changeset 0:c785cec34cdc draft

Uploaded
author elixir-it
date Fri, 09 Nov 2018 05:27:39 -0500
parents
children 48dc4c9bc497
files bed_macros.xml covacs_ApplyRecalibrator.xml mv_untar_gatk.sh tool-data/covacs_bed.loc.sample tool-data/covacs_gatk_indexes.loc.sample tool_data_table_conf.xml.sample
diffstat 6 files changed, 199 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bed_macros.xml	Fri Nov 09 05:27:39 2018 -0500
@@ -0,0 +1,22 @@
+<macros>
+  <macro name="bed_loc">
+      <conditional name="bed_source">
+            <param name="bed_source_selector" type="select" label="Will you select a bed file from your history or use a built-in bed?" optional="true">
+                <option value="cached">Use a built-in bed</option>
+                <option value="history">Use a bed from history as reference</option>
+            </param>
+            <when value="cached">
+                <param name="bed_cached" type="select" label="Using reference bed" help="Select bed from the list">
+                    <options from_data_table="covacs_bed">
+                        <filter type="sort_by" column="2" />
+                        <validator type="no_options" message="No bed are available" />
+                    </options>
+                    <validator type="no_options" message="A built-in bed file is not available"/>
+                </param>
+            </when>
+            <when value="history">
+                <param name="bed_history" type="data" format="bed" label="Use the following dataset as reference bed " help="You can upload a bed file to the history and use it" optional="true" />
+            </when> 
+      </conditional>
+  </macro>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/covacs_ApplyRecalibrator.xml	Fri Nov 09 05:27:39 2018 -0500
@@ -0,0 +1,103 @@
+ <tool id="covacs_ApplyRecalibrator" name="covacs_ApplyRecalibrator" version="3.8">
+  <description>gatk ApplyRecalibrator wrapper </description>
+  <macros>
+	<import>bed_macros.xml</import>
+  </macros>
+  <requirements>
+  	<requirement type="package" version="3.8" >gatk</requirement>
+  </requirements>
+  <command>
+    <![CDATA[
+	 ### call the .sh to untar the package 
+        sh $__tool_directory__/mv_untar_gatk.sh &&	
+
+
+	
+	#if $bed_source.bed_source_selector == "history" and $bed_source.bed_history
+	 ln -s $bed_source.bed_history region.bed &&
+	#end if
+
+	 ln -s $input1 input1.vcf &&
+
+	java  -jar \$CONDA_PREFIX/../../GenomeAnalysisTK.jar -T ApplyRecalibration
+	
+
+
+	#if $bed_source.bed_source_selector == "history" and $bed_source.bed_history
+        -L  region.bed
+        #end if
+        #if $bed_source.bed_source_selector == "cached"
+        -L $bed_source.bed_cached.fields.path
+        #end if
+
+
+	-ip $ip
+	###index from .loc
+	-R $ref_file.fields.path
+
+	-input input1.vcf
+	--ts_filter_level $ts_filter_level
+	-tranchesFile $input2
+	-recalFile $input3
+	-mode $mode
+	-ef -o variants_recal.filtered.98HQ.vcf 2> $log
+
+
+
+
+	]]>
+  </command>
+  <inputs>
+    <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list">
+       <options from_data_table="covacs_gatk_indexes">
+         <filter type="sort_by" column="2" />
+         <validator type="no_options" message="No indexes are available" />
+       </options>
+       <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
+    </param>
+    <param format="vcf" name="input1" label="input vcf" type="data" optional="true" />
+    <expand macro="bed_loc"/>
+    <param name="ip" type="integer" value="100" help="Amount of padding (in bp) to add to each interval"/>
+    <param name="ts_filter_level" type="float" value="99.5" help="The truth sensitivity level at which to start filtering"/>
+    <param name="input2" type="data" label="tranchesfile" help="tranches file from VariantRecalibrator"/>
+    <param name="input3" type="data" label="recalfile" help="tranches file from VariantRecalibrator"/>
+    <param name="mode" type="select" help="Recalibration mode to employ: SNP for recalibrating only SNPs, INDEL for indels">
+	<option value="SNP">snp</option>
+	<option value="INDEL">INDEL</option>
+    </param>
+  </inputs>
+  <outputs>
+    <data format="vcf" name="variants_recal" from_work_dir="variants_recal.filtered.98HQ.vcf" label="${tool.name} on ${on_string}:recal_filtered"/>
+    <data format="txt" name="log"  label="${tool.name} on ${on_string}:log"/>
+  </outputs>
+  <help>
+.. class:: warningmark
+
+**IMPORTANT** to get the wrapper ready to start the admin user have to download gatk GATK version 3.8 from the broadinstitute site https://software.broadinstitute.org/gatk/download/archive and then move it in the conda_prefix folder, the path of the conda_prefix is written in the galaxy.ini(or .yml) file
+
+		**more informations** at https://software.broadinstitute.org/gatk/documentation/tooldocs/3.8-0/org_broadinstitute_gatk_tools_walkers_variantrecalibration_ApplyRecalibration.php
+
+-----
+
+**implemented options** ApplyRecalibrator:
+
+**-L**                  : One or more genomic intervals over which to operate(file.bed)
+
+**-ip**                 : Amount of padding (in bp) to add to each interval
+
+**-R**                  : Reference sequence file
+
+**-ts\_filter_\level**    : The truth sensitivity level at which to start filtering
+
+**-tranchesFile**       : Level of sensitivity. A tranchesfile is required. Please read the GATK manual if you do according to the input tranches file
+
+**-recallFile**         : The input recal file used by ApplyRecalibration
+
+**-mode**               : Recalibration mode to employ: SNP for recalibrating only SNPs, INDEL for indels
+
+  </help>
+  <citations>
+        <citation type="doi">10.1186/s12864-018-4508-1</citation>
+  </citations>
+</tool>
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/mv_untar_gatk.sh	Fri Nov 09 05:27:39 2018 -0500
@@ -0,0 +1,9 @@
+#!/bin/bash
+#if the .jar file is not present in the conda_prefix the script search the tar.gz in the conda_prefix of the vm
+#and untar the archive
+if [[ ! -f $CONDA_PREFIX/../../GenomeAnalysisTK.jar ]] ; then
+	tar -zxvf $CONDA_PREFIX/../../GenomeAnalysis*.tar.gz -C $CONDA_PREFIX/../../ 
+	
+else
+	echo GATK is present
+fi
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/covacs_bed.loc.sample	Fri Nov 09 05:27:39 2018 -0500
@@ -0,0 +1,17 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory bed file for covacs sequences data files. You will need
+#to create these data files and then create a bed_loc.loc file
+#similar to this one (store it in this directory) that points to
+#the directories in which those files are stored. The bed_loc.loc
+#file has this format (longer white space characters are TAB characters):
+#
+#<unique_id>   <dbkey>   <display_name>   <file_path>
+#
+#
+#Note that for backwards compatibility with workflows, the unique ID of
+#an entry must be the path that was in the original loc file, because that
+#is the value stored in the workflow for that parameter. That is why the
+#hg19 entry above looks odd. New genomes can be better-looking.
+#
+hg19	hg19	hg19-padded	/export/BED/S07084713_Padded.bed
+hgbed	hg19	hg19-bed-test	/export/BED/chr22.bed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/covacs_gatk_indexes.loc.sample	Fri Nov 09 05:27:39 2018 -0500
@@ -0,0 +1,36 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory of all covacs wrapper that need a gatk reference. You will need
+#to create these data files and then create a covacs_gatk_indexes.loc file
+#similar to this one (store it in this directory) that points to
+#the directories in which those files are stored. The covacs_gatk_indexes.loc
+#file has this format (longer white space characters are TAB characters):
+#
+#<unique_build_id>   <dbkey>   <display_name>   <file_path>
+#
+#So, for example, if you had phiX indexed stored in 
+#/depot/data2/galaxy/phiX/base/, 
+#then the bwa_index.loc entry would look like this:
+#
+#phiX174   phiX   phiX Pretty   /depot/data2/galaxy/phiX/base/phiX.fa
+#
+#and your /depot/data2/galaxy/phiX/base/ directory
+#would contain phiX.dict, phiX.fa.fai files.
+#
+#
+#Your covacs_gatk_indexes.loc file should include an entry per line for each
+#index set you have stored. The "file" in the path does not actually
+#exist, but it is the prefix for the actual index files.  For example:
+#
+#phiX174                                phiX    phiX174                 /depot/data2/galaxy/phiX/base/phiX.fa
+#hg18canon                              hg18    hg18 Canonical  /depot/data2/galaxy/hg18/base/hg18canon.fa
+#hg18full                               hg18    hg18 Full               /depot/data2/galaxy/hg18/base/hg18full.fa
+#/orig/path/hg19.fa             hg19    hg19                    /depot/data2/galaxy/hg19/base/hg19.fa
+#...etc...
+#
+#Note that for backwards compatibility with workflows, the unique ID of
+#an entry must be the path that was in the original loc file, because that
+#is the value stored in the workflow for that parameter. That is why the
+#hg19 entry above looks odd. New genomes can be better-looking.
+#
+hg38	hg38	hg38_GDC	/export/gatkhg38pl/GRCh38.d1.vd1.fa
+hg19	hg19	hg19	/export/gatk_hg19_index_bundle/ucsc.hg19.fasta
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Fri Nov 09 05:27:39 2018 -0500
@@ -0,0 +1,12 @@
+<tables>
+<!-- Location of bed-file for covacs -->
+    <table name="covacs_bed" comment_char="#">
+        <columns> value, dbkey, name, path</columns>
+        <file path="tool-data/covacs_bed.loc" />
+    </table>
+<!-- Location of index file  for covacs gatk wrapper -->
+    <table name="covacs_gatk_indexes" comment_char="#">
+        <columns> value, dbkey, name, path</columns>
+        <file path="tool-data/covacs_gatk_indexes.loc" />
+    </table>
+</tables>