Added the profile2cami tool, a component of the TaxonKit suite. (#6085)

* Added the profile2cami tool, a component of the TaxonKit suite. * Renamed shed.yml -> .shed.yml * Shrinked delnodes.dmp 684kb -> 150kb * Renamed test.loc -> ncbi_taxonomy.loc * Adjusted taxonkit, removed folder profile2cami, added suite in .shed.yml * Updated Taxonkit to version 0.17.0 - worked on issues. * Renamed taxonomy.loc -> taxonomy.loc.test * Adjusted test, adjusted loc.sample * Try to fix linting error * Resolving linting error * Adjusted the output label.
galaxyproject · Jul 26, 2024 · 695ea58 · 695ea58
1 parent 3cce4c7
commit 695ea58
Show file tree

Hide file tree

Showing 20 changed files with 15,768 additions and 0 deletions.
diff --git a/tools/taxonkit/.shed.yml b/tools/taxonkit/.shed.yml
@@ -0,0 +1,18 @@
+name: taxonkit
+owner: iuc
+description: TaxonKit - A Practical and Efficient NCBI Taxonomy Toolkit
+homepage_url: https://bioinf.shenwei.me/taxonkit/
+long_description: |
+  TaxonKit is a set of tools for analyzing and manipulating taxonomic data. It includes utilities for converting metagenomic profile tables to CAMI format, among other functionalities.
+remote_repository_url: https://github.com/shenwei356/taxonkit
+categories: 
+- Metagenomics
+type: unrestricted
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "Wrapper for TaxonKit function: {{ tool_name }}."
+suite:
+  name: "suite_taxonkit"
+  description: "A suite of tools that brings the TaxonKit project into Galaxy."
+  long_description: |
+      TaxonKit is a set of tools for analyzing and manipulating taxonomic data, including converting metagenomic profile tables to CAMI format.
diff --git a/tools/taxonkit/macros.xml b/tools/taxonkit/macros.xml
@@ -0,0 +1,22 @@
+ <macros>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">taxonkit</requirement>
+            <yield/>
+        </requirements>
+    </xml>
+    <token name="@TOOL_VERSION@">0.17.0</token>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@PROFILE@">21.05</token>
+    <xml name="biotools">
+        <xrefs>
+            <xref type="bio.tools">taxonkit</xref>
+        </xrefs>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1016/j.jgg.2021.03.006</citation>
+            <yield/>
+        </citations>
+    </xml>
+</macros>
diff --git a/tools/taxonkit/taxonkit_profile2cami.xml b/tools/taxonkit/taxonkit_profile2cami.xml
@@ -0,0 +1,111 @@
+<tool id="profile2cami" name="Profile2CAMI" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>Convert metagenomic profile table to CAMI format</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>    
+    <expand macro="biotools"/>
+    <expand macro="requirements" />
+    <command detect_errors="exit_code">
+    <![CDATA[
+        taxonkit profile2cami
+        --data-dir '${taxonomy.fields.path}'
+        --abundance-field '${abundance_field}'
+        --taxid-field '${taxid_field}'
+
+        $percentage
+        $recompute_abd
+        $keep_zero
+        $no_sum_up
+
+        #if $sample_id:
+            -s '${sample_id}'
+        #end if
+        #if $taxonomy_id:
+            -t '${taxonomy_id}'
+        #end if
+        #if $ranks:
+            --show-rank '${ranks}'
+        #end if
+        ${input_file}
+        > '${cami_output}'
+    ]]>
+    </command>
+    <inputs>
+        <param name="input_file" type="data" format="txt" label="Input Profile File" help="A tab-delimited profile file with TaxId and abundance columns." />
+        <param argument="--taxonomy" type="select" label="NCBI taxonomy" help="This NCBI database is used to map human-readable taxon names to TaxId's.">
+            <options from_data_table="ncbi_taxonomy">
+                <validator message="No NCBI database is available" type="no_options"/>
+            </options>
+        </param>
+        <param name="abundance_field" type="integer" value="2" label="Abundance Field Index" help="Field index of abundance in the input data." />
+        <param name="taxid_field" type="integer" value="1" label="TaxId Field Index" help="Field index of TaxId in the input data." />
+        <param name="percentage" type="boolean" value="false" label="Abundance in Percentage" help="Check if the abundance values are in percentage." truevalue="-p" falsevalue=""/>
+        <param name="recompute_abd" type="boolean" value="false" label="Recompute Abundance" help="Check to recompute abundance if some TaxIds are deleted in the current taxonomy version." truevalue="-R" falsevalue=""/>
+        <param name="keep_zero" type="boolean" value="false" label="Keep Zero Abundances" help="Check to keep taxons with abundance of zero." truevalue="-0" falsevalue=""/>
+        <param name="no_sum_up" type="boolean" value="false" label="Do Not Sum Up Abundance" help="Do not sum up abundance from child to parent TaxIds." truevalue="-S" falsevalue="" />
+        <param name="sample_id" type="text" value="" label="Sample ID" help="Optional sample ID to include in the result file." />
+        <param name="taxonomy_id" type="text" value="" label="Taxonomy ID" help="Optional taxonomy ID to include in the result file." />
+        <param name ="ranks" argument="--show-rank" type="select" multiple="true" label="Show Ranks" help="Specify the ranks to show in the result file (default [superkingdom,phylum,class,order,family,genus,species,strain]).">
+            <option value="superkingdom">Superkingdom</option>
+            <option value="phylum">Phylum</option>
+            <option value="class">Class</option>
+            <option value="order">Order</option>
+            <option value="family">Family</option>
+            <option value="genus">Genus</option>
+            <option value="species">Species</option>
+            <option value="strain">Strain</option>
+        </param>
+    </inputs>
+    <outputs>
+        <data name="cami_output" format="tsv" label="${tool.name} on ${on_string}" />
+    </outputs>
+    <tests>
+        <!-- Test 1: Basic functionality with default parameters -->
+        <test expect_num_outputs="1">
+            <param name="input_file" value="abundance.tsv" ftype="tsv" />
+            <output name="cami_output" file="output1_basic_functionality.tsv" />
+        </test>
+
+        <!-- Test 2: Using percentage flag -->
+        <test expect_num_outputs="1">
+            <param name="input_file" value="abundance.tsv" ftype="tsv" />
+            <param name="percentage" value="true" />
+            <output name="cami_output" file="output2_percentage_flag.tsv" />
+        </test>
+
+        <!-- Test 3: Recomputing abundance with deleted TaxIds -->
+        <test expect_num_outputs="1">
+            <param name="input_file" value="abundance.tsv" ftype="tsv" />
+            <param name="recompute_abd" value="true" />
+            <output name="cami_output" file="output3_recompute_abd.tsv" />
+        </test>
+
+        <!-- Test 4: Profile2Cami with all parameters checked -->
+        <test expect_num_outputs="1">
+            <param name="input_file" value="abundance.tsv" ftype="tsv" />
+            <param name="percentage" value="true" />
+            <param name="recompute_abd" value="true" />
+            <param name="keep_zero" value="true" />
+            <param name="no_sum_up" value="true" />
+            <output name="cami_output" file="output4_all_param.tsv" />
+        </test>
+        </tests>
+        <help>
+        <![CDATA[
+            **What is Profile2CAMI**
+
+            Profile2CAMI is a tool for converting metagenomic profile tables to CAMI format.
+
+            **Inputs**
+
+            - A tab-delimited profile file with TaxId and abundance columns.
+
+            **Outputs**
+
+            - A CAMI formatted file.
+
+            For more information, please refer to the tool's documentation.
+        ]]>
+        </help>
+    <expand macro="citations" />
+</tool>
diff --git a/tools/taxonkit/test-data/abundance.tsv b/tools/taxonkit/test-data/abundance.tsv
@@ -0,0 +1,4 @@
+83333	0.2	merged to 562
+83333	0.2	absord 562
+561	0.5	no change
+91347	0.1	deleted
diff --git a/tools/taxonkit/test-data/ncbi_taxonomy.loc.test b/tools/taxonkit/test-data/ncbi_taxonomy.loc.test
@@ -0,0 +1 @@
+test-db-tox	Test Database	${__HERE__}/test-db
diff --git a/tools/taxonkit/test-data/output1_basic_functionality.tsv b/tools/taxonkit/test-data/output1_basic_functionality.tsv
@@ -0,0 +1,12 @@
+@SampleID:
+@Version:0.10.0
+@Ranks:superkingdom|phylum|class|order|family|genus|species|strain
+@TaxonomyID:
+@@TAXID	RANK	TAXPATH	TAXPATHSN	PERCENTAGE
+2	superkingdom	2	Bacteria	100.000000000000000
+1224	phylum	2|1224	Bacteria|Proteobacteria	100.000000000000000
+1236	class	2|1224|1236	Bacteria|Proteobacteria|Gammaproteobacteria	100.000000000000000
+91347	order	2|1224|1236|91347	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales	100.000000000000000
+543	family	2|1224|1236|91347|543	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales|Enterobacteriaceae	90.000000000000000
+561	genus	2|1224|1236|91347|543|561	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales|Enterobacteriaceae|Escherichia	90.000000000000000
+562	species	2|1224|1236|91347|543|561|562	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales|Enterobacteriaceae|Escherichia|Escherichia coli	40.000000000000000
diff --git a/tools/taxonkit/test-data/output2_percentage_flag.tsv b/tools/taxonkit/test-data/output2_percentage_flag.tsv
@@ -0,0 +1,12 @@
+@SampleID:
+@Version:0.10.0
+@Ranks:superkingdom|phylum|class|order|family|genus|species|strain
+@TaxonomyID:
+@@TAXID	RANK	TAXPATH	TAXPATHSN	PERCENTAGE
+2	superkingdom	2	Bacteria	1.000000000000000
+1224	phylum	2|1224	Bacteria|Proteobacteria	1.000000000000000
+1236	class	2|1224|1236	Bacteria|Proteobacteria|Gammaproteobacteria	1.000000000000000
+91347	order	2|1224|1236|91347	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales	1.000000000000000
+543	family	2|1224|1236|91347|543	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales|Enterobacteriaceae	0.900000000000000
+561	genus	2|1224|1236|91347|543|561	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales|Enterobacteriaceae|Escherichia	0.900000000000000
+562	species	2|1224|1236|91347|543|561|562	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales|Enterobacteriaceae|Escherichia|Escherichia coli	0.400000000000000
diff --git a/tools/taxonkit/test-data/output3_recompute_abd.tsv b/tools/taxonkit/test-data/output3_recompute_abd.tsv
@@ -0,0 +1,12 @@
+@SampleID:
+@Version:0.10.0
+@Ranks:superkingdom|phylum|class|order|family|genus|species|strain
+@TaxonomyID:
+@@TAXID	RANK	TAXPATH	TAXPATHSN	PERCENTAGE
+2	superkingdom	2	Bacteria	190.000000000000000
+1224	phylum	2|1224	Bacteria|Proteobacteria	190.000000000000000
+1236	class	2|1224|1236	Bacteria|Proteobacteria|Gammaproteobacteria	190.000000000000000
+91347	order	2|1224|1236|91347	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales	190.000000000000000
+543	family	2|1224|1236|91347|543	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales|Enterobacteriaceae	90.000000000000000
+561	genus	2|1224|1236|91347|543|561	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales|Enterobacteriaceae|Escherichia	90.000000000000000
+562	species	2|1224|1236|91347|543|561|562	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales|Enterobacteriaceae|Escherichia|Escherichia coli	40.000000000000000
diff --git a/tools/taxonkit/test-data/output4_all_param.tsv b/tools/taxonkit/test-data/output4_all_param.tsv
@@ -0,0 +1,12 @@
+@SampleID:
+@Version:0.10.0
+@Ranks:superkingdom|phylum|class|order|family|genus|species|strain
+@TaxonomyID:
+@@TAXID	RANK	TAXPATH	TAXPATHSN	PERCENTAGE
+2	superkingdom	2	Bacteria	0.500000000000000
+1224	phylum	2|1224	Bacteria|Proteobacteria	0.500000000000000
+1236	class	2|1224|1236	Bacteria|Proteobacteria|Gammaproteobacteria	0.500000000000000
+91347	order	2|1224|1236|91347	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales	0.500000000000000
+543	family	2|1224|1236|91347|543	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales|Enterobacteriaceae	0.500000000000000
+561	genus	2|1224|1236|91347|543|561	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales|Enterobacteriaceae|Escherichia	0.500000000000000
+562	species	2|1224|1236|91347|543|561|562	Bacteria|Proteobacteria|Gammaproteobacteria|Enterobacteriales|Enterobacteriaceae|Escherichia|Escherichia coli	0.400000000000000