From f8fe833da2622afe96f188309ca3facb59a324eb Mon Sep 17 00:00:00 2001
From: drosofff <drosofff@gmail.com>
Date: Wed, 30 Oct 2024 20:24:24 +0100
Subject: [PATCH] seed wisecondorx galaxy wrapper

---
 tools/wisecondorx/.shed.yml                | 13 +++
 tools/wisecondorx/macro.xml                |  6 ++
 tools/wisecondorx/wisecondor_reference.xml | 63 +++++++++++++++
 tools/wisecondorx/wisecondor_test.xml      | 92 ++++++++++++++++++++++
 4 files changed, 174 insertions(+)
 create mode 100644 tools/wisecondorx/.shed.yml
 create mode 100644 tools/wisecondorx/macro.xml
 create mode 100644 tools/wisecondorx/wisecondor_reference.xml
 create mode 100644 tools/wisecondorx/wisecondor_test.xml

diff --git a/tools/wisecondorx/.shed.yml b/tools/wisecondorx/.shed.yml
new file mode 100644
index 00000000..29cc5335
--- /dev/null
+++ b/tools/wisecondorx/.shed.yml
@@ -0,0 +1,13 @@
+# .shed.yml supporting automatic pushes.
+owner: artbio
+name: wisecondorx
+description: Infer copy number variations from BAM files using WisecondorX
+long_description: |
+  Infer copy number variations from BAM files using WisecondorX
+  see GitHub repo: https://github.com/CenterForMedicalGeneticsGhent/WisecondorX/tree/master
+categories:
+  - Variant Analysis
+homepage_url: https://github.com/CenterForMedicalGeneticsGhent/WisecondorX/tree/master
+remote_repository_url: https://github.com/ARTbio/tools-artbio/tree/master/tools/wisecondorx
+toolshed:
+  - toolshed
diff --git a/tools/wisecondorx/macro.xml b/tools/wisecondorx/macro.xml
new file mode 100644
index 00000000..c755679e
--- /dev/null
+++ b/tools/wisecondorx/macro.xml
@@ -0,0 +1,6 @@
+<macros>
+    <token name="@VERSION@">1.0</token>
+    <token name="@WRAPPER_VERSION@">@VERSION@+galaxy1</token>
+    <token name="@PROFILE@">23.0</token>
+    <token name="@pipefail@"><![CDATA[set -o | grep -q pipefail && set -o pipefail;]]></token>
+</macros>
diff --git a/tools/wisecondorx/wisecondor_reference.xml b/tools/wisecondorx/wisecondor_reference.xml
new file mode 100644
index 00000000..a7aa37f6
--- /dev/null
+++ b/tools/wisecondorx/wisecondor_reference.xml
@@ -0,0 +1,63 @@
+<tool id="wisecondorx_reference" name="WisecondorX build reference" version="@WRAPPER_VERSION@" profile="@PROFILE@">
+    <description>
+    </description>
+    <macros>
+        <import>macro.xml</import>
+    </macros>
+    <requirements>
+        <requirement type="package" version="3.0.0">sequenza-utils</requirement>
+    </requirements>
+    <stdio>
+        <exit_code range="1:" level="fatal" description="Error occured" />
+    </stdio>
+    <command detect_errors="exit_code"><![CDATA[
+    @pipefail@
+    sequenza-utils gc_wiggle  --fasta $reference -o $refwig -w $window
+    ]]></command>
+    <inputs>
+        <param name="reference" type="data" format="fasta" label="Genome in fasta format"
+               help="the fasta genome whose GC content will be indexed"/>
+        <param name="window" type="integer" value="50" label="window size" help="The size of the wiggle for GC content calculation" />
+     </inputs>
+    <outputs>
+        <data name="refwig" format="wig" label="reference_wig" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="window" value="100" ftype="vcf" />
+            <param name="reference" value="hg19_chr22.fa.gz" />
+            <output name="refwig" file="hg19.GCref.txt" ftype="wig" />
+        </test>
+        <test>
+            <param name="window" value="100" ftype="vcf" />
+            <param name="reference" value="hg38_chr22.fa.gz" />
+            <output name="refwig" file="hg38.GCref.txt" ftype="wig" />
+        </test>
+
+    </tests>
+    <help>
+
+snvtocnv
+============================
+
+Analyzes genomic sequencing data from paired normal-tumor samples, including
+cellularity and ploidy estimation; mutation and copy number (allele-specific and total
+copy number) detection, quantification and visualization.
+
+This tools builds the GC wigle index of the reference genome required to perform analysis
+of the somatic single nucleotide variations using the tool "Infer CNVs from SNVs"
+
+    
+Inputs
+--------
+
+The reference genome in a fasta format
+
+*Warning* the genome fasta must be sorted according to the chromosomes
+(e.g. chr1, chr2, .. chr21, chr22)
+
+    </help>
+    <citations>
+        <citation type="doi">10.1093/annonc/mdu479</citation>
+    </citations>
+</tool>
diff --git a/tools/wisecondorx/wisecondor_test.xml b/tools/wisecondorx/wisecondor_test.xml
new file mode 100644
index 00000000..fcd19b6a
--- /dev/null
+++ b/tools/wisecondorx/wisecondor_test.xml
@@ -0,0 +1,92 @@
+<tool id="wisecondorx_test" name="WisecondorX infer CNVs" version="@WRAPPER_VERSION@" profile="@PROFILE@">
+    <description>
+    </description>
+    <macros>
+        <import>macro.xml</import>
+    </macros>
+    <requirements>
+        <requirement type="package" version="3.0.0">sequenza-utils</requirement>
+        <requirement type="package" version="3.0.0">r-sequenza</requirement>
+        <requirement type="package" version="1.6.6">r-optparse</requirement>
+        <requirement type="package" version="1.24.0">bioconductor-biocparallel</requirement>
+        <requirement type="package" version="1.3.0">r-tidyverse</requirement>
+        <requirement type="package" version="2021a=he74cb21_0">tzdata</requirement>
+    </requirements>
+    <stdio>
+        <exit_code range="1:" level="fatal" description="Error occured" />
+    </stdio>
+    <command detect_errors="exit_code"><![CDATA[
+    @pipefail@
+    sequenza-utils snp2seqz -v '$input_snvs'  -gc $refwig -o sample.seqz.gz &&
+    sequenza-utils seqz_binning --seqz sample.seqz.gz -w 50 -o '$wiggle' &&
+    Rscript $__tool_directory__/segmentation_sequenza.R
+            -i '$wiggle'
+            -s sample
+            -O test &&
+    Rscript $__tool_directory__/sequenza_to_hrdtools_input.R
+            -i test/sample_segments.txt
+            -s test/sample_alternative_solutions.txt
+            -o '$cnvs' &&
+    ls test
+    ]]></command>
+    <inputs>
+        <param name="refwig" type="data" format="txt" label="GC wigle of reference genome"/>
+        <param name="input_snvs" type="data" format="vcf" label="SNVs to process in a vcf file"/>
+    </inputs>
+    <outputs>
+        <data name="wiggle" format="wig" label="binned wiggle" />
+        <data name="sample_segment" format="tabular" label="sample segments" from_work_dir="test/sample_segments.txt" />
+        <data name="alt_solutions" format="tabular" label="alternate solutions" from_work_dir="test/sample_alternative_solutions.txt" />
+        <data name="cnvs" format="tabular" label="Annotated CNVs" />
+        <data name="chrom_depths" format="pdf" label="Chromosomes sequencing depth" from_work_dir="test/sample_chromosome_depths.pdf"/>
+        <data name="chrom_view" format="pdf" label="Chromosomes views" from_work_dir="test/sample_chromosome_view.pdf"/>
+        <data name="genome_view" format="pdf" label="Genome view" from_work_dir="test/sample_genome_view.pdf"/>        
+        <data name="model_fit" format="pdf" label="Cellularity and Diploidy model" from_work_dir="test/sample_model_fit.pdf"/>        
+        <data name="CN_histo" format="pdf" label="Copy Numbers histogram" from_work_dir="test/sample_CN_bars.pdf"/>        
+    </outputs>
+    <tests>
+        <test>
+            <param name="input_snvs" value="hg19_chr22.vcf" ftype="vcf" />
+            <param name="refwig" value="hg19.GCref.txt" />
+            <output name="cnvs" file="hg19.cnv.tab" ftype="tabular" />
+            <output name="chrom_depths" ftype="pdf" file="hg19_chrom_depths.pdf"/>
+            <output name="chrom_view" ftype="pdf" file="hg19_chrom_view.pdf"/>
+            <output name="genome_view" ftype="pdf" file="hg19_genome_view.pdf"/>        
+            <output name="model_fit" ftype="pdf" file="hg19_model.pdf"/>        
+            <output name="CN_histo" ftype="pdf" file="hg19_CN_histo.pdf"/>        
+        </test>
+        <test>
+            <param name="input_snvs" value="hg38_chr22.vcf" ftype="vcf" />
+            <param name="refwig" value="hg38.GCref.txt" />
+            <output name="cnvs" file="hg38.cnv.tab" ftype="tabular" />
+            <output name="chrom_depths" ftype="pdf" file="hg38_chrom_depths.pdf"/>
+            <output name="chrom_view" ftype="pdf" file="hg38_chrom_view.pdf"/>
+            <output name="genome_view" ftype="pdf" file="hg38_genome_view.pdf"/>        
+            <output name="model_fit" ftype="pdf" file="hg38_model.pdf"/>        
+            <output name="CN_histo" ftype="pdf" file="hg38_CN_histo.pdf"/>        
+        </test>
+    </tests>
+    <help>
+
+snvtocnv
+============================
+
+Analyze genomic sequencing data from paired normal-tumor samples, including
+cellularity and ploidy estimation; mutation and copy number (allele-specific and total
+copy number) detection, quantification and visualization.
+
+    
+Inputs
+--------
+
+A GC wigle of genome index generated with the tool "create GC_wiggle of reference genome"
+available from this galaxy wrapper
+
+A vcf file of somatic *single* nucleotide variations observed in a tumor sample
+
+
+    </help>
+    <citations>
+        <citation type="doi">10.1093/annonc/mdu479</citation>
+    </citations>
+</tool>