
+    <requirements>
+        <requirement type="package" version="@TOOL_VERSION@">kmetashot</requirement>
+    </requirements>
+    <command detect_errors="exit_code">
+        <![CDATA[
+            #import re
+
+            mkdir "output" "bins" &&
+
+            #for $file in $bins_dir:
+                #set $identifier = re.sub("[^\s\w\-]", "_", str($file.element_identifier))
+                ln -s "$file" "bins/${identifier}.$file.ext" &&
+            #end for
+
+            kMetaShot_classifier_NV.py 
+            -b "bins"
+            -o "output"
+            -r "$reference.fields.path"
+            -p "\${GALAXY_SLOTS:-1}"
+            -a ${ass2ref}
+
+        ]]>
+    </command>
+    <inputs>
+        <param argument="--bins_dir" type="data" multiple="true" format="fasta,fasta.gz" label="Bin(s)/MAG(s) fasta file"/>
+        <param argument="--reference" type="select" label="Select reference">
+            <options from_data_table="kmetashot">
+                <filter type="sort_by" column="2"/>
+            </options>
+            <validator type="no_options" message="No reference data for kMetaShot is installed. Please contact the Galaxy adminstrators to request one be installed."/>
+        </param>
+        <param argument="--ass2ref" type="float" min="0.0" value="0.0" max="1.0" label="Set ass2ref parameter" help="Set the number of non redundant minimizers found in classified MAG for classified strain"/>
+    </inputs>
+    <outputs>
+        <collection name="result" type="list">
+            <discover_datasets pattern="(?P&lt;designation&gt;.*)\.csv" format="tabular" directory="output"/>
+        </collection>
+    </outputs>
+    <tests>
+        <!-- Since this tool need his ref data to work there is no way to test this tool really because of this there is only this test to see of the tool is starting or not -->
+         <test expect_exit_code="1" expect_failure="true">
+            <param name="bins_dir" value="all_contig.fasta.gz" ftype="fasta.gz"/>
+            <param name="ass2ref" value="0.2"/>
+            <assert_command>
+                <has_text text="kMetaShot_classifier_NV.py -b bins"/>
+                <has_text text="-o output"/>
+                <has_text text="-a 0.2"/>
+            </assert_command>
+         </test>
+         <test expect_exit_code="1" expect_failure="true">
+            <param name="bins_dir" value="all_contig.fasta.gz" ftype="fasta.gz"/>
+            <param name="ass2ref" value="0.3"/>
+            <assert_command>
+                <has_text text="kMetaShot_classifier_NV.py -b bins"/>
+                <has_text text="-o output"/>
+                <has_text text="-a 0.3"/>
+            </assert_command>
+         </test>
+    </tests>
+    <help>
+        <![CDATA[
+
+            To learn more about the inside of the tool you can visit the `kMetaShot GitHub page <https://github.com/gdefazio/kMetaShot>`_!
+
+            **Input**
+
+            Fasta file(s) in fasta format or/and fasta.gz format (.fa, .fasta, .fna, .fa.gz, .fasta.gz, .fna.gz are allowed extensions)
+
+            **Reference**
+
+            The reference data needed for this tool must be provided from the data manager which always installs the latest version of the data
+
+            **Output**
+
+            The Output is a collection with csv file(s) which contained the classification for the inputted bin(s)/MAG(s)
+
+            In the output files(s) each line has the followed structure: num,bin,ass2ref,taxid,species,genus,family,order,class,phylum,superkingdom,organism_name 
+            This means each bin will be classified by this tool and all ids (NCBI) will be written in this order if the tool can classified it together with the organism name!
+
+        ]]>
+    </help>  
+    <citations>
+        <citation type="doi">10.1093/bib/bbae680</citation>
+    </citations>
+</tool>