Add name2taxid function from taxonkit

tools/taxonkit/.shed.yml

@@ -16,3 +16,4 @@ suite:
   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.
+

tools/taxonkit/macros.xml

@@ -1,4 +1,4 @@
- <macros>
+<macros>
     <xml name="requirements">
         <requirements>
             <requirement type="package" version="@TOOL_VERSION@">taxonkit</requirement>

tools/taxonkit/taxonkit_name2taxid.xml

@@ -0,0 +1,134 @@
+<tool id="name2taxid" name="Name2taxid" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>Convert taxon names to NCBI Taxids</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="biotools"/>
+    <expand macro="requirements"/>
+    <command detect_errors="exit_code">
+    <![CDATA[
+
+        mkdir -p ../home/.taxonkit &&
+
+        #if $data.is_select == 'his':
+            ln -s '$taxdump' 'taxdump.tar.gz' &&
+            tar -xf 'taxdump.tar.gz' -C '.' &&
+        #else:
+            ln -s '$ncbi.fields.path/names.dmp' 'names.dmp' &&
+            ln -s '$ncbi.fields.path/merged.dmp' 'merged.dmp' &&
+            ln -s '$ncbi.fields.path/nodes.dmp' 'nodes.dmp' &&
+            ln -s '$ncbi.fields.path/delnodes.dmp' 'delnodes.dmp' &&
+        #end if
+
+        taxonkit name2taxid
+        --data-dir '.'
+        --name-field '$name_field'
+        $sci_name
+        $show_rank
+        '$input'
+        > '$output'
+    ]]>
+    </command>
+    <inputs>
+        <param name="input" type="data" format="tabular" label="Input file" help="Input any tsv file where the NCBI names are written. You can also use a .txt but only one name per row!"/>
+        <param argument="--name-field" type="data_column" data_ref="input" label="Select column with the names" help="Select the column where the name is written"/>
+        <param argument="--sci-name" type="boolean" falsevalue="" truevalue="--sci-name" checked="false" label="Only searching scientific names" help="With this option a non-scientific name will not yield any taxid since the tool will ignore them in the search. NOTE: The non-scientific names will still be in the output without taxid! "/>
+        <param argument="--show-rank" type="boolean" falsevalue="" truevalue="--show-rank" checked="false" label="Show rank" help="Use this option to yield the rank of the name in the output. For an example look at the help section!"/>
+        <conditional name="data">
+            <param name="is_select" type="select" label="Use either a cached NCBI database or provide a downloaded version.">
+                <option value="dm">Cached database</option>
+                <option value="his">History</option>
+            </param>
+            <when value="dm">
+                <param name="ncbi" type="select" label="NCBI database" help="Choose NCBI database version">
+                    <options from_data_table="ncbi_taxonomy">
+                        <validator message="No NCBI database is available" type="no_options"/>
+                    </options>
+                </param>
+            </when>
+            <when value="his">
+                <param name="taxdump" type="data" format="tgz" label="Input the taxdump.tar.gz file"
+                    help="You can find the taxdum.tar.gz at ftp://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz"/>
+            </when>
+        </conditional>
+    </inputs>
+    <outputs>
+        <data name="output" format="tabular" label="Names2taxID"/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="input" value="name2taxid_test1.tsv" ftype="tabular"/>
+            <param name="name_field" value="1"/>
+            <param name="sci_name" value="True"/>
+            <conditional name="data">
+                <param name="is_select" value="dm"/>
+                <param name="ncbi" value="test-db-tox"/>
+            </conditional>
+            <output name="output" file="name2taxid_result1.tsv"/>
+        </test>
+        <test>
+            <param name="input" value="name2taxid_test2.tsv" ftype="tabular"/>
+            <param name="show_rank" value="True"/>
+            <conditional name="data">
+                <param name="is_select" value="dm"/>
+                <param name="ncbi" value="test-db-tox"/>
+            </conditional>
+            <param name="name_field" value="2"/>
+            <output name="output" file="name2taxid_result2.tsv"/>
+        </test>
+        <test>
+            <param name="input" value="name2taxid_test3.txt" ftype="tabular"/>
+            <param name="name_field" value="1"/>
+            <conditional name="data">
+                <param name="is_select" value="his"/>
+                <param name="taxdump" ftype="tgz" value="test.tar.gz"/>
+             </conditional>
+            <output name="output" file="name2taxid_result3.tsv"/>
+        </test>
+    </tests>
+    <help>
+    <![CDATA[
+
+        This tool can convert a NCBI name to its corresponding taxid. Input a tsv or txt file and state the column where the name are written
+
+        .. class:: infomark
+
+        Example
+
+        ::
+
+            Homo sapiens
+            Akkermansia muciniphila ATCC BAA-835
+            Akkermansia muciniphila 
+            Mouse Intracisternal A-particle 
+
+        **sci_name option**
+        .. class:: infomark
+
+        For example, the name "Enterococcus coli" is not a scientific name which means with this option you can remove it from the query to find a taxid to it but it will still be in the output. In contrast, for example, Drosophila is a scientific name which means that this will always be searched in the query even if the option is on or off.
+
+        **show_rank option**
+        ..class:: infomark
+
+        Here is an example of the output if you use the option:
+
+        ::
+
+            Homo sapiens    9606    species
+            Akkermansia muciniphila ATCC BAA-835    349741    strain
+            Akkermansia muciniphila    239935    species
+            Mouse Intracisternal A-particle    11932    species
+
+        without this option the output will be:
+
+        ::
+
+            Homo sapiens    9606
+            Akkermansia muciniphila ATCC BAA-835    349741
+            Akkermansia muciniphila    239935
+            Mouse Intracisternal A-particle    11932
+
+    ]]>
+    </help>
+    <expand macro="citations"/>
+</tool>

tools/taxonkit/test-data/name2taxid_result1.tsv

@@ -0,0 +1,5 @@
+Homo sapiens	9606
+Akkermansia muciniphila ATCC BAA-835	349741
+Akkermansia muciniphila	239935
+Mouse Intracisternal A-particle	11932
+Enterococcus coli	

tools/taxonkit/test-data/name2taxid_result2.tsv

@@ -0,0 +1,4 @@
+test	Homo sapiens	9606	
+test	Akkermansia muciniphila ATCC BAA-835	349741	
+test	Akkermansia muciniphila	239935	
+test	Mouse Intracisternal A-particle	11932	

tools/taxonkit/test-data/name2taxid_result3.tsv

@@ -0,0 +1,4 @@
+Drosophila	7215
+Drosophila	32281
+Drosophila	2081351
+Enterococcus coli	562

tools/taxonkit/test-data/name2taxid_test1.tsv

@@ -0,0 +1,5 @@
+Homo sapiens
+Akkermansia muciniphila ATCC BAA-835
+Akkermansia muciniphila 
+Mouse Intracisternal A-particle
+Enterococcus coli

tools/taxonkit/test-data/name2taxid_test2.tsv

@@ -0,0 +1,4 @@
+test	Homo sapiens
+test	Akkermansia muciniphila ATCC BAA-835
+test	Akkermansia muciniphila 
+test	Mouse Intracisternal A-particle 

tools/taxonkit/test-data/name2taxid_test3.txt

@@ -0,0 +1,2 @@
+Drosophila
+Enterococcus coli

tools/taxonkit/test-data/ncbi_taxonomy.loc.test

@@ -1 +1,2 @@
+#value	name	path
 test-db-tox	Test Database	${__HERE__}/test-db

tools/taxonkit/test-data/test-db/delnodes.dmp

@@ -1,3 +1,4 @@
+
 2923441	|
 2923440	|
 2923439	|

tools/taxonkit/test-data/test-db/names.dmp

@@ -71,5 +71,4 @@
 1	|	all	|		|	synonym	|
 1	|	root	|		|	scientific name	|
 131567	|	biota	|		|	synonym	|
-131567	|	cellular organisms	|		|	scientific name	|
-
+131567	|	cellular organisms	|		|	scientific name	|

tools/taxonkit/tool-data/ncbi_taxonomy.loc.sample

@@ -1,2 +1,2 @@
 #value	name	path
-# test-db-tox	"Test Database"  tool-data/test-db
+test-db-tox	"Test Database"  ${__HERE__}/test-db

tools/taxonkit/tool_data_table_conf.xml.sample

@@ -3,6 +3,6 @@
         <!-- Locations of taxonomy data downloaded from NCBI -->
     <table name="ncbi_taxonomy" comment_char="#">
         <columns>value, name, path</columns>
-        <file path="tool-data/ncbi_taxonomy.loc" />
+        <file path="${__HERE__}/test-data/ncbi_taxonomy.loc.test" />
     </table>
 </tables>