# HG changeset patch
# User elixir-it
# Date 1541761338 18000
# Node ID 75d5828ff3434e23496a04b135862cb2f895d90b
Uploaded
diff -r 000000000000 -r 75d5828ff343 bed_macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bed_macros.xml Fri Nov 09 06:02:18 2018 -0500
@@ -0,0 +1,22 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff -r 000000000000 -r 75d5828ff343 covacs_HaplotypeCaller.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/covacs_HaplotypeCaller.xml Fri Nov 09 06:02:18 2018 -0500
@@ -0,0 +1,133 @@
+
+ GATK HaplotypeCaller wrapper Version 3.8
+
+ bed_macros.xml
+
+
+ samtools
+ gatk
+
+
+ $log
+
+ ]]>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+.. class:: warningmark
+
+**IMPORTANT** to get the wrapper ready to start the admin user have to download gatk GATK version 3.8 in tar.gz extension 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_haplotypecaller_HaplotypeCaller.php
+
+-----
+
+**Implemented options** HaplotypeCaller:
+
+**-L** : One or more genomic intervals over which to operate(file.bed)
+
+**-stand\_call\_conf** : The minimum phred-scaled confidence threshold at which variants should be called
+
+**-R** : Reference sequence file
+
+**--dbsnp** dbsnp file : rsIDs from this file are used to populate the ID column of the output. Also, the DB INFO flag will be set when appropriate. dbSNP is not used in any way for the calculations themselves.
+
+-----
+
+**in case of output in GVCF format the following fixed option are implemented:**
+
+**--emitRefConfidence** (GVCF|VCF) : Mode for emitting reference confidence scores
+
+**-variant_index_type** LINEAR : Type of IndexCreator to use for VCF indices
+
+**-variant_index_parameter** 128000 : Parameter to pass to the VCF/BCF IndexCreator
+
+
+
+
+ 10.1186/s12864-018-4508-1
+
+
+
diff -r 000000000000 -r 75d5828ff343 mv_untar_gatk.sh
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mv_untar_gatk.sh Fri Nov 09 06:02:18 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
diff -r 000000000000 -r 75d5828ff343 tool-data/covacs_bed.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/covacs_bed.loc.sample Fri Nov 09 06:02:18 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):
+#
+#
+#
+#
+#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
diff -r 000000000000 -r 75d5828ff343 tool-data/covacs_gatk_indexes.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/covacs_gatk_indexes.loc.sample Fri Nov 09 06:02:18 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):
+#
+#
+#
+#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
diff -r 000000000000 -r 75d5828ff343 tool_data_table_conf.xml.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample Fri Nov 09 06:02:18 2018 -0500
@@ -0,0 +1,12 @@
+
+
+