diff arriba.xml @ 5:005b200c8841 draft

"planemo upload for repository https://github.com/jj-umn/tools-iuc/tree/arriba/tools/arriba commit bdefea23247f7d999b96e232ce810e2887338680"

--- a/arriba.xml	Sat Oct 09 15:41:49 2021 +0000
+++ b/arriba.xml	Sun Oct 10 13:00:45 2021 +0000
@@ -71,7 +71,9 @@
         -t '$tags'
     #end if
     -o fusions.tsv
+#if $output_fusions_discarded
     -O fusions.discarded.tsv 
+#end if
 #if str($input_params.input_source) == "use_fastq"
     && samtools sort -@ \${GALAXY_SLOTS:-1} -m 4G -T tmp -O bam Aligned.out.bam > Aligned.sortedByCoord.out.bam
     && samtools index Aligned.sortedByCoord.out.bam
@@ -88,7 +90,7 @@
     #if $visualization.cytobands
     --cytobands='$visualization.cytobands'
     #end if
-    #if '$protein_domains'
+    #if $protein_domains
     --proteinDomains='$protein_domains'
     #end if
 #end if
@@ -130,13 +132,14 @@
         </conditional>
         <param name="genome_assembly" argument="-a" type="data" format="fasta" label="genome assembly fasta"/>
         <param name="gtf" argument="-g" type="data" format="gtf" label="GTF file with gene annotation"/>
-        <param name="blacklist" argument="-b" type="data" format="tabular" optional="true" label="File containing blacklisted ranges."/>
+        <param name="blacklist" argument="-b" type="data" format="tabular,tabular.gz" optional="true" label="File containing blacklisted ranges."/>
         <param name="protein_domains" argument="-p" type="data" format="gff3" optional="true" label="File containing protein domains"/>
-        <param name="known_fusions" argument="-k" type="data" format="tabular"  optional="true" label="File containing known fusions">
+        <param name="known_fusions" argument="-k" type="data" format="tabular,tabular.gz"  optional="true" label="File containing known fusions">
             <help><![CDATA[ file two TAB separated columns: five-prime region three-prime region ]]></help>
         </param>
         <param name="tags" argument="-t" type="data" format="tabular" optional="true" label="File containing tag names for a fusion."
                help="This can be the known fusions if that input has a third column with a name"/>
+        <param name="output_fusions_discarded" type="boolean" truevalue="yes" falsevalue="no" checked="true" label="Output fusions.discarded.tsv"/>
         <conditional name="visualization">
             <param name="do_viz" type="select" label="Generate visualization">
                 <option value="yes">Yes</option>
@@ -147,11 +150,12 @@
             </when>
             <when value="no"/>
         </conditional>
-        
     </inputs>
     <outputs>
         <data name="fusions" format="tabular" label="${tool.name} on ${on_string}: fusions.tsv" from_work_dir="fusions.tsv"/>
-        <data name="discarded" format="tabular" label="${tool.name} on ${on_string}: fusions.discarded.tsv" from_work_dir="fusions.discarded.tsv"/>
+        <data name="discarded" format="tabular" label="${tool.name} on ${on_string}: fusions.discarded.tsv" from_work_dir="fusions.discarded.tsv">
+            <filter> output_fusions_discarded == "yes"</filter>
+        </data> 
         <data name="aligned_bam" format="bam" label="${tool.name} on ${on_string}: Aligned.bam" from_work_dir="Aligned.sortedByCoord.out.bam">
             <filter>input_params['input_source'] == "use_fastq"</filter>
         </data> 
@@ -168,8 +172,10 @@
             </conditional>
             <param name="genome_assembly" ftype="fasta" value="genome.fasta"/>
             <param name="gtf" ftype="gtf" value="genome.gtf"/>
+            <param name="protein_domains" ftype="gff3" value="protein_domains.gff3"/>
             <conditional name="visualization">
                 <param name="do_viz" value="no"/>
+                <param name="cytobands" ftype="tabular" value="cytobands.tsv"/>
             </conditional>
             <output name="fusions">
                 <assert_contents>
@@ -177,6 +183,24 @@
                 </assert_contents>
             </output>
         </test>
+        <!-- Test 2 - From exisitng BAM with protein_domains and visualization -->
+        <test> 
+            <conditional name="input_params">
+                <param name="input_source" value="use_star"/>
+                <param name="input" ftype="sam" value="Aligned.out.sam"/>
+            </conditional>
+            <param name="genome_assembly" ftype="fasta" value="genome.fasta"/>
+            <param name="gtf" ftype="gtf" value="genome.gtf"/>
+            <conditional name="visualization">
+                <param name="do_viz" value="yes"/>
+            </conditional>
+            <output name="fusions">
+                <assert_contents>
+                    <has_text_matching expression="BCR\tABL1"/>
+                </assert_contents>
+            </output>
+        </test>
+
     </tests>
     <help><![CDATA[
 ** Arriba **
@@ -379,7 +403,10 @@
     The file fusions.discarded.tsv (as specified by the parameter -O) contains all events that Arriba classified as an artifact or that are also observed in healthy tissue. It has the same format as the file fusions.tsv. 
 
 
+** VISUALIZATION_ **
+  - fusions.pdf
 
+    A PDF file with one page for each predicted fusion. Each page depicts the fusion partners, their orientation, the retained exons in the fusion transcript, statistics about the number of supporting reads, and if the column fusion_transcript has a value an excerpt of the sequence around the breakpoint.
 
 
 Code repository: https://github.com/suhrig/arriba
@@ -391,6 +418,7 @@
 .. _Arriba: https://arriba.readthedocs.io/en/latest/
 .. _INPUTS: https://arriba.readthedocs.io/en/latest/input-files/
 .. _OUTPUTS: https://arriba.readthedocs.io/en/latest/output-files/
+.. _VISUALIZATION: https://arriba.readthedocs.io/en/latest/visualization/
 
     ]]></help>
     <expand macro="citations" />