changeset 3:2d32e6c86c48 draft

"planemo upload for repository https://github.com/jj-umn/tools-iuc/tree/arriba/tools/arriba commit b4882afed9ec678b576f126907094c77c03eae96"
author jjohnson
date Fri, 08 Oct 2021 20:44:25 +0000
parents 7420753b0671
children 77021ad5037d
files arriba.xml arriba_download_reference.xml
diffstat 2 files changed, 41 insertions(+), 3 deletions(-) [+]
line wrap: on
line diff
--- a/arriba.xml	Fri Oct 08 19:23:48 2021 +0000
+++ b/arriba.xml	Fri Oct 08 20:44:25 2021 +0000
@@ -70,6 +70,27 @@
     #end if
     -o fusions.tsv
     -O fusions.discarded.tsv 
+#if str($input_params.input_source) == "use_fastq"
+    && samtools sort -@ "$THREADS" -m 4G -T tmp -O bam Aligned.out.bam > Aligned.sortedByCoord.out.bam
+    && samtools index Aligned.sortedByCoord.out.bam
+#elif str($visualization.do_viz) == "yes"
+    && samtools sort -@ "$THREADS" -m 4G -T tmp -O bam '$input_params.input' > Aligned.sortedByCoord.out.bam
+    && samtools index Aligned.sortedByCoord.out.bam
+#end if
+#if str($visualization.do_viz) == "yes"
+draw_fusions.R \
+    --fusions=fusions.tsv 
+    --alignments=Aligned.sortedByCoord.out.bam 
+    --output=fusions.pdf 
+    --annotation='$gtf'
+    #if $visualization.cytobands
+    --cytobands='$visualization.cytobands'
+    #end if
+    #if '$protein_domains'
+    --proteinDomains=database/protein_domains_hg19_hs37d5_GRCh37_v2.1.0.gff3
+    #end if
+#end if
+
     ]]></command>
     <inputs>
         <conditional name="input_params">
@@ -107,16 +128,33 @@
         </conditional>
         <param name="genome_assembly" argument="-a" type="data" format="fasta" label="genome assembly fasta"/>
         <param name="gtf" argument="-g" type="data" format="gtf" label="GTF file with gene annotation"/>
-        <param name="blacklist" argument="-b" type="data" format="tabular" label="File containing blacklisted ranges."/>
+        <param name="blacklist" argument="-b" type="data" format="tabular" optional="true" label="File containing blacklisted ranges."/>
         <param name="protein_domains" argument="-p" type="data" format="gff3" optional="true" label="File containing blacklisted ranges."/>
         <param name="known_fusions" argument="-k" type="data" format="tabular"  optional="true" label="File containing known fusions">
             <help><![CDATA[ file two TAB separated columns: five-prime region three-prime region ]]></help>
         </param>
         <param name="tags" argument="-t" type="data" format="tabular" optional="true" label="File containing tag names for a fusion."/>
+        <conditional name="visualization">
+            <param name="do_viz" type="select" label="Generate visualization">
+                <option value="yes">Yes</option>
+                <option value="no">no</option>
+            </param>
+            <when value="yes">
+                <param name="cytobands" argument="--cytobands" type="data" format="tabular" optional="true" label="Cytobands"/>
+            </when>
+            <when value="no"/>
+        </conditional>
+        
     </inputs>
     <outputs>
         <data name="fusions" format="tabular" label="${tool.name} on ${on_string}: fusions.tsv" from_work_dir="fusions.tsv"/>
         <data name="discarded" format="tabular" label="${tool.name} on ${on_string}: fusions.discarded.tsv" from_work_dir="fusions.discarded.tsv"/>
+        <data name="aligned_bam" format="bam" label="${tool.name} on ${on_string}: Aligned.bam" from_work_dir="Aligned.sortedByCoord.out.bam">
+            <filter>input_params['input_source'] == "use_fastq"</filter>
+        </data> 
+        <data name="fusions_png" format="png" label="${tool.name} on ${on_string}: fusions.pdf" from_work_dir="fusions.pdf">
+            <filter>visualization['do_viz'] == "yes"</filter>
+        </data> 
     </outputs>
     <help><![CDATA[
 ** Arriba **
--- a/arriba_download_reference.xml	Fri Oct 08 19:23:48 2021 +0000
+++ b/arriba_download_reference.xml	Fri Oct 08 20:44:25 2021 +0000
@@ -10,8 +10,8 @@
     BASE_DIR=\$(dirname \$(dirname `which arriba`)) &&
     REF_SCRIPT=`find \$BASE_DIR -name 'download_references.sh'` &&
     \$REF_SCRIPT '$arriba_reference_name' &&
-    cp *.fa* > '$genome_fasta' &&
-    cp *.gtf* > '$genome_gtf' &&
+    cp *.fa*  '$genome_fasta' &&
+    cp *.gtf*  '$genome_gtf' &&
     mv STAR*/* '$star_index.extra_files_path'
     ]]></command>
     <inputs>