# HG changeset patch # User elixir-it # Date 1541761445 18000 # Node ID 3d969c748317f5454ce68dd507024a78dc71b413 Uploaded diff -r 000000000000 -r 3d969c748317 bed_macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bed_macros.xml Fri Nov 09 06:04:05 2018 -0500 @@ -0,0 +1,22 @@ + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r 3d969c748317 covacs_VariantRecalibrator.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/covacs_VariantRecalibrator.xml Fri Nov 09 06:04:05 2018 -0500 @@ -0,0 +1,223 @@ + + GATK VariantRecalibrator wrapper Version = 3.8 + + bed_macros.xml + vcf_macros.xml + + + gatk + + + $log + ]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +.. 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_VariantRecalibrator.php + +----- + +**Implemented options** VariantRecalibrator: + +**-L** : One or more genomic intervals over which to operate(file.bed) + +**-ip** Amount of padding (in bp) to add to each interval + +**--resource:NAME,known=true/false,training=true/false,truth=true/false,prior=float $file** :A list of sites for which to apply a prior probability of being correct but which aren't used by the algorithm (training and truth sets are required to run) + +**-mode** : Recalibration mode to employ (SNP|INDEL) + +**-an** : annotations which should used for calculations + +**-tranche** The levels of truth sensitivity at which to slice the data. (in percent, that is 1.0 for 1 percent) + +**in case of indels mode** + +**--minNumBadVariants** : Minimum number of bad variants + +**--maxGaussians** : Max number of Gaussians for the positive model + +**-mNG** : Max number of Gaussians for the negative model + +**OUTPUTS** + +-recalFile + +-tranchesFile + +----- + +.. class:: infomark + +**Recommended CoVaCS command** + +**-ip** 100 + +**-R** genome.fa + +**-input** VCF + +**-resource**:hapmap,known=false,training=true,truth=true,prior=15.0 hapmap.vcf + +**-resource**:omni,known=false,training=true,truth=true,prior=12.0 omni.vcf + +**-resource**:1000G,known=false,training=false,truth=false,prior=8.0 1000G.vcf + +**-resource**:dbsnp,known=true,training=false,truth=false,prior=2.0 dbsnp.vcf + +**-mode** SNP + +**-an** DP **-an** QD **-an** MQ **-an** MQRankSum **-an** ReadPosRankSum **-an** FS + +**-tranche** 100.0 **-tranche** 99.5 **-tranche** 99.0 **-tranche** 98.5 **-tranche** 90.0 + + + + 10.1186/s12864-018-4508-1 + + + diff -r 000000000000 -r 3d969c748317 mv_untar_gatk.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mv_untar_gatk.sh Fri Nov 09 06:04:05 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 3d969c748317 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 06:04:05 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 3d969c748317 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 06:04:05 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 3d969c748317 tool-data/covacs_vcf.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/covacs_vcf.loc.sample Fri Nov 09 06:04:05 2018 -0500 @@ -0,0 +1,29 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory vcf file for covacs sequences data files. You will need +#to create these data files and then create a vcf_loc.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The vcf_loc.loc +#file has this format (longer white space characters are TAB characters): +# +# +# +#So, for example, if you had vcf file stored in +#/export/resource/, +#then the covacs_vcf.loc entry would look like this: +# +#hapmap hapmap /export/resource/hapmap.vcf +# +#and your /export/resource directory +#would contain hapmap.vcf. +# +# +#Your covacs_vcf.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. +#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. +# +hapmap hapmap /export/resources/hapmap.vcf +1000G 1000G /export/resources/1000G.vcf + diff -r 000000000000 -r 3d969c748317 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 06:04:05 2018 -0500 @@ -0,0 +1,17 @@ + + + + value, dbkey, name, path + +
+ + + value, dbkey, name, path + +
+ + + value, name, path + +
+