# HG changeset patch # User avowinkel # Date 1443111001 14400 # Node ID b80ff7f43ad115aec5f18f9738bf14fd30b3e990 planemo upload for repository https://github.com/kaktus42/galaxytools/tree/master/tools/gatk commit 8764cef47529f6285678af4ca24b66d0fe516b88-dirty diff -r 000000000000 -r b80ff7f43ad1 analyze_covariates.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/analyze_covariates.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,37 @@ + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r b80ff7f43ad1 base_recalibrator.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/base_recalibrator.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,38 @@ + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r b80ff7f43ad1 combine_gvcfs.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/combine_gvcfs.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,44 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r b80ff7f43ad1 combine_variants.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/combine_variants.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,96 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r b80ff7f43ad1 gatk.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gatk.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,179 @@ + + + tool collection Version @VERSION@ + + gatk_macros.xml + realigner_target_creator.xml + indel_realigner.xml + base_recalibrator.xml + analyze_covariates.xml + print_reads.xml + haplotype_caller.xml + genotype_gvcfs.xml + combine_gvcfs.xml + combine_variants.xml + + + + + + + + + + + &1 | awk '\$1 != "INFO" && \$1 != "WARN"' >&2 +]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + analysis_type['analysis_type_selector'] == 'RealignerTargetCreator' + + + analysis_type['analysis_type_selector'] == 'IndelRealigner' + + + analysis_type['analysis_type_selector'] == 'BaseRecalibrator' + + + analysis_type['analysis_type_selector'] == 'AnalyzeCovariates' + + + analysis_type['analysis_type_selector'] == 'PrintReads' + + + analysis_type['analysis_type_selector'] == 'HaplotypeCaller' + + + analysis_type['analysis_type_selector'] == 'GenotypeGVCFs' + + + analysis_type['analysis_type_selector'] == 'CombineGVCFs' + + + analysis_type['analysis_type_selector'] == 'CombineVariants' + + + + + + 10.1101/gr.107524.110 + 10.1038/ng.806 + 10.1002/0471250953.bi1110s43 + + diff -r 000000000000 -r b80ff7f43ad1 gatk_macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gatk_macros.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,166 @@ + + + + + gatk + GATK_PATH + GATK_SITE_OPTIONS + package_r_for_gatk_3_4_0 + + + + + + + + 3.4-0 + ${tool.name} - ${analysis_type.analysis_type_selector} + + 1: + THREAD_STRING="-nct $cond_threads.nct" && + #end if + #if int($cond_threads.nt) > 1: + THREAD_STRING=$THREAD_STRING" -nt $cond_threads.nt" && + #end if + #if int($cond_threads.mem) > 0: + GATK_MEM=$cond_threads.mem && + #end if + #end if + java -Xmx\${GATK_MEM:-\${SLURM_MEM_PER_NODE:-4096}}M -jar "\$GATK_PATH/GenomeAnalysisTK.jar" \${THREAD_STRING:-} +]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r b80ff7f43ad1 generation/gatk.xsl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/generation/gatk.xsl Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,162 @@ + + + + + + + + tool collection Version @VERSION@ + + + gatk_macros.xml + + + + + + + + + + + + + + + + + +<![CDATA[ + ############################ + ## import analysis specific preprocessings by using cheetahs internal searchList + ## if not defined, ignore + ############################ + #if $analysis_type.analysis_type_selector + "Preprocessing" in vars()['SL'][2] + #set $analysisPreprocessing = vars()['SL'][2][$analysis_type.analysis_type_selector + "Preprocessing"] + #include source=$analysisPreprocessing + #end if + + ############################ + ## GATK tool unspecific options + ############################ + @GATK_EXEC@ + + --analysis_type ${analysis_type.analysis_type_selector} + --reference_sequence ${ref_file.fields.path} + + --log_to_file ${output_log} + + #if $cond_intervals.cond_intervals_enabled + #for $interval in $cond_intervals.intervals: + --intervals ${interval.L} + #end for + #end if + + #if $cond_BQSR.cond_BQSR_enabled + --BQSR $cond_BQSR.BQSR + #end if + + ############################ + ## import analysis specific options by using cheetahs internal searchList + ## if not defined throw raw python error until better idea + ############################ + #if $analysis_type.analysis_type_selector + "Options" in vars()['SL'][2] + #set $analysisOptions = vars()['SL'][2][$analysis_type.analysis_type_selector + "Options"] + #include source=$analysisOptions + #else + #set $analysisOptions = vars()['SL'][2][$analysis_type.analysis_type_selector + "Options"] + #end if + + ############################ + ## only put ERROR or FATAL log messages into stderr + ## but keep full log for printing into log file + ############################ + 2>&1 | awk '\$1 != "INFO" && \$1 != "WARN"' >&2 +]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + analysis_type['analysis_type_selector'] == '' + + + + + + + + + 10.1101/gr.107524.110 + 10.1038/ng.806 + 10.1002/0471250953.bi1110s43 + + + + + + + diff -r 000000000000 -r b80ff7f43ad1 generation/gatk.xsldb.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/generation/gatk.xsldb.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,57 @@ + + + + RealignerTargetCreator + bam + rtc + realigner_target_creator.xml + + + IndelRealigner + bam + ir + indel_realigner.xml + + + BaseRecalibrator + bam + br + base_recalibrator.xml + + + AnalyzeCovariates + bam + ac + analyze_covariates.xml + + + PrintReads + bam + pr + print_reads.xml + + + HaplotypeCaller + bam + hc + haplotype_caller.xml + + + GenotypeGVCFs + gvcf + gg + genotype_gvcfs.xml + + + CombineGVCFs + gvcf + cg + combine_gvcfs.xml + + + CombineVariants + vcf + cv + combine_variants.xml + + diff -r 000000000000 -r b80ff7f43ad1 genotype_gvcfs.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/genotype_gvcfs.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,43 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r b80ff7f43ad1 haplotype_caller.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/haplotype_caller.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,65 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r b80ff7f43ad1 indel_realigner.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/indel_realigner.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,90 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r b80ff7f43ad1 print_reads.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/print_reads.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,71 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r b80ff7f43ad1 realigner_target_creator.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/realigner_target_creator.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,57 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r b80ff7f43ad1 tool-data/destinations.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/destinations.py Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,62 @@ +from galaxy.jobs import JobDestination +import os +import sys +import json +import cStringIO +import logging + +log = logging.getLogger( __name__ ) + + +def dump(obj, nested_level=0, output=sys.stdout): + spacing = ' ' + if type(obj) == dict: + print >> output, '%s{' % ((nested_level) * spacing) + for k, v in obj.items(): + if hasattr(v, '__iter__'): + print >> output, '%s%s:' % ((nested_level + 1) * spacing, k) + dump(v, nested_level + 1, output) + else: + print >> output, '%s%s: %s' % ((nested_level + 1) * spacing, k, v) + print >> output, '%s}' % (nested_level * spacing) + elif type(obj) == list: + print >> output, '%s[' % ((nested_level) * spacing) + for v in obj: + if hasattr(v, '__iter__'): + dump(v, nested_level + 1, output) + else: + print >> output, '%s%s' % ((nested_level + 1) * spacing, v) + print >> output, '%s]' % ((nested_level) * spacing) + else: + print >> output, '%s%s' % (nested_level * spacing, obj) + + +def dynamic_slurm_cluster_gatk(job, tool_id): + # Allocate extra time + inp_data = dict( [ ( da.name, da.dataset ) for da in job.input_datasets ] ) + inp_data.update( [ ( da.name, da.dataset ) for da in job.input_library_datasets ] ) + inp_data.update( [ ( da.name, json.loads(da.value) ) for da in job.parameters ] ) + out = cStringIO.StringIO() + dump(inp_data, 1, out) + log.debug(out.getvalue()) + + nativeSpecs = '--nodes=1 --ntasks=1' + + # runner doesn't allow to specify --cpus-per-task + # thus the mem calculation gets messy with more than 1 node + # --> translate nt ==> nodes, nct ==> ntasks + + if 'cond_threads' not in inp_data: + return JobDestination(runner="slurm") + + if inp_data['cond_threads']['cond_threads_enabled'] == "True": + nNodes = int(inp_data['cond_threads']['nt']) + nCPU = int(inp_data['cond_threads']['nct']) + nMEM = int(inp_data['cond_threads']['mem']) + if nMEM > 0: + nativeSpecs = '--nodes=%d --ntasks=%d --mem=%d' % (nNodes, nCPU*nNodes, nMEM) + else: + nativeSpecs = '--nodes=%d --ntasks=%d' % (nNodes, nCPU*nNodes) + + return JobDestination(runner="slurm", params={"nativeSpecification": nativeSpecs}) + diff -r 000000000000 -r b80ff7f43ad1 tool-data/picard_index.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/picard_index.loc.sample Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,26 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of Picard dict and associated files. You will need +#to create these data files and then create a picard_index.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The picard_index.loc +#file has this format (longer white space is the TAB character): +# +# +# +#So, for example, if you had hg18 indexed and stored in +#/depot/data2/galaxy/srma/hg18/, +#then the srma_index.loc entry would look like this: +# +#hg18 hg18 hg18 Pretty /depot/data2/galaxy/picard/hg18/hg18.fa +# +#and your /depot/data2/galaxy/srma/hg18/ directory +#would contain the following three files: +#hg18.fa +#hg18.dict +#hg18.fa.fai +# +#The dictionary file for each reference (ex. hg18.dict) must be +#created via Picard (http://picard.sourceforge.net). Note that +#the dict file does not have the .fa extension although the +#path list in the loc file does include it. +# diff -r 000000000000 -r b80ff7f43ad1 tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,7 @@ + + + + value, dbkey, name, path + +
+
diff -r 000000000000 -r b80ff7f43ad1 tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Thu Sep 24 12:10:01 2015 -0400 @@ -0,0 +1,19 @@ + + + + /mnt/galaxy/tools/GATK/3.4-0 + + + + + + + + +