| Previous changeset 2:2c7824a8d764 (2019-09-12) |
|
Commit message:
Uploaded |
|
added:
ngsap-vc/Haplotypecaller.ga ngsap-vc/SAMTools.ga ngsap-vc/SVDetect.ga ngsap-vc/VARSCAN.ga ngsap-vc/gatk/analyze_covariates.xml ngsap-vc/gatk/base_recalibrator.xml ngsap-vc/gatk/combine_gvcfs.xml ngsap-vc/gatk/combine_variants.xml ngsap-vc/gatk/gatk.xml ngsap-vc/gatk/gatk_macros.xml ngsap-vc/gatk/generation/gatk.xsl ngsap-vc/gatk/generation/gatk.xsldb.xml ngsap-vc/gatk/genotype_gvcfs.xml ngsap-vc/gatk/haplotype_caller.xml ngsap-vc/gatk/indel_realigner.xml ngsap-vc/gatk/print_reads.xml ngsap-vc/gatk/realigner_target_creator.xml ngsap-vc/gatk/tool-data/destinations.py ngsap-vc/gatk/tool-data/picard_index.loc.sample ngsap-vc/gatk/tool_data_table_conf.xml.sample ngsap-vc/gatk/tool_dependencies.xml ngsap-vc/package_r_for_gatk_3_4_0/tool_dependencies.xml ngsap-vc/suite_samtools_1_2/repository_dependencies.xml ngsap-vc/svdetect/BAM_preprocessingPairs.pl ngsap-vc/svdetect/BAM_preprocessingPairs.xml ngsap-vc/svdetect/SVDetect_compare.pl ngsap-vc/svdetect/SVDetect_compare.xml ngsap-vc/svdetect/SVDetect_import.sh ngsap-vc/svdetect/SVDetect_import.xml ngsap-vc/svdetect/SVDetect_run_parallel.pl ngsap-vc/svdetect/SVDetect_run_parallel.xml ngsap-vc/svdetect/circos_graph.xml ngsap-vc/varscan/tool_dependencies.xml ngsap-vc/varscan/varscan_mpileup.pl ngsap-vc/varscan/varscan_mpileup.xml ngsap-vc/varscan/varscan_somatic.pl ngsap-vc/varscan/varscan_somatic.xml |
|
removed:
GATK/gatk/analyze_covariates.xml GATK/gatk/base_recalibrator.xml GATK/gatk/combine_gvcfs.xml GATK/gatk/combine_variants.xml GATK/gatk/gatk.xml GATK/gatk/gatk_macros.xml GATK/gatk/generation/gatk.xsl GATK/gatk/generation/gatk.xsldb.xml GATK/gatk/genotype_gvcfs.xml GATK/gatk/haplotype_caller.xml GATK/gatk/indel_realigner.xml GATK/gatk/print_reads.xml GATK/gatk/realigner_target_creator.xml GATK/gatk/tool-data/destinations.py GATK/gatk/tool-data/picard_index.loc.sample GATK/gatk/tool_data_table_conf.xml.sample GATK/gatk/tool_dependencies.xml GATK/package_picard_1_135/tool_dependencies.xml GATK/package_r_for_gatk_3_4_0/tool_dependencies.xml |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/analyze_covariates.xml --- a/GATK/gatk/analyze_covariates.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,37 +0,0 @@ -<macros> - <xml name="AnalyzeCovariatesParameters" tokens="tag"> - - <!-- BQSR in main config --> - - <param name="afterReportFile" type="data" format="tabular" optional="true" label="file containing the BQSR second-pass report file" help="-after,‑‑afterReportFile &lt;afterReportFile&gt;" /> - - <param name="beforeReportFile" type="data" format="tabular" optional="true" label="file containing the BQSR first-pass report file" help="-before,‑‑beforeReportFile &lt;beforeReportFile&gt;" /> - - </xml> - - <xml name="AnalyzeCovariatesOutput"> - <data format="pdf" name="ac_plotsReportFile" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (PDF Recalibration Report)"> - <yield /> - </data> - </xml> - - <template name="AnalyzeCovariatesPreprocessing"> -<![CDATA[ -]]> - </template> - - <template name="AnalyzeCovariatesOptions"> -<![CDATA[ - --plotsReportFile ${ac_plotsReportFile} - - #if str($analysis_type.afterReportFile) - --afterReportFile $analysis_type.afterReportFile - #end if - #if str($analysis_type.beforeReportFile) - --beforeReportFile $analysis_type.beforeReportFile - #end if -]]> - </template> -</macros> - - |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/base_recalibrator.xml --- a/GATK/gatk/base_recalibrator.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,38 +0,0 @@ -<macros> - <xml name="BaseRecalibratorParameters" tokens="tag"> - - <expand macro="macro_bam_input" tag="@TAG@" /> - - <param name="knownSites" type="data" format="vcf,bcf,bed,pileup,tabular,table" label="Database of known Sites (ROD files; e.g. VCF format)" multiple="true" title="A database of known polymorphic sites to skip over in the recalibration algorithm" help="-knownSites,‑‑knownSites &lt;knownSites&gt;" /> - - </xml> - - <xml name="BaseRecalibratorOutput"> - <data format="tabular" name="br_table" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (Table)"> - <yield /> - </data> - </xml> - - <template name="BaseRecalibratorPreprocessing"> -<![CDATA[ - @token_bam_input_pre@ - #for $i, $variant in enumerate($analysis_type.knownSites): - ln -s -f ${variant} variant_${i}.vcf && - #end for -]]> - </template> - - <template name="BaseRecalibratorOptions"> -<![CDATA[ - --out ${br_table} - - @token_bam_input@ - - #for $i, $variant in enumerate($analysis_type.knownSites): - --knownSites variant_${i}.vcf - #end for -]]> - </template> -</macros> - - |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/combine_gvcfs.xml --- a/GATK/gatk/combine_gvcfs.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,44 +0,0 @@ -<macros> - <xml name="CombineGVCFsParameters" tokens="tag"> - - <expand macro="macro_gvcf_input" tag="@TAG@" /> - - <expand macro="macro_optional_parameters"> - - <param name="breakBandsAtMultiplesOf" type="integer" value="0" label="If > 0, reference bands will be broken up at genomic positions that are multiples of this number" help="-breakBandsAtMultiplesOf,‑‑breakBandsAtMultiplesOf &lt;breakBandsAtMultiplesOf&gt;" /> - - </expand> - - </xml> - - <xml name="CombineGVCFsOutput"> - <data format="vcf" name="cg_output_vcf" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (VCF)"> - <yield /> - </data> - </xml> - - <template name="CombineGVCFsPreprocessing"> -<![CDATA[ - @token_gvcf_input_pre@ -]]> - </template> - - <template name="CombineGVCFsOptions"> -<![CDATA[ - --out ${cg_output_vcf} - - @token_gvcf_input@ - - #set $optionals = $analysis_type.optional_parameters - #if $optionals.optional_parameters_enabled - #if $optionals.breakBandsAtMultiplesOf > 0 - --breakBandsAtMultiplesOf $optionals.breakBandsAtMultiplesOf - #end if - #end if -]]> - </template> - - -</macros> - - |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/combine_variants.xml --- a/GATK/gatk/combine_variants.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,96 +0,0 @@ -<macros> - <xml name="CombineVariantsParameters" tokens="tag"> - - <expand macro="macro_vcf_input" tag="@TAG@" /> - - <expand macro="macro_optional_parameters"> - - <param name="filteredRecordsMergeType" type="select" label="Determines how we should handle records seen at the same site in the VCF, but with different FILTER fields" help="-filteredRecordsMergeType,‑‑filteredrecordsmergetype &lt;filteredrecordsmergetype&gt;"> - <option value="">No Selection</option> - <option value="KEEP_IF_ANY_UNFILTERED">KEEP_IF_ANY_UNFILTERED</option> - <option value="KEEP_IF_ALL_UNFILTERED">KEEP_IF_ALL_UNFILTERED</option> - <option value="KEEP_UNCONDITIONAL">KEEP_UNCONDITIONAL</option> - </param> - - <param name="genotypeMergeOptions" type="select" label="Determines how we should merge genotype records for samples shared across the ROD files" help="-genotypeMergeOptions,‑‑genotypemergeoption &lt;genotypemergeoption&gt;"> - <option value="">No Selection</option> - <option value="UNIQUIFY">UNIQUIFY</option> - <option value="PRIORITIZE">PRIORITIZE</option> - <option value="UNSORTED">UNSORTED</option> - <option value="REQUIRE_UNIQUE">REQUIRE_UNIQUE</option> - </param> - - <param name="minimumN" type="integer" value="1" optional="true" label="Combine variants and output site only if the variant is present in at least N input files" help="-minN,‑‑minimumN &lt;minimumN&gt;" /> - - <param name="rod_priority_list" type="text" value="" optional="true" label="A comma-separated string describing the priority ordering for the genotypes as far as which record gets emitted" help="-priority,‑‑rod_priority_list &lt;rod_priority_list&gt;" /> - - <param name="setKey" type="text" value="" optional="true" label="Key used in the INFO key=value tag emitted describing which set the combined VCF record came from" help="-setKey,‑‑setKey &lt;setKey&gt;" /> - - <param name="assumeIdenticalSamples" type="boolean" truevalue="--assumeIdenticalSamples" falsevalue="" label="If true, assume input VCFs have identical sample sets and disjoint calls" help="-assumeIdenticalSamples,‑‑assumeIdenticalSamples" /> - - <param name="excludeNonVariants" type="boolean" truevalue="--excludeNonVariants" falsevalue="" label="Don't include loci found to be non-variant after the combining procedure" help="-env,‑‑excludeNonVariants" /> - - <param name="filteredAreUncalled" type="boolean" truevalue="--filteredAreUncalled" falsevalue="" label="If true, then filtered VCFs are treated as uncalled, so that filtered set annotations don't appear in the combined VCF" help="-filteredAreUncalled,‑‑filteredAreUncalled" /> - - <param name="mergeInfoWithMaxAC" type="boolean" truevalue="--mergeInfoWithMaxAC" falsevalue="" label="If true, when VCF records overlap the info field is taken from the one with the max AC instead of only taking the fields which are identical across the overlapping records." help="-mergeInfoWithMaxAC,‑‑mergeInfoWithMaxAC" /> - - <param name="minimalVCF" type="boolean" truevalue="--minimalVCF" falsevalue="" label="If true, then the output VCF will contain no INFO or genotype FORMAT fields" help="-minimalVCF,‑‑minimalVCF" /> - - <param name="printComplexMerges" type="boolean" truevalue="--printComplexMerges" falsevalue="" label="Print out interesting sites requiring complex compatibility merging" help="-printComplexMerges,‑‑printComplexMerges" /> - - <param name="suppressCommandLineHeader" type="boolean" truevalue="--suppressCommandLineHeader" falsevalue="" label="If true, do not output the header containing the command line used" help="-suppressCommandLineHeader,‑‑suppressCommandLineHeader" /> - - </expand> - - </xml> - - <xml name="CombineVariantsOutput"> - <data format="vcf" name="cv_output_vcf" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (VCF)"> - <yield /> - </data> - </xml> - - <template name="CombineVariantsPreprocessing"> -<![CDATA[ - @token_vcf_input_pre@ -]]> - </template> - - <template name="CombineVariantsOptions"> -<![CDATA[ - --out ${cv_output_vcf} - - @token_vcf_input@ - - #set $optionals = $analysis_type.optional_parameters - #if $optionals.optional_parameters_enabled - - #if $optionals.filteredRecordsMergeType - --filteredRecordsMergeType $optionals.filteredRecordsMergeType - #end if - #if $optionals.genotypeMergeOptions - --genotypeMergeOptions $optionals.genotypeMergeOptions - #end if - #if $optionals.minimumN != 1 - --minimumN $optionals.minimumN - #end if - #if $optionals.rod_priority_list - --rod_priority_list $optionals.rod_priority_list - #end if - - $optionals.assumeIdenticalSamples - $optionals.excludeNonVariants - $optionals.filteredAreUncalled - $optionals.mergeInfoWithMaxAC - $optionals.minimalVCF - $optionals.printComplexMerges - $optionals.suppressCommandLineHeader - - #end if -]]> - </template> - - -</macros> - - |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/gatk.xml --- a/GATK/gatk/gatk.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,179 +0,0 @@\n-<?xml version="1.0" encoding="utf-8"?>\n-<tool id="gatk" name="GATK" version="@VERSION@.d9">\n- <description>tool collection Version @VERSION@</description>\n- <macros>\n- <import>gatk_macros.xml</import>\n- <import>realigner_target_creator.xml</import>\n- <import>indel_realigner.xml</import>\n- <import>base_recalibrator.xml</import>\n- <import>analyze_covariates.xml</import>\n- <import>print_reads.xml</import>\n- <import>haplotype_caller.xml</import>\n- <import>genotype_gvcfs.xml</import>\n- <import>combine_gvcfs.xml</import>\n- <import>combine_variants.xml</import>\n- </macros>\n- <expand macro="requirements"/>\n- <stdio>\n- <regex match="^INFO" level="log"/>\n- <regex match="^WARN" level="warning"/>\n- <regex match="Using .* implementation of PairHMM" level="warning"/>\n- <regex match="There is insufficient memory for the Java Runtime Environment to continue" level="fatal"/>\n- <regex match="^##### ERROR" level="fatal"/>\n- <exit_code range="1:" level="fatal"/>\n- </stdio>\n- <command><![CDATA[\n- ############################\n- ## import analysis specific preprocessings by using cheetahs internal searchList\n- ## if not defined, ignore\n- ############################\n- #if $analysis_type.analysis_type_selector + "Preprocessing" in vars()[\'SL\'][2]\n- #set $analysisPreprocessing = vars()[\'SL\'][2][$analysis_type.analysis_type_selector + "Preprocessing"]\n- #include source=$analysisPreprocessing\n- #end if\n- \n- ############################\n- ## GATK tool unspecific options\n- ############################\n- @GATK_EXEC@\n- \n- --analysis_type ${analysis_type.analysis_type_selector}\n- --reference_sequence ${ref_file.fields.path}\n-\n- --log_to_file ${output_log}\n-\n- #if $cond_intervals.cond_intervals_enabled\n- #for $interval in $cond_intervals.intervals:\n- --intervals ${interval.L}\n- #end for\n- #end if\n-\n- #if $cond_BQSR.cond_BQSR_enabled\n- --BQSR $cond_BQSR.BQSR\n- #end if\n-\n- ############################\n- ## import analysis specific options by using cheetahs internal searchList\n- ## if not defined throw raw python error until better idea\n- ############################\n- #if $analysis_type.analysis_type_selector + "Options" in vars()[\'SL\'][2]\n- #set $analysisOptions = vars()[\'SL\'][2][$analysis_type.analysis_type_selector + "Options"]\n- #include source=$analysisOptions\n- #else\n- #set $analysisOptions = vars()[\'SL\'][2][$analysis_type.analysis_type_selector + "Options"]\n- #end if\n- \n- ############################\n- ## only put ERROR or FATAL log messages into stderr\n- ## but keep full log for printing into log file\n- ############################\n- 2>&1 | awk \'\\$1 != "INFO" && \\$1 != "WARN"\' >&2\n-]]></command>\n- <inputs>\n- <param name="ref_file" type="select" label="Using reference genome" help="-R,\xe2\x80\x91\xe2\x80\x91reference_sequence &lt;reference_sequence&gt;">\n- <options from_data_table="picard_indexes"/>\n- <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>\n- </param>\n- <conditional name="cond_intervals">\n- <param name="cond_intervals_enabled" type="boolean" label="Select interval subset to operate on?"/>\n- <when value="true">\n- <repeat name="intervals" title="genomic interval over which to operate" help="-L,\xe2\x80\x91\xe2\x80\x91intervals &lt;intervals&gt;">\n- <param name="L" type="text" value=""/>\n- </repeat>\n- </when>\n- <when value="false"/>\n- </conditional>\n- <conditional name="cond_BQSR">\n- <param name="cond_BQSR_enabled" type="boolean" label="Select covariates for on-the-fly recalibration?"/>\n- <when '..b'"nct" type="integer" value="1" label="Number of CPU threads to allocate per data thread" help="make sure, the option is available for the chosen tool"/>\n- <param name="mem" type="integer" value="0" label="Overwrite Memory in MB (0 = don\'t overwrite)" help="Overwrites all other defaults and might lead to crash the run. States mem per data thread"/>\n- </when>\n- <when value="false"/>\n- </conditional>\n- <conditional name="analysis_type">\n- <param name="analysis_type_selector" type="select" label="Analysis Type">\n- <option value="RealignerTargetCreator">RealignerTargetCreator</option>\n- <option value="IndelRealigner">IndelRealigner</option>\n- <option value="BaseRecalibrator">BaseRecalibrator</option>\n- <option value="AnalyzeCovariates">AnalyzeCovariates</option>\n- <option value="PrintReads">PrintReads</option>\n- <option value="HaplotypeCaller">HaplotypeCaller</option>\n- <option value="GenotypeGVCFs">GenotypeGVCFs</option>\n- <option value="CombineGVCFs">CombineGVCFs</option>\n- <option value="CombineVariants">CombineVariants</option>\n- </param>\n- <when value="RealignerTargetCreator">\n- <expand macro="RealignerTargetCreatorParameters" tag="rtc"/>\n- </when>\n- <when value="IndelRealigner">\n- <expand macro="IndelRealignerParameters" tag="ir"/>\n- </when>\n- <when value="BaseRecalibrator">\n- <expand macro="BaseRecalibratorParameters" tag="br"/>\n- </when>\n- <when value="AnalyzeCovariates">\n- <expand macro="AnalyzeCovariatesParameters" tag="ac"/>\n- </when>\n- <when value="PrintReads">\n- <expand macro="PrintReadsParameters" tag="pr"/>\n- </when>\n- <when value="HaplotypeCaller">\n- <expand macro="HaplotypeCallerParameters" tag="hc"/>\n- </when>\n- <when value="GenotypeGVCFs">\n- <expand macro="GenotypeGVCFsParameters" tag="gg"/>\n- </when>\n- <when value="CombineGVCFs">\n- <expand macro="CombineGVCFsParameters" tag="cg"/>\n- </when>\n- <when value="CombineVariants">\n- <expand macro="CombineVariantsParameters" tag="cv"/>\n- </when>\n- </conditional>\n- </inputs>\n- <outputs>\n- <expand macro="RealignerTargetCreatorOutput" tag="rtc">\n- <filter>analysis_type[\'analysis_type_selector\'] == \'RealignerTargetCreator\'</filter>\n- </expand>\n- <expand macro="IndelRealignerOutput" tag="ir">\n- <filter>analysis_type[\'analysis_type_selector\'] == \'IndelRealigner\'</filter>\n- </expand>\n- <expand macro="BaseRecalibratorOutput" tag="br">\n- <filter>analysis_type[\'analysis_type_selector\'] == \'BaseRecalibrator\'</filter>\n- </expand>\n- <expand macro="AnalyzeCovariatesOutput" tag="ac">\n- <filter>analysis_type[\'analysis_type_selector\'] == \'AnalyzeCovariates\'</filter>\n- </expand>\n- <expand macro="PrintReadsOutput" tag="pr">\n- <filter>analysis_type[\'analysis_type_selector\'] == \'PrintReads\'</filter>\n- </expand>\n- <expand macro="HaplotypeCallerOutput" tag="hc">\n- <filter>analysis_type[\'analysis_type_selector\'] == \'HaplotypeCaller\'</filter>\n- </expand>\n- <expand macro="GenotypeGVCFsOutput" tag="gg">\n- <filter>analysis_type[\'analysis_type_selector\'] == \'GenotypeGVCFs\'</filter>\n- </expand>\n- <expand macro="CombineGVCFsOutput" tag="cg">\n- <filter>analysis_type[\'analysis_type_selector\'] == \'CombineGVCFs\'</filter>\n- </expand>\n- <expand macro="CombineVariantsOutput" tag="cv">\n- <filter>analysis_type[\'analysis_type_selector\'] == \'CombineVariants\'</filter>\n- </expand>\n- <data format="txt" name="output_log" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (log)"/>\n- </outputs>\n- <expand macro="macro_tests"/>\n- <citations>\n- <citation type="doi">10.1101/gr.107524.110</citation>\n- <citation type="doi">10.1038/ng.806</citation>\n- <citation type="doi">10.1002/0471250953.bi1110s43</citation>\n- </citations>\n-</tool>\n' |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/gatk_macros.xml --- a/GATK/gatk/gatk_macros.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,166 +0,0 @@ -<macros> - - <xml name="requirements"> - <requirements> - <requirement type="package">gatk</requirement> - <requirement type="set_environment">GATK_PATH</requirement> - <requirement type="set_environment">GATK_SITE_OPTIONS</requirement> - <requirement type="package" version="3.1.2.1">package_r_for_gatk_3_4_0</requirement> - </requirements> - </xml> - - <xml name="version_command"> - <version_command><![CDATA[ @GATK_EXEC@ --help|grep '^The Genome' ]]></version_command> - </xml> - - <token name="@VERSION@">3.4-0</token> - <token name="@OUTPUT_NAME_PREFIX@">${tool.name} - ${analysis_type.analysis_type_selector}</token> - <token name="@GATK_EXEC@"> -<![CDATA[ - #if $cond_threads.cond_threads_enabled: - #if int($cond_threads.nct) > 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:-} -]]> - </token> - - <xml name="macro_vcf_input" tokens="tag"> - <param name="input" type="data" format="vcf" multiple="true" label="Variant files (VCF format)" help="-V, ‑‑variant"> - <validator type="unspecified_build" /> - <validator type="dataset_metadata_in_data_table" table_name="picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build." /> - </param> - </xml> - <token name="@token_vcf_input_pre@" tokens="tag"> -<![CDATA[ - ############################ - ## create links to gVCF input files with correct extensions - ############################ - #for $i, $variant in enumerate($analysis_type.input): - ln -s -f ${variant} variant_${i}.vcf && - #end for -]]> - </token> - <token name="@token_vcf_input@"> -<![CDATA[ - #for $i, $variant in enumerate($analysis_type.input): - --variant variant_${i}.vcf - #end for - @token_reference_input@ -]]> - </token> - - - <xml name="macro_gvcf_input" tokens="tag"> - <param name="input" type="data" format="vcf" multiple="true" label="Variant files (gVCF format)" help="-V, ‑‑variant"> - <validator type="unspecified_build" /> - <validator type="dataset_metadata_in_data_table" table_name="picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build." /> - </param> - </xml> - <token name="@token_gvcf_input_pre@" tokens="tag"> -<![CDATA[ - ############################ - ## create links to gVCF input files with correct extensions - ############################ - #for $i, $variant in enumerate($analysis_type.input): - ln -s -f ${variant} variant_${i}.g.vcf && - #end for -]]> - </token> - <token name="@token_gvcf_input@"> -<![CDATA[ - #for $i, $variant in enumerate($analysis_type.input): - --variant variant_${i}.g.vcf - #end for - @token_reference_input@ -]]> - </token> - - <xml name="macro_bam_input"> - <conditional name="cond_bam_input"> - <param name="all_in_one" type="boolean" value="false" label="Input all BAM files in a single command" /> - <when value="true"> - <param name="input" type="data" format="bam" multiple="true" label="Input file containing sequence data (BAM)" help="-I, ‑‑input_file"> - <validator type="unspecified_build"/> - <validator type="dataset_metadata_in_data_table" table_name="picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build."/> - </param> - </when> - <when value="false"> - <param name="input" type="data" format="bam" label="Input file containing sequence data (BAM)" help="-I, ‑‑input_file"> - <validator type="unspecified_build"/> - <validator type="dataset_metadata_in_data_table" table_name="picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build."/> - </param> - </when> - </conditional> - </xml> - <token name="@token_bam_input_pre@"> -<![CDATA[ - ############################ - ## create links to bam input files with correct extensions - ############################ - #if $analysis_type.cond_bam_input.all_in_one - #for $i, $bam in enumerate($analysis_type.cond_bam_input.input): - ln -s -f ${bam} input_${i}.bam && - ln -s -f ${bam.metadata.bam_index} input_${i}.bam.bai && - #end for - #else - ln -s -f ${analysis_type.cond_bam_input.input} input.bam && - ln -s -f ${analysis_type.cond_bam_input.input.metadata.bam_index} input.bam.bai && - #end if -]]> - </token> - <token name="@token_bam_input@"> -<![CDATA[ - #if $analysis_type.cond_bam_input.all_in_one - #for $i, $bam in enumerate($analysis_type.cond_bam_input.input): - --input_file input_${i}.bam - #end for - #else - --input_file input.bam - #end if - @token_reference_input@ -]]> - </token> - - <token name="@token_reference_input@"> -<![CDATA[ -]]> - </token> - <xml name="macro_input" tokens="tag"> - <yield /> - </xml> - - <xml name="macro_optional_parameters"> - <conditional name="optional_parameters"> - <param name="optional_parameters_enabled" type="boolean" label="Configure Optional Parameters" /> - <when value="true"> - <yield /> - </when> - <when value="false" /> - </conditional> - </xml> - - <xml name="macro_advanced_parameters"> - <conditional name="advanced_parameters"> - <param name="advanced_parameters_enabled" type="boolean" label="Configure Advanced Parameters" /> - <when value="true"> - <yield /> - </when> - <when value="false" /> - </conditional> - </xml> - - <xml name="macro_tests"> - <tests> - - </tests> - </xml> - -</macros> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/generation/gatk.xsl --- a/GATK/gatk/generation/gatk.xsl Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,162 +0,0 @@ -<?xml version="1.0" encoding="UTF-8"?> -<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"> -<xsl:output - method="xml" - encoding="utf-8" - indent="yes" - cdata-section-elements="script style" /> - -<xsl:template match="/"> - -<tool id="gatk" name="GATK" version="@VERSION@.d9"> - <description>tool collection Version @VERSION@</description> - - <macros> - <import>gatk_macros.xml</import> - <xsl:for-each select="analyses/analysis"> - <import><xsl:value-of select="macro_file" /></import> - </xsl:for-each> - </macros> - - <expand macro="requirements" /> - - <stdio> - <regex match="^INFO" level="log" /> - <regex match="^WARN" level="warning" /> - <regex match="Using .* implementation of PairHMM" level="warning" /> - <regex match="There is insufficient memory for the Java Runtime Environment to continue" level="fatal" /> - <regex match="^##### ERROR" level="fatal" /> - <exit_code range="1:" level="fatal"/> - </stdio> - - <command> -<xsl:text disable-output-escaping="yes"><![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 -]]></xsl:text> - </command> - - <inputs> - - <param name="ref_file" type="select" label="Using reference genome" help="-R,‑‑reference_sequence &lt;reference_sequence&gt;" > - <options from_data_table="picard_indexes"> - <!--filter type="data_meta" key="dbkey" ref="@TAG@_input" column="dbkey" /--> - </options> - <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> - </param> - - <conditional name="cond_intervals"> - <param name="cond_intervals_enabled" type="boolean" label="Select interval subset to operate on?" /> - <when value="true"> - <repeat name="intervals" title="genomic interval over which to operate" help="-L,‑‑intervals &lt;intervals&gt;"> - <param name="L" type="text" value="" /> - </repeat> - </when> - <when value="false" /> - </conditional> - - <conditional name="cond_BQSR"> - <param name="cond_BQSR_enabled" type="boolean" label="Select covariates for on-the-fly recalibration?" /> - <when value="true"> - <param name="BQSR" type="data" format="tabular" label="Input covariates table file for on-the-fly base quality score recalibration" help="-BQSR,‑‑BQSR &lt;BQSR&gt; intended primarily for use with BaseRecalibrator and PrintReads" /> - </when> - <when value="false" /> - </conditional> - - <conditional name="cond_threads"> - <param name="cond_threads_enabled" type="boolean" label="Set computational options (cpu, mem)?" /> - <when value="true"> - <param name="nt" type="integer" value="1" label="Number of data threads to allocate to this analysis" help="make sure, the option is available for the chosen tool" /> - <param name="nct" type="integer" value="1" label="Number of CPU threads to allocate per data thread" help="make sure, the option is available for the chosen tool" /> - <param name="mem" type="integer" value="0" label="Overwrite Memory in MB (0 = don't overwrite)" help="Overwrites all other defaults and might lead to crash the run. States mem per data thread" /> - </when> - <when value="false" /> - </conditional> - - <conditional name="analysis_type"> - <param name="analysis_type_selector" type="select" label="Analysis Type"> - <xsl:for-each select="analyses/analysis"> - <option value="{name}"><xsl:value-of select="name" /></option> - </xsl:for-each> - </param> - <xsl:for-each select="analyses/analysis"> - <when value="{name}"> - <!--xsl:choose> - <xsl:when test="input_type = 'bam'"> - <expand macro="macro_bam_input" tag="{tag}" /> - </xsl:when> - <xsl:when test="input_type = 'gvcf'"> - <expand macro="macro_gvcf_input" tag="{tag}" /> - </xsl:when> - </xsl:choose--> - <expand macro="{name}Parameters" tag="{tag}" /> - </when> - </xsl:for-each> - </conditional> - </inputs> - - <outputs> - <xsl:for-each select="analyses/analysis"> - <expand macro="{name}Output" tag="{tag}"> - <filter>analysis_type['analysis_type_selector'] == '<xsl:value-of select="name" />'</filter> - </expand> - </xsl:for-each> - <data format="txt" name="output_log" label="${{tool.name}} - ${{analysis_type.analysis_type_selector}} on ${{on_string}} (log)" /> - </outputs> - - <expand macro="macro_tests" /> - - <citations> - <citation type="doi">10.1101/gr.107524.110</citation> - <citation type="doi">10.1038/ng.806</citation> - <citation type="doi">10.1002/0471250953.bi1110s43</citation> - </citations> -</tool> - -</xsl:template> -</xsl:stylesheet> - - |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/generation/gatk.xsldb.xml --- a/GATK/gatk/generation/gatk.xsldb.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,57 +0,0 @@ -<?xml version="1.0" encoding="UTF-8"?> -<analyses> - <analysis> - <name>RealignerTargetCreator</name> - <input_type>bam</input_type> - <tag>rtc</tag> - <macro_file>realigner_target_creator.xml</macro_file> - </analysis> - <analysis> - <name>IndelRealigner</name> - <input_type>bam</input_type> - <tag>ir</tag> - <macro_file>indel_realigner.xml</macro_file> - </analysis> - <analysis> - <name>BaseRecalibrator</name> - <input_type>bam</input_type> - <tag>br</tag> - <macro_file>base_recalibrator.xml</macro_file> - </analysis> - <analysis> - <name>AnalyzeCovariates</name> - <input_type>bam</input_type> - <tag>ac</tag> - <macro_file>analyze_covariates.xml</macro_file> - </analysis> - <analysis> - <name>PrintReads</name> - <input_type>bam</input_type> - <tag>pr</tag> - <macro_file>print_reads.xml</macro_file> - </analysis> - <analysis> - <name>HaplotypeCaller</name> - <input_type>bam</input_type> - <tag>hc</tag> - <macro_file>haplotype_caller.xml</macro_file> - </analysis> - <analysis> - <name>GenotypeGVCFs</name> - <input_type>gvcf</input_type> - <tag>gg</tag> - <macro_file>genotype_gvcfs.xml</macro_file> - </analysis> - <analysis> - <name>CombineGVCFs</name> - <input_type>gvcf</input_type> - <tag>cg</tag> - <macro_file>combine_gvcfs.xml</macro_file> - </analysis> - <analysis> - <name>CombineVariants</name> - <input_type>vcf</input_type> - <tag>cv</tag> - <macro_file>combine_variants.xml</macro_file> - </analysis> -</analyses> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/genotype_gvcfs.xml --- a/GATK/gatk/genotype_gvcfs.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,43 +0,0 @@ -<macros> - <xml name="GenotypeGVCFsParameters" tokens="tag"> - - <expand macro="macro_gvcf_input" tag="@TAG@" /> - - <expand macro="macro_optional_parameters"> - - - <param name="sample_ploidy" type="integer" value="2" label="Ploidy (number of chromosomes) per sample. For pooled data, set to (Number of samples in each pool * Sample Ploidy)" help="-ploidy,‑‑sample_ploidy &lt;sample_ploidy&gt;" /> - - </expand> - - </xml> - - <xml name="GenotypeGVCFsOutput"> - <data format="vcf" name="gg_output_gvcf" from_work_dir="output.g.vcf" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (gVCF)"> - <yield /> - </data> - </xml> - - <template name="GenotypeGVCFsPreprocessing"> -<![CDATA[ - @token_gvcf_input_pre@ -]]> - </template> - - <template name="GenotypeGVCFsOptions"> -<![CDATA[ - --out output.g.vcf - - @token_gvcf_input@ - - #set $optionals = $analysis_type.optional_parameters - #if $optionals.optional_parameters_enabled - --sample_ploidy $optionals.sample_ploidy - #end if -]]> - </template> - - -</macros> - - |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/haplotype_caller.xml --- a/GATK/gatk/haplotype_caller.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,65 +0,0 @@ -<macros> - <xml name="HaplotypeCallerParameters" tokens="tag"> - - <expand macro="macro_bam_input" tag="@TAG@" /> - - <conditional name="cond_usage"> - <param name="cond_usage_selector" type="select" label="Select usage"> - <option value="GVCF">Single-sample all-sites calling on DNAseq (GVCF mode)</option> - </param> - <when value="GVCF"> - <expand macro="HaplotypeCallerGVCF" /> - </when> - </conditional> - - <expand macro="macro_optional_parameters"> - - <param name="sample_ploidy" type="integer" value="2" label="Ploidy (number of chromosomes) per sample. For pooled data, set to (Number of samples in each pool * Sample Ploidy)" help="-ploidy,‑‑sample_ploidy &lt;sample_ploidy&gt;" /> - - </expand> - - </xml> - - <xml name="HaplotypeCallerOutput"> - <data format="vcf" name="hc_output_gvcf" from_work_dir="output.g.vcf" label="${tool.name} on ${on_string} (gVCF)"> - <yield /> - </data> - </xml> - - <template name="HaplotypeCallerPreprocessing"> -<![CDATA[ - @token_bam_input_pre@ -]]> - </template> - - <template name="HaplotypeCallerOptions"> -<![CDATA[ - --out output.g.vcf - - @token_bam_input@ - - #set $optionals = $analysis_type.optional_parameters - #if $optionals.optional_parameters_enabled - --sample_ploidy $optionals.sample_ploidy - #end if - - #set $usage_selector = $analysis_type.cond_usage.cond_usage_selector - #set $usage = $analysis_type.cond_usage - - #if str($usage_selector) == 'GVCF' - --emitRefConfidence "GVCF" - #end if -]]> - </template> - - - - <xml name="HaplotypeCallerGVCF"> - <param name="emitRefConfidence" type="select" optional="true" label="Mode for emitting reference confidence scores" help="-ERC,‑‑emitRefConfidence &lt;emitRefConfidence&gt;"> - <option value="GVCF">GVCF (Reference model emitted with condensed non-variant blocks)</option> - </param> - </xml> - -</macros> - - |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/indel_realigner.xml --- a/GATK/gatk/indel_realigner.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,90 +0,0 @@ -<macros> - <xml name="IndelRealignerParameters" tokens="tag"> - - <expand macro="macro_bam_input" tag="@TAG@" /> - - <param name="targetIntervals" type="data" format="gatk_interval" label="Intervals file output from RealignerTargetCreator" help="-targetIntervals,--targetIntervals &lt;targetIntervals&gt;" /> - - <expand macro="macro_optional_parameters"> - <repeat name="knownAlleles" title="Input VCF file(s) with known indels" help="-known,‑‑knownAlleles &lt;knownAlleles&gt;"> - <param name="knownAllele" type="data" format="vcf" label="Variant file (VCF format)" /> - </repeat> - - <param name="consensusDeterminationModel" type="select" label="minimum reads at a locus to enable using the entropy calculation" help="-model,‑‑consensusDeterminationModel &lt;consensusDeterminationModel&gt;"> - <option value="USE_READS">USE_READS - Additionally uses indels already present in the original alignments of the reads</option> - <option value="KNOWNS_ONLY">KNOWNS_ONLYS - Uses only indels from a provided ROD of known indels</option> - <option value="USE_SW">USE_SW - Additionally uses 'Smith-Waterman' to generate alternate consenses</option> - </param> - <param name="LODThresholdForCleaning" type="float" value="5.0" label="LOD threshold above which the cleaner will clean" help="-LOD,‑‑LODThresholdForCleaning &lt;LODThresholdForCleaning&gt;" /> - <!--param name="nWayOut" type="float" value="5.0" label="Generate one output file for each input (-I) bam file (not compatible with -output)" help="-nWayOut,--nWayOut &lt;nWayOut&gt;" /--> - </expand> - - - <expand macro="macro_advanced_parameters"> - <param name="entropyThreshold" type="float" value="0.15" label="Percentage of mismatches at a locus to be considered having high entropy (0.0 < entropy <= 1.0)" help="-entropy,‑‑entropyThreshold &lt;entropyThreshold&gt;" /> - - <param name="maxConsensuses" type="integer" value="30" label="Max alternate consensuses to try (necessary to improve performance in deep coverage)" help="-maxConsensuses,‑‑maxConsensuses &lt;maxConsensuses&gt;" /> - - <param name="maxIsizeForMovement" type="integer" value="3000" label="maximum insert size of read pairs that we attempt to realign" help="-maxIsize,‑‑maxIsizeForMovement &lt;maxIsizeForMovement&gt;" /> - - <param name="maxPositionalMoveAllowed" type="integer" value="200" label="Maximum positional move in basepairs that a read can be adjusted during realignment" help="-maxPosMove,‑‑maxPositionalMoveAllowed &lt;maxPositionalMoveAllowed&gt;" /> - - <param name="maxReadsForConsensuses" type="integer" value="120" label="Max reads used for finding the alternate consensuses (necessary to improve performance in deep coverage)" help="-greedy,‑‑maxReadsForConsensuses &lt;maxReadsForConsensuses&gt;" /> - - <param name="maxReadsForRealignment" type="integer" value="20000" label="Max reads allowed at an interval for realignment" help="-maxReads,‑‑maxReadsForRealignment &lt;maxReadsForRealignment&gt;" /> - - <param name="maxReadsInMemory" type="integer" value="150000" label="max reads allowed to be kept in memory at a time by the SAMFileWriter" help="-maxInMemory,‑‑maxReadsInMemory &lt;maxReadsInMemory&gt;" /> - - <param name="noOriginalAlignmentTags" type="boolean" truevalue="--noOriginalAlignmentTags" falsevalue="" label="Don't output the original cigar or alignment start tags for each realigned read in the output bam" help="-noTags,‑‑noOriginalAlignmentTags" /> - </expand> - - </xml> - - <xml name="IndelRealignerOutput"> - <data format="bam" name="ir_output_bam" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (BAM)"> - <yield /> - </data> - </xml> - - <template name="IndelRealignerPreprocessing"> -<![CDATA[ - @token_bam_input_pre@ - - ln -s -f ${analysis_type.targetIntervals} target.intervals && - - #if $analysis_type.optional_parameters.optional_parameters_enabled - #for $i, $knownAllele in enumerate($analysis_type.optional_parameters.knownAlleles): - ln -s -f ${knownAllele.knownAllele} knownAllele_${i}.vcf && - #end for - #end if -]]> - </template> - - <template name="IndelRealignerOptions"> -<![CDATA[ - --out ${ir_output_bam} - - @token_bam_input@ - --targetIntervals target.intervals - - #if $analysis_type.optional_parameters.optional_parameters_enabled - #for $i, $knownAllele in enumerate($analysis_type.optional_parameters.knownAlleles): - --knownAlleles knownAllele_${i}.vcf - #end for - --consensusDeterminationModel ${analysis_type.consensusDeterminationModel} - --LODThresholdForCleaning ${analysis_type.LODThresholdForCleaning} - #end if - - #if $analysis_type.advanced_parameters.advanced_parameters_enabled - --entropyThreshold ${analysis_type.advanced_parameters.entropyThreshold} - --maxConsensuses ${analysis_type.advanced_parameters.maxConsensuses} - --maxIsizeForMovement ${analysis_type.advanced_parameters.maxIsizeForMovement} - --maxPositionalMoveAllowed ${analysis_type.advanced_parameters.maxPositionalMoveAllowed} - --maxReadsForConsensuses ${analysis_type.advanced_parameters.maxReadsForConsensuses} - --maxReadsForRealignment ${analysis_type.advanced_parameters.maxReadsForRealignment} - --maxReadsInMemory ${analysis_type.advanced_parameters.maxReadsInMemory} - ${analysis_type.advanced_parameters.noOriginalAlignmentTags} - #end if -]]> - </template> -</macros> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/print_reads.xml --- a/GATK/gatk/print_reads.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,71 +0,0 @@ -<macros> - <xml name="PrintReadsParameters" tokens="tag"> - - <expand macro="macro_bam_input" tag="@TAG@" /> - - <!-- BQSR in main config --> - - <expand macro="macro_optional_parameters"> - - <param name="number" type="integer" value="" optional="true" label="Print the first n reads from the file, discarding the rest" help="-n,‑‑number &lt;number&gt;" /> - - <param name="platform" type="text" value="" optional="true" label="Exclude all reads with this platform from the output" help="-platform,‑‑platform &lt;platform&gt;" /> - - <param name="readGroup" type="text" value="" optional="true" label="Exclude all reads with this read group from the output" help="-readGroup,‑‑readGroup &lt;readGroup&gt;" /> - - <param name="sample_file" type="data" format="txt" optional="true" label="File containing a list of samples (one per line). Can be specified multiple times" help="-sf,‑‑sample_file &lt;sample_file&gt;" /> - - <repeat name="sample_names" title="Sample names to be included in the analysis" help="-sn,‑‑sample_name &lt;sample_name&gt;"> - <param name="sample_name" type="text" value="" title="Sample name to be included in the analysis" /> - </repeat> - - <param name="simplify" type="text" truevalue="-s" falsevalue="" label="Erase all extra attributes in the read but keep the read group information" help="-s,‑‑simplify" /> - - </expand> - - </xml> - - <xml name="PrintReadsOutput"> - <data format="bam" name="pr_output_bam" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (BAM)"> - <yield /> - </data> - </xml> - - <template name="PrintReadsPreprocessing"> -<![CDATA[ - @token_bam_input_pre@ -]]> - </template> - - <template name="PrintReadsOptions"> -<![CDATA[ - --out ${pr_output_bam} - - @token_bam_input@ - - #set $optionals = $analysis_type.optional_parameters - #if $optionals.optional_parameters_enabled - #if int($optionals.number) > 0 - --number $optionals.number - #end if - #if str($optionals.platform) - --platform $optionals.platform - #end if - #if str($optionals.readGroup) - --readGroup $optionals.readGroup - #end if - #if $optionals.sample_file - --sample_file $optionals.sample_file - #end if - #if $optionals.sample_names - #for $sample in $optionals.sample_names: - --intervals ${sample.sample_name} - #end for - #end if - $optionals.simplify - #end if -]]> - </template> -</macros> - - |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/realigner_target_creator.xml --- a/GATK/gatk/realigner_target_creator.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,57 +0,0 @@ -<macros> - <xml name="RealignerTargetCreatorParameters" tokens="tag"> - - <expand macro="macro_bam_input" tag="@TAG@" /> - - <expand macro="macro_optional_parameters"> - <param name="maxIntervalSize" type="integer" value="500" label="maximum interval size; any intervals larger than this value will be dropped" help="-maxInterval,‑‑maxIntervalSize &lt;maxIntervalSize&gt;" /> - <param name="minReadsAtLocus" type="integer" value="4" label="minimum reads at a locus to enable using the entropy calculation" help="-minReads,‑‑minReadsAtLocus &lt;minReadsAtLocus&gt;" /> - <param name="windowSize" type="integer" value="10" label="window size for calculating entropy or SNP clusters" help="-window,‑‑windowSize &lt;windowSize&gt;" /> - - <param name="mismatchFraction" type="float" value="0.0" label="fraction of base qualities needing to mismatch for a position to have high entropy" help="-mismatch,‑‑mismatchFraction &lt;mismatchFraction&gt;" /> - <repeat name="rod_bindings" title="Input VCF files with known indels" help="-known,‑‑known &lt;known&gt;"> - <param name="input_rod" type="data" format="vcf" label="Variant file (VCF format)" /> - </repeat> - </expand> - - </xml> - - <xml name="RealignerTargetCreatorOutput"> - <data format="gatk_interval" name="rtc_output_intervals" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (GATK intervals)"> - <yield /> - </data> - </xml> - - <template name="RealignerTargetCreatorPreprocessing"> -<![CDATA[ - @token_bam_input_pre@ - - #if $analysis_type.optional_parameters.optional_parameters_enabled - #for $i, $rod_binding in enumerate($analysis_type.optional_parameters.rod_bindings): - ln -s -f ${rod_binding.input_rod} rod_binding_${i}.vcf && - #end for - #end if -]]> - </template> - - <template name="RealignerTargetCreatorOptions"> -<![CDATA[ - --out ${rtc_output_intervals} - - @token_bam_input@ - - #if $analysis_type.optional_parameters.optional_parameters_enabled - --maxIntervalSize ${analysis_type.optional_parameters.maxIntervalSize} - --minReadsAtLocus ${analysis_type.optional_parameters.minReadsAtLocus} - --windowSize ${analysis_type.optional_parameters.windowSize} - --mismatchFraction ${analysis_type.optional_parameters.mismatchFraction} - - #for $i, $rod_binding in enumerate($analysis_type.optional_parameters.rod_bindings): - --known rod_binding_${i}.vcf - #end for - #end if -]]> - </template> -</macros> - - |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/tool-data/destinations.py --- a/GATK/gatk/tool-data/destinations.py Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,62 +0,0 @@ -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}) - |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/tool-data/picard_index.loc.sample --- a/GATK/gatk/tool-data/picard_index.loc.sample Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,26 +0,0 @@ -#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): -# -#<unique_build_id> <dbkey> <display_name> <fasta_file_path> -# -#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. -# |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/tool_data_table_conf.xml.sample --- a/GATK/gatk/tool_data_table_conf.xml.sample Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,7 +0,0 @@ -<tables> - <!-- Location of Picard dict files valid for GATK --> - <table name="picard_indexes" comment_char="#"> - <columns>value, dbkey, name, path</columns> - <file path="tool-data/picard_index.loc" /> - </table> -</tables> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/gatk/tool_dependencies.xml --- a/GATK/gatk/tool_dependencies.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,19 +0,0 @@ -<?xml version="1.0"?> -<tool_dependency> - <set_environment version="1.0"> - <environment_variable action="set_to" name="GATK_PATH">/mnt/galaxy/tools/GATK/3.4-0</environment_variable> - </set_environment> - <!-- - Use GATK_SITE_OPTIONS to set additional parameters that should be inserted in every GATK call. - The intended use case was to prohibit GATK to collect and send data. - For example: - - -et "NO_ET" -K "/data/gatk_key_file" ##ET no phone home - --> - <set_environment version="1.0"> - <environment_variable action="set_to" name="GATK_SITE_OPTIONS"> </environment_variable> - </set_environment> - <package name="package_r_for_gatk_3_4_0" version="3.1.2.1"> - <repository changeset_revision="49c62e9b71ad" name="package_r_for_gatk_3_4_0" owner="avowinkel" toolshed="https://toolshed.g2.bx.psu.edu" /> - </package> -</tool_dependency> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/package_picard_1_135/tool_dependencies.xml --- a/GATK/package_picard_1_135/tool_dependencies.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,22 +0,0 @@ -<?xml version="1.0"?> -<tool_dependency> - <package name="picard" version="1.135"> - <install version="1.0"> - <actions_group> - <actions architecture="x86_64" os="linux"> - <action type="download_by_url">https://github.com/broadinstitute/picard/releases/download/1.135/picard-tools-1.135.zip</action> - <action type="move_directory_files"> - <source_directory>.</source_directory> - <destination_directory>$INSTALL_DIR</destination_directory> - </action> - </actions> - <action type="set_environment"> - <environment_variable name="JAVA_JAR_PATH" action="set_to">$INSTALL_DIR</environment_variable> - </action> - </actions_group> - </install> - <readme> -This picard package dependency is retrieved directly from https://github.com/broadinstitute/picard/releases - </readme> - </package> -</tool_dependency> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 GATK/package_r_for_gatk_3_4_0/tool_dependencies.xml --- a/GATK/package_r_for_gatk_3_4_0/tool_dependencies.xml Thu Sep 12 06:50:21 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,48 +0,0 @@ -<?xml version="1.0"?> -<tool_dependency> - <package name="R" version="3.1.2"> - <repository changeset_revision="9f2fddb9d6e2" name="package_r_3_1_2" owner="iuc" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu" /> - </package> - <package name="package_r_for_gatk_3_4_0" version="3.1.2.1"> - <install version="1.0"> - <actions> - <action type="setup_r_environment"> - - <repository changeset_revision="9f2fddb9d6e2" name="package_r_3_1_2" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu"> - <package name="R" version="3.1.2" /> - </repository> - <package>https://github.com/cran/stringi/archive/0.5-5.tar.gz</package> - <package>https://github.com/cran/magrittr/archive/1.5.tar.gz</package> - <package>https://github.com/cran/stringr/archive/1.0.0.tar.gz</package> - <package>https://github.com/cran/RColorBrewer/archive/1.1-2.tar.gz</package> - <package>https://github.com/cran/dichromat/archive/2.0-0.tar.gz</package> - <package>https://github.com/cran/colorspace/archive/1.2-6.tar.gz</package> - <package>https://github.com/cran/munsell/archive/0.4.2.tar.gz</package> - <package>https://github.com/cran/labeling/archive/0.3.tar.gz</package> - <package>https://github.com/cran/Rcpp/archive/0.11.6.tar.gz</package> - <package>https://github.com/cran/digest/archive/0.6.8.tar.gz</package> - <package>https://github.com/cran/gtable/archive/0.1.2.tar.gz</package> - <package>https://github.com/cran/bitops/archive/1.0-6.tar.gz</package> - <package>https://github.com/cran/caTools/archive/1.17.1.tar.gz</package> - <package>https://github.com/cran/gtools/archive/3.5.0.tar.gz</package> - <package>https://github.com/cran/gdata/archive/2.17.0.tar.gz</package> - <package>https://github.com/cran/gsalib/archive/2.1.tar.gz</package> - <package>https://github.com/cran/gplots/archive/2.17.0.tar.gz</package> - <package>https://github.com/cran/plyr/archive/1.8.3.tar.gz</package> - <package>https://github.com/cran/reshape/archive/0.8.5.tar.gz</package> - <package>https://github.com/cran/reshape2/archive/1.4.1.tar.gz</package> - <package>https://github.com/cran/scales/archive/0.2.5.tar.gz</package> - <package>https://github.com/cran/proto/archive/0.3-10.tar.gz</package> - <package>https://github.com/cran/MASS/archive/7.3-43.tar.gz</package> - <package>https://github.com/cran/ggplot2/archive/1.0.1.tar.gz</package> - </action> - </actions> - </install> - <readme> - ggplot2 is a plotting system for R, based on the grammar of graphics, which tries to take the good parts of base and lattice graphics and none of the bad parts. - It takes care of many of the fiddly details that make plotting a hassle (like drawing legends) as well as providing a powerful model of graphics that makes it easy to produce complex multi-layered graphics. - - http://ggplot2.org/ - </readme> - </package> -</tool_dependency> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/Haplotypecaller.ga --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/Haplotypecaller.ga Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,101 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "Haplotypecaller workflow.", + "format-version": "0.1", + "name": "Haplotypecaller", + "steps": { + "0": { + "annotation": "", + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "Input Dataset" + } + ], + "label": null, + "name": "Input dataset", + "outputs": [], + "position": { + "left": 198, + "top": 208.1666717529297 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"Input Dataset\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [], + "uuid": "b9fb671f-f07f-498c-8c85-619987501313" + }, + "1": { + "annotation": "", + "id": 1, + "input_connections": { + "analysis_type|cond_bam_input|input": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "GATK", + "outputs": [ + { + "name": "rtc_output_intervals", + "type": "gatk_interval" + }, + { + "name": "ir_output_bam", + "type": "bam" + }, + { + "name": "br_table", + "type": "tabular" + }, + { + "name": "ac_plotsReportFile", + "type": "pdf" + }, + { + "name": "pr_output_bam", + "type": "bam" + }, + { + "name": "hc_output_gvcf", + "type": "vcf" + }, + { + "name": "gg_output_gvcf", + "type": "vcf" + }, + { + "name": "cg_output_vcf", + "type": "vcf" + }, + { + "name": "cv_output_vcf", + "type": "vcf" + }, + { + "name": "output_log", + "type": "txt" + } + ], + "position": { + "left": 484.83331298828125, + "top": 200 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/avowinkel/gatk/gatk/3.4-0.d9", + "tool_state": "{\"__page__\": 0, \"cond_threads\": \"{\\\"cond_threads_enabled\\\": \\\"False\\\", \\\"__current_case__\\\": 1}\", \"ref_file\": \"{\\\"__class__\\\": \\\"UnvalidatedValue\\\", \\\"value\\\": \\\"\\\"}\", \"__rerun_remap_job_id__\": null, \"cond_BQSR\": \"{\\\"cond_BQSR_enabled\\\": \\\"False\\\", \\\"__current_case__\\\": 1}\", \"analysis_type\": \"{\\\"analysis_type_selector\\\": \\\"HaplotypeCaller\\\", \\\"cond_usage\\\": {\\\"emitRefConfidence\\\": \\\"GVCF\\\", \\\"__current_case__\\\": 0, \\\"cond_usage_selector\\\": \\\"GVCF\\\"}, \\\"optional_parameters\\\": {\\\"optional_parameters_enabled\\\": \\\"False\\\", \\\"__current_case__\\\": 1}, \\\"cond_bam_input\\\": {\\\"input\\\": null, \\\"all_in_one\\\": \\\"False\\\", \\\"__current_case__\\\": 1}, \\\"__current_case__\\\": 5}\", \"cond_intervals\": \"{\\\"cond_intervals_enabled\\\": \\\"False\\\", \\\"__current_case__\\\": 1}\"}", + "tool_version": "3.4-0.d9", + "type": "tool", + "user_outputs": [], + "uuid": "5988799c-5658-4475-89ee-86f267cfbee1" + } + }, + "uuid": "e4f99de3-d6b0-4554-9562-60b2b0eed2d3" +} \ No newline at end of file |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/SAMTools.ga --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/SAMTools.ga Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,160 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "SAMTools workflow", + "format-version": "0.1", + "name": "SAMTools", + "steps": { + "0": { + "annotation": "", + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "Input Dataset" + } + ], + "label": null, + "name": "Input dataset", + "outputs": [], + "position": { + "left": 162, + "top": 169 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"Input Dataset\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [], + "uuid": "1eec712c-2fe0-43a8-b033-f027a74c6a48" + }, + "1": { + "annotation": "", + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "Input Dataset" + } + ], + "label": null, + "name": "Input dataset", + "outputs": [], + "position": { + "left": 273.83331298828125, + "top": 341.83331298828125 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"Input Dataset\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [], + "uuid": "98d5e3bf-4715-48a2-9b2b-29b21179c425" + }, + "2": { + "annotation": "", + "id": 2, + "input_connections": { + "input1": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Sort", + "outputs": [ + { + "name": "output1", + "type": "bam" + } + ], + "position": { + "left": 330, + "top": 222 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/samtools_sort/samtools_sort/2.0", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input1\": \"null\", \"sort_mode\": \"\\\"\\\"\"}", + "tool_version": "2.0", + "type": "tool", + "user_outputs": [], + "uuid": "5e9aef3e-c2ad-43d1-b248-7d94d6a974bc" + }, + "3": { + "annotation": "", + "id": 3, + "input_connections": { + "reference_source|input_bams_0|input_bam": { + "id": 2, + "output_name": "output1" + }, + "reference_source|ref_file": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "MPileup", + "outputs": [ + { + "name": "output_mpileup", + "type": "pileup" + }, + { + "name": "output_log", + "type": "txt" + } + ], + "position": { + "left": 484.83331298828125, + "top": 313.83331298828125 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/samtools_mpileup/samtools_mpileup/2.0", + "tool_state": "{\"__page__\": 0, \"advanced_options\": \"{\\\"advanced_options_selector\\\": \\\"basic\\\", \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"genotype_likelihood_computation_type\": \"{\\\"output_mapping_quality\\\": \\\"False\\\", \\\"genotype_likelihood_computation_type_selector\\\": \\\"do_not_perform_genotype_likelihood_computation\\\", \\\"__current_case__\\\": 1, \\\"base_position_on_reads\\\": \\\"False\\\"}\", \"reference_source\": \"{\\\"ref_file\\\": null, \\\"reference_source_selector\\\": \\\"history\\\", \\\"input_bams\\\": [{\\\"__index__\\\": 0, \\\"input_bam\\\": null}], \\\"__current_case__\\\": 1}\"}", + "tool_version": "2.0", + "type": "tool", + "user_outputs": [], + "uuid": "84c6d18e-1930-4eef-b58a-46c88a35339e" + }, + "4": { + "annotation": "", + "id": 4, + "input_connections": { + "input_file": { + "id": 3, + "output_name": "output_mpileup" + } + }, + "inputs": [], + "label": null, + "name": "Pileup to VCF", + "outputs": [ + { + "name": "output_file", + "type": "vcf" + } + ], + "position": { + "left": 562.8333129882812, + "top": 469.83331298828125 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/jjohnson/pileup_to_vcf/pileup_to_vcf/2.2", + "tool_state": "{\"snps_only\": \"\\\"False\\\"\", \"min_cvrg\": \"\\\"5\\\"\", \"allow_multiples\": \"\\\"False\\\"\", \"input_file\": \"null\", \"__page__\": 0, \"vcf_id\": \"\\\"\\\"\", \"__rerun_remap_job_id__\": null, \"cols\": \"{\\\"select_order\\\": \\\"no\\\", \\\"__current_case__\\\": 0}\", \"depth_as\": \"\\\"ref\\\"\", \"min_base_qual\": \"\\\"20\\\"\", \"min_var_pct\": \"\\\"0.5\\\"\"}", + "tool_version": "2.2", + "type": "tool", + "user_outputs": [], + "uuid": "335581bc-838e-431d-8247-1e1580260275" + } + }, + "uuid": "0c40a63d-b349-49b8-90b0-c927a05253ef" +} \ No newline at end of file |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/SVDetect.ga --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/SVDetect.ga Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,163 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "SVDetect workflow.", + "format-version": "0.1", + "name": "SVDetect", + "steps": { + "0": { + "annotation": "", + "id": 0, + "input_connections": {}, + "inputs": [], + "label": null, + "name": "Import data", + "outputs": [ + { + "name": "outbamfile", + "type": "bam" + }, + { + "name": "outlenfile", + "type": "len" + }, + { + "name": "outsvfile", + "type": "sv" + } + ], + "position": { + "left": 171.99998474121094, + "top": 168 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bzeitouni/svdetect/svdetect_import/1.0.0", + "tool_state": "{\"file_name\": \"\\\"file1\\\"\", \"__rerun_remap_job_id__\": null, \"type\": \"{\\\"file_type\\\": \\\"bam\\\", \\\"__current_case__\\\": 0}\", \"file_path\": \"\\\"\\\"\", \"__page__\": 0}", + "tool_version": "1.0.0", + "type": "tool", + "user_outputs": [], + "uuid": "296478bf-9b67-47e8-9685-ced05bad2857" + }, + "1": { + "annotation": "", + "id": 1, + "input_connections": {}, + "inputs": [], + "label": null, + "name": "Import data", + "outputs": [ + { + "name": "outbamfile", + "type": "bam" + }, + { + "name": "outlenfile", + "type": "len" + }, + { + "name": "outsvfile", + "type": "sv" + } + ], + "position": { + "left": 266.99998474121094, + "top": 430.99998474121094 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bzeitouni/svdetect/svdetect_import/1.0.0", + "tool_state": "{\"file_name\": \"\\\"file1\\\"\", \"__rerun_remap_job_id__\": null, \"type\": \"{\\\"file_type\\\": \\\"len\\\", \\\"__current_case__\\\": 1}\", \"file_path\": \"\\\"\\\"\", \"__page__\": 0}", + "tool_version": "1.0.0", + "type": "tool", + "user_outputs": [], + "uuid": "481cf408-cef1-4ccd-bd08-9394bac04050" + }, + "2": { + "annotation": "", + "id": 2, + "input_connections": { + "inputBam": { + "id": 0, + "output_name": "outbamfile" + } + }, + "inputs": [], + "label": null, + "name": "BAM preprocessing", + "outputs": [ + { + "name": "abBAM", + "type": "bam" + }, + { + "name": "log", + "type": "txt" + }, + { + "name": "normBAM", + "type": "bam" + } + ], + "position": { + "left": 344.49998474121094, + "top": 224 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bzeitouni/svdetect/svdetect_preprocessing/1.0.0", + "tool_state": "{\"__page__\": 0, \"isizeMin\": \"\\\"0\\\"\", \"newBam\": \"{\\\"__current_case__\\\": 1, \\\"pairNormal\\\": \\\"no\\\"}\", \"isizeMax\": \"\\\"10000\\\"\", \"inputBam\": \"null\", \"__rerun_remap_job_id__\": null, \"nbrePair\": \"\\\"1000000\\\"\", \"readType\": \"\\\"1\\\"\", \"sample_name\": \"\\\"sample\\\"\", \"pairType\": \"\\\"1\\\"\", \"foldPair\": \"\\\"3.0\\\"\"}", + "tool_version": "1.0.0", + "type": "tool", + "user_outputs": [], + "uuid": "01f2c8d8-123b-4eac-9c5e-6101e9264dbf" + }, + "3": { + "annotation": "", + "id": 3, + "input_connections": { + "cmap_file": { + "id": 1, + "output_name": "outlenfile" + }, + "mates_file": { + "id": 2, + "output_name": "abBAM" + } + }, + "inputs": [], + "label": null, + "name": "Detect clusters of anomalously mapped pairs", + "outputs": [ + { + "name": "sv_file", + "type": "sv" + }, + { + "name": "circos_file", + "type": "segdup" + }, + { + "name": "bed_file", + "type": "bed" + }, + { + "name": "log_file", + "type": "txt" + } + ], + "position": { + "left": 472.49998474121094, + "top": 375.99998474121094 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bzeitouni/svdetect/svdetect_run_parallel/1.0.0", + "tool_state": "{\"__page__\": 0, \"sv_type\": \"\\\"all\\\"\", \"getLinks\": \"{\\\"window_size\\\": \\\"3000\\\", \\\"step_length\\\": \\\"250\\\", \\\"splitmate\\\": \\\"True\\\", \\\"__current_case__\\\": 1, \\\"linking\\\": \\\"linking\\\"}\", \"mates_file\": \"null\", \"__rerun_remap_job_id__\": null, \"getFilteredLinks\": \"{\\\"nb_pairs_threshold\\\": \\\"5\\\", \\\"filtering\\\": \\\"filtering\\\", \\\"chromosomes\\\": \\\"\\\", \\\"file_conversion\\\": {\\\"file_conversion_select\\\": \\\"do_not_convert\\\", \\\"__current_case__\\\": 0}, \\\"splitlink\\\": \\\"False\\\", \\\"filter1\\\": {\\\"strand_filtering\\\": \\\"strand\\\", \\\"final_score_threshold\\\": \\\"1.0\\\", \\\"__current_case__\\\": 1, \\\"filter2\\\": {\\\"nb_pairs_order_threshold\\\": \\\"2\\\", \\\"order_filtering\\\": \\\"order\\\", \\\"__current_case__\\\": 1, \\\"filter3\\\": {\\\"indel_sigma_threshold\\\": \\\"3.0\\\", \\\"dup_sigma_threshold\\\": \\\"3.0\\\", \\\"singleton_sigma_threshold\\\": \\\"4.0\\\", \\\"__current_case__\\\": 1, \\\"insert_size_filtering\\\": \\\"insert\\\"}, \\\"mu_length\\\": \\\"3000\\\", \\\"sigma_length\\\": \\\"250\\\"}}, \\\"__current_case__\\\": 1, \\\"links2SV\\\": \\\"True\\\"}\", \"read2_length\": \"\\\"50\\\"\", \"read1_length\": \"\\\"50\\\"\", \"sample_name\": \"\\\"sample\\\"\", \"mates_orientation\": \"\\\"FR\\\"\", \"cmap_file\": \"null\"}", + "tool_version": "1.0.0", + "type": "tool", + "user_outputs": [], + "uuid": "2edd1fca-fc2d-453e-aead-c95a2e250d0a" + } + }, + "uuid": "bb58fd42-403a-48ad-80d2-59d81f0c8f0b" +} \ No newline at end of file |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/VARSCAN.ga --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/VARSCAN.ga Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,133 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "VARSCAN workflow.", + "format-version": "0.1", + "name": "VARSCAN", + "steps": { + "0": { + "annotation": "", + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "Input Dataset" + } + ], + "label": null, + "name": "Input dataset", + "outputs": [], + "position": { + "left": 161, + "top": 187 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"Input Dataset\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [], + "uuid": "72a1326a-cd57-4567-8c41-cc66411642be" + }, + "1": { + "annotation": "", + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "Input Dataset" + } + ], + "label": null, + "name": "Input dataset", + "outputs": [], + "position": { + "left": 163.83331298828125, + "top": 263.8333282470703 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"Input Dataset\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [], + "uuid": "d8444634-af6c-44c5-9b55-8c3284da2823" + }, + "2": { + "annotation": "", + "id": 2, + "input_connections": { + "reference_source|input_bams_0|input_bam": { + "id": 0, + "output_name": "output" + }, + "reference_source|ref_file": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "MPileup", + "outputs": [ + { + "name": "output_mpileup", + "type": "pileup" + }, + { + "name": "output_log", + "type": "txt" + } + ], + "position": { + "left": 370, + "top": 187 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/samtools_mpileup/samtools_mpileup/2.0", + "tool_state": "{\"__page__\": 0, \"advanced_options\": \"{\\\"advanced_options_selector\\\": \\\"basic\\\", \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"genotype_likelihood_computation_type\": \"{\\\"output_mapping_quality\\\": \\\"False\\\", \\\"genotype_likelihood_computation_type_selector\\\": \\\"do_not_perform_genotype_likelihood_computation\\\", \\\"__current_case__\\\": 1, \\\"base_position_on_reads\\\": \\\"False\\\"}\", \"reference_source\": \"{\\\"ref_file\\\": null, \\\"reference_source_selector\\\": \\\"history\\\", \\\"input_bams\\\": [{\\\"__index__\\\": 0, \\\"input_bam\\\": null}], \\\"__current_case__\\\": 1}\"}", + "tool_version": "2.0", + "type": "tool", + "user_outputs": [], + "uuid": "26d34295-7783-40e1-950f-a485ff569f5b" + }, + "3": { + "annotation": "", + "id": 3, + "input_connections": { + "in_file": { + "id": 2, + "output_name": "output_mpileup" + } + }, + "inputs": [], + "label": null, + "name": "VarScan mpileup", + "outputs": [ + { + "name": "output", + "type": "vcf" + }, + { + "name": "log", + "type": "txt" + } + ], + "position": { + "left": 563.8333129882812, + "top": 364.83331298828125 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/fcaramia/varscan/varscan_mpileup/2.3.5", + "tool_state": "{\"strand_filter\": \"\\\"1\\\"\", \"min_avg_qual\": \"\\\"15\\\"\", \"min_coverage\": \"\\\"8\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"min_freq_for_hom\": \"\\\"0.75\\\"\", \"min_var_freq\": \"\\\"0.01\\\"\", \"exe_command\": \"\\\"mpileup2snp\\\"\", \"min_reads2\": \"\\\"2\\\"\", \"p_value\": \"\\\"0.99\\\"\", \"variants\": \"\\\"1\\\"\", \"vcf_sample_list\": \"null\", \"in_file\": \"null\"}", + "tool_version": "2.3.5", + "type": "tool", + "user_outputs": [], + "uuid": "5ff6cf71-5d74-42ad-bcdc-7c75891dc10e" + } + }, + "uuid": "5b7bf29e-1272-4211-b345-37695989c6fa" +} \ No newline at end of file |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/analyze_covariates.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/analyze_covariates.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,37 @@ +<macros> + <xml name="AnalyzeCovariatesParameters" tokens="tag"> + + <!-- BQSR in main config --> + + <param name="afterReportFile" type="data" format="tabular" optional="true" label="file containing the BQSR second-pass report file" help="-after,‑‑afterReportFile &lt;afterReportFile&gt;" /> + + <param name="beforeReportFile" type="data" format="tabular" optional="true" label="file containing the BQSR first-pass report file" help="-before,‑‑beforeReportFile &lt;beforeReportFile&gt;" /> + + </xml> + + <xml name="AnalyzeCovariatesOutput"> + <data format="pdf" name="ac_plotsReportFile" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (PDF Recalibration Report)"> + <yield /> + </data> + </xml> + + <template name="AnalyzeCovariatesPreprocessing"> +<![CDATA[ +]]> + </template> + + <template name="AnalyzeCovariatesOptions"> +<![CDATA[ + --plotsReportFile ${ac_plotsReportFile} + + #if str($analysis_type.afterReportFile) + --afterReportFile $analysis_type.afterReportFile + #end if + #if str($analysis_type.beforeReportFile) + --beforeReportFile $analysis_type.beforeReportFile + #end if +]]> + </template> +</macros> + + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/base_recalibrator.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/base_recalibrator.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,38 @@ +<macros> + <xml name="BaseRecalibratorParameters" tokens="tag"> + + <expand macro="macro_bam_input" tag="@TAG@" /> + + <param name="knownSites" type="data" format="vcf,bcf,bed,pileup,tabular,table" label="Database of known Sites (ROD files; e.g. VCF format)" multiple="true" title="A database of known polymorphic sites to skip over in the recalibration algorithm" help="-knownSites,‑‑knownSites &lt;knownSites&gt;" /> + + </xml> + + <xml name="BaseRecalibratorOutput"> + <data format="tabular" name="br_table" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (Table)"> + <yield /> + </data> + </xml> + + <template name="BaseRecalibratorPreprocessing"> +<![CDATA[ + @token_bam_input_pre@ + #for $i, $variant in enumerate($analysis_type.knownSites): + ln -s -f ${variant} variant_${i}.vcf && + #end for +]]> + </template> + + <template name="BaseRecalibratorOptions"> +<![CDATA[ + --out ${br_table} + + @token_bam_input@ + + #for $i, $variant in enumerate($analysis_type.knownSites): + --knownSites variant_${i}.vcf + #end for +]]> + </template> +</macros> + + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/combine_gvcfs.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/combine_gvcfs.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,44 @@ +<macros> + <xml name="CombineGVCFsParameters" tokens="tag"> + + <expand macro="macro_gvcf_input" tag="@TAG@" /> + + <expand macro="macro_optional_parameters"> + + <param name="breakBandsAtMultiplesOf" type="integer" value="0" label="If > 0, reference bands will be broken up at genomic positions that are multiples of this number" help="-breakBandsAtMultiplesOf,‑‑breakBandsAtMultiplesOf &lt;breakBandsAtMultiplesOf&gt;" /> + + </expand> + + </xml> + + <xml name="CombineGVCFsOutput"> + <data format="vcf" name="cg_output_vcf" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (VCF)"> + <yield /> + </data> + </xml> + + <template name="CombineGVCFsPreprocessing"> +<![CDATA[ + @token_gvcf_input_pre@ +]]> + </template> + + <template name="CombineGVCFsOptions"> +<![CDATA[ + --out ${cg_output_vcf} + + @token_gvcf_input@ + + #set $optionals = $analysis_type.optional_parameters + #if $optionals.optional_parameters_enabled + #if $optionals.breakBandsAtMultiplesOf > 0 + --breakBandsAtMultiplesOf $optionals.breakBandsAtMultiplesOf + #end if + #end if +]]> + </template> + + +</macros> + + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/combine_variants.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/combine_variants.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,96 @@ +<macros> + <xml name="CombineVariantsParameters" tokens="tag"> + + <expand macro="macro_vcf_input" tag="@TAG@" /> + + <expand macro="macro_optional_parameters"> + + <param name="filteredRecordsMergeType" type="select" label="Determines how we should handle records seen at the same site in the VCF, but with different FILTER fields" help="-filteredRecordsMergeType,‑‑filteredrecordsmergetype &lt;filteredrecordsmergetype&gt;"> + <option value="">No Selection</option> + <option value="KEEP_IF_ANY_UNFILTERED">KEEP_IF_ANY_UNFILTERED</option> + <option value="KEEP_IF_ALL_UNFILTERED">KEEP_IF_ALL_UNFILTERED</option> + <option value="KEEP_UNCONDITIONAL">KEEP_UNCONDITIONAL</option> + </param> + + <param name="genotypeMergeOptions" type="select" label="Determines how we should merge genotype records for samples shared across the ROD files" help="-genotypeMergeOptions,‑‑genotypemergeoption &lt;genotypemergeoption&gt;"> + <option value="">No Selection</option> + <option value="UNIQUIFY">UNIQUIFY</option> + <option value="PRIORITIZE">PRIORITIZE</option> + <option value="UNSORTED">UNSORTED</option> + <option value="REQUIRE_UNIQUE">REQUIRE_UNIQUE</option> + </param> + + <param name="minimumN" type="integer" value="1" optional="true" label="Combine variants and output site only if the variant is present in at least N input files" help="-minN,‑‑minimumN &lt;minimumN&gt;" /> + + <param name="rod_priority_list" type="text" value="" optional="true" label="A comma-separated string describing the priority ordering for the genotypes as far as which record gets emitted" help="-priority,‑‑rod_priority_list &lt;rod_priority_list&gt;" /> + + <param name="setKey" type="text" value="" optional="true" label="Key used in the INFO key=value tag emitted describing which set the combined VCF record came from" help="-setKey,‑‑setKey &lt;setKey&gt;" /> + + <param name="assumeIdenticalSamples" type="boolean" truevalue="--assumeIdenticalSamples" falsevalue="" label="If true, assume input VCFs have identical sample sets and disjoint calls" help="-assumeIdenticalSamples,‑‑assumeIdenticalSamples" /> + + <param name="excludeNonVariants" type="boolean" truevalue="--excludeNonVariants" falsevalue="" label="Don't include loci found to be non-variant after the combining procedure" help="-env,‑‑excludeNonVariants" /> + + <param name="filteredAreUncalled" type="boolean" truevalue="--filteredAreUncalled" falsevalue="" label="If true, then filtered VCFs are treated as uncalled, so that filtered set annotations don't appear in the combined VCF" help="-filteredAreUncalled,‑‑filteredAreUncalled" /> + + <param name="mergeInfoWithMaxAC" type="boolean" truevalue="--mergeInfoWithMaxAC" falsevalue="" label="If true, when VCF records overlap the info field is taken from the one with the max AC instead of only taking the fields which are identical across the overlapping records." help="-mergeInfoWithMaxAC,‑‑mergeInfoWithMaxAC" /> + + <param name="minimalVCF" type="boolean" truevalue="--minimalVCF" falsevalue="" label="If true, then the output VCF will contain no INFO or genotype FORMAT fields" help="-minimalVCF,‑‑minimalVCF" /> + + <param name="printComplexMerges" type="boolean" truevalue="--printComplexMerges" falsevalue="" label="Print out interesting sites requiring complex compatibility merging" help="-printComplexMerges,‑‑printComplexMerges" /> + + <param name="suppressCommandLineHeader" type="boolean" truevalue="--suppressCommandLineHeader" falsevalue="" label="If true, do not output the header containing the command line used" help="-suppressCommandLineHeader,‑‑suppressCommandLineHeader" /> + + </expand> + + </xml> + + <xml name="CombineVariantsOutput"> + <data format="vcf" name="cv_output_vcf" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (VCF)"> + <yield /> + </data> + </xml> + + <template name="CombineVariantsPreprocessing"> +<![CDATA[ + @token_vcf_input_pre@ +]]> + </template> + + <template name="CombineVariantsOptions"> +<![CDATA[ + --out ${cv_output_vcf} + + @token_vcf_input@ + + #set $optionals = $analysis_type.optional_parameters + #if $optionals.optional_parameters_enabled + + #if $optionals.filteredRecordsMergeType + --filteredRecordsMergeType $optionals.filteredRecordsMergeType + #end if + #if $optionals.genotypeMergeOptions + --genotypeMergeOptions $optionals.genotypeMergeOptions + #end if + #if $optionals.minimumN != 1 + --minimumN $optionals.minimumN + #end if + #if $optionals.rod_priority_list + --rod_priority_list $optionals.rod_priority_list + #end if + + $optionals.assumeIdenticalSamples + $optionals.excludeNonVariants + $optionals.filteredAreUncalled + $optionals.mergeInfoWithMaxAC + $optionals.minimalVCF + $optionals.printComplexMerges + $optionals.suppressCommandLineHeader + + #end if +]]> + </template> + + +</macros> + + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/gatk.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/gatk.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| b'@@ -0,0 +1,179 @@\n+<?xml version="1.0" encoding="utf-8"?>\n+<tool id="gatk" name="GATK" version="@VERSION@.d9">\n+ <description>tool collection Version @VERSION@</description>\n+ <macros>\n+ <import>gatk_macros.xml</import>\n+ <import>realigner_target_creator.xml</import>\n+ <import>indel_realigner.xml</import>\n+ <import>base_recalibrator.xml</import>\n+ <import>analyze_covariates.xml</import>\n+ <import>print_reads.xml</import>\n+ <import>haplotype_caller.xml</import>\n+ <import>genotype_gvcfs.xml</import>\n+ <import>combine_gvcfs.xml</import>\n+ <import>combine_variants.xml</import>\n+ </macros>\n+ <expand macro="requirements"/>\n+ <stdio>\n+ <regex match="^INFO" level="log"/>\n+ <regex match="^WARN" level="warning"/>\n+ <regex match="Using .* implementation of PairHMM" level="warning"/>\n+ <regex match="There is insufficient memory for the Java Runtime Environment to continue" level="fatal"/>\n+ <regex match="^##### ERROR" level="fatal"/>\n+ <exit_code range="1:" level="fatal"/>\n+ </stdio>\n+ <command><![CDATA[\n+ ############################\n+ ## import analysis specific preprocessings by using cheetahs internal searchList\n+ ## if not defined, ignore\n+ ############################\n+ #if $analysis_type.analysis_type_selector + "Preprocessing" in vars()[\'SL\'][2]\n+ #set $analysisPreprocessing = vars()[\'SL\'][2][$analysis_type.analysis_type_selector + "Preprocessing"]\n+ #include source=$analysisPreprocessing\n+ #end if\n+ \n+ ############################\n+ ## GATK tool unspecific options\n+ ############################\n+ @GATK_EXEC@\n+ \n+ --analysis_type ${analysis_type.analysis_type_selector}\n+ --reference_sequence ${ref_file.fields.path}\n+\n+ --log_to_file ${output_log}\n+\n+ #if $cond_intervals.cond_intervals_enabled\n+ #for $interval in $cond_intervals.intervals:\n+ --intervals ${interval.L}\n+ #end for\n+ #end if\n+\n+ #if $cond_BQSR.cond_BQSR_enabled\n+ --BQSR $cond_BQSR.BQSR\n+ #end if\n+\n+ ############################\n+ ## import analysis specific options by using cheetahs internal searchList\n+ ## if not defined throw raw python error until better idea\n+ ############################\n+ #if $analysis_type.analysis_type_selector + "Options" in vars()[\'SL\'][2]\n+ #set $analysisOptions = vars()[\'SL\'][2][$analysis_type.analysis_type_selector + "Options"]\n+ #include source=$analysisOptions\n+ #else\n+ #set $analysisOptions = vars()[\'SL\'][2][$analysis_type.analysis_type_selector + "Options"]\n+ #end if\n+ \n+ ############################\n+ ## only put ERROR or FATAL log messages into stderr\n+ ## but keep full log for printing into log file\n+ ############################\n+ 2>&1 | awk \'\\$1 != "INFO" && \\$1 != "WARN"\' >&2\n+]]></command>\n+ <inputs>\n+ <param name="ref_file" type="select" label="Using reference genome" help="-R,\xe2\x80\x91\xe2\x80\x91reference_sequence &lt;reference_sequence&gt;">\n+ <options from_data_table="picard_indexes"/>\n+ <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>\n+ </param>\n+ <conditional name="cond_intervals">\n+ <param name="cond_intervals_enabled" type="boolean" label="Select interval subset to operate on?"/>\n+ <when value="true">\n+ <repeat name="intervals" title="genomic interval over which to operate" help="-L,\xe2\x80\x91\xe2\x80\x91intervals &lt;intervals&gt;">\n+ <param name="L" type="text" value=""/>\n+ </repeat>\n+ </when>\n+ <when value="false"/>\n+ </conditional>\n+ <conditional name="cond_BQSR">\n+ <param name="cond_BQSR_enabled" type="boolean" label="Select covariates for on-the-fly recalibration?"/>\n+ <when '..b'"nct" type="integer" value="1" label="Number of CPU threads to allocate per data thread" help="make sure, the option is available for the chosen tool"/>\n+ <param name="mem" type="integer" value="0" label="Overwrite Memory in MB (0 = don\'t overwrite)" help="Overwrites all other defaults and might lead to crash the run. States mem per data thread"/>\n+ </when>\n+ <when value="false"/>\n+ </conditional>\n+ <conditional name="analysis_type">\n+ <param name="analysis_type_selector" type="select" label="Analysis Type">\n+ <option value="RealignerTargetCreator">RealignerTargetCreator</option>\n+ <option value="IndelRealigner">IndelRealigner</option>\n+ <option value="BaseRecalibrator">BaseRecalibrator</option>\n+ <option value="AnalyzeCovariates">AnalyzeCovariates</option>\n+ <option value="PrintReads">PrintReads</option>\n+ <option value="HaplotypeCaller">HaplotypeCaller</option>\n+ <option value="GenotypeGVCFs">GenotypeGVCFs</option>\n+ <option value="CombineGVCFs">CombineGVCFs</option>\n+ <option value="CombineVariants">CombineVariants</option>\n+ </param>\n+ <when value="RealignerTargetCreator">\n+ <expand macro="RealignerTargetCreatorParameters" tag="rtc"/>\n+ </when>\n+ <when value="IndelRealigner">\n+ <expand macro="IndelRealignerParameters" tag="ir"/>\n+ </when>\n+ <when value="BaseRecalibrator">\n+ <expand macro="BaseRecalibratorParameters" tag="br"/>\n+ </when>\n+ <when value="AnalyzeCovariates">\n+ <expand macro="AnalyzeCovariatesParameters" tag="ac"/>\n+ </when>\n+ <when value="PrintReads">\n+ <expand macro="PrintReadsParameters" tag="pr"/>\n+ </when>\n+ <when value="HaplotypeCaller">\n+ <expand macro="HaplotypeCallerParameters" tag="hc"/>\n+ </when>\n+ <when value="GenotypeGVCFs">\n+ <expand macro="GenotypeGVCFsParameters" tag="gg"/>\n+ </when>\n+ <when value="CombineGVCFs">\n+ <expand macro="CombineGVCFsParameters" tag="cg"/>\n+ </when>\n+ <when value="CombineVariants">\n+ <expand macro="CombineVariantsParameters" tag="cv"/>\n+ </when>\n+ </conditional>\n+ </inputs>\n+ <outputs>\n+ <expand macro="RealignerTargetCreatorOutput" tag="rtc">\n+ <filter>analysis_type[\'analysis_type_selector\'] == \'RealignerTargetCreator\'</filter>\n+ </expand>\n+ <expand macro="IndelRealignerOutput" tag="ir">\n+ <filter>analysis_type[\'analysis_type_selector\'] == \'IndelRealigner\'</filter>\n+ </expand>\n+ <expand macro="BaseRecalibratorOutput" tag="br">\n+ <filter>analysis_type[\'analysis_type_selector\'] == \'BaseRecalibrator\'</filter>\n+ </expand>\n+ <expand macro="AnalyzeCovariatesOutput" tag="ac">\n+ <filter>analysis_type[\'analysis_type_selector\'] == \'AnalyzeCovariates\'</filter>\n+ </expand>\n+ <expand macro="PrintReadsOutput" tag="pr">\n+ <filter>analysis_type[\'analysis_type_selector\'] == \'PrintReads\'</filter>\n+ </expand>\n+ <expand macro="HaplotypeCallerOutput" tag="hc">\n+ <filter>analysis_type[\'analysis_type_selector\'] == \'HaplotypeCaller\'</filter>\n+ </expand>\n+ <expand macro="GenotypeGVCFsOutput" tag="gg">\n+ <filter>analysis_type[\'analysis_type_selector\'] == \'GenotypeGVCFs\'</filter>\n+ </expand>\n+ <expand macro="CombineGVCFsOutput" tag="cg">\n+ <filter>analysis_type[\'analysis_type_selector\'] == \'CombineGVCFs\'</filter>\n+ </expand>\n+ <expand macro="CombineVariantsOutput" tag="cv">\n+ <filter>analysis_type[\'analysis_type_selector\'] == \'CombineVariants\'</filter>\n+ </expand>\n+ <data format="txt" name="output_log" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (log)"/>\n+ </outputs>\n+ <expand macro="macro_tests"/>\n+ <citations>\n+ <citation type="doi">10.1101/gr.107524.110</citation>\n+ <citation type="doi">10.1038/ng.806</citation>\n+ <citation type="doi">10.1002/0471250953.bi1110s43</citation>\n+ </citations>\n+</tool>\n' |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/gatk_macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/gatk_macros.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,166 @@ +<macros> + + <xml name="requirements"> + <requirements> + <requirement type="package">gatk</requirement> + <requirement type="set_environment">GATK_PATH</requirement> + <requirement type="set_environment">GATK_SITE_OPTIONS</requirement> + <requirement type="package" version="3.1.2.1">package_r_for_gatk_3_4_0</requirement> + </requirements> + </xml> + + <xml name="version_command"> + <version_command><![CDATA[ @GATK_EXEC@ --help|grep '^The Genome' ]]></version_command> + </xml> + + <token name="@VERSION@">3.4-0</token> + <token name="@OUTPUT_NAME_PREFIX@">${tool.name} - ${analysis_type.analysis_type_selector}</token> + <token name="@GATK_EXEC@"> +<![CDATA[ + #if $cond_threads.cond_threads_enabled: + #if int($cond_threads.nct) > 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:-} +]]> + </token> + + <xml name="macro_vcf_input" tokens="tag"> + <param name="input" type="data" format="vcf" multiple="true" label="Variant files (VCF format)" help="-V, ‑‑variant"> + <validator type="unspecified_build" /> + <validator type="dataset_metadata_in_data_table" table_name="picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build." /> + </param> + </xml> + <token name="@token_vcf_input_pre@" tokens="tag"> +<![CDATA[ + ############################ + ## create links to gVCF input files with correct extensions + ############################ + #for $i, $variant in enumerate($analysis_type.input): + ln -s -f ${variant} variant_${i}.vcf && + #end for +]]> + </token> + <token name="@token_vcf_input@"> +<![CDATA[ + #for $i, $variant in enumerate($analysis_type.input): + --variant variant_${i}.vcf + #end for + @token_reference_input@ +]]> + </token> + + + <xml name="macro_gvcf_input" tokens="tag"> + <param name="input" type="data" format="vcf" multiple="true" label="Variant files (gVCF format)" help="-V, ‑‑variant"> + <validator type="unspecified_build" /> + <validator type="dataset_metadata_in_data_table" table_name="picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build." /> + </param> + </xml> + <token name="@token_gvcf_input_pre@" tokens="tag"> +<![CDATA[ + ############################ + ## create links to gVCF input files with correct extensions + ############################ + #for $i, $variant in enumerate($analysis_type.input): + ln -s -f ${variant} variant_${i}.g.vcf && + #end for +]]> + </token> + <token name="@token_gvcf_input@"> +<![CDATA[ + #for $i, $variant in enumerate($analysis_type.input): + --variant variant_${i}.g.vcf + #end for + @token_reference_input@ +]]> + </token> + + <xml name="macro_bam_input"> + <conditional name="cond_bam_input"> + <param name="all_in_one" type="boolean" value="false" label="Input all BAM files in a single command" /> + <when value="true"> + <param name="input" type="data" format="bam" multiple="true" label="Input file containing sequence data (BAM)" help="-I, ‑‑input_file"> + <validator type="unspecified_build"/> + <validator type="dataset_metadata_in_data_table" table_name="picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build."/> + </param> + </when> + <when value="false"> + <param name="input" type="data" format="bam" label="Input file containing sequence data (BAM)" help="-I, ‑‑input_file"> + <validator type="unspecified_build"/> + <validator type="dataset_metadata_in_data_table" table_name="picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build."/> + </param> + </when> + </conditional> + </xml> + <token name="@token_bam_input_pre@"> +<![CDATA[ + ############################ + ## create links to bam input files with correct extensions + ############################ + #if $analysis_type.cond_bam_input.all_in_one + #for $i, $bam in enumerate($analysis_type.cond_bam_input.input): + ln -s -f ${bam} input_${i}.bam && + ln -s -f ${bam.metadata.bam_index} input_${i}.bam.bai && + #end for + #else + ln -s -f ${analysis_type.cond_bam_input.input} input.bam && + ln -s -f ${analysis_type.cond_bam_input.input.metadata.bam_index} input.bam.bai && + #end if +]]> + </token> + <token name="@token_bam_input@"> +<![CDATA[ + #if $analysis_type.cond_bam_input.all_in_one + #for $i, $bam in enumerate($analysis_type.cond_bam_input.input): + --input_file input_${i}.bam + #end for + #else + --input_file input.bam + #end if + @token_reference_input@ +]]> + </token> + + <token name="@token_reference_input@"> +<![CDATA[ +]]> + </token> + <xml name="macro_input" tokens="tag"> + <yield /> + </xml> + + <xml name="macro_optional_parameters"> + <conditional name="optional_parameters"> + <param name="optional_parameters_enabled" type="boolean" label="Configure Optional Parameters" /> + <when value="true"> + <yield /> + </when> + <when value="false" /> + </conditional> + </xml> + + <xml name="macro_advanced_parameters"> + <conditional name="advanced_parameters"> + <param name="advanced_parameters_enabled" type="boolean" label="Configure Advanced Parameters" /> + <when value="true"> + <yield /> + </when> + <when value="false" /> + </conditional> + </xml> + + <xml name="macro_tests"> + <tests> + + </tests> + </xml> + +</macros> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/generation/gatk.xsl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/generation/gatk.xsl Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,162 @@ +<?xml version="1.0" encoding="UTF-8"?> +<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"> +<xsl:output + method="xml" + encoding="utf-8" + indent="yes" + cdata-section-elements="script style" /> + +<xsl:template match="/"> + +<tool id="gatk" name="GATK" version="@VERSION@.d9"> + <description>tool collection Version @VERSION@</description> + + <macros> + <import>gatk_macros.xml</import> + <xsl:for-each select="analyses/analysis"> + <import><xsl:value-of select="macro_file" /></import> + </xsl:for-each> + </macros> + + <expand macro="requirements" /> + + <stdio> + <regex match="^INFO" level="log" /> + <regex match="^WARN" level="warning" /> + <regex match="Using .* implementation of PairHMM" level="warning" /> + <regex match="There is insufficient memory for the Java Runtime Environment to continue" level="fatal" /> + <regex match="^##### ERROR" level="fatal" /> + <exit_code range="1:" level="fatal"/> + </stdio> + + <command> +<xsl:text disable-output-escaping="yes"><![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 +]]></xsl:text> + </command> + + <inputs> + + <param name="ref_file" type="select" label="Using reference genome" help="-R,‑‑reference_sequence &lt;reference_sequence&gt;" > + <options from_data_table="picard_indexes"> + <!--filter type="data_meta" key="dbkey" ref="@TAG@_input" column="dbkey" /--> + </options> + <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> + </param> + + <conditional name="cond_intervals"> + <param name="cond_intervals_enabled" type="boolean" label="Select interval subset to operate on?" /> + <when value="true"> + <repeat name="intervals" title="genomic interval over which to operate" help="-L,‑‑intervals &lt;intervals&gt;"> + <param name="L" type="text" value="" /> + </repeat> + </when> + <when value="false" /> + </conditional> + + <conditional name="cond_BQSR"> + <param name="cond_BQSR_enabled" type="boolean" label="Select covariates for on-the-fly recalibration?" /> + <when value="true"> + <param name="BQSR" type="data" format="tabular" label="Input covariates table file for on-the-fly base quality score recalibration" help="-BQSR,‑‑BQSR &lt;BQSR&gt; intended primarily for use with BaseRecalibrator and PrintReads" /> + </when> + <when value="false" /> + </conditional> + + <conditional name="cond_threads"> + <param name="cond_threads_enabled" type="boolean" label="Set computational options (cpu, mem)?" /> + <when value="true"> + <param name="nt" type="integer" value="1" label="Number of data threads to allocate to this analysis" help="make sure, the option is available for the chosen tool" /> + <param name="nct" type="integer" value="1" label="Number of CPU threads to allocate per data thread" help="make sure, the option is available for the chosen tool" /> + <param name="mem" type="integer" value="0" label="Overwrite Memory in MB (0 = don't overwrite)" help="Overwrites all other defaults and might lead to crash the run. States mem per data thread" /> + </when> + <when value="false" /> + </conditional> + + <conditional name="analysis_type"> + <param name="analysis_type_selector" type="select" label="Analysis Type"> + <xsl:for-each select="analyses/analysis"> + <option value="{name}"><xsl:value-of select="name" /></option> + </xsl:for-each> + </param> + <xsl:for-each select="analyses/analysis"> + <when value="{name}"> + <!--xsl:choose> + <xsl:when test="input_type = 'bam'"> + <expand macro="macro_bam_input" tag="{tag}" /> + </xsl:when> + <xsl:when test="input_type = 'gvcf'"> + <expand macro="macro_gvcf_input" tag="{tag}" /> + </xsl:when> + </xsl:choose--> + <expand macro="{name}Parameters" tag="{tag}" /> + </when> + </xsl:for-each> + </conditional> + </inputs> + + <outputs> + <xsl:for-each select="analyses/analysis"> + <expand macro="{name}Output" tag="{tag}"> + <filter>analysis_type['analysis_type_selector'] == '<xsl:value-of select="name" />'</filter> + </expand> + </xsl:for-each> + <data format="txt" name="output_log" label="${{tool.name}} - ${{analysis_type.analysis_type_selector}} on ${{on_string}} (log)" /> + </outputs> + + <expand macro="macro_tests" /> + + <citations> + <citation type="doi">10.1101/gr.107524.110</citation> + <citation type="doi">10.1038/ng.806</citation> + <citation type="doi">10.1002/0471250953.bi1110s43</citation> + </citations> +</tool> + +</xsl:template> +</xsl:stylesheet> + + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/generation/gatk.xsldb.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/generation/gatk.xsldb.xml Thu Oct 03 10:42:15 2019 -0400 |
| b |
| @@ -0,0 +1,57 @@ +<?xml version="1.0" encoding="UTF-8"?> +<analyses> + <analysis> + <name>RealignerTargetCreator</name> + <input_type>bam</input_type> + <tag>rtc</tag> + <macro_file>realigner_target_creator.xml</macro_file> + </analysis> + <analysis> + <name>IndelRealigner</name> + <input_type>bam</input_type> + <tag>ir</tag> + <macro_file>indel_realigner.xml</macro_file> + </analysis> + <analysis> + <name>BaseRecalibrator</name> + <input_type>bam</input_type> + <tag>br</tag> + <macro_file>base_recalibrator.xml</macro_file> + </analysis> + <analysis> + <name>AnalyzeCovariates</name> + <input_type>bam</input_type> + <tag>ac</tag> + <macro_file>analyze_covariates.xml</macro_file> + </analysis> + <analysis> + <name>PrintReads</name> + <input_type>bam</input_type> + <tag>pr</tag> + <macro_file>print_reads.xml</macro_file> + </analysis> + <analysis> + <name>HaplotypeCaller</name> + <input_type>bam</input_type> + <tag>hc</tag> + <macro_file>haplotype_caller.xml</macro_file> + </analysis> + <analysis> + <name>GenotypeGVCFs</name> + <input_type>gvcf</input_type> + <tag>gg</tag> + <macro_file>genotype_gvcfs.xml</macro_file> + </analysis> + <analysis> + <name>CombineGVCFs</name> + <input_type>gvcf</input_type> + <tag>cg</tag> + <macro_file>combine_gvcfs.xml</macro_file> + </analysis> + <analysis> + <name>CombineVariants</name> + <input_type>vcf</input_type> + <tag>cv</tag> + <macro_file>combine_variants.xml</macro_file> + </analysis> +</analyses> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/genotype_gvcfs.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/genotype_gvcfs.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,43 @@ +<macros> + <xml name="GenotypeGVCFsParameters" tokens="tag"> + + <expand macro="macro_gvcf_input" tag="@TAG@" /> + + <expand macro="macro_optional_parameters"> + + + <param name="sample_ploidy" type="integer" value="2" label="Ploidy (number of chromosomes) per sample. For pooled data, set to (Number of samples in each pool * Sample Ploidy)" help="-ploidy,‑‑sample_ploidy &lt;sample_ploidy&gt;" /> + + </expand> + + </xml> + + <xml name="GenotypeGVCFsOutput"> + <data format="vcf" name="gg_output_gvcf" from_work_dir="output.g.vcf" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (gVCF)"> + <yield /> + </data> + </xml> + + <template name="GenotypeGVCFsPreprocessing"> +<![CDATA[ + @token_gvcf_input_pre@ +]]> + </template> + + <template name="GenotypeGVCFsOptions"> +<![CDATA[ + --out output.g.vcf + + @token_gvcf_input@ + + #set $optionals = $analysis_type.optional_parameters + #if $optionals.optional_parameters_enabled + --sample_ploidy $optionals.sample_ploidy + #end if +]]> + </template> + + +</macros> + + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/haplotype_caller.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/haplotype_caller.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,65 @@ +<macros> + <xml name="HaplotypeCallerParameters" tokens="tag"> + + <expand macro="macro_bam_input" tag="@TAG@" /> + + <conditional name="cond_usage"> + <param name="cond_usage_selector" type="select" label="Select usage"> + <option value="GVCF">Single-sample all-sites calling on DNAseq (GVCF mode)</option> + </param> + <when value="GVCF"> + <expand macro="HaplotypeCallerGVCF" /> + </when> + </conditional> + + <expand macro="macro_optional_parameters"> + + <param name="sample_ploidy" type="integer" value="2" label="Ploidy (number of chromosomes) per sample. For pooled data, set to (Number of samples in each pool * Sample Ploidy)" help="-ploidy,‑‑sample_ploidy &lt;sample_ploidy&gt;" /> + + </expand> + + </xml> + + <xml name="HaplotypeCallerOutput"> + <data format="vcf" name="hc_output_gvcf" from_work_dir="output.g.vcf" label="${tool.name} on ${on_string} (gVCF)"> + <yield /> + </data> + </xml> + + <template name="HaplotypeCallerPreprocessing"> +<![CDATA[ + @token_bam_input_pre@ +]]> + </template> + + <template name="HaplotypeCallerOptions"> +<![CDATA[ + --out output.g.vcf + + @token_bam_input@ + + #set $optionals = $analysis_type.optional_parameters + #if $optionals.optional_parameters_enabled + --sample_ploidy $optionals.sample_ploidy + #end if + + #set $usage_selector = $analysis_type.cond_usage.cond_usage_selector + #set $usage = $analysis_type.cond_usage + + #if str($usage_selector) == 'GVCF' + --emitRefConfidence "GVCF" + #end if +]]> + </template> + + + + <xml name="HaplotypeCallerGVCF"> + <param name="emitRefConfidence" type="select" optional="true" label="Mode for emitting reference confidence scores" help="-ERC,‑‑emitRefConfidence &lt;emitRefConfidence&gt;"> + <option value="GVCF">GVCF (Reference model emitted with condensed non-variant blocks)</option> + </param> + </xml> + +</macros> + + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/indel_realigner.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/indel_realigner.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,90 @@ +<macros> + <xml name="IndelRealignerParameters" tokens="tag"> + + <expand macro="macro_bam_input" tag="@TAG@" /> + + <param name="targetIntervals" type="data" format="gatk_interval" label="Intervals file output from RealignerTargetCreator" help="-targetIntervals,--targetIntervals &lt;targetIntervals&gt;" /> + + <expand macro="macro_optional_parameters"> + <repeat name="knownAlleles" title="Input VCF file(s) with known indels" help="-known,‑‑knownAlleles &lt;knownAlleles&gt;"> + <param name="knownAllele" type="data" format="vcf" label="Variant file (VCF format)" /> + </repeat> + + <param name="consensusDeterminationModel" type="select" label="minimum reads at a locus to enable using the entropy calculation" help="-model,‑‑consensusDeterminationModel &lt;consensusDeterminationModel&gt;"> + <option value="USE_READS">USE_READS - Additionally uses indels already present in the original alignments of the reads</option> + <option value="KNOWNS_ONLY">KNOWNS_ONLYS - Uses only indels from a provided ROD of known indels</option> + <option value="USE_SW">USE_SW - Additionally uses 'Smith-Waterman' to generate alternate consenses</option> + </param> + <param name="LODThresholdForCleaning" type="float" value="5.0" label="LOD threshold above which the cleaner will clean" help="-LOD,‑‑LODThresholdForCleaning &lt;LODThresholdForCleaning&gt;" /> + <!--param name="nWayOut" type="float" value="5.0" label="Generate one output file for each input (-I) bam file (not compatible with -output)" help="-nWayOut,--nWayOut &lt;nWayOut&gt;" /--> + </expand> + + + <expand macro="macro_advanced_parameters"> + <param name="entropyThreshold" type="float" value="0.15" label="Percentage of mismatches at a locus to be considered having high entropy (0.0 < entropy <= 1.0)" help="-entropy,‑‑entropyThreshold &lt;entropyThreshold&gt;" /> + + <param name="maxConsensuses" type="integer" value="30" label="Max alternate consensuses to try (necessary to improve performance in deep coverage)" help="-maxConsensuses,‑‑maxConsensuses &lt;maxConsensuses&gt;" /> + + <param name="maxIsizeForMovement" type="integer" value="3000" label="maximum insert size of read pairs that we attempt to realign" help="-maxIsize,‑‑maxIsizeForMovement &lt;maxIsizeForMovement&gt;" /> + + <param name="maxPositionalMoveAllowed" type="integer" value="200" label="Maximum positional move in basepairs that a read can be adjusted during realignment" help="-maxPosMove,‑‑maxPositionalMoveAllowed &lt;maxPositionalMoveAllowed&gt;" /> + + <param name="maxReadsForConsensuses" type="integer" value="120" label="Max reads used for finding the alternate consensuses (necessary to improve performance in deep coverage)" help="-greedy,‑‑maxReadsForConsensuses &lt;maxReadsForConsensuses&gt;" /> + + <param name="maxReadsForRealignment" type="integer" value="20000" label="Max reads allowed at an interval for realignment" help="-maxReads,‑‑maxReadsForRealignment &lt;maxReadsForRealignment&gt;" /> + + <param name="maxReadsInMemory" type="integer" value="150000" label="max reads allowed to be kept in memory at a time by the SAMFileWriter" help="-maxInMemory,‑‑maxReadsInMemory &lt;maxReadsInMemory&gt;" /> + + <param name="noOriginalAlignmentTags" type="boolean" truevalue="--noOriginalAlignmentTags" falsevalue="" label="Don't output the original cigar or alignment start tags for each realigned read in the output bam" help="-noTags,‑‑noOriginalAlignmentTags" /> + </expand> + + </xml> + + <xml name="IndelRealignerOutput"> + <data format="bam" name="ir_output_bam" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (BAM)"> + <yield /> + </data> + </xml> + + <template name="IndelRealignerPreprocessing"> +<![CDATA[ + @token_bam_input_pre@ + + ln -s -f ${analysis_type.targetIntervals} target.intervals && + + #if $analysis_type.optional_parameters.optional_parameters_enabled + #for $i, $knownAllele in enumerate($analysis_type.optional_parameters.knownAlleles): + ln -s -f ${knownAllele.knownAllele} knownAllele_${i}.vcf && + #end for + #end if +]]> + </template> + + <template name="IndelRealignerOptions"> +<![CDATA[ + --out ${ir_output_bam} + + @token_bam_input@ + --targetIntervals target.intervals + + #if $analysis_type.optional_parameters.optional_parameters_enabled + #for $i, $knownAllele in enumerate($analysis_type.optional_parameters.knownAlleles): + --knownAlleles knownAllele_${i}.vcf + #end for + --consensusDeterminationModel ${analysis_type.consensusDeterminationModel} + --LODThresholdForCleaning ${analysis_type.LODThresholdForCleaning} + #end if + + #if $analysis_type.advanced_parameters.advanced_parameters_enabled + --entropyThreshold ${analysis_type.advanced_parameters.entropyThreshold} + --maxConsensuses ${analysis_type.advanced_parameters.maxConsensuses} + --maxIsizeForMovement ${analysis_type.advanced_parameters.maxIsizeForMovement} + --maxPositionalMoveAllowed ${analysis_type.advanced_parameters.maxPositionalMoveAllowed} + --maxReadsForConsensuses ${analysis_type.advanced_parameters.maxReadsForConsensuses} + --maxReadsForRealignment ${analysis_type.advanced_parameters.maxReadsForRealignment} + --maxReadsInMemory ${analysis_type.advanced_parameters.maxReadsInMemory} + ${analysis_type.advanced_parameters.noOriginalAlignmentTags} + #end if +]]> + </template> +</macros> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/print_reads.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/print_reads.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,71 @@ +<macros> + <xml name="PrintReadsParameters" tokens="tag"> + + <expand macro="macro_bam_input" tag="@TAG@" /> + + <!-- BQSR in main config --> + + <expand macro="macro_optional_parameters"> + + <param name="number" type="integer" value="" optional="true" label="Print the first n reads from the file, discarding the rest" help="-n,‑‑number &lt;number&gt;" /> + + <param name="platform" type="text" value="" optional="true" label="Exclude all reads with this platform from the output" help="-platform,‑‑platform &lt;platform&gt;" /> + + <param name="readGroup" type="text" value="" optional="true" label="Exclude all reads with this read group from the output" help="-readGroup,‑‑readGroup &lt;readGroup&gt;" /> + + <param name="sample_file" type="data" format="txt" optional="true" label="File containing a list of samples (one per line). Can be specified multiple times" help="-sf,‑‑sample_file &lt;sample_file&gt;" /> + + <repeat name="sample_names" title="Sample names to be included in the analysis" help="-sn,‑‑sample_name &lt;sample_name&gt;"> + <param name="sample_name" type="text" value="" title="Sample name to be included in the analysis" /> + </repeat> + + <param name="simplify" type="text" truevalue="-s" falsevalue="" label="Erase all extra attributes in the read but keep the read group information" help="-s,‑‑simplify" /> + + </expand> + + </xml> + + <xml name="PrintReadsOutput"> + <data format="bam" name="pr_output_bam" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (BAM)"> + <yield /> + </data> + </xml> + + <template name="PrintReadsPreprocessing"> +<![CDATA[ + @token_bam_input_pre@ +]]> + </template> + + <template name="PrintReadsOptions"> +<![CDATA[ + --out ${pr_output_bam} + + @token_bam_input@ + + #set $optionals = $analysis_type.optional_parameters + #if $optionals.optional_parameters_enabled + #if int($optionals.number) > 0 + --number $optionals.number + #end if + #if str($optionals.platform) + --platform $optionals.platform + #end if + #if str($optionals.readGroup) + --readGroup $optionals.readGroup + #end if + #if $optionals.sample_file + --sample_file $optionals.sample_file + #end if + #if $optionals.sample_names + #for $sample in $optionals.sample_names: + --intervals ${sample.sample_name} + #end for + #end if + $optionals.simplify + #end if +]]> + </template> +</macros> + + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/realigner_target_creator.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/realigner_target_creator.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,57 @@ +<macros> + <xml name="RealignerTargetCreatorParameters" tokens="tag"> + + <expand macro="macro_bam_input" tag="@TAG@" /> + + <expand macro="macro_optional_parameters"> + <param name="maxIntervalSize" type="integer" value="500" label="maximum interval size; any intervals larger than this value will be dropped" help="-maxInterval,‑‑maxIntervalSize &lt;maxIntervalSize&gt;" /> + <param name="minReadsAtLocus" type="integer" value="4" label="minimum reads at a locus to enable using the entropy calculation" help="-minReads,‑‑minReadsAtLocus &lt;minReadsAtLocus&gt;" /> + <param name="windowSize" type="integer" value="10" label="window size for calculating entropy or SNP clusters" help="-window,‑‑windowSize &lt;windowSize&gt;" /> + + <param name="mismatchFraction" type="float" value="0.0" label="fraction of base qualities needing to mismatch for a position to have high entropy" help="-mismatch,‑‑mismatchFraction &lt;mismatchFraction&gt;" /> + <repeat name="rod_bindings" title="Input VCF files with known indels" help="-known,‑‑known &lt;known&gt;"> + <param name="input_rod" type="data" format="vcf" label="Variant file (VCF format)" /> + </repeat> + </expand> + + </xml> + + <xml name="RealignerTargetCreatorOutput"> + <data format="gatk_interval" name="rtc_output_intervals" label="${tool.name} - ${analysis_type.analysis_type_selector} on ${on_string} (GATK intervals)"> + <yield /> + </data> + </xml> + + <template name="RealignerTargetCreatorPreprocessing"> +<![CDATA[ + @token_bam_input_pre@ + + #if $analysis_type.optional_parameters.optional_parameters_enabled + #for $i, $rod_binding in enumerate($analysis_type.optional_parameters.rod_bindings): + ln -s -f ${rod_binding.input_rod} rod_binding_${i}.vcf && + #end for + #end if +]]> + </template> + + <template name="RealignerTargetCreatorOptions"> +<![CDATA[ + --out ${rtc_output_intervals} + + @token_bam_input@ + + #if $analysis_type.optional_parameters.optional_parameters_enabled + --maxIntervalSize ${analysis_type.optional_parameters.maxIntervalSize} + --minReadsAtLocus ${analysis_type.optional_parameters.minReadsAtLocus} + --windowSize ${analysis_type.optional_parameters.windowSize} + --mismatchFraction ${analysis_type.optional_parameters.mismatchFraction} + + #for $i, $rod_binding in enumerate($analysis_type.optional_parameters.rod_bindings): + --known rod_binding_${i}.vcf + #end for + #end if +]]> + </template> +</macros> + + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/tool-data/destinations.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/tool-data/destinations.py Thu Oct 03 10:42:15 2019 -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}) + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/tool-data/picard_index.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/tool-data/picard_index.loc.sample Thu Oct 03 10:42:15 2019 -0400 |
| b |
| @@ -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): +# +#<unique_build_id> <dbkey> <display_name> <fasta_file_path> +# +#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. +# |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/tool_data_table_conf.xml.sample Thu Oct 03 10:42:15 2019 -0400 |
| b |
| @@ -0,0 +1,7 @@ +<tables> + <!-- Location of Picard dict files valid for GATK --> + <table name="picard_indexes" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/picard_index.loc" /> + </table> +</tables> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/gatk/tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/gatk/tool_dependencies.xml Thu Oct 03 10:42:15 2019 -0400 |
| b |
| @@ -0,0 +1,19 @@ +<?xml version="1.0"?> +<tool_dependency> + <set_environment version="1.0"> + <environment_variable action="set_to" name="GATK_PATH">/mnt/galaxy/tools/GATK/3.4-0</environment_variable> + </set_environment> + <!-- + Use GATK_SITE_OPTIONS to set additional parameters that should be inserted in every GATK call. + The intended use case was to prohibit GATK to collect and send data. + For example: + + -et "NO_ET" -K "/data/gatk_key_file" ##ET no phone home + --> + <set_environment version="1.0"> + <environment_variable action="set_to" name="GATK_SITE_OPTIONS"> </environment_variable> + </set_environment> + <package name="package_r_for_gatk_3_4_0" version="3.1.2.1"> + <repository changeset_revision="49c62e9b71ad" name="package_r_for_gatk_3_4_0" owner="avowinkel" toolshed="https://toolshed.g2.bx.psu.edu" /> + </package> +</tool_dependency> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/package_r_for_gatk_3_4_0/tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/package_r_for_gatk_3_4_0/tool_dependencies.xml Thu Oct 03 10:42:15 2019 -0400 |
| b |
| @@ -0,0 +1,48 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="R" version="3.1.2"> + <repository changeset_revision="9f2fddb9d6e2" name="package_r_3_1_2" owner="iuc" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu" /> + </package> + <package name="package_r_for_gatk_3_4_0" version="3.1.2.1"> + <install version="1.0"> + <actions> + <action type="setup_r_environment"> + + <repository changeset_revision="9f2fddb9d6e2" name="package_r_3_1_2" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu"> + <package name="R" version="3.1.2" /> + </repository> + <package>https://github.com/cran/stringi/archive/0.5-5.tar.gz</package> + <package>https://github.com/cran/magrittr/archive/1.5.tar.gz</package> + <package>https://github.com/cran/stringr/archive/1.0.0.tar.gz</package> + <package>https://github.com/cran/RColorBrewer/archive/1.1-2.tar.gz</package> + <package>https://github.com/cran/dichromat/archive/2.0-0.tar.gz</package> + <package>https://github.com/cran/colorspace/archive/1.2-6.tar.gz</package> + <package>https://github.com/cran/munsell/archive/0.4.2.tar.gz</package> + <package>https://github.com/cran/labeling/archive/0.3.tar.gz</package> + <package>https://github.com/cran/Rcpp/archive/0.11.6.tar.gz</package> + <package>https://github.com/cran/digest/archive/0.6.8.tar.gz</package> + <package>https://github.com/cran/gtable/archive/0.1.2.tar.gz</package> + <package>https://github.com/cran/bitops/archive/1.0-6.tar.gz</package> + <package>https://github.com/cran/caTools/archive/1.17.1.tar.gz</package> + <package>https://github.com/cran/gtools/archive/3.5.0.tar.gz</package> + <package>https://github.com/cran/gdata/archive/2.17.0.tar.gz</package> + <package>https://github.com/cran/gsalib/archive/2.1.tar.gz</package> + <package>https://github.com/cran/gplots/archive/2.17.0.tar.gz</package> + <package>https://github.com/cran/plyr/archive/1.8.3.tar.gz</package> + <package>https://github.com/cran/reshape/archive/0.8.5.tar.gz</package> + <package>https://github.com/cran/reshape2/archive/1.4.1.tar.gz</package> + <package>https://github.com/cran/scales/archive/0.2.5.tar.gz</package> + <package>https://github.com/cran/proto/archive/0.3-10.tar.gz</package> + <package>https://github.com/cran/MASS/archive/7.3-43.tar.gz</package> + <package>https://github.com/cran/ggplot2/archive/1.0.1.tar.gz</package> + </action> + </actions> + </install> + <readme> + ggplot2 is a plotting system for R, based on the grammar of graphics, which tries to take the good parts of base and lattice graphics and none of the bad parts. + It takes care of many of the fiddly details that make plotting a hassle (like drawing legends) as well as providing a powerful model of graphics that makes it easy to produce complex multi-layered graphics. + + http://ggplot2.org/ + </readme> + </package> +</tool_dependency> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/suite_samtools_1_2/repository_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/suite_samtools_1_2/repository_dependencies.xml Thu Oct 03 10:42:15 2019 -0400 |
| b |
| @@ -0,0 +1,17 @@ +<?xml version="1.0"?> +<repositories description="A suite of Galaxy tools designed to work with version 1.2 of the SAMtools package."> + <repository changeset_revision="cf875cbe2df4" name="data_manager_sam_fasta_index_builder" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="af7c50162f0b" name="bam_to_sam" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="d04d9f1c6791" name="sam_to_bam" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="8c3472790020" name="samtools_bedcov" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="1ebb4ecdc1ef" name="samtools_calmd" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="0072bf593791" name="samtools_flagstat" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="87398ae795c7" name="samtools_idxstats" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="c6fdfe3331d6" name="samtools_mpileup" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="020e144b5f78" name="samtools_reheader" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="3735f950b2f5" name="samtools_rmdup" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="2b474ebbfc7d" name="samtools_slice_bam" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="a430da4f04cd" name="samtools_sort" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="57f3e32f809d" name="samtools_split" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="0d71d9467847" name="samtools_stats" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> +</repositories> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/svdetect/BAM_preprocessingPairs.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/svdetect/BAM_preprocessingPairs.pl Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| b'@@ -0,0 +1,340 @@\n+#!/usr/bin/perl -w\n+\n+use strict;\n+use warnings;\n+use Getopt::Std;\n+my $version = \'0.5_galaxy\';\n+\n+my $SAMTOOLS_BIN_DIR="/bioinfo/local/samtools";\n+\n+my %opts = ( t=>1, p=>1, n=>1000000, f=>3, s=>0, S=>10000, o=>"." );\n+\n+getopts(\'dt:p:n:f:s:S:o:b:l:x:N:\', \\%opts); #GALAXY \n+\n+my $working_dir=($opts{o} ne ".")? $opts{o}:"working directory";\n+\n+my $pt_bad_mates_file=$opts{b}; #GALAXY \n+my $pt_log_file=$opts{l}; #GALAXY \n+my $pt_good_mates_file=$opts{x} if($opts{d}); #GALAXY \n+\n+\n+die(qq/\n+ \n+Description:\n+ \n+ Preprocessing of mates to get anomalously mapped mate-pair\\/paired-end reads as input\n+ for SVDetect.\n+\n+ From all pairs mapped onto the reference genome, this script outputs abnormal pairs:\n+ - mapped on two different chromosomes\n+ - with an incorrect strand orientation and\\/or pair order\n+ - with an insert size distance +- sigma threshold\n+ into a file <prefix.ab.bam\\/sam>\n+ \n+ -BAM\\/SAM File input format only, sorted by read names\n+\n+ Version : $version\n+ SAMtools required for BAM files\n+ \n+ \n+Usage: BAM_preprocessingPairs.pl [options] <all_mate_file.sorted.bam\\/sam>\n+\n+Options: -t BOOLEAN read type: =1 (Illumina), =0 (SOLiD) [$opts{t}]\n+ -p BOOLEAN pair type: =1 (paired-end), =0 (mate-pair) [$opts{p}]\n+ -n INTEGER number of pairs for calculating mu and sigma lengths [$opts{n}]\n+\t -s INTEGER minimum value of ISIZE for calculating mu and sigma lengths [$opts{s}]\n+\t -S INTEGER maximum value of ISIZE for calculating mu and sigma lengths [$opts{S}]\n+ -f REAL minimal number of sigma fold for filtering pairs [$opts{f}]\n+ -d dump normal pairs into a file [<prefix.norm.bam\\/sam>] (optional)\n+\t -o STRING output directory [$working_dir]\n+\n+\\n/) if (@ARGV == 0 && -t STDIN);\n+\n+unless (-d $opts{o}){\n+\tmkdir $opts{o} or die;\n+}\n+$opts{o}.="/" if($opts{o}!~/\\/$/);\n+\n+my $mates_file=shift(@ARGV);\n+\n+$mates_file=readlink($mates_file);\n+\n+my $bad_mates_file=(split(/\\//,$mates_file))[$#_];\n+\n+if($bad_mates_file=~/.(s|b)am$/){\n+ $bad_mates_file=~s/.(b|s)am$/.ab.sam/;\n+ $bad_mates_file=$opts{o}.$bad_mates_file;\n+}\n+\n+else{\n+ die "Error: mate_file with the extension <.bam> or <.sam> needed !\\n";\n+}\n+\n+my $good_mates_file;\n+if($opts{d}){\n+ $good_mates_file=(split(/\\//,$mates_file))[$#_];\n+ $good_mates_file=~s/.(b|s)am$/.norm.sam/;\n+ $good_mates_file=$opts{o}.$good_mates_file;\n+}\n+\n+my $log_file=$opts{o}.$opts{N}.".svdetect_preprocessing.log"; #GALAXY \n+\n+#------------------------------------------------------------------------------#\n+#Calculate mu and sigma\n+\n+open LOG,">$log_file" or die "$0: can\'t open ".$log_file.":$!\\n";\n+\n+print LOG "\\# Calculating mu and sigma lengths...\\n";\n+print LOG "-- file=$mates_file\\n";\n+print LOG "-- n=$opts{n}\\n";\n+print LOG "-- ISIZE min=$opts{s}, max=$opts{S}\\n";\n+\n+my ($record, $sumX,$sumX2) = (0,0,0);\n+my $warn=$opts{n}/10;\n+my $prev_pair="FIRST";\n+\n+my $bam=($mates_file =~ /.bam$/)? 1:0;\n+\n+if($bam){\n+ open(MATES, "${SAMTOOLS_BIN_DIR}/samtools view $mates_file |") or die "$0: can\'t open ".$mates_file.":$!\\n";\n+}else{\n+ open MATES, "<".$mates_file or die "$0: can\'t open ".$mates_file.":$!\\n";\n+}\n+\n+while(<MATES>){\n+ \n+ my @t=split;\n+ \n+ next if ($t[0]=~/^@/);\n+ \n+ my $current_pair=$t[0];\n+ next if($current_pair eq $prev_pair);\n+ $prev_pair=$current_pair; \n+ \n+ my ($chr1,$chr2,$length)=($t[2],$t[6],abs($t[8]));\n+ \n+ next if (($t[1]&0x0004) || ($t[1]&0x0008));\n+ next if ($length<$opts{s} || $length>$opts{S}) ;\n+ \n+ if($chr2 eq "="){\n+\n+ $sumX += $length;\t\t\t\t\t\t\t#add to sum and sum^2 for mean and variance calculation\n+\t$sumX2 += $length*$length;\n+ $record++;\n+ }\n+\n+ if($record>$warn){\n+\tprint LOG "-- $warn pairs analysed\\n";\n+ $warn+=$warn;\n+ }\n+ \n+ last if ($record>$opts{n});\n+ \n+}\n+close (MATES);\n+\n+$record--;\n+my'..b'ad=-1;\n+ $count{unmap}++;\n+ $record++;\n+ next;\n+ \n+ }\n+ \n+ my $strand1 = (($t[1]&0x0010))? \'R\':\'F\';\n+ my $strand2 = (($t[1]&0x0020))? \'R\':\'F\';\n+ my $order1 = (($t[1]&0x0040))? \'1\':\'2\';\n+ my $order2 = (($t[1]&0x0080))? \'1\':\'2\';\n+ \n+ if($order1 == 2){\n+ ($strand1,$strand2)=($strand2,$strand1);\n+ ($chr1,$chr2)=($chr2,$chr1);\n+ ($pos1,$pos2)=($pos2,$pos1);\n+ ($order1,$order2)=($order2,$order1);\n+ }\n+ \n+ my $sense=$strand1.$strand2;\n+ \n+ if($chr1 ne "=" && $chr2 ne "="){\n+ $bad=1;\n+ $count{chr}++;\n+ }\n+ \n+ if($opts{p}){ #paired-end\n+ if(!(($sense eq "FR" && $pos1<$pos2) || ($sense eq "RF" && $pos2<$pos1))){\n+ $bad=1;\n+ $count{sense}++;\n+ }\n+ }else{ #mate-pair\n+ if($opts{t}){ #Illumina\n+ if(!(($sense eq "FR" && $pos2<$pos1) || ($sense eq "RF" && $pos1<$pos2))){\n+ $bad=1;\n+ $count{sense}++;\n+ }\n+ }else{ #SOLiD\n+ if(!(($sense eq "FF" && $pos2<$pos1) || ($sense eq "RR" && $pos1<$pos2))){\n+ $bad=1;\n+ $count{sense}++;\n+ }\n+ }\n+ }\n+ \n+ if(($chr1 eq "=" || $chr2 eq "=") && ($length <$mu - $opts{f}*$sigma || $length>$mu + $opts{f}*$sigma)){\n+ $bad=1;\n+ $count{dist}++;\n+ }\n+ \n+ if($bad){\n+ print AB;\n+ $count{ab}++;\n+ $prev_bad=$bad;\n+ }else{\n+ print NORM if ($opts{d});\n+ $count{norm}++;\n+ $prev_bad=$bad;\n+ }\n+ \n+ $record++;\n+ \n+ if($record>$warn){\n+ print LOG "-- $warn pairs analysed\\n";\n+ $warn+=100000;\n+ }\n+}\n+\n+close AB;\n+close NORM if($opts{d});\n+\n+print LOG "-- Total : $record pairs analysed\\n";\n+print LOG "-- $count{unmap} pairs whose one or both reads are unmapped\\n";\n+print LOG "-- ".($count{ab}+$count{norm})." mapped pairs\\n";\n+print LOG "---- $count{ab} abnormal mapped pairs\\n";\n+print LOG "------ $count{chr} pairs mapped on two different chromosomes\\n";\n+print LOG "------ $count{sense} pairs with incorrect strand orientation and\\/or pair order\\n";\n+print LOG "------ $count{dist} pairs with incorrect insert size distance\\n";\n+print LOG "--- $count{norm} correct mapped pairs\\n";\n+\n+#------------------------------------------------------------------------------#\n+#------------------------------------------------------------------------------#\n+#OUTPUT\n+\n+if($bam){\n+ \n+ my $bam_file=$bad_mates_file;\n+ $bam_file=~s/.sam$/.bam/;\n+ print LOG "\\# Converting sam to bam for abnormal mapped pairs\\n";\n+ system("${SAMTOOLS_BIN_DIR}/samtools view -bS $bad_mates_file > $bam_file 2>".$opts{o}."samtools.log");\n+ unlink($bad_mates_file);\n+ print LOG "-- output created: $bam_file\\n";\n+\n+ system "rm $pt_bad_mates_file ; ln -s $bam_file $pt_bad_mates_file"; #GALAXY\n+ \n+ if($opts{d}){\n+ $bam_file=$good_mates_file;\n+ $bam_file=~s/.sam$/.bam/;\n+ print LOG "\\# Converting sam to bam for correct mapped pairs\\n";\n+ system("${SAMTOOLS_BIN_DIR}/samtools view -bS $good_mates_file > $bam_file 2>".$opts{o}."samtools.log");\n+ unlink($good_mates_file);\n+ print LOG "-- output created: $bam_file\\n";\n+\n+\tsystem "rm $pt_good_mates_file ; ln -s $bam_file $pt_good_mates_file"; #GALAXY\n+\n+ }\n+\n+}\n+\n+else{\n+ print LOG "-- output created: $bad_mates_file\\n";\n+ print LOG "-- output created: $good_mates_file\\n" if($opts{d});\n+}\n+\n+close LOG;\n+\n+system "rm $pt_log_file ; ln -s $log_file $pt_log_file"; #GALAXY\n+\n+\n+#------------------------------------------------------------------------------#\n+#------------------------------------------------------------------------------#\n+sub decimal{\n+ \n+ my $num=shift;\n+ my $digs_to_cut=shift;\n+\n+ $num=sprintf("%.".($digs_to_cut-1)."f", $num) if ($num=~/\\d+\\.(\\d){$digs_to_cut,}/);\n+\n+ return $num;\n+}\n+#------------------------------------------------------------------------------#\n' |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/svdetect/BAM_preprocessingPairs.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/svdetect/BAM_preprocessingPairs.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,77 @@ +<tool id="svdetect_preprocessing" name="BAM preprocessing"> + + <description>to get abnormal pairs</description> + + <command interpreter="perl"> BAM_preprocessingPairs.pl -t '$readType' -p '$pairType' -n '$nbrePair' -s '$isizeMin' -S '$isizeMax' -f '$foldPair' -o $__new_file_path__/svdetect -b '$abBAM' -l '$log' -N $sample_name + #if $newBam.pairNormal=="yes" + -d -x '$normBAM' + #end if + '$inputBam' + </command> + + <inputs> + <param name="sample_name" type="text" value="sample" label="Sample Name"/> + <param name="inputBam" type="data" format="bam" label="BAM input file"/> + <param name="readType" type="select" label="Read type"> + <option value="1">Illumina</option> + <option value="0">SOLiD</option> + </param> + <param name="pairType" type="select" label="Library type"> + <option value="1">Paired-end</option> + <option value="0">Mate-Pair</option> + </param> + <conditional name="newBam"> + <param name="pairNormal" type="select" label="Do you want an additional bam file listing concordant mapped pairs?" help="Dump normal pairs into a file sample_name.norm.bam/sam"> + <option value="no">No</option> + <option value="yes">Yes</option> + </param> + <when value="yes"> + <!-- do nothing here --> + </when> + <when value="no"> + <!-- do nothing here --> + </when> + </conditional> + <param name="nbrePair" value="1000000" type="integer" size="30" label="Number of pairs for calculating mu (µ) and sigma (σ) lengths"/> + <param name="isizeMin" value="0" type="integer" size="30" label="Minimum value of ISIZE for calculating mu (µ) and sigma (σ) lengths"/> + <param name="isizeMax" value="10000" type="integer" size="30" label="Maximum value of ISIZE for calculating mu (µ)and sigma( σ) lengths"/> + <param name="foldPair" value="3" type="float" size="30" label="Minimal number of sigma (σ) fold for filtering pairs"/> + </inputs> + + <outputs> + <data format="bam" name="abBAM" label="${$sample_name}.ab.bam"/> + <data format="txt" name="log" label="${$sample_name}.svdetect_preprocessing.log"/> + <data format="bam" name="normBAM" label="${$sample_name}.norm.bam"> + <filter>newBam['pairNormal'] == 'yes'</filter> + </data> + </outputs> + + <help> + +**What it does** + +Bam_preprocessingPairs - Version 0.5 + +Preprocessing of mates to get anomalously mapped mate-pair/paired-end reads as input for SVDetect. + +From all pairs mapped onto the reference genome, this script outputs abnormal pairs: + + * mapped on two different chromosomes + * with an incorrect strand orientation and/or pair order + * with an insert size distance +- sigma threshold + +into a file prefix.ab.bam/sam sorted by read names + +-BAM/SAM File input format only. + +SAMtools required for BAM files + +----- + +.. class:: infomark + +Contact Bruno Zeitouni (svdetect@curie.fr) for any questions or concerns about the Galaxy implementation of SVDetect. + + </help> + +</tool> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/svdetect/SVDetect_compare.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/svdetect/SVDetect_compare.pl Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| b'@@ -0,0 +1,716 @@\n+#!/usr/bin/perl -w\n+\n+=pod\n+\n+=head1 NAME\n+\n+SVDetect Compare for Galaxy\n+\n+Version: 0.8b for Galaxy\n+\n+=head1 SYNOPSIS\n+\n+SVDetect_compare.pl links2compare -conf <configuration_file> [-help] [-man]\n+\n+=cut\n+\n+# -------------------------------------------------------------------\n+\n+use strict;\n+use warnings;\n+\n+use Pod::Usage;\n+use Getopt::Long;\n+\n+use Config::General;\n+use Tie::IxHash;\n+\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n+#PARSE THE COMMAND LINE\n+my %OPT;\n+GetOptions(\\%OPT,\n+\t \'conf=s\',\n+\t \'out1=s\', #GALAXY\n+\t \'out2=s\', #GALAXY\n+\t \'out3=s\', #GALAXY\n+\t \'out4=s\', #GALAXY\n+\t \'out5=s\', #GALAXY\n+\t \'out6=s\', #GALAXY\n+\t \'out7=s\', #GALAXY\n+\t \'out8=s\', #GALAXY\n+\t \'out9=s\', #GALAXY\n+\t \'l=s\', #GALAXY\n+\t \'N=s\', #GALAXY\n+\t \'help\',\n+ \'man\'\n+\t );\n+\n+pod2usage() if $OPT{help};\n+pod2usage(-verbose=>2) if $OPT{man};\n+pod2usage(-message=> "$!", -exitval => 2) if (!defined $OPT{conf});\n+\n+\n+pod2usage() if(@ARGV<1);\n+\n+tie (my %func, \'Tie::IxHash\',links2compare=>\\&links2compare);\n+\n+foreach my $command (@ARGV){\n+ pod2usage(-message=> "Unknown command \\"$command\\"", -exitval => 2) if (!defined($func{$command}));\n+}\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n+\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n+#READ THE CONFIGURATION FILE\n+my $conf=Config::General->new( -ConfigFile => $OPT{conf},\n+ -Tie => "Tie::IxHash",\n+ -AllowMultiOptions => 1,\n+\t\t\t\t -LowerCaseNames => 1,\n+\t\t\t\t -AutoTrue => 1);\n+my %CONF= $conf->getall;\n+validateconfiguration(\\%CONF);\t\t\t\t\t\t\t#validation of the configuration parameters\n+\n+\n+my $SAMTOOLS_BIN_DIR="/bioinfo/local/samtools"; #GALAXY\n+my $BEDTOOLS_BIN_DIR="/bioinfo/local/BEDTools/bin"; #GALAXY\n+\n+my $pt_log_file=$OPT{l}; #GALAXY\n+my $log_file=$CONF{general}{output_dir}.$OPT{N}.".svdetect_compare.log"; #GALAXY\n+open LOG,">$log_file" or die "$0: can\'t open ".$log_file.":$!\\n";#GALAXY\n+\n+my @pt_sv_file=($OPT{out1},$OPT{out2},$OPT{out3}) if($OPT{out1}); #GALAXY common,sample,reference\n+my @pt_circos_file=($OPT{out4},$OPT{out5},$OPT{out6}) if($OPT{out4}); #GALAXY common,sample,reference\n+my @pt_bed_file=($OPT{out7},$OPT{out8},$OPT{out9}) if($OPT{out7}); #GALAXY common,sample,reference\n+\n+$CONF{compare}{sample_link_file}=readlink($CONF{compare}{sample_link_file});#GALAXY\n+$CONF{compare}{sample_link_file}=~s/.sv.txt//; #GALAXY\n+\n+$CONF{compare}{reference_link_file}=readlink($CONF{compare}{reference_link_file});#GALAXY\n+$CONF{compare}{reference_link_file}=~s/.sv.txt//; #GALAXY\n+\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n+\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n+#COMMAND EXECUTION\n+foreach my $command (@ARGV){\n+ &{$func{$command}}();\n+}\n+print LOG "-- end\\n";\n+\n+close LOG;#GALAXY\n+system "rm $pt_log_file ; ln -s $log_file $pt_log_file"; #GALAXY\n+\n+exit(0);\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n+\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n+#FUNCTIONS\n+\n+# -----------------------------------------------------------------------------#\n+#MAIN FUNCTION number 5:Comparison between samples, common or specific links\n+sub links2compare{\n+ \n+ my @compare_files;\n+ \n+ compareSamples($CONF{general}{output_dir},\n+\t\t $CONF{compare}{list_samples},\n+\t\t $CONF{compare}{sample_link_file},\n+\t\t $CONF{compare}{reference_link_file},\n+\t\t $CONF{compare}{min_overlap},\n+\t\t $CONF{compare}{same_sv_type},\n+\t\t \\@compare_files);\n+\n+ my $pt_ind=0;\n+ \n+ for my $input_file (@comp'..b'->[$i] eq \'F\'){\n+\t $starts->[$i]=$positions->[$i];\n+\t $ends->[$i]=$positions->[$i]+$tag_length->{$end_order->[$i]}-1;\n+\t}else{\n+\t $starts->[$i]=$positions->[$i]-$tag_length->{$end_order->[$i]}+1;\n+\t $ends->[$i]=$positions->[$i];\n+\t}\n+ } \n+}\n+#------------------------------------------------------------------------------#\n+#------------------------------------------------------------------------------#\n+sub floor {\n+ my $nb = $_[0];\n+ $nb=~ s/\\..*//;\n+ return $nb;\n+}\n+#------------------------------------------------------------------------------#\n+#------------------------------------------------------------------------------#\n+sub decimal{\n+ \n+ my $num=shift;\n+ my $digs_to_cut=shift;\n+\n+ $num=sprintf("%.".($digs_to_cut-1)."f", $num) if ($num=~/\\d+\\.(\\d){$digs_to_cut,}/);\n+\n+ return $num;\n+}\n+\n+#------------------------------------------------------------------------------#\n+#------------------------------------------------------------------------------#\n+#Sort links according the concerned chromosomes and their coordinates\n+sub sortLinks{\n+ \n+ my ($links_file,$sortedlinks_file,$unique)=@_;\n+ \n+ print LOG "# Sorting links...\\n";\n+ \n+ my $pipe=($unique)? "| sort -u":"";\n+ system "sort -k 1,1 -k 4,4 -k 2,2n -k 5,5n -k 8,8n $links_file $pipe > $sortedlinks_file";\n+\n+}\n+#------------------------------------------------------------------------------#\n+#------------------------------------------------------------------------------#\n+sub getColor{\n+\n+ my($count,$hcolor,$format)=@_;\n+ for my $col ( keys % { $hcolor} ) {\n+ return $col if($count>=$hcolor->{$col}->[0] && $count<=$hcolor->{$col}->[1]);\n+ }\n+ return "white" if($format eq "circos");\n+ return "255,255,255" if($format eq "bed");\n+}\n+#------------------------------------------------------------------------------#\n+#------------------------------------------------------------------------------#\n+#check if the configuration file is correct\n+sub validateconfiguration{\n+ \n+ my %conf=%{$_[0]};\n+ my $list_prgs="@ARGV";\n+ \n+ my @circos_params=qw(organism_id colorcode);\n+ my @bed_params=qw(colorcode);\n+ my @compare_params=qw(list_samples list_read_lengths sample_link_file reference_link_file);\n+ \n+ unless (defined($conf{general}{output_dir})) {\n+\t$conf{general}{output_dir} = ".";\n+ }\n+ unless (-d $conf{general}{output_dir}){\n+\tmkdir $conf{general}{output_dir} or die;\n+ }\n+ $conf{general}{output_dir}.="/" if($conf{general}{output_dir}!~/\\/$/);\n+\n+ \n+ if($list_prgs=~/links2compare/){\n+\tforeach my $p (@compare_params) {\n+\t die("Error Config : The compare parameter \\"$p\\" is not defined\\n") if (!defined $conf{compare}{$p});\n+\t}\n+\t\n+\tunless (defined($conf{compare}{same_sv_type})) {\n+\t $conf{compare}{same_sv_type} = 0;\n+\t}\n+\t\n+\tunless (defined($conf{compare}{min_overlap})) {\n+\t $conf{compare}{min_overlap} = 1E-9;\n+\t}\n+\t\n+\tif($conf{compare}{circos_output}){\n+\t foreach my $p (@circos_params) {\n+\t\tnext if($list_prgs=~/^ratio/ && $p eq "colorcode");\n+\t\tdie("Error Config : The circos parameter \\"$p\\" is not defined\\n") if (!defined $conf{circos}{$p});\n+\t }\n+\t}\n+\tif($conf{compare}{bed_output}){\n+\t foreach my $p (@bed_params) {\n+\t\tdie("Error Config : The bed parameter \\"$p\\" is not defined\\n") if (!defined $conf{bed}{$p});\n+\t }\n+\t die("Error Config : The compare parameter \\"list_read_lengths\\" is not defined\\n") if (!defined $conf{compare}{list_read_lengths});\n+\n+\t my @samples=split(",",$conf{compare}{list_samples});\n+\t my @read_lengths=split(",",$conf{compare}{list_read_lengths});\n+\t for my $i (0..$#samples){\n+\t\tmy @l=split("-",$read_lengths[$i]);\n+\t\t$conf{compare}{read_lengths}{$samples[$i]}={ 1=> $l[0], 2=> $l[1]};\n+\t }\n+\t}\n+ }\n+ \n+ \n+}\n+#------------------------------------------------------------------------------#\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n' |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/svdetect/SVDetect_compare.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/svdetect/SVDetect_compare.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,218 @@ +<tool id="svdetect_compare" name="Compare"> + +<description>structural variants between two samples</description> + +<command interpreter="perl">SVDetect_compare.pl links2compare -conf '$config_file' -l '$log_file' -N '$sample_name.$reference_name' + +#if $links2SV +-out1 '$common_sv_file' +-out2 '$sample_sv_file' +-out3 '$reference_sv_file' +#end if + +#if $file_conversion.file_conversion_select=="convert" and $file_conversion.links2circos +-out4 '$common_circos_file' +-out5 '$sample_circos_file' +-out6 '$reference_circos_file' +#end if + +#if $file_conversion.file_conversion_select=="convert" and $file_conversion.links2bed +-out7 '$common_bed_file' +-out8 '$sample_bed_file' +-out9 '$reference_bed_file' +#end if + +</command> + +<inputs> + <param name="sample_name" type="text" size="20" value="sample" label="Sample Name"/> + <param name="sample_read1_length" type="integer" size="10" value="50" label="Sample read 1 length (bp)"/> + <param name="sample_read2_length" type="integer" size="10" value="50" label="Sample read 2 length (bp)"/> + <param name="sample_mates_file" type="data" format="sv" label="Sample input file" help=".sv file"/> + + <param name="reference_name" type="text" size="20" value="reference" label="Reference Name"/> + <param name="reference_read1_length" type="integer" size="10" value="50" label="Reference read 1 length (bp)"/> + <param name="reference_read2_length" type="integer" size="10" value="50" label="Reference read 2 length (bp)"/> + <param name="reference_mates_file" type="data" format="sv" label="Reference input file" help=".sv file"/> + + <param name="min_overlap" type="float" size="10" value="0.05" label="Minimum overlap of links required as a fraction"/> + <param name="same_sv_type" label="Comparison of SVs with the same type only ?" type="boolean" truevalue="1" falsevalue="0" checked="True"/> + + <param name="links2SV" label="Do you want to have filtered links in a tabulated file format showing significant SVs?" type="boolean" truevalue="1" falsevalue="0" checked="True"/> + + <conditional name="file_conversion"> + <param name="file_conversion_select" type="select" label="Output file conversion" help="Converts filtered links to Circos/BED files format for graphical view of SVs"> + <option value="do_not_convert">No</option> + <option value="convert">Yes</option> + </param> + <when value="do_not_convert"> + <!-- do nothing here --> + </when> + <when value="convert"> + <param name="links2circos" label="Converts the link list to the Circos link format" type="boolean" truevalue="1" falsevalue="0" checked="True"/> + <param name="links2bed" label="Converts the link list to the UCSC BED format" type="boolean" truevalue="1" falsevalue="0" checked="False"/> + <param name="organism_id" type="text" size="10" value="hs" label="Organism ID"/> + <repeat name="color_code" title="Color-code" min="1" max="7"> + <param name="color" type="select" label="Color"> + <option value="grey">grey</option> + <option value="black">black</option> + <option value="blue">blue</option> + <option value="green">green</option> + <option value="purple">purple</option> + <option value="orange">orange</option> + <option value="red">red</option> + </param> + <param name="interval" type="text" value="1,3" label="Interval"/> + </repeat> + </when> + </conditional> +</inputs> + + + +<outputs> + <data format="sv" name="common_sv_file" label="common.compared.sv"> + <filter>links2SV is True</filter> + </data> + <data format="sv" name="sample_sv_file" label="${sample_name}.compared.sv"> + <filter>links2SV is True</filter> + </data> + <data format="sv" name="reference_sv_file" label="${reference_name}.compared.sv"> + <filter>links2SV is True</filter> + </data> + + <data format="segdup" name="common_circos_file" label="common.compared.segdup"> + <filter>( + file_conversion['file_conversion_select']=="convert" and + file_conversion['links2circos'] is True + ) + </filter> + </data> + <data format="segdup" name="sample_circos_file" label="${sample_name}.compared.segdup"> + <filter>( + file_conversion['file_conversion_select']=="convert" and + file_conversion['links2circos'] is True + ) + </filter> + </data> + <data format="segdup" name="reference_circos_file" label="${reference_name}.compared.segdup"> + <filter>( + file_conversion['file_conversion_select']=="convert" and + file_conversion['links2circos'] is True + ) + </filter> + </data> + + <data format="bed" name="common_bed_file" label="common.compared.bed"> + <filter>( + file_conversion['file_conversion_select']=="convert" and + file_conversion['links2bed'] is True + ) + </filter> + </data> + <data format="bed" name="sample_bed_file" label="${sample_name}.compared.bed"> + <filter>( + file_conversion['file_conversion_select']=="convert" and + file_conversion['links2bed'] is True + ) + </filter> + </data> + <data format="bed" name="reference_bed_file" label="${reference_name}.compared.bed"> + <filter>( + file_conversion['file_conversion_select']=="convert" and + file_conversion['links2bed'] is True + ) + </filter> + </data> + + <data format="txt" name="log_file" label="${sample_name}.${reference_name}.svdetect_compare.log"/> +</outputs> + + + +<configfiles> + <configfile name="config_file"> +<general> +output_dir=$__new_file_path__/svdetect +</general> + +#if $file_conversion.file_conversion_select == "convert" +#if $file_conversion.links2circos +<circos> +organism_id=${file_conversion.organism_id} +<colorcode> +#for $color_repeat in $file_conversion.color_code +${color_repeat.color}=${color_repeat.interval} +#end for +</colorcode> +</circos> +#end if +#if $file_conversion.links2bed +<bed> +<colorcode> +#for $color_repeat in $file_conversion.color_code +#if str($color_repeat.color)== "grey" +190,190,190=${color_repeat.interval} +#end if +#if str($color_repeat.color)== "black" +0,0,0=${color_repeat.interval} +#end if +#if str($color_repeat.color)== "blue" +0,0,255=${color_repeat.interval} +#end if +#if str($color_repeat.color)== "green" +0,255,0=${color_repeat.interval} +#end if +#if str($color_repeat.color)== "purple" +153,50,205=${color_repeat.interval} +#end if +#if str($color_repeat.color)== "orange" +255,140,0=${color_repeat.interval} +#end if +#if str($color_repeat.color)== "red" +255,0,0=${color_repeat.interval} +#end if +#end for +</colorcode> +</bed> +#end if +#end if + +<compare> +list_samples=${sample_name},${reference_name} +list_read_lengths=${sample_read1_length}-${sample_read2_length},${reference_read1_length}-${reference_read2_length} +sample_link_file=${sample_mates_file} +reference_link_file=${reference_mates_file} +min_overlap=${min_overlap} +same_sv_type=${same_sv_type} +sv_output=${links2SV} +#if $file_conversion.file_conversion_select == "convert" +circos_output=${$file_conversion.links2circos} +bed_output=${$file_conversion.links2bed} +#end if +</compare> + + </configfile> +</configfiles> + + <help> +**What it does** + +SVDetect - Version : 0.8b + +Comparison of clusters between two samples to get common or sample-specific SVs + +This program is designed to compare filtered links between two anomalously mapped mate-pair/paired-end datasets +and to identify common and sample-specific SVs (like the usual sample/reference design). +Overlaps between coordinates of clusters and types of SVs are used as parameters of comparison. + +Manual documentation available at the http://svdetect.sourceforge.net/Site/Manual.html + +----- + +.. class:: infomark + +Contact Bruno Zeitouni (svdetect@curie.fr) for any questions or concerns about the Galaxy implementation of SVDetect. + </help> + +</tool> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/svdetect/SVDetect_import.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/svdetect/SVDetect_import.sh Thu Oct 03 10:42:15 2019 -0400 |
| b |
| @@ -0,0 +1,15 @@ +#!/bin/bash + + +while getopts "i:o:" optionName; do +case "$optionName" in + +i) INPUT="$OPTARG";; +o) OUTPUT="$OPTARG";; + +esac +done + +rm $OUTPUT + +ln -s $INPUT $OUTPUT |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/svdetect/SVDetect_import.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/svdetect/SVDetect_import.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,85 @@ +<tool id="svdetect_import" name="Import data"> + <description>BAM, chromosome info or sv files</description> + <command interpreter="bash">SVDetect_import.sh -i $file_path + #if str($type.file_type)=="bam" + -o $outbamfile + #elif str($type.file_type)=="len" + -o $outlenfile + #elif str($type.file_type)=="sv" + -o $outsvfile + #end if + </command> + <inputs> + <param name="file_name" type="text" value="file1" label="File Name"/> + <conditional name="type"> + <param name="file_type" type="select" label="Select the file type to import" help="BAM file (BAM) or text file (SAM, chromosome list or a SV tabulated text file)"> + <option value="bam">BAM file (.bam)</option> + <option value="len">Chromosome info file (.len)</option> + <option value="sv">SVDetect output file (.sv)</option> + </param> + <when value="bam"> + <!-- do nothing here --> + </when> + <when value="len"> + <!-- do nothing here --> + </when> + <when value="sv"> + <!-- do nothing here --> + </when> + </conditional> + <param name="file_path" type="text" size="150" label="Path to file"/> + </inputs> + <outputs> + <data format="bam" name="outbamfile" label="${file_name}.bam"> + <filter>type['file_type']=="bam"</filter> + </data> + <data format="len" name="outlenfile" label="${file_name}.len"> + <filter>type['file_type']=="len"</filter> + </data> + <data format="sv" name="outsvfile" label="${file_name}.sv"> + <filter>type['file_type']=="sv"</filter> + </data> + </outputs> + <help> +**What it does** + +This tool allows you to import quickly a BAM file, a chromosome info file or a SVDetect output file from you computer as inputs for SVDetect. + + +**Example of chromosome file** + +Input len file:: + + 1 chr1 247249719 + 2 chr2 242951149 + 3 chr3 199501827 + 4 chr4 191273063 + 5 chr5 180857866 + 6 chr6 170899992 + 7 chr7 158821424 + 8 chr8 146274826 + 9 chr9 140273252 + 10 chr10 135374737 + 11 chr11 134452384 + 12 chr12 132349534 + 13 chr13 114142980 + 14 chr14 106368585 + 15 chr15 100338915 + 16 chr16 88827254 + 17 chr17 78774742 + 18 chr18 76117153 + 19 chr19 63811651 + 20 chr20 62435964 + 21 chr21 46944323 + 22 chr22 49691432 + 23 chrX 154913754 + 24 chrY 57772954 + +----- + +.. class:: infomark + +Contact Bruno Zeitouni (svdetect@curie.fr) for any questions or concerns about the Galaxy implementation of SVDetect. + </help> + +</tool> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/svdetect/SVDetect_run_parallel.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/svdetect/SVDetect_run_parallel.pl Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| b'@@ -0,0 +1,3537 @@\n+#!/usr/bin/perl -w\n+\n+=pod\n+\n+=head1 NAME\n+\n+SVDetect - Program designed to the detection of structural variations\n+from paired-end/mate-pair sequencing data, compatible with SOLiD and Illumina (>=1.3) reads\n+\n+Version: 0.8b for Galaxy\n+\n+=head1 SYNOPSIS\n+\n+SVDetect <command> -conf <configuration_file> [-help] [-man]\n+ \n+ Command:\n+\n+ \tlinking\t\tdetection and isolation of links\n+ filtering\tfiltering of links according different parameters\n+ links2circos\tlinks conversion to circos format\n+\tlinks2bed \tpaired-ends of links converted to bed format (UCSC)\n+\tlinks2SV\tformatted output to show most significant SVs\n+\tcnv\t\tcalculate copy-number profiles\n+\tratio2circos\tratio conversion to circos density format\n+\tratio2bedgraph\tratio conversion to bedGraph density format (UCSC)\n+ \n+=head1 DESCRIPTION\n+\n+This is a command-line interface to SVDetect.\n+\n+\n+=head1 AUTHORS\n+\n+Bruno Zeitouni E<lt>bruno.zeitouni@curie.frE<gt>,\n+Valentina Boeva E<lt>valentina.boeva@curie.frE<gt>\n+\n+=cut\n+\n+# -------------------------------------------------------------------\n+\n+use strict;\n+use warnings;\n+\n+use Pod::Usage;\n+use Getopt::Long;\n+\n+use Config::General;\n+use Tie::IxHash;\n+use FileHandle;\n+use Parallel::ForkManager;\n+\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n+#PARSE THE COMMAND LINE\n+my %OPT;\n+GetOptions(\\%OPT,\n+\t \'conf=s\',\n+\t \'out1=s\', #GALAXY\n+\t \'out2=s\', #GALAXY\n+\t \'out3=s\', #GALAXY\n+\t \'out4=s\', #GALAXY\n+\t \'out5=s\', #GALAXY\n+\t \'l=s\', #GALAXY\n+\t \'N=s\',#GALAXY\n+\t \'help\',#GALAXY\n+ \'man\'\n+\t );\n+\n+pod2usage() if $OPT{help};\n+pod2usage(-verbose=>2) if $OPT{man};\n+pod2usage(-message=> "$!", -exitval => 2) if (!defined $OPT{conf});\n+\n+pod2usage() if(@ARGV<1);\n+\n+tie (my %func, \'Tie::IxHash\',linking=>\\&createlinks,\n+\t\t\t filtering=>\\&filterlinks,\n+\t\t\t links2circos=>\\&links2circos,\n+\t\t\t links2bed=>\\&links2bed,\n+\t\t\t links2compare=>\\&links2compare,\n+\t\t\t links2SV=>\\&links2SV,\n+\t\t\t cnv=>\\&cnv,\n+\t\t\t ratio2circos=>\\&ratio2circos,\n+\t\t\t ratio2bedgraph=>\\&ratio2bedgraph);\n+\n+foreach my $command (@ARGV){\n+ pod2usage(-message=> "Unknown command \\"$command\\"", -exitval => 2) if (!defined($func{$command}));\n+}\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n+\n+\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n+#READ THE CONFIGURATION FILE\n+my $conf=Config::General->new( -ConfigFile => $OPT{conf},\n+ -Tie => "Tie::IxHash",\n+ -AllowMultiOptions => 1,\n+\t\t\t\t -LowerCaseNames => 1,\n+\t\t\t\t -AutoTrue => 1);\n+my %CONF= $conf->getall;\n+validateconfiguration(\\%CONF);\t\t\t\t\t\t\t#validation of the configuration parameters\n+\n+my $SAMTOOLS_BIN_DIR="/bioinfo/local/samtools"; #GALAXY\n+\n+my $pt_log_file=$OPT{l}; #GALAXY\n+my $pt_links_file=$OPT{out1} if($OPT{out1}); #GALAXY\n+my $pt_flinks_file=$OPT{out2} if($OPT{out2}); #GALAXY\n+my $pt_sv_file=$OPT{out3} if($OPT{out3}); #GALAXY\n+my $pt_circos_file=$OPT{out4} if($OPT{out4}); #GALAXY\n+my $pt_bed_file=$OPT{out5} if($OPT{out5}); #GALAXY\n+\n+$CONF{general}{mates_file}=readlink($CONF{general}{mates_file});#GALAXY\n+$CONF{general}{cmap_file}=readlink($CONF{general}{cmap_file});#GALAXY\n+\n+my $log_file=$CONF{general}{output_dir}.$OPT{N}.".svdetect_run.log"; #GALAXY\n+open LOG,">$log_file" or die "$0: can\'t open ".$log_file.":$!\\n";#GALAXY\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n+\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n+#COMMAND EXECUTION\n+foreach my $command (@ARGV){\n+ &{$func{$command}}();\n+}\n+print LOG "-- end\\n";#GALAXY\n+\n+close LOG;#GALAXY\n+system "rm $pt_log_file ; ln -s $log_file $pt_log_file"; #GALAXY\n+exi'..b'y $chrName (@chrs){\n+\t \n+\t\tdie("Error Config : The filtering parameter \\"chromosomes\\" is not valid\\n")\n+\t\tif(($chrName!~/^\\-/ && $exclude) || ($chrName=~/^\\-/ && !$exclude));\n+\t\t\n+\t }\n+\t}\n+\t\n+\tif (( $conf{filtering}{order_filtering} )&& !$conf{filtering}{strand_filtering}) {\n+\t die("Error Config : The parameter strand_filtering is set to \\"0\\" while order_filtering is selected".\n+\t\t"\\nChange strand_filtering to \\"1\\" if you want to use the order filtering\\n");\n+\t}\n+\tif (( !defined($conf{filtering}{mu_length}) || !defined($conf{filtering}{sigma_length}) )&& $conf{filtering}{order_filtering}) {\n+\t die("Error Config : You should set parameters \\"mu_length\\" and \\"sigma_length\\" to use order filtering\\n");\n+\t}\n+\tif (( $conf{filtering}{insert_size_filtering} )&& !$conf{filtering}{strand_filtering}) {\n+\t die("Error Config : The parameter strand_filtering is set to \\"0\\" while insert_size_filtering is selected".\n+\t\t"\\nChange strand_filtering to \\"1\\" if you want to use the insert size filtering\\n");\n+\t}\n+\tif (( !defined($conf{filtering}{mu_length}) || !defined($conf{filtering}{sigma_length}) )&& $conf{filtering}{insert_size_filtering}) {\n+\t die("Error Config : You should set parameters \\"mu_length\\" and \\"sigma_length\\" to use discriminate insertions from deletions\\n");\n+\t}\n+\t\n+\tif (!defined($conf{filtering}{indel_sigma_threshold})) {\n+\t $conf{filtering}{indel_sigma_threshold} = 2;\n+\t}\n+\tif (!defined($conf{filtering}{dup_sigma_threshold})) {\n+\t $conf{filtering}{dup_sigma_threshold} = 2;\n+\t}\n+\tif (!defined($conf{filtering}{singleton_sigma_threshold})) {\n+\t $conf{filtering}{singleton_sigma_threshold} = 4;\n+\t}\n+\t\n+\tif (!defined($conf{filtering}{nb_pairs_order_threshold})) {\n+\t $conf{filtering}{nb_pairs_order_threshold} = 1;\n+\t}\n+\t\n+\tif (!defined($conf{filtering}{final_score_threshold})) {\n+\t $conf{filtering}{final_score_threshold} = 0.8;\n+\t}\n+\t\n+\tif ($conf{filtering}{nb_pairs_order_threshold}>$conf{filtering}{nb_pairs_threshold}) {\n+\t die("Error Config : Parameter \\"nb_pairs_order_threshold\\" should not exceed \\"nb_pairs_threshold\\"\\n");\n+\t}\n+\t\n+ }\n+ \n+ if($list_prgs=~/2circos$/){\n+\tforeach my $p (@circos_params) {\n+\t next if($list_prgs=~/^ratio/ && $p eq "colorcode");\n+\t die("Error Config : The circos parameter \\"$p\\" is not defined\\n") if (!defined $conf{circos}{$p});\n+\t}\n+ }\n+ \n+ if($list_prgs=~/2bed$/){\n+\tforeach my $p (@bed_params) {\n+\t die("Error Config : The bed parameter \\"$p\\" is not defined\\n") if (!defined $conf{bed}{$p});\n+\t}\n+ }\n+ \n+ if($list_prgs=~/links2compare/){\n+\tforeach my $p (@compare_params) {\n+\t die("Error Config : The compare parameter \\"$p\\" is not defined\\n") if (!defined $conf{compare}{$p});\n+\t}\n+\t\n+\tunless (defined($conf{compare}{same_sv_type})) {\n+\t $conf{compare}{same_sv_type} = 0;\n+\t}\n+\t\n+\tunless (defined($conf{compare}{min_overlap})) {\n+\t $conf{compare}{min_overlap} = 1E-9;\n+\t}\n+\t\n+\tif($conf{compare}{circos_output}){\n+\t foreach my $p (@circos_params) {\n+\t\tnext if($list_prgs=~/^ratio/ && $p eq "colorcode");\n+\t\tdie("Error Config : The circos parameter \\"$p\\" is not defined\\n") if (!defined $conf{circos}{$p});\n+\t }\n+\t}\n+\tif($conf{compare}{bed_output}){\n+\t foreach my $p (@bed_params) {\n+\t\tdie("Error Config : The bed parameter \\"$p\\" is not defined\\n") if (!defined $conf{bed}{$p});\n+\t }\n+\t die("Error Config : The compare parameter \\"list_read_lengths\\" is not defined\\n") if (!defined $conf{compare}{list_read_lengths});\n+\n+\t my @samples=split(",",$conf{compare}{list_samples});\n+\t my @read_lengths=split(",",$conf{compare}{list_read_lengths});\n+\t for my $i (0..$#samples){\n+\t\tmy @l=split("-",$read_lengths[$i]);\n+\t\t$conf{compare}{read_lengths}{$samples[$i]}={ 1=> $l[0], 2=> $l[1]};\n+\t }\n+\t}\n+ }\n+ \n+ \n+}\n+#------------------------------------------------------------------------------#\n+#::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::#\n' |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/svdetect/SVDetect_run_parallel.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/svdetect/SVDetect_run_parallel.xml Thu Oct 03 10:42:15 2019 -0400 |
| b |
| b'@@ -0,0 +1,324 @@\n+<tool id="svdetect_run_parallel" name="Detect clusters of anomalously mapped pairs">\n+\n+<description>and identify structural variants</description>\n+\n+<command interpreter="perl">SVDetect_run_parallel.pl\n+\n+#if $getLinks.linking == "linking"\n+linking\n+<!-- -out1 \'$links_file\' -->\n+#end if\n+#if $getFilteredLinks.filtering == "filtering"\n+filtering\n+<!--- out2 \'$flinks_file\' -->\n+#if str($getFilteredLinks.links2SV) == "create"\n+links2SV\n+-out3 \'$sv_file\'\n+#end if\n+#if $getFilteredLinks.file_conversion.file_conversion_select=="convert" and str($getFilteredLinks.file_conversion.links2circos) == "create"\n+links2circos\n+-out4 \'$circos_file\'\n+#end if\n+#if $getFilteredLinks.file_conversion.file_conversion_select=="convert" and str($getFilteredLinks.file_conversion.links2bed) == "create"\n+links2bed\n+-out5 \'$bed_file\'\n+#end if\n+#end if\n+-conf \'$config_file\'\n+-l \'$log_file\'\n+-N \'$sample_name\'\n+\n+</command>\n+\n+<inputs>\n+\t<param name="sample_name" type="text" value="sample" label="Sample Name"/>\n+\t<param name="mates_file" format="bam" type="data" label="Input BAM file (.ab.bam)"/>\n+ \t<param name="cmap_file" format="len" type="data" label="Chromosomes list file (.len)" help="Tabulated file format with Chromosome ID (integer from 1), name and length"/>\n+ \t<param name="mates_orientation" type="select" format="txt" label="Type of sequencing technology and libraries">\n+\t\t<option value="FR">Illumina paired-ends</option>\n+\t\t<option value="RF">Illumina mate-pairs</option>\n+\t\t<option value="FR">SOLiD paired-ends</option>\n+\t\t<option value="RR">SOLiD mate-pairs</option>\n+ \t</param>\n+\t<param name="read1_length" type="integer" size="10" value="50" label="Read 1 length (bp)" help="Length of the first read in a pair (left read)"/>\n+\t<param name="read2_length" type="integer" size="10" value="50" label="Read 2 length (bp)" help="Length of the second read in a pair (right read)"/>\n+\t<param name="sv_type" type="select" format="txt" label="Type of SV to detect">\n+\t\t<option value="all">all types of SVs</option>\n+\t\t<option value="intra">intrachromosomal SVs only</option>\n+\t\t<option value="inter">interchromosomal SVs only</option>\n+ \t</param>\n+ \t\n+ \t<conditional name="getLinks">\n+ \t\t<param name="linking" type="select" label="Linking procedure" help="Detection and isolation of links">\n+\t\t\t<option value="linking">Yes</option>\n+\t\t\t<option value="">No, already done</option>\n+ \t\t</param>\n+\t\t<when value="">\n+ \t\t\t<!-- do nothing here -->\n+ \t\t</when>\n+ \t\t<when value="linking">\n+\t\t\t<param name="splitmate" label="Do you want to split the original mate file per chromosome for parallel computing?" type="boolean" truevalue="split" falsevalue="do_not_split" checked="True" help="Untick it if already done"/>\n+ \t\t\t<param name="window_size" type="integer" size="20" value="3000" label="Window size (bp)" help="Equal to at least \xe2\x80\x9c2\xc2\xb5+2\xe2\x88\x9a2\xcf\x83"/>\n+\t\t\t<param name="step_length" type="integer" size="20" value="250" label="Step length size (bp)" help="Equal to 1/2 or 1/4 of the window size"/>\n+ \t\t</when>\n+ \t</conditional>\n+\n+ \t<conditional name="getFilteredLinks">\n+\t \t<param name="filtering" type="select" label="Filtering procedure" help="Filtering of links according different parameters and thresholds">\n+\t\t\t<option value="filtering">Yes</option>\n+ <option value="">No</option>\n+\t \t</param>\n+\t\t<when value="">\n+\t \t\t<!-- do nothing here -->\n+\t \t</when>\n+\t \t<when value="filtering">\n+\t\t\t\n+\t\t\t<param name="splitlink" label="Do you want to split the original link file per chromosome for parallel computing?" type="boolean" truevalue="split" falsevalue="do_not_split" checked="False" help="Untick it if (the linking is) already done"/>\n+\t\t\t<param name="chromosomes" type="text" size="20" label="List of chromosome names to keep or exclude"/>\n+\t\t\t<param name="nb_pairs_threshold" type="integer" size="20" value="5" label="Minimum number of pairs in a cluster"/>\n+\t\t\n+\t\t\t<conditional name="filter1">\n+\t \t\t\t<param name='..b'">\n+<general>\n+input_format = bam\n+sv_type = ${sv_type}\n+mates_orientation=${mates_orientation}\n+read1_length=${read1_length}\n+read2_length=${read2_length}\n+mates_file=${mates_file}\n+cmap_file=${cmap_file}\n+tmp_dir=$__new_file_path__/svdetect/tmp\n+output_dir=$__new_file_path__/svdetect\n+num_threads=8\n+</general> \n+\n+#if $getLinks.linking == "linking"\n+<detection>\n+#if str($getLinks.splitmate) == "split"\n+split_mate_file=1\n+#else\n+split_mate_file=0\n+#end if\n+window_size=${getLinks.window_size}\n+step_length=${getLinks.step_length}\n+</detection> \n+#end if\n+\n+#if $getFilteredLinks.filtering == "filtering"\n+<filtering>\n+#if str($getFilteredLinks.splitlink) == "split"\n+split_link_file=1\n+#else\n+split_link_file=0\n+#end if\n+#if str($getFilteredLinks.chromosomes) != ""\n+chromosomes=${getFilteredLinks.chromosomes}\n+#end if\n+nb_pairs_threshold=${getFilteredLinks.nb_pairs_threshold}\n+#if $getFilteredLinks.filter1.strand_filtering == "strand"\n+strand_filtering=1\n+final_score_threshold=${getFilteredLinks.filter1.final_score_threshold}\n+#if $getFilteredLinks.filter1.filter2.order_filtering == "order"\n+order_filtering=1\n+mu_length=${getFilteredLinks.filter1.filter2.mu_length}\n+sigma_length=${getFilteredLinks.filter1.filter2.sigma_length}\n+nb_pairs_order_threshold=${getFilteredLinks.filter1.filter2.nb_pairs_order_threshold}\n+#if $getFilteredLinks.filter1.filter2.filter3.insert_size_filtering == "insert"\n+insert_size_filtering=1\n+indel_sigma_threshold=${getFilteredLinks.filter1.filter2.filter3.indel_sigma_threshold}\n+dup_sigma_threshold=${getFilteredLinks.filter1.filter2.filter3.dup_sigma_threshold}\n+singleton_sigma_threshold=${getFilteredLinks.filter1.filter2.filter3.singleton_sigma_threshold}\n+#else\n+insert_size_filtering=0\n+#end if\n+#else\n+order_filtering=0\n+#end if\n+#else\n+strand_filtering=0\n+#end if\n+</filtering> \n+#end if\n+\n+#if $getFilteredLinks.filtering == "filtering"\n+#if $getFilteredLinks.file_conversion.file_conversion_select == "convert"\n+#if str($getFilteredLinks.file_conversion.links2circos) == "create"\n+<circos>\n+organism_id=${getFilteredLinks.file_conversion.organism_id}\n+<colorcode>\n+#for $color_repeat in $getFilteredLinks.file_conversion.color_code\n+${color_repeat.color}=${color_repeat.interval}\n+#end for\n+</colorcode>\n+</circos>\n+#end if\n+#if str($getFilteredLinks.file_conversion.links2bed) == "create"\n+<bed>\n+<colorcode>\n+#for $color_repeat in $getFilteredLinks.file_conversion.color_code\n+#if str($color_repeat.color)== "grey"\n+190,190,190=${color_repeat.interval}\n+#end if\n+#if str($color_repeat.color)== "black"\n+0,0,0=${color_repeat.interval}\n+#end if\n+#if str($color_repeat.color)== "blue"\n+0,0,255=${color_repeat.interval}\n+#end if\n+#if str($color_repeat.color)== "green"\n+0,255,0=${color_repeat.interval}\n+#end if\n+#if str($color_repeat.color)== "purple"\n+153,50,205=${color_repeat.interval}\n+#end if\n+#if str($color_repeat.color)== "orange"\n+255,140,0=${color_repeat.interval}\n+#end if\n+#if str($color_repeat.color)== "red"\n+255,0,0=${color_repeat.interval}\n+#end if\n+#end for\n+</colorcode>\n+</bed>\n+#end if\n+#end if\n+#end if\t\n+\t</configfile>\n+</configfiles>\n+\n+ <help>\n+**What it does**\n+\n+SVDetect - Version : 0.8b\n+\n+Parallel version (nCPU=8)\n+\n+SVDetect is a application for the isolation and the type prediction of intra- and inter-chromosomal rearrangements from paired-end/mate-pair sequencing data provided by the high-throughput sequencing technologies\n+\n+This tool aims to identifying structural variations (SVs) with both clustering and sliding-window strategies, and helping in their visualization at the genome scale.\n+SVDetect is compatible with SOLiD and Illumina (>=1.3) reads.\n+\n+Manual documentation available at the http://svdetect.sourceforge.net/Site/Manual.html\n+\n+-----\n+\n+.. class:: infomark\n+\n+Contact Bruno Zeitouni (svdetect@curie.fr) for any questions or concerns about the Galaxy implementation of SVDetect.\n+\n+ </help>\n+\n+</tool>\n' |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/svdetect/circos_graph.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/svdetect/circos_graph.xml Thu Oct 03 10:42:15 2019 -0400 |
| b |
| @@ -0,0 +1,290 @@ +<tool id="circos_graph" name="Circos" version="1.1.0"> + +<description>plots</description> + +<command interpreter="perl">circos/bin/circos + +-conf '$circos_config_file' +-outputfile '${outputfile}.dat' +-png + +> '$log_file' + +; + +rm '$outputfile'; ln -s '${outputfile}.png' '$outputfile' + +</command> + + +<inputs> + <param name="graph_name" type="text" size="20" value="graph1" label="Graph name"/> + + <param name="karyotype" type="select" format="txt" label="Type of model organism"> + <option value="data/karyotype.human_hg19.txt">Human (homo sapiens, hs) -hg19-</option> + <option value="data/karyotype.human.txt">Human (homo sapiens, hs) -hg18-</option> + <option value="data/2/karyotype.mouse.txt">Mouse (Mus Musculus, mm)</option> + <option value="data/2/karyotype.dog.txt">Dog (Canis familiaris, cf)</option> + <option value="data/2/karyotype.rt.txt">Rat (Rattus norvegicus, rn)</option> + <option value="data/karyotype.yeast.txt">Yeast (Saccharomyces Cerevisiae, sc) -SGD-</option> + + </param> + <param name="chromosomes_units" type="integer" size="50" value="1000000" label="Chromosomes units"/> + <param name="chromosomes" type="text" size="100" value="" label="List of chromosome names to keep or exclude" help="ex: hs2;hs3 or -hsX;-hsY"> + <sanitizer> + <valid initial="string.printable"> + <add value=";"/> + </valid> + </sanitizer> + </param> + <param name="link_file" format="segdup" type="data" label="Input link file (.segdup)"/> +</inputs> + +<outputs> + <data format="txt" name="log_file" label="${graph_name}.circos.log"/> + <data format="png" name="outputfile" label="${graph_name}.png"/> +</outputs> + + + +<configfiles> + <configfile name="ideogram_config_file"> + +<ideogram> + +<spacing> + +default = 5u +break = 1u + +axis_break_at_edge = yes +axis_break = yes +axis_break_style = 2 + +<break_style 1> +stroke_color = black +fill_color = blue +thickness = 0.25r +stroke_thickness = 2 +</break> + +<break_style 2> +stroke_color = black +stroke_thickness = 3p +thickness = 1.5r +</break> + +</spacing> + +## thickness (px) of chromosome ideogram +thickness = 100p +stroke_thickness = 2 +## ideogram border color +stroke_color = black +fill = yes +## the default chromosome color is set here and any value +## defined in the karyotype file overrides it +fill_color = black + +## fractional radius position of chromosome ideogram within image +radius = 0.85r +show_label = yes +label_with_tag = yes +label_font = condensedbold +label_radius = dims(ideogram,radius) + 0.075r +label_size = 60p + +## cytogenetic bands +band_stroke_thickness = 2 + +## show_bands determines whether the outline of cytogenetic bands +## will be seen +show_bands = yes +## in order to fill the bands with the color defined in the karyotype +## file you must set fill_bands +fill_bands = yes + +</ideogram> + + </configfile> + + <configfile name="ticks_config_file"> + +show_ticks = yes +show_tick_labels = yes + +<ticks> +radius = dims(ideogram,radius_outer) +multiplier = 1e-6 + +<tick> +spacing = 0.5u +size = 2p +thickness = 2p +color = grey +show_label = no +label_size = 12p +label_offset = 0p +format = %.2f +</tick> + +<tick> +spacing = 1u +size = 3p +thickness = 2p +color = dgrey +show_label = no +label_size = 12p +label_offset = 0p +format = %.2f +</tick> + +<tick> +spacing = 5u +size = 5p +thickness = 2p +color = black +show_label = yes +label_size = 16p +label_offset = 0p +format = %d +</tick> + +<tick> +spacing = 10u +size = 8p +thickness = 2p +color = black +show_label = yes +label_size = 20p +label_offset = 5p +format = %d +</tick> +</ticks> + </configfile> + + + <configfile name="circos_config_file"> +<colors> +<<include etc/colors.conf>> +</colors> + +<fonts> +<<include etc/fonts.conf>> +</fonts> + +<<include $ideogram_config_file>> +<<include $ticks_config_file>> + +karyotype = $karyotype + +<image> +24bit = yes +##png = yes +##svg = no +## radius of inscribed circle in image +radius = 1500p +background = white +## by default angle=0 is at 3 o'clock position +angle_offset = -90 +#angle_orientation = counterclockwise + +auto_alpha_colors = yes +auto_alpha_steps = 5 +</image> + +chromosomes_units= $chromosomes_units + +#if str($chromosomes)=="" +chromosomes_display_default = yes +#else +chromosomes_display_default = no +chromosomes = $chromosomes +#end if + +<links> + +z = 0 +radius = 0.95r +bezier_radius = 0.2r + +<link segdup> +show = yes +color = dgrey_a5 +thickness = 2 +file = $link_file +record_limit = 1000 +</link> + +</links> + + +anglestep = 0.5 +minslicestep = 10 +beziersamples = 40 +debug = no +warnings = no +imagemap = no + +units_ok = bupr +units_nounit = n + </configfile> +</configfiles> + + <help> +**What it does** + +Circos + +Manual documentation available at the http://circos.ca/ + + +**Example of link segdup file** + +segdup file:: + + 1 hs1 1077096 1078746 color=red + 1 hs1 1080923 1082805 color=red + 2 hs1 1137684 1137961 color=red + 2 hs3 1138138 1138423 color=red + 3 hs11 1169417 1170000 color=red + 3 hs11 1170025 1170975 color=red + 4 hs11 1222480 1224271 color=green + 4 hs11 1223328 1225675 color=green + 5 hs12 1223336 1225812 color=grey + 5 hs13 1224709 1227633 color=grey + 6 hs11 1223621 1226460 color=red + 6 hs11 1224918 1227633 color=red + 7 hs11 1399510 1401513 color=white + 7 hs11 1401628 1403697 color=white + 8 hs15 1652045 1653746 color=red + 8 hs15 1657167 1658940 color=red + 9 hs11 165333 165887 color=white + 9 hs11 165981 168016 color=white + 10 hs11 1702700 1702841 color=red + 10 hs11 1702903 1703057 color=red + 11 hs11 1912272 1915186 color=white + 11 hs11 1937111 1939824 color=white + 12 hs11 1983211 1983355 color=red + 12 hs11 1983591 1983748 color=red + 13 hs11 2913657 2913898 color=white + 13 hs11 2914048 2914341 color=white + 14 hs11 3090593 3090749 color=purple + 14 hs11 3090709 3090864 color=purple + 15 hs21 3466365 3466434 color=red + 15 hs21 3466554 3466620 color=red + 16 hsX 3603073 3603321 color=white + 16 hsX 3603295 3603520 color=white + + + +----- + +.. class:: infomark + +Contact Bruno Zeitouni (svdetect@curie.fr) for any questions or concerns about the Galaxy implementation of Circos. + + + </help> + +</tool> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/varscan/tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/varscan/tool_dependencies.xml Thu Oct 03 10:42:15 2019 -0400 |
| b |
| @@ -0,0 +1,19 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="VarScan" version="2.3.5"> + <install version="1.0"> + <actions> + <action type="download_by_url">http://downloads.sourceforge.net/project/varscan/VarScan.v2.3.5.jar</action> + <action type="move_file"> + <source>VarScan.v2.3.5.jar</source> + <destination>$INSTALL_DIR/jars</destination> + </action> + <action type="set_environment"> + <environment_variable name="JAVA_JAR_PATH" action="set_to">$INSTALL_DIR/jars</environment_variable> + </action> + </actions> + </install> + <readme> + </readme> + </package> +</tool_dependency> |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/varscan/varscan_mpileup.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/varscan/varscan_mpileup.pl Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,116 @@ +#!/usr/bin/perl + +use strict; +use Cwd; + +die qq( +Bad numbr of inputs + +) if(!@ARGV); + +my $options =""; +my $file=""; +my $command=""; +my $output=""; +my $working_dir = cwd(); +my $temp_vcf = "$working_dir/temp"; +my $log=""; + +foreach my $input (@ARGV) +{ + my @tmp = split "::", $input; + if($tmp[0] eq "COMMAND") + { + $command = $tmp[1]; + } + elsif($tmp[0] eq "INPUT") + { + $file = $tmp[1]; + } + elsif($tmp[0] eq "OPTION") + { + $options = "$options ${tmp[1]}"; + } + elsif($tmp[0] eq "OUTPUT") + { + $output = $tmp[1]; + } + elsif($tmp[0] eq "LOG") + { + $log = $tmp[1]; + } + else + { + die("Unknown Input: $input\n"); + } +} + +system ("$command $file $options 1>$temp_vcf 2>$log"); + +vs2vcf($temp_vcf, $output); + + +sub vs2vcf +{ + + # + # G l o b a l v a r i a b l e s + # + my $version = '0.1'; + + # + # Read in file + # + my $input = shift; + my $output = shift; + my $chr_ord = shift; + open(IN, $input) or die "Can't open $input': $!\n"; + open(OUT, ">$output") or die "Can't create $output': $!\n"; + my %output; + + while ( <IN> ) + { + if ( /^#/ ) + { + print OUT; + next; + } + chomp; + my $line = $_; + + my @flds = split ( "\t", $line ); + my $ref = $flds[3]; + my $alt = $flds[4]; + # + # Deletion of bases + # + if ( $alt =~ /^\-/ ) + { + ($flds[3], $flds[4]) = ($ref.substr($alt,1), $ref); + } + + # + # Insertion of bases + # + if ( $alt =~ /^\+/ ) + { + $flds[4] = $ref.substr($alt,1); + } + print OUT join( "\t", @flds),"\n" unless defined $chr_ord; + $output{$flds[0]}{$flds[1]} = join( "\t", @flds)."\n" if defined $chr_ord; + } + close(IN); + # if chromosome order given return in sorted order + if(defined $chr_ord) + { + for my $chrom (@{ $chr_ord }) + { + for my $pos (sort {$a<=>$b} keys %{ $output{$chrom} }) + { + print OUT $output{$chrom}{$pos}; + } + } + } + close(OUT); +} + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/varscan/varscan_mpileup.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/varscan/varscan_mpileup.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,124 @@ +<tool id="varscan_mpileup" name="VarScan mpileup" version="2.3.5"> + <description> + mutation caller for targeted, exome, and whole-genome resequencing + </description> + <requirements> + <requirement type="package" version="2.3.5">VarScan</requirement> + </requirements> + <command interpreter="perl"> + + varscan_mpileup.pl + "COMMAND::java -jar \$JAVA_JAR_PATH/VarScan.v2.3.5.jar $exe_command" + "INPUT::$in_file" + "OUTPUT::$output" + "LOG::$log" + "OPTION::--min-coverage $min_coverage" + "OPTION::--min-reads2 $min_reads2" + "OPTION::--min-avg-qual $min_avg_qual" + "OPTION::--min-var-freq $min_var_freq" + "OPTION::--min-freq-for-hom $min_freq_for_hom" + "OPTION::--p-value $p_value" + "OPTION::--strand-filter $strand_filter" + "OPTION::--output-vcf 1" + + #if ($vcf_sample_list): + "OPTION::--vcf-sample-list $vcf_sample_list" + #end if + "OPTION::--variants $variants" + + + + </command> + + <inputs> + + <param name="exe_command" type="select" label="Command" help="" optional="false"> + <option value="mpileup2snp" >mpileup2snp</option> + <option value="mpileup2indel">mpileup2indel</option> + <option value="mpileup2cns">mpileup2cns</option> + </param> + <param name="in_file" type="data" format="pileup" label="mpileup file" help="The SAMtools mpileup file" /> + <param name="min_coverage" type="integer" label="min-coverage" help="" optional="true" value="8"/> + <param name="min_reads2" type="integer" label="min-reads2" help="" optional="true" value="2"/> + <param name="min_avg_qual" type="integer" label="min-avg-qual" help="" optional="true" value="15"/> + <param name="min_var_freq" type="float" label="min-var-freq" help="" optional="true" value="0.01"/> + <param name="min_freq_for_hom" type="float" label="min-freq-for-hom" help="" optional="true" value="0.75"/> + <param name="p_value" type="text" label="p-value" help="" optional="true" value="0.99"/> + <param name="strand_filter" type="integer" label="strand-filter" help="" optional="true" value="1"/> + <param name="vcf_sample_list" type="data" label="vcf-sample-list" format="txt" help="" optional="true" /> + <param name="variants" type="integer" label="variants" help="Set to 1 to report only variants" optional="true" value="1"/> + + + </inputs> + <outputs> + <data type="data" format="vcf" name="output" label="${tool.name} result on ${on_string}"/> + <data type="data" format="txt" name="log" label="${tool.name} result on ${on_string} (log) "/> + </outputs> + + <help> + +.. class:: infomark + +**What it does** + +:: + + VarScan is a platform-independent mutation caller for targeted, exome, and whole-genome resequencing data generated on Illumina, SOLiD, Life/PGM, Roche/454, and similar instruments. The newest version, VarScan 2, is written in Java, so it runs on most operating systems. It can be used to detect different types of variation: + + Germline variants (SNPs an dindels) in individual samples or pools of samples. + Multi-sample variants (shared or private) in multi-sample datasets (with mpileup). + Somatic mutations, LOH events, and germline variants in tumor-normal pairs. + Somatic copy number alterations (CNAs) in tumor-normal exome data. + + +**Input** + +:: + + mpileup file - The SAMtools mpileup file + + +**Parameters** + +:: + + commands + mpileup2snp Identify SNPs from an mpileup file + mpileup2indel Identify indels an mpileup file + mpileup2cns Call consensus and variants from an mpileup file + + min-coverage + Minimum read depth at a position to make a call [8] + + min-reads2 + Minimum supporting reads at a position to call variants [2] + + min-avg-qual + Minimum base quality at a position to count a read [15] + + min-var-freq + Minimum variant allele frequency threshold [0.01] + + min-freq-for-hom + Minimum frequency to call homozygote [0.75] + + p-value + Default p-value threshold for calling variants [99e-02] + + strand-filter + Ignore variants with >90% support on one strand [1] + + output-vcf + If set to 1, outputs in VCF format + + vcf-sample-list + For VCF output, a list of sample names in order, one per line + + variants + Report only variant (SNP/indel) positions [0] + + + + </help> +</tool> + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/varscan/varscan_somatic.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/varscan/varscan_somatic.pl Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,138 @@ +#!/usr/bin/perl + + +use strict; +use Cwd; + +die qq( +Bad numbr of inputs + +) if(!@ARGV); + +my $options =""; +my $normal=""; +my $command=""; +my $tumor=""; +my $output=""; +my $working_dir = cwd(); +my $snp = "$working_dir/output.snp.vcf"; +my $indels = "$working_dir/output.indel.vcf"; + +foreach my $input (@ARGV) +{ + my @tmp = split "::", $input; + if($tmp[0] eq "COMMAND") + { + $command = $tmp[1]; + } + if($tmp[0] eq "NORMAL") + { + $normal = $tmp[1]; + } + elsif($tmp[0] eq "TUMOR") + { + $tumor = $tmp[1]; + } + elsif($tmp[0] eq "OPTION") + { + $options = "$options ${tmp[1]}"; + } + elsif($tmp[0] eq "OUTPUT") + { + $output = $tmp[1]; + } + + else + { + die("Unknown Input: $input\n"); + } +} + +system ("$command $normal $tumor $options "); +system("grep -v '^\#' $indels | grep -v '^chrom position' >> $snp"); + +my @chr_ord = chromosome_order($tumor); + +vs2vcf($snp, $output,\@chr_ord); + + +sub vs2vcf +{ + + # + # G l o b a l v a r i a b l e s + # + my $version = '0.1'; + + # + # Read in file + # + my $input = shift; + my $output = shift; + my $chr_ord = shift; + open(IN, $input) or die "Can't open $input': $!\n"; + open(OUT, ">$output") or die "Can't create $output': $!\n"; + my %output; + + while ( <IN> ) + { + if ( /^#/ ) + { + print OUT; + next; + } + chomp; + my $line = $_; + + my @flds = split ( "\t", $line ); + my $ref = $flds[3]; + my $alt = $flds[4]; + # + # Deletion of bases + # + if ( $alt =~ /^\-/ ) + { + ($flds[3], $flds[4]) = ($ref.substr($alt,1), $ref); + } + + # + # Insertion of bases + # + if ( $alt =~ /^\+/ ) + { + $flds[4] = $ref.substr($alt,1); + } + print OUT join( "\t", @flds),"\n" unless defined $chr_ord; + $output{$flds[0]}{$flds[1]} = join( "\t", @flds)."\n" if defined $chr_ord; + } + close(IN); + # if chromosome order given return in sorted order + if(defined $chr_ord) + { + for my $chrom (@{ $chr_ord }) + { + for my $pos (sort {$a<=>$b} keys %{ $output{$chrom} }) + { + print OUT $output{$chrom}{$pos}; + } + } + } + close(OUT); +} + + +sub chromosome_order +{ + my $input = shift; + # calculate flagstats + my $COMM = "samtools view -H $input | grep '^\@SQ'"; + my @SQ = `$COMM`; + chomp @SQ; + for(my $i = 0; $i <= $#SQ; $i++) + { + $SQ[$i] =~ s/^\@SQ\tSN:(.*?)\tLN:\d+$/$1/; + } + return(@SQ); +} + + |
| b |
| diff -r 2c7824a8d764 -r 0d10255b5434 ngsap-vc/varscan/varscan_somatic.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ngsap-vc/varscan/varscan_somatic.xml Thu Oct 03 10:42:15 2019 -0400 |
| [ |
| @@ -0,0 +1,131 @@ +<tool id="varscan_somatic" name="VarScan Somatic" version="2.3.5"> + <description> + somatic mutation caller for cancer genomics + </description> + <requirements> + <requirement type="package" version="2.3.5">VarScan</requirement> + </requirements> + <command interpreter="perl"> + varscan_somatic.pl + "COMMAND::java -jar \$JAVA_JAR_PATH/VarScan.v2.3.5.jar somatic" + "NORMAL::$normal" + "TUMOR::$tumor" + "OUTPUT::$output" + + "OPTION::--min-coverage $min_coverage" + "OPTION::--min-coverage-normal $min_coverage_normal" + "OPTION::--min-coverage-tumor $min_coverage_tumor" + + "OPTION::--min-var-freq $min_var_freq" + "OPTION::--min-freq-for-hom $min_freq_for_hom" + + "OPTION::--normal-purity $normal_purity" + "OPTION::--tumor-purity $tumor_purity" + + "OPTION::--p-value $p_value" + "OPTION::--somatic-p-value $somatic_p_value" + + "OPTION::--strand-filter $strand_filter" + "OPTION::--validation $validation" + "OPTION::--output-vcf 1" + + + + </command> + + <inputs> + + <param name="normal" type="data" format="pileup" label="normal mpileup file" help="The SAMtools mpileup file for normal sample" /> + <param name="tumor" type="data" format="pileup" label="tumor mpileup file" help="The SAMtools mpileup file for tumor sample" /> + + <param name="min_coverage" type="integer" label="min-coverage" help="" optional="true" value="8"/> + <param name="min_coverage_normal" type="integer" label="min-coverage-normal" help="" optional="true" value="8"/> + <param name="min_coverage_tumor" type="integer" label="min-coverage-tumor" help="" optional="true" value="6"/> + + <param name="min_var_freq" type="float" label="min-var-freq" help="" optional="true" value="0.10"/> + <param name="min_freq_for_hom" type="float" label="min-freq-for-hom" help="" optional="true" value="0.75"/> + + <param name="normal_purity" type="float" label="normal-purity" help="" optional="true" value="1.00"/> + <param name="tumor_purity" type="float" label="tumor-purity" help="" optional="true" value="1.00"/> + + + <param name="p_value" type="text" label="p-value" help="" optional="true" value="0.99"/> + <param name="somatic_p_value" type="text" label="somatic-p-value" help="" optional="true" value="0.05"/> + + <param name="strand_filter" type="integer" label="strand-filter" help="" optional="true" value="1"/> + <param name="validation" type="integer" label="validation" help="" optional="true" value="0"/> + + </inputs> + <outputs> + <data type="data" format="vcf" name="output" label="${tool.name} result on ${on_string}"/> + </outputs> + + <help> + +.. class:: infomark + +**What it does** + +:: + + VarScan is a platform-independent mutation caller for targeted, exome, and whole-genome resequencing data generated on Illumina, SOLiD, Life/PGM, Roche/454, and similar instruments. The newest version, VarScan 2, is written in Java, so it runs on most operating systems. It can be used to detect different types of variation: + + Germline variants (SNPs an dindels) in individual samples or pools of samples. + Multi-sample variants (shared or private) in multi-sample datasets (with mpileup). + Somatic mutations, LOH events, and germline variants in tumor-normal pairs. + Somatic copy number alterations (CNAs) in tumor-normal exome data. + + +**Input** + +:: + + mpileup normal file - The SAMtools mpileup file for normal + mpileup tumor file - The SAMtools mpileup file for tumor + + +**Parameters** + +:: + + min-coverage + Minimum read depth at a position to make a call [8] + + min-coverage-normal + Minimum coverage in normal to call somatic [8] + + min-coverage-tumor + Minimum coverage in tumor to call somatic [6] + + min-var-freq + Minimum variant frequency to call a heterozygote [0.10] + + min-freq-for-hom + Minimum frequency to call homozygote [0.75] + + normal-purity + Estimated purity (non-tumor content) of normal sample [1.00] + + tumor-purity + Estimated purity (tumor content) of tumor sample [1.00] + + p-value + Default p-value threshold for calling variants [0.99] + + somatic-p-value + P-value threshold to call a somatic site [0.05] + + strand-filter + If set to 1, removes variants with >90% strand bias + + validation + If set to 1, outputs all compared positions even if non-variant + + output-vcf + If set to 1, outputs in VCF format [Default] + + + + </help> +</tool> + |