diff taxonomy_filter_refseq.xml @ 1:d9662c76b6d5 draft default tip

"planemo upload for repository https://github.com/galaxyproject/tools-iuc commit e68b434ae52d29f038bac26874ceb51d4911b4fb"
author iuc
date Wed, 29 Apr 2020 16:50:22 -0400
parents 28e95c6a944d
children
line wrap: on
line diff
--- a/taxonomy_filter_refseq.xml	Wed Jan 16 08:30:47 2019 -0500
+++ b/taxonomy_filter_refseq.xml	Wed Apr 29 16:50:22 2020 -0400
@@ -1,7 +1,7 @@
 <tool id="taxonomy_filter_refseq" name="Filter RefSeq by taxonomy" version="@TOOL_VERSION@+galaxy0">
     <description>Only retain sequences that are descendants of a given taxonomic node.</description>
     <macros>
-        <token name="@TOOL_VERSION@">0.1.4</token>
+        <token name="@TOOL_VERSION@">0.3.0</token>
     </macros>
     <edam_topics>
         <edam_topic>topic_0091</edam_topic>
@@ -26,7 +26,7 @@
             mkdir taxonomy && ln -s '$taxonomy.nodes' taxonomy/nodes.dmp && ln -s '$taxonomy.names' taxonomy/names.dmp &&
             #set $taxonomy_dir = 'taxonomy'
         #end if
-	    taxonomy_filter_refseq '$refseq_input' '$taxonomy_dir' '$ancestor_name' >'$refseq_output_fasta'
+	    taxonomy_filter_refseq $no_curated $no_predicted '$refseq_input' '$taxonomy_dir' '$ancestor_name' >'$refseq_output_fasta'
     ]]></command>
     <inputs>
         <conditional name="taxonomy">
@@ -67,6 +67,14 @@
             </when>
         </conditional>
         <param name="ancestor_name" type="text" label="Ancestor taxon (scientific) name" />
+        <param argument="--no_curated" type="boolean" truevalue="--no_curated" falsevalue="" checked="false"
+            label="Exclude curated sequences from dataset"
+            help="Curated sequences are identified by their accession number prefixes and excluded if this option is checked"
+        />
+        <param argument="--no_predicted" type="boolean" truevalue="--no_predicted" falsevalue="" checked="false"
+            label="Exclude predicted sequences from the dataset"
+            help="Computationally predicted (but not curated) sequences are identifed by their accession number prefix and excluded if this option is checked"
+        />
     </inputs>
     <outputs>
         <data name="refseq_output_fasta" format="fasta" label="${tool.name} on ${on_string}" />
@@ -90,8 +98,32 @@
             <param name="names" ftype="txt" value="sample_tree_names.dmp" />
             <param name="history_refseq" ftype="fasta" value="sample_refseq.fasta" />
             <param name="ancestor_name" value="unclassified bacterial viruses" />
+            <param name="no_predicted" value="false" />
+            <param name="no_curated" value="false" />
             <output name="refseq_output_fasta" value="output1.fasta" />
         </test>
+        <test>
+            <param name="taxonomy_source" value="history" />
+            <param name="refseq_source" value="history" />
+            <param name="nodes" ftype="txt" value="sample_tree_nodes.dmp" />
+            <param name="names" ftype="txt" value="sample_tree_names.dmp" />
+            <param name="history_refseq" ftype="fasta" value="sample_refseq.fasta" />
+            <param name="ancestor_name" value="unclassified bacterial viruses" />
+            <param name="no_predicted" value="true" />
+            <param name="no_curated" value="false" />
+            <output name="refseq_output_fasta" value="output2.fasta" />
+        </test>        
+        <test>
+            <param name="taxonomy_source" value="history" />
+            <param name="refseq_source" value="history" />
+            <param name="nodes" ftype="txt" value="sample_tree_nodes.dmp" />
+            <param name="names" ftype="txt" value="sample_tree_names.dmp" />
+            <param name="history_refseq" ftype="fasta" value="sample_refseq.fasta" />
+            <param name="ancestor_name" value="unclassified bacterial viruses" />
+            <param name="no_predicted" value="false" />
+            <param name="no_curated" value="true" />
+            <output name="refseq_output_fasta" value="output3.fasta" />
+        </test>        
     </tests>
     <help><![CDATA[
         This tool allows NCBI RefSeq sequences to be filtered so that only those whose species name are