Create GATK wrapper which includes a workflow for each WDL

scripts/wrappers/gatk/GATKToolWorkflows_3.6/ASEReadCounter_3.6.wdl

@@ -0,0 +1,72 @@
+# --------------------------------------------------------------------------------------------
+# This ASEReadCounter WDL task was generated on 10/04/16 for use with GATK version 3.6
+# For more information on using this wrapper, please see the WDL repository at 
+# https://github.com/broadinstitute/wdl/tree/develop/scripts/wrappers/gatk/README.md
+# Task Summary: Calculate read counts per allele for allele-specific expression analysis
+# --------------------------------------------------------------------------------------------
+
+task ASEReadCounter { 
+	File gatk
+	File ref
+	File refIndex
+	File refDict
+	String ? userString #If a parameter you'd like to use is missing from this task, use this term to add your own string
+	Array[String] input_file
+	Array[String] ? intervals
+	String unsafe
+	String ? countOverlapReadsType
+	String ? minBaseQuality
+	Int ? minDepthOfNonFilteredBase
+	Int ? minMappingQuality
+	String ? out
+	String ? outputFormat
+	String sitesVCFFile
+
+	command {
+		java -jar ${gatk} \
+			-T ASEReadCounter \
+			-R ${ref} \
+			--input_file ${input_file} \
+			${default="" "--intervals " + intervals} \
+			--unsafe ${unsafe} \
+			-overlap ${default="COUNT_FRAGMENTS_REQUIRE_SAME_BASE" countOverlapReadsType} \
+			-mbq ${default="0" minBaseQuality} \
+			-minDepth ${default="-1" minDepthOfNonFilteredBase} \
+			-mmq ${default="0" minMappingQuality} \
+			-o ${default="stdout" out} \
+			outputFormat ${default="RTABLE" outputFormat} \
+			-sites ${sitesVCFFile} \
+			${default="\n" userString} 
+	}
+
+	output {
+		#To track additional outputs from your task, please manually add them below
+		String taskOut = "${out}"
+	}
+
+	runtime {
+		docker: "broadinstitute/genomes-in-the-cloud:2.2.2-1466113830"
+	}
+
+	parameter_meta {
+		gatk: "Executable jar for the GenomeAnalysisTK"
+		ref: "fasta file of reference genome"
+		refIndex: "Index file of reference genome"
+		refDict: "dict file of reference genome"
+		userString: "An optional parameter which allows the user to specify additions to the command line at run time"
+		countOverlapReadsType: "Handling of overlapping reads from the same fragment"
+		minBaseQuality: "Minimum base quality"
+		minDepthOfNonFilteredBase: "Minimum number of bases that pass filters"
+		minMappingQuality: "Minimum read mapping quality"
+		out: "An output file created by the walker.  Will overwrite contents if file exists"
+		outputFormat: "Format of the output file, can be CSV, TABLE, RTABLE"
+		sitesVCFFile: "Undocumented option"
+		input_file: "Input file containing sequence data (BAM or CRAM)"
+		intervals: "One or more genomic intervals over which to operate"
+		unsafe: "Enable unsafe operations: nothing will be checked at runtime"
+	}
+}
+
+workflow ASEReadCounterWf { 
+	call ASEReadCounter
+}

scripts/wrappers/gatk/GATKToolWorkflows_3.6/AnalyzeCovariates_3.6.wdl

@@ -0,0 +1,60 @@
+# --------------------------------------------------------------------------------------------
+# This AnalyzeCovariates WDL task was generated on 10/04/16 for use with GATK version 3.6
+# For more information on using this wrapper, please see the WDL repository at 
+# https://github.com/broadinstitute/wdl/tree/develop/scripts/wrappers/gatk/README.md
+# Task Summary: Create plots to visualize base recalibration results
+# --------------------------------------------------------------------------------------------
+
+task AnalyzeCovariates { 
+	File gatk
+	File ref
+	File refIndex
+	File refDict
+	String ? userString #If a parameter you'd like to use is missing from this task, use this term to add your own string
+	File ? BQSR
+	File ? afterReportFile
+	File ? beforeReportFile
+	Boolean ? ignoreLastModificationTimes
+	File ? intermediateCsvFile
+	File ? plotsReportFile
+
+	command {
+		java -jar ${gatk} \
+			-T AnalyzeCovariates \
+			-R ${ref} \
+			${default="" "--BQSR " + BQSR} \
+			${default="" "-after " + afterReportFile} \
+			${default="" "-before " + beforeReportFile} \
+			-ignoreLMT ${default="false" ignoreLastModificationTimes} \
+			${default="" "-csv " + intermediateCsvFile} \
+			${default="" "-plots " + plotsReportFile} \
+			${default="\n" userString} 
+	}
+
+	output {
+		#To track additional outputs from your task, please manually add them below
+		String taskOut = "${out}"
+	}
+
+	runtime {
+		docker: "broadinstitute/genomes-in-the-cloud:2.2.2-1466113830"
+	}
+
+	parameter_meta {
+		gatk: "Executable jar for the GenomeAnalysisTK"
+		ref: "fasta file of reference genome"
+		refIndex: "Index file of reference genome"
+		refDict: "dict file of reference genome"
+		userString: "An optional parameter which allows the user to specify additions to the command line at run time"
+		afterReportFile: "file containing the BQSR second-pass report file"
+		beforeReportFile: "file containing the BQSR first-pass report file"
+		ignoreLastModificationTimes: "do not emit warning messages related to suspicious last modification time order of inputs"
+		intermediateCsvFile: "location of the csv intermediate file"
+		plotsReportFile: "location of the output report"
+		BQSR: "Input covariates table file for on-the-fly base quality score recalibration"
+	}
+}
+
+workflow AnalyzeCovariatesWf { 
+	call AnalyzeCovariates
+}

scripts/wrappers/gatk/GATKToolWorkflows_3.6/ApplyRecalibration_3.6.wdl

@@ -0,0 +1,80 @@
+# --------------------------------------------------------------------------------------------
+# This ApplyRecalibration WDL task was generated on 10/04/16 for use with GATK version 3.6
+# For more information on using this wrapper, please see the WDL repository at 
+# https://github.com/broadinstitute/wdl/tree/develop/scripts/wrappers/gatk/README.md
+# Task Summary: Apply a score cutoff to filter variants based on a recalibration table
+# --------------------------------------------------------------------------------------------
+
+task ApplyRecalibration { 
+	File gatk
+	File ref
+	File refIndex
+	File refDict
+	String ? userString #If a parameter you'd like to use is missing from this task, use this term to add your own string
+	Array[String] ? intervals
+	Int ? ntVal
+	Boolean ? excludeFiltered
+	Boolean ? ignore_all_filters
+	String ? ignore_filter
+	Array[String] task_input
+	Float ? lodCutoff
+	String ? mode
+	String ? out
+	String recal_file
+	File ? tranches_file
+	Float ? ts_filter_level
+	Boolean ? useAlleleSpecificAnnotations
+
+	command {
+		java -jar ${gatk} \
+			-T ApplyRecalibration \
+			-R ${ref} \
+			${default="" "--intervals " + intervals} \
+			${default="" "-nt" + ntVal} \
+			-ef ${default="false" excludeFiltered} \
+			-ignoreAllFilters ${default="false" ignore_all_filters} \
+			${default="" "-ignoreFilter " + ignore_filter} \
+			-input ${task_input} \
+			${default="" "-lodCutoff " + lodCutoff} \
+			-mode ${default="SNP" mode} \
+			-o ${default="stdout" out} \
+			-recalFile ${recal_file} \
+			${default="" "-tranchesFile " + tranches_file} \
+			${default="" "-ts_filter_level " + ts_filter_level} \
+			-AS ${default="false" useAlleleSpecificAnnotations} \
+			${default="\n" userString} 
+	}
+
+	output {
+		#To track additional outputs from your task, please manually add them below
+		String taskOut = "${out}"
+	}
+
+	runtime {
+		docker: "broadinstitute/genomes-in-the-cloud:2.2.2-1466113830"
+	}
+
+	parameter_meta {
+		gatk: "Executable jar for the GenomeAnalysisTK"
+		ref: "fasta file of reference genome"
+		refIndex: "Index file of reference genome"
+		refDict: "dict file of reference genome"
+		userString: "An optional parameter which allows the user to specify additions to the command line at run time"
+		excludeFiltered: "Don't output filtered loci after applying the recalibration"
+		ignore_all_filters: "If specified, the variant recalibrator will ignore all input filters. Useful to rerun the VQSR from a filtered output file."
+		ignore_filter: "If specified, the recalibration will be applied to variants marked as filtered by the specified filter name in the input VCF file"
+		task_input: "The raw input variants to be recalibrated"
+		lodCutoff: "The VQSLOD score below which to start filtering"
+		mode: "Recalibration mode to employ: 1.) SNP for recalibrating only SNPs (emitting indels untouched in the output VCF); 2.) INDEL for indels; and 3.) BOTH for recalibrating both SNPs and indels simultaneously."
+		out: "The output filtered and recalibrated VCF file in which each variant is annotated with its VQSLOD value"
+		recal_file: "The input recal file used by ApplyRecalibration"
+		tranches_file: "The input tranches file describing where to cut the data"
+		ts_filter_level: "The truth sensitivity level at which to start filtering"
+		useAlleleSpecificAnnotations: "If specified, the tool will attempt to apply a filter to each allele based on the input tranches and allele-specific .recal file."
+		intervals: "One or more genomic intervals over which to operate"
+	}
+}
+
+workflow ApplyRecalibrationWf { 
+	call ApplyRecalibration
+}

scripts/wrappers/gatk/GATKToolWorkflows_3.6/BaseRecalibrator_3.6.wdl

@@ -0,0 +1,113 @@
+# --------------------------------------------------------------------------------------------
+# This BaseRecalibrator WDL task was generated on 10/04/16 for use with GATK version 3.6
+# For more information on using this wrapper, please see the WDL repository at 
+# https://github.com/broadinstitute/wdl/tree/develop/scripts/wrappers/gatk/README.md
+# Task Summary: Detect systematic errors in base quality scores
+# --------------------------------------------------------------------------------------------
+
+task BaseRecalibrator { 
+	File gatk
+	File ref
+	File refIndex
+	File refDict
+	String ? userString #If a parameter you'd like to use is missing from this task, use this term to add your own string
+	Array[String] input_file
+	Array[String] ? intervals
+	File ? BQSR
+	Int ? nctVal
+	String ? binary_tag_name
+	Float ? bqsrBAQGapOpenPenalty
+	String ? covariate
+	String ? deletions_default_quality
+	Int ? indels_context_size
+	String ? insertions_default_quality
+	Array[String] ? knownSites
+	Boolean ? list
+	String ? low_quality_tail
+	Boolean ? lowMemoryMode
+	Int ? maximum_cycle_value
+	Int ? mismatches_context_size
+	String ? mismatches_default_quality
+	Boolean ? no_standard_covs
+	File out
+	Int ? quantizing_levels
+	Boolean ? run_without_dbsnp_potentially_ruining_quality
+	String ? solid_nocall_strategy
+	String ? solid_recal_mode
+	Boolean ? sort_by_all_columns
+
+	command {
+		java -jar ${gatk} \
+			-T BaseRecalibrator \
+			-R ${ref} \
+			--input_file ${input_file} \
+			${default="" "--intervals " + intervals} \
+			${default="" "--BQSR " + BQSR} \
+			${default="" "-nct" + nctVal} \
+			${default="" "-bintag " + binary_tag_name} \
+			-bqsrBAQGOP ${default="40.0" bqsrBAQGapOpenPenalty} \
+			${default="" "-cov " + covariate} \
+			-ddq ${default="45" deletions_default_quality} \
+			-ics ${default="3" indels_context_size} \
+			-idq ${default="45" insertions_default_quality} \
+			-knownSites ${default="[]" knownSites} \
+			-ls ${default="false" list} \
+			-lqt ${default="2" low_quality_tail} \
+			-lowMemoryMode ${default="false" lowMemoryMode} \
+			-maxCycle ${default="500" maximum_cycle_value} \
+			-mcs ${default="2" mismatches_context_size} \
+			-mdq ${default="-1" mismatches_default_quality} \
+			-noStandard ${default="false" no_standard_covs} \
+			-o ${out} \
+			-ql ${default="16" quantizing_levels} \
+			-run_without_dbsnp_potentially_ruining_quality ${default="false" run_without_dbsnp_potentially_ruining_quality} \
+			-solid_nocall_strategy ${default="THROW_EXCEPTION" solid_nocall_strategy} \
+			-sMode ${default="SET_Q_ZERO" solid_recal_mode} \
+			-sortAllCols ${default="false" sort_by_all_columns} \
+			${default="\n" userString} 
+	}
+
+	output {
+		#To track additional outputs from your task, please manually add them below
+		String taskOut = "${out}"
+	}
+
+	runtime {
+		docker: "broadinstitute/genomes-in-the-cloud:2.2.2-1466113830"
+	}
+
+	parameter_meta {
+		gatk: "Executable jar for the GenomeAnalysisTK"
+		ref: "fasta file of reference genome"
+		refIndex: "Index file of reference genome"
+		refDict: "dict file of reference genome"
+		userString: "An optional parameter which allows the user to specify additions to the command line at run time"
+		binary_tag_name: "the binary tag covariate name if using it"
+		bqsrBAQGapOpenPenalty: "BQSR BAQ gap open penalty (Phred Scaled).  Default value is 40.  30 is perhaps better for whole genome call sets"
+		covariate: "One or more covariates to be used in the recalibration. Can be specified multiple times"
+		deletions_default_quality: "default quality for the base deletions covariate"
+		indels_context_size: "Size of the k-mer context to be used for base insertions and deletions"
+		insertions_default_quality: "default quality for the base insertions covariate"
+		knownSites: "A database of known polymorphic sites"
+		list: "List the available covariates and exit"
+		low_quality_tail: "minimum quality for the bases in the tail of the reads to be considered"
+		lowMemoryMode: "Reduce memory usage in multi-threaded code at the expense of threading efficiency"
+		maximum_cycle_value: "The maximum cycle value permitted for the Cycle covariate"
+		mismatches_context_size: "Size of the k-mer context to be used for base mismatches"
+		mismatches_default_quality: "default quality for the base mismatches covariate"
+		no_standard_covs: "Do not use the standard set of covariates, but rather just the ones listed using the -cov argument"
+		out: "The output recalibration table file to create"
+		quantizing_levels: "number of distinct quality scores in the quantized output"
+		run_without_dbsnp_potentially_ruining_quality: "If specified, allows the recalibrator to be used without a dbsnp rod. Very unsafe and for expert users only."
+		solid_nocall_strategy: "Defines the behavior of the recalibrator when it encounters no calls in the color space. Options = THROW_EXCEPTION, LEAVE_READ_UNRECALIBRATED, or PURGE_READ"
+		solid_recal_mode: "How should we recalibrate solid bases in which the reference was inserted? Options = DO_NOTHING, SET_Q_ZERO, SET_Q_ZERO_BASE_N, or REMOVE_REF_BIAS"
+		sort_by_all_columns: "Sort the rows in the tables of reports"
+		input_file: "Input file containing sequence data (BAM or CRAM)"
+		intervals: "One or more genomic intervals over which to operate"
+		BQSR: "Input covariates table file for on-the-fly base quality score recalibration"
+	}
+}
+
+workflow BaseRecalibratorWf { 
+	call BaseRecalibrator
+}