changeset 2:7420753b0671 draft

"planemo upload for repository https://github.com/jj-umn/tools-iuc/tree/arriba/tools/arriba commit 7dbe725aaa7b4b84d7b14ea52f38f63d362bf09c"
author jjohnson
date Fri, 08 Oct 2021 19:23:48 +0000
parents 9f2665b32c45
children 2d32e6c86c48
files arriba.xml arriba_download_reference.xml arriba_get_filters.xml
diffstat 3 files changed, 79 insertions(+), 13 deletions(-) [+]
line wrap: on
line diff
--- a/arriba.xml	Fri Oct 08 11:16:21 2021 +0000
+++ b/arriba.xml	Fri Oct 08 19:23:48 2021 +0000
@@ -19,9 +19,12 @@
         #set read2 = 'input_2.fastq'
     #end if
     ln -f -s '${input_params.right_fq}' ${read2} &&
+    #if str($input_params.index.index_source) == "history"
+        #set $star_index_dir = $input_params.index.star_index.files_path
+    #end if
     STAR 
     --runThreadN \${GALAXY_SLOTS:-1} 
-    --genomeDir /path/to/STAR_index 
+    --genomeDir $star_index_dir
     --genomeLoad NoSharedMemory 
     --readFilesIn $read1 $read2
     --readFilesCommand zcat 
@@ -70,9 +73,7 @@
     ]]></command>
     <inputs>
         <conditional name="input_params">
-            <param name="input_source"
-                   type="select"
-                   label="Use output from earlier STAR run or let Arriba running STAR">
+            <param name="input_source" type="select" label="Use output from earlier STAR run or let Arriba running STAR">
                 <option value="use_star">Use output from earlier STAR</option>
                 <option value="use_fastq">Let Arriba control running STAR</option>
             </param>
@@ -93,6 +94,15 @@
                        format="fastqsanger,fastqsanger.gz"
                        argument="--right_fq"
                        label="right.fq file"/>
+                <conditional name="index">
+                    <param name="index_source" type="select" label="Arriba STAR index source">
+                        <option value="history">Arriba STAR index from your history</option>
+                    </param>
+                    <when value="history">
+                        <param name="star_index" argument="--genomeDir" type="data" format="txt" label="Arriba STAR index"
+                            help="generated by:  Arriba Reference"/>
+                    </when> 
+                </conditional>
             </when>
         </conditional>
         <param name="genome_assembly" argument="-a" type="data" format="fasta" label="genome assembly fasta"/>
@@ -219,6 +229,7 @@
       * Name=PROTEIN_DOMAIN_NAME;
       * gene_id=GENE_ID;
       * gene_name=GENE_NAME
+
     The attribute Name is reported in the column retained_protein_domains of Arriba's output file. Some special characters in the name are replaced with underscores (_). The columns gene_id and gene_name are used to match the protein domains to the genes given in the gene annotation. If a match cannot be found, Arriba cannot determine the retained protein domains of the respective gene and a warning is issued. There may be many warnings if RefSeq annotation is used, because the protein domains file distributed with Arriba uses ENSEMBL gene names/IDs.
 
   - Structural variant calls from WGS
--- a/arriba_download_reference.xml	Fri Oct 08 11:16:21 2021 +0000
+++ b/arriba_download_reference.xml	Fri Oct 08 19:23:48 2021 +0000
@@ -1,17 +1,18 @@
-<tool id="arriba_download_reference" name="Arriba Download Reference" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" python_template_version="3.5">
-    <description></description>
+<tool id="arriba_download_reference" name="Arriba Reference" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" python_template_version="3.5">
+    <description>Download to history</description>
     <macros>
         <import>macros.xml</import>
     </macros>
     <expand macro="requirements" />
     <expand macro="version_command" />
     <command detect_errors="exit_code"><![CDATA[
-    echo $arriba_reference_name > '$arriba_reference'
-    mkdir -p '$arriba_reference.files_path' &&
-    cd '$arriba_reference.files_path' &&
-    BASE_DIR=$(dirname $(dirname `which arriba`)) &&
-    REF_SCRIPT=`find $BASE_DIR -name 'download_references.sh'` &&
-    $REF_SCRIPT '$arriba_reference_name'
+    echo $arriba_reference_name > '$star_index' &&
+    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* > '$genome_gtf' &&
+    mv STAR*/* '$star_index.extra_files_path'
     ]]></command>
     <inputs>
         <param name="arriba_reference_name" type="select" label="Select reference">
@@ -56,7 +57,9 @@
         </param>
     </inputs>
     <outputs>
-        <data name="arriba_reference" format="txt" label="$arriba_reference_name"/>
+        <data name="genome_fasta" format="fasta" label="${tool.name} ${arriba_reference_name} fasta"/>
+        <data name="genome_gtf" format="gtf" label="${tool.name} ${arriba_reference_name} GTF"/>
+        <data name="star_index" format="txt" label="${tool.name} ${arriba_reference_name} STAR index"/>
     </outputs>
     <help><![CDATA[
 ** Arriba **
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/arriba_get_filters.xml	Fri Oct 08 19:23:48 2021 +0000
@@ -0,0 +1,52 @@
+<tool id="arriba_get_filters" name="Arriba Get Filters" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" python_template_version="3.5">
+    <description>to history</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <expand macro="version_command" />
+    <command detect_errors="exit_code"><![CDATA[
+    BASE_DIR=\$(dirname \$(dirname `which arriba`)) &&
+    REF_SCRIPT=`find \$BASE_DIR -name 'download_references.sh'` &&
+    REF_DIR=\$(dirname \$REF_SCRIPT) &&
+    REF_NAME=${arriba_reference_name.split('+')[0].replace('viral','')} &&
+    echo \$REF_NAME &&
+    cp `find \$REF_DIR -name 'blacklist_*' | grep -i \$REF_NAME` '$blacklist' && 
+    cp `find \$REF_DIR -name 'known_fusions_*' | grep -i \$REF_NAME` '$known_fusions' &&
+    cp `find \$REF_DIR -name 'protein_domains_*' | grep -i \$REF_NAME` '$protein_domains' &&
+    cp `find \$REF_DIR -name 'cytobands_*' | grep -i \$REF_NAME` '$cytobands'
+    #*
+    cp "\$REF_DIR/blacklist_*${arriba_reference_name}*" '$blacklist' &&
+    cp "\$REF_DIR/known_fusions_*${arriba_reference_name}*" '$known_fusions' &&
+    cp "\$REF_DIR/protein_domains_*${arriba_reference_name}*" '$protein_domains' &&
+    cp "\$REF_DIR/cytobands_*${arriba_reference_name}*" '$cytobands'
+    *#
+    ]]></command>
+    <inputs>
+        <param name="arriba_reference_name" type="text" label="Select reference">
+            <help>GRCh38 GRCh37 hg38 hg19 GRCm38 mm10</help>
+            <option value="GRCh38">GRCh38</option>
+            <option value="GRCh37">GRCh37</option>
+            <option value="hg38">hg38</option>
+            <option value="hg19">hg19</option>
+            <option value="GRCm38">GRCm38</option>
+            <option value="mm10">mm10</option>
+        </param>
+    </inputs>
+    <outputs>
+        <data name="blacklist" format="tabular" label="${tool.name} ${arriba_reference_name} blacklist"/>
+        <data name="known_fusions" format="tabular" label="${tool.name} ${arriba_reference_name} known_fusions"/>
+        <data name="protein_domains" format="tabular" label="${tool.name} ${arriba_reference_name} protein_domains"/>
+        <data name="cytobands" format="tabular" label="${tool.name} ${arriba_reference_name} cytobands"/>
+    </outputs>
+    <help><![CDATA[
+** Arriba **
+
+Arriba_ is a fast tool to search for aberrant transcripts such as gene fusions.
+It is based on chimeric alignments found by the STAR RNA-Seq aligner.
+
+.. _Arriba: https://arriba.readthedocs.io/en/latest/
+
+]]></help>
+    <expand macro="citations" />
+</tool>