changeset 28:6ef8eb568700 draft

Move GATK tool_dependency to a repository dependency, use 2 env vars: GATK2_NUM_THREADS and GATK2_NUM_CPU_THREADS for site threading values
author Jim Johnson <jj@umn.edu>
date Mon, 18 Feb 2013 15:48:46 -0600
parents b23ecdd665d0
children c511aa6f93da
files base_recalibrator.xml depth_of_coverage.xml haplotype_caller.xml indel_realigner.xml print_reads.xml realigner_target_creator.xml reduce_reads.xml tool_dependencies.xml unified_genotyper.xml variant_annotator.xml variant_apply_recalibration.xml variant_combine.xml variant_eval.xml variant_filtration.xml variant_recalibrator.xml variant_select.xml variants_validate.xml
diffstat 17 files changed, 18 insertions(+), 58 deletions(-) [+]
line wrap: on
line diff
--- a/base_recalibrator.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/base_recalibrator.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -15,7 +15,7 @@
     -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
     -T "BaseRecalibrator"
     \$GATK2_SITE_OPTIONS
-    ## \$GATK2_THREAD_OPTIONS
+    \$GATK2_CPU_THREADS
     ##--num_threads 4 ##hard coded, for now
     ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
--- a/depth_of_coverage.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/depth_of_coverage.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -17,9 +17,8 @@
     -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
     -T "DepthOfCoverage"
     \$GATK2_SITE_OPTIONS
-    \$GATK2_THREAD_OPTIONS
+    ## \$GATK2_NUM_THREADS
     ##--num_threads 4 ##hard coded, for now
-    
     ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home
     #if $reference_source.reference_source_selector != "history":
         -R "${reference_source.ref_file.fields.path}"
--- a/haplotype_caller.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/haplotype_caller.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -16,7 +16,7 @@
     -T "HaplotypeCaller"
     -o "${output_vcf}"
     ## \$GATK2_SITE_OPTIONS
-    ## \$GATK2_THREAD_OPTIONS
+    ## \$GATK2_NUM_THREADS
     ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home
     ##--num_threads 4 ##not supported yet
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
--- a/indel_realigner.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/indel_realigner.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -16,7 +16,7 @@
     -T "IndelRealigner"
     -o "${output_bam}"
     \$GATK2_SITE_OPTIONS
-    ## \$GATK2_THREAD_OPTIONS
+    ## \$GATK2_NUM_THREADS 
     ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home
     ##--num_threads 4 ##hard coded, for now
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
--- a/print_reads.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/print_reads.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -16,6 +16,7 @@
     -T "PrintReads"
     -o "${output_bam}"
     \$GATK2_SITE_OPTIONS
+    \$GATK2_NUM_CPU_THREADS
     ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home
     ##--num_threads 4 ##not supported yet
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
--- a/realigner_target_creator.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/realigner_target_creator.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -16,7 +16,7 @@
     -T "RealignerTargetCreator"
     -o "${output_interval}"
     \$GATK2_SITE_OPTIONS
-    ## \$GATK2_THREAD_OPTIONS
+    \$GATK2_NUM_THREADS
     ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home
     ##--num_threads 4 ##hard coded, for now
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
--- a/reduce_reads.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/reduce_reads.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -16,7 +16,7 @@
     -T "ReduceReads"
     -o "${output_bam}"
     ## \$GATK2_SITE_OPTIONS
-    ## \$GATK2_THREAD_OPTIONS
+    ## \$GATK2_NUM_THREADS
     ##-et "NO_ET" -K "/data/galaxy/appList/GenomeAnalysisTK-2.0-36-gf5c1c1a/gatk2_key_file" ##ET no phone home
     ##--num_threads 4 ##not supported yet
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
--- a/tool_dependencies.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/tool_dependencies.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -1,48 +1,7 @@
 <?xml version="1.0"?>
 <tool_dependency>
     <package name="gatk" version="2.3">
-        <install version="1.0">
-            <actions>
-                <action type="download_by_url">ftp://ftp.broadinstitute.org/pub/gsa/GenomeAnalysisTK/GenomeAnalysisTKLite-2.3-4-gb8f1308.tar.bz2</action>
-                <action type="move_file">
-                    <source>GenomeAnalysisTKLite.jar</source>
-                    <destination>$INSTALL_DIR</destination>
-                </action>
-                <action type="shell_command">ln -s GenomeAnalysisTKLite.jar GenomeAnalysisTK.jar</action>
-                <action type="move_file">
-                    <source>GenomeAnalysisTK.jar</source>
-                    <destination>$INSTALL_DIR</destination>
-                </action>
-                <action type="set_environment">
-                    <environment_variable name="GATK2_PATH" action="set_to">$INSTALL_DIR</environment_variable>
-                    <environment_variable name="GATK2_SITE_OPTIONS" action="set_to">"--phone_home STANDARD"</environment_variable>
-                    <environment_variable name="GATK2_THREAD_OPTIONS" action="set_to">"--num_threads 4 --num_cpu_threads_per_data_thread 3"</environment_variable>
-                </action>
-            </actions>
-        </install>
-        <readme>
-The following GATK2 analysis types require a License for commercial use and the full GATK2 build will need to be manually installed:
-
- haplotypecaller                 
-   HaplotypeCaller               Call SNPs and indels simultaneously via local de-novo assembly of haplotypes in an 
-                                 active region.
-   HaplotypeResolver             Haplotype-based resolution of variants in 2 different eval files.
-
- reducereads                     
-   CompareBAM                    Given two BAMs with different read groups, it compares them based on ReduceReads 
-                                 metrics.
-   ReduceReads                   Reduces the BAM file using read based compression that keeps only essential information 
-                                 for variant calling
-                                 
-
-See: http://www.appistry.com/gatk/gatk-faqs-static for Licensing details.
-The full GATK build can be acquired from:  http://www.broadinstitute.org/gatk/download 
-and GenomeAnalysisTK.jar need to be manually installed into the GATK2_PATH set for the GenomeAnalysisTKLite.jar
-
-The GATK2_SITE_OPTIONS environment variable can be modified in the env.sh in the tool_dependencies path can be modified 
-for the local installation.  
-
-        </readme>
+        <repository toolshed="http://testtoolshed.g2.bx.psu.edu" name="gatk_lite_2_3_9" owner="jjohnson" changeset_revision="10c2fe2d3b39" />
     </package>
     <package name="samtools" version="0.1.18">
         <repository toolshed="http://testtoolshed.g2.bx.psu.edu" name="package_samtools_0_1_18" owner="devteam" changeset_revision="5f7ec5048224" />
--- a/unified_genotyper.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/unified_genotyper.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -20,7 +20,8 @@
     --out "${output_vcf}"
     --metrics_file "${output_metrics}"
     \$GATK2_SITE_OPTIONS
-    \$GATK2_THREAD_OPTIONS
+    \$GATK2_NUM_THREADS
+    \$GATK2_NUM_CPU_THREADS
     ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
     #if $reference_source.reference_source_selector != "history":
--- a/variant_annotator.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/variant_annotator.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -19,7 +19,7 @@
     ##--list
     -T "VariantAnnotator"
     \$GATK2_SITE_OPTIONS
-    \$GATK2_THREAD_OPTIONS
+    ## \$GATK2_NUM_THREADS
     ##--num_threads 4 ##hard coded, for now
     ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
--- a/variant_apply_recalibration.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/variant_apply_recalibration.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -13,7 +13,7 @@
     -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
     -T "ApplyRecalibration"
     \$GATK2_SITE_OPTIONS
-    \$GATK2_THREAD_OPTIONS
+    \$GATK2_NUM_THREADS
     ##--num_threads 4 ##hard coded, for now
     ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
     #if $reference_source.reference_source_selector != "history":
--- a/variant_combine.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/variant_combine.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -19,7 +19,7 @@
     -T "CombineVariants"
     --out "${output_variants}"
     \$GATK2_SITE_OPTIONS
-    \$GATK2_THREAD_OPTIONS
+    \$GATK2_NUM_THREADS
     ##--num_threads 4 ##hard coded, for now
     ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
--- a/variant_eval.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/variant_eval.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -15,7 +15,7 @@
     -T "VariantEval"
     --out "${output_report}"
     \$GATK2_SITE_OPTIONS
-    \$GATK2_THREAD_OPTIONS
+    \$GATK2_NUM_THREADS
     ##--num_threads 4 ##hard coded, for now
     ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
--- a/variant_filtration.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/variant_filtration.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -12,7 +12,7 @@
     -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
     -T "VariantFiltration"
     \$GATK2_SITE_OPTIONS
-    \$GATK2_THREAD_OPTIONS
+    \$GATK2_NUM_THREADS
     ##--num_threads 4 ##hard coded, for now
     ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
     -o "${output_vcf}"
--- a/variant_recalibrator.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/variant_recalibrator.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -13,7 +13,7 @@
     -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
     -T "VariantRecalibrator"
     \$GATK2_SITE_OPTIONS
-    \$GATK2_THREAD_OPTIONS
+    \$GATK2_NUM_THREADS
     ##--num_threads 4 ##hard coded, for now
     ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file"##ET no phone home
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
--- a/variant_select.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/variant_select.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -12,7 +12,7 @@
     -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
     -T "SelectVariants"
     \$GATK2_SITE_OPTIONS
-    \$GATK2_THREAD_OPTIONS
+    \$GATK2_NUM_THREADS
     ##--num_threads 4 ##hard coded, for now
     ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
     -o "${output_vcf}"
--- a/variants_validate.xml	Mon Feb 18 11:17:32 2013 -0600
+++ b/variants_validate.xml	Mon Feb 18 15:48:46 2013 -0600
@@ -12,7 +12,7 @@
     -T "ValidateVariants"
     
     \$GATK2_SITE_OPTIONS
-    \$GATK2_THREAD_OPTIONS
+    \$GATK2_NUM_THREADS
     ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
     ##--num_threads 4 ##hard coded, for now
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout