1. kmdaily
  2. galaxy-central

Commits

Daniel Blankenberg  committed 20215fc

Update existing GATK tools. Add 4 new GATK tools: VariantAnnotator, VariantFiltration, VariantRecalibrator, ApplyRecalibration, ValidateVariants, VariantEval and CombineVariants. All GATK tool wrappers are still considered BETA and (workflow/rerun/etc) backwards-incompatible changes should be expected.

  • Participants
  • Parent commits d3349e0
  • Branches default

Comments (0)

Files changed (28)

File datatypes_conf.xml.sample

View file
  • Ignore whitespace
         <datatype extension="picard_interval_list" type="galaxy.datatypes.data:Text" subclass="True" display_in_upload="True"/>
         <datatype extension="gatk_interval" type="galaxy.datatypes.data:Text" subclass="True" display_in_upload="True"/>
         <datatype extension="gatk_dbsnp" type="galaxy.datatypes.tabular:Tabular" subclass="True" display_in_upload="True"/>
+        <datatype extension="gatk_tranche" type="galaxy.datatypes.tabular:Tabular" subclass="True" display_in_upload="True"/>
+        <datatype extension="gatk_recal" type="galaxy.datatypes.tabular:Tabular" subclass="True" display_in_upload="True"/>
         <datatype extension="jpg" type="galaxy.datatypes.images:Jpg" mimetype="image/jpeg"/>
         <datatype extension="tiff" type="galaxy.datatypes.images:Tiff" mimetype="image/tiff"/>
         <datatype extension="bmp" type="galaxy.datatypes.images:Bmp" mimetype="image/bmp"/>

File test-data/gatk/gatk_analyze_covariates/gatk_analyze_covariates_out_1.log.contains

View file
  • Ignore whitespace
 Reading in input csv file...
 ...Done!
 Writing out intermediate tables for R...
-Writing out data tables for read group: A Fake phiX Sample	with 360 observations	and aggregate residual error = -8.888
+Writing out data tables for read group: A Fake phiX Sample	with 340 observations	and aggregate residual error = -9.136
 ...Done!
 Calling analysis R scripts and writing out figures...
 Analyzing read group: A Fake phiX Sample
-...Done!
+...Done!

File test-data/gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv

View file
  • Ignore whitespace
-# Counted Sites    43
-# Counted Bases    360
-# Skipped Sites    0
-# Fraction Skipped 1 / Infinity bp
+# Counted Sites    41
+# Counted Bases    340
+# Skipped Sites    2
+# Fraction Skipped 1 / 21 bp
 ReadGroup,QualityScore,Cycle,Dinuc,Homopolymer,MinimumNQS,Position,nObservations,nMismatches,Qempirical
 A Fake phiX Sample,26,1,NN,0,26,0,9,0,40
 A Fake phiX Sample,26,1,NN,1,26,0,1,0,40
 A Fake phiX Sample,26,25,GC,0,26,24,1,0,40
 A Fake phiX Sample,26,25,GG,0,26,24,1,0,40
 A Fake phiX Sample,26,25,TA,1,26,24,1,0,40
-A Fake phiX Sample,26,26,AA,0,26,25,1,0,40
 A Fake phiX Sample,26,26,AG,1,26,25,2,0,40
 A Fake phiX Sample,26,26,CG,0,26,25,1,0,40
 A Fake phiX Sample,26,26,CT,0,26,25,1,0,40
 A Fake phiX Sample,26,26,GC,0,26,25,1,0,40
 A Fake phiX Sample,26,26,GG,0,26,25,1,0,40
 A Fake phiX Sample,26,26,TA,1,26,25,1,0,40
-A Fake phiX Sample,26,27,AA,0,26,26,1,0,40
 A Fake phiX Sample,26,27,AC,2,26,26,1,0,40
 A Fake phiX Sample,26,27,AG,1,26,26,2,0,40
 A Fake phiX Sample,26,27,CT,0,26,26,1,0,40
 A Fake phiX Sample,26,27,GC,0,26,26,1,0,40
 A Fake phiX Sample,26,27,GG,0,26,26,2,0,40
 A Fake phiX Sample,26,27,TA,1,26,26,1,0,40
-A Fake phiX Sample,26,28,AA,0,26,27,1,0,40
 A Fake phiX Sample,26,28,AC,2,26,27,1,0,40
 A Fake phiX Sample,26,28,AG,1,26,27,1,0,40
 A Fake phiX Sample,26,28,CC,1,26,27,1,0,40
 A Fake phiX Sample,26,28,GC,0,26,27,2,0,40
 A Fake phiX Sample,26,28,GG,0,26,27,2,0,40
 A Fake phiX Sample,26,28,TA,1,26,27,1,0,40
-A Fake phiX Sample,26,29,AA,0,26,28,1,0,40
 A Fake phiX Sample,26,29,AC,2,26,28,1,0,40
-A Fake phiX Sample,26,29,CC,0,26,28,1,0,40
 A Fake phiX Sample,26,29,CC,1,26,28,1,0,40
 A Fake phiX Sample,26,29,CT,0,26,28,2,0,40
 A Fake phiX Sample,26,29,GC,0,26,28,2,0,40
 A Fake phiX Sample,26,29,GG,0,26,28,1,0,40
 A Fake phiX Sample,26,29,TA,1,26,28,1,0,40
-A Fake phiX Sample,26,30,AA,0,26,29,1,0,40
 A Fake phiX Sample,26,30,AC,2,26,29,1,0,40
-A Fake phiX Sample,26,30,CC,0,26,29,1,0,40
 A Fake phiX Sample,26,30,CC,1,26,29,1,0,40
 A Fake phiX Sample,26,30,CT,0,26,29,3,0,40
 A Fake phiX Sample,26,30,GC,0,26,29,1,0,40
 A Fake phiX Sample,26,30,TA,1,26,29,2,0,40
-A Fake phiX Sample,26,31,AA,0,26,30,2,0,40
 A Fake phiX Sample,26,31,AC,2,26,30,1,0,40
-A Fake phiX Sample,26,31,CC,0,26,30,1,0,40
 A Fake phiX Sample,26,31,CC,1,26,30,1,0,40
 A Fake phiX Sample,26,31,CT,0,26,30,2,0,40
 A Fake phiX Sample,26,31,TA,1,26,30,3,0,40
-A Fake phiX Sample,26,32,AA,0,26,31,3,0,40
+A Fake phiX Sample,26,32,AA,0,26,31,1,0,40
 A Fake phiX Sample,26,32,AC,1,26,31,1,0,40
 A Fake phiX Sample,26,32,AC,2,26,31,1,0,40
-A Fake phiX Sample,26,32,CC,0,26,31,1,0,40
 A Fake phiX Sample,26,32,CC,1,26,31,1,0,40
 A Fake phiX Sample,26,32,CT,0,26,31,1,0,40
 A Fake phiX Sample,26,32,TA,1,26,31,2,0,40
-A Fake phiX Sample,26,33,AA,0,26,32,2,0,40
+A Fake phiX Sample,26,33,AA,0,26,32,1,0,40
 A Fake phiX Sample,26,33,AC,1,26,32,1,0,40
 A Fake phiX Sample,26,33,AC,2,26,32,1,0,40
 A Fake phiX Sample,26,33,AT,0,26,32,1,0,40
-A Fake phiX Sample,26,33,CC,0,26,32,2,0,40
 A Fake phiX Sample,26,33,CC,1,26,32,1,0,40
 A Fake phiX Sample,26,33,CT,0,26,32,1,0,40
 A Fake phiX Sample,26,33,TA,1,26,32,1,0,40
 A Fake phiX Sample,26,34,AA,0,26,33,1,0,40
 A Fake phiX Sample,26,34,AC,1,26,33,1,0,40
 A Fake phiX Sample,26,34,AT,0,26,33,1,0,40
-A Fake phiX Sample,26,34,CC,0,26,33,2,0,40
 A Fake phiX Sample,26,34,CC,1,26,33,1,0,40
 A Fake phiX Sample,26,34,CT,0,26,33,2,0,40
 A Fake phiX Sample,26,34,TA,1,26,33,1,0,40
 A Fake phiX Sample,26,34,TG,0,26,33,1,0,40
 A Fake phiX Sample,26,35,AA,0,26,34,1,0,40
 A Fake phiX Sample,26,35,AT,0,26,34,1,0,40
-A Fake phiX Sample,26,35,CC,0,26,34,2,0,40
 A Fake phiX Sample,26,35,CT,0,26,34,2,0,40
 A Fake phiX Sample,26,35,GA,0,26,34,1,0,40
 A Fake phiX Sample,26,35,TA,1,26,34,2,0,40

File test-data/gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam

  • Ignore whitespace
Binary file modified.

File test-data/gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.vcf

View file
  • Ignore whitespace
-##fileformat=VCFv4.0
+##fileformat=VCFv4.1
 ##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
 ##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth (only filtered reads used for calling)">
 ##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality">
 ##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
-##FORMAT=<ID=PL,Number=3,Type=Float,Description="Normalized, Phred-scaled likelihoods for AA,AB,BB genotypes where A=ref and B=alt; not applicable if site is not biallelic">
-##INFO=<ID=AC,Number=.,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
-##INFO=<ID=AF,Number=.,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
 ##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
 ##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP Membership">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Filtered Depth">
 ##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">
 ##INFO=<ID=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
 ##INFO=<ID=HRun,Number=1,Type=Integer,Description="Largest Contiguous Homopolymer Run of Variant Allele In Either Direction">
 ##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">
+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
 ##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
 ##INFO=<ID=MQ0,Number=1,Type=Integer,Description="Total Mapping Quality Zero Reads">
 ##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
 ##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
 ##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
 ##INFO=<ID=SB,Number=1,Type=Float,Description="Strand Bias">
-##UnifiedGenotyper="analysis_type=UnifiedGenotyper input_file=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmp4XA21z/gatk_input_0.bam] sample_metadata=[] read_buffer_size=null phone_home=NO_ET read_filter=[] intervals=null excludeIntervals=null reference_sequence=/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmp4XA21z/gatk_input.fasta rodBind=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmp4XA21z/input_snps_0.bed] rodToIntervalTrackName=null BTI_merge_rule=UNION nonDeterministicRandomSeed=false DBSNP=null downsampling_type=null downsample_to_fraction=null downsample_to_coverage=null baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=1 interval_merging=ALL read_group_black_list=null processingTracker=null restartProcessingTracker=false processingTrackerStatusFile=null processingTrackerID=-1 allow_intervals_with_unindexed_bam=false disable_experimental_low_memory_sharding=false logging_level=INFO log_to_file=null help=false genotype_likelihoods_model=BOTH p_nonref_model=EXACT heterozygosity=0.0010 pcr_error_rate=1.0E-4 genotyping_mode=DISCOVERY output_mode=EMIT_ALL_CONFIDENT_SITES standard_min_confidence_threshold_for_calling=4.0 standard_min_confidence_threshold_for_emitting=4.0 noSLOD=false assume_single_sample_reads=null abort_at_too_much_coverage=-1 min_base_quality_score=17 min_mapping_quality_score=20 max_deletion_fraction=-1.0 min_indel_count_for_genotyping=2 indel_heterozygosity=1.25E-4 indelGapContinuationPenalty=10.0 indelGapOpenPenalty=3.0 indelHaplotypeSize=80 doContextDependentGapPenalties=true getGapPenaltiesFromData=false indel_recal_file=indel.recal_data.csv indelDebug=false dovit=false GSA_PRODUCTION_ONLY=false exactCalculation=LINEAR_EXPERIMENTAL output_all_callable_bases=false genotype=false out=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub NO_HEADER=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub sites_only=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub debug_file=null metrics_file=null annotation=[]"
+##UnifiedGenotyper="analysis_type=UnifiedGenotyper input_file=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpXqIddV/gatk_input_0.bam] sample_metadata=[] read_buffer_size=null phone_home=NO_ET read_filter=[] intervals=null excludeIntervals=null reference_sequence=/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpXqIddV/gatk_input.fasta rodBind=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpXqIddV/input_dbsnp_0.bed] rodToIntervalTrackName=null BTI_merge_rule=UNION nonDeterministicRandomSeed=false DBSNP=null downsampling_type=null downsample_to_fraction=null downsample_to_coverage=null baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=1 interval_merging=ALL read_group_black_list=null processingTracker=null restartProcessingTracker=false processingTrackerStatusFile=null processingTrackerID=-1 allow_intervals_with_unindexed_bam=false disable_experimental_low_memory_sharding=false logging_level=INFO log_to_file=null help=false genotype_likelihoods_model=BOTH p_nonref_model=EXACT heterozygosity=0.0010 pcr_error_rate=1.0E-4 genotyping_mode=DISCOVERY output_mode=EMIT_ALL_CONFIDENT_SITES standard_min_confidence_threshold_for_calling=4.0 standard_min_confidence_threshold_for_emitting=4.0 noSLOD=false assume_single_sample_reads=null abort_at_too_much_coverage=-1 min_base_quality_score=17 min_mapping_quality_score=20 max_deletion_fraction=-1.0 min_indel_count_for_genotyping=2 indel_heterozygosity=1.25E-4 indelGapContinuationPenalty=10.0 indelGapOpenPenalty=3.0 indelHaplotypeSize=80 doContextDependentGapPenalties=true getGapPenaltiesFromData=false indel_recal_file=indel.recal_data.csv indelDebug=false dovit=false GSA_PRODUCTION_ONLY=false exactCalculation=LINEAR_EXPERIMENTAL ignoreSNPAlleles=false output_all_callable_bases=false genotype=false out=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub NO_HEADER=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub sites_only=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub debug_file=null metrics_file=null annotation=[]"
 #CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	A Fake phiX Sample
-phiX174	1443	.	AC	.	37.27	.	AC=0;AF=0.00;AN=2;Dels=0.30;MQ=37.74;MQ0=0	GT:DP:GQ:PL	0/0:7:0:0,0,0
+phiX174	1443	.	AC	.	37.27	.	AC=0;AF=0.00;AN=2;DP=10;MQ=37.74;MQ0=0	GT:DP:GQ:PL	0/0:7:0:0,0,0

File test-data/gatk/gatk_validate_variants/gatk_validate_variants_out_1.log.contains

View file
  • Ignore whitespace
+Found 1 records with failures.

File test-data/gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.log.contains

View file
  • Ignore whitespace
+GenomeAnalysisEngine - Strictness is SILENT 
+TraversalEngine - [INITIALIZATION COMPLETE; TRAVERSAL STARTING] 
+TraversalEngine -        Location processed.sites  runtime per.1M.sites completed total.runtime remaining 
+VariantAnnotator - Processed 1 loci.
+TraversalEngine - 0 reads were filtered out during traversal out of 10 total (0.00%) 

File test-data/gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf

View file
  • Ignore whitespace
+##fileformat=VCFv4.1
+##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth (only filtered reads used for calling)">
+##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##INFO=<ID=AB,Number=1,Type=Float,Description="Allele Balance for hets (ref/(ref+alt))">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP Membership">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Filtered Depth">
+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">
+##INFO=<ID=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=HRun,Number=1,Type=Integer,Description="Largest Contiguous Homopolymer Run of Variant Allele In Either Direction">
+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">
+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQ0,Number=1,Type=Integer,Description="Total Mapping Quality Zero Reads">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##INFO=<ID=SB,Number=1,Type=Float,Description="Strand Bias">
+##UnifiedGenotyper="analysis_type=UnifiedGenotyper input_file=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpXqIddV/gatk_input_0.bam] sample_metadata=[] read_buffer_size=null phone_home=NO_ET read_filter=[] intervals=null excludeIntervals=null reference_sequence=/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpXqIddV/gatk_input.fasta rodBind=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpXqIddV/input_dbsnp_0.bed] rodToIntervalTrackName=null BTI_merge_rule=UNION nonDeterministicRandomSeed=false DBSNP=null downsampling_type=null downsample_to_fraction=null downsample_to_coverage=null baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=1 interval_merging=ALL read_group_black_list=null processingTracker=null restartProcessingTracker=false processingTrackerStatusFile=null processingTrackerID=-1 allow_intervals_with_unindexed_bam=false disable_experimental_low_memory_sharding=false logging_level=INFO log_to_file=null help=false genotype_likelihoods_model=BOTH p_nonref_model=EXACT heterozygosity=0.0010 pcr_error_rate=1.0E-4 genotyping_mode=DISCOVERY output_mode=EMIT_ALL_CONFIDENT_SITES standard_min_confidence_threshold_for_calling=4.0 standard_min_confidence_threshold_for_emitting=4.0 noSLOD=false assume_single_sample_reads=null abort_at_too_much_coverage=-1 min_base_quality_score=17 min_mapping_quality_score=20 max_deletion_fraction=-1.0 min_indel_count_for_genotyping=2 indel_heterozygosity=1.25E-4 indelGapContinuationPenalty=10.0 indelGapOpenPenalty=3.0 indelHaplotypeSize=80 doContextDependentGapPenalties=true getGapPenaltiesFromData=false indel_recal_file=indel.recal_data.csv indelDebug=false dovit=false GSA_PRODUCTION_ONLY=false exactCalculation=LINEAR_EXPERIMENTAL ignoreSNPAlleles=false output_all_callable_bases=false genotype=false out=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub NO_HEADER=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub sites_only=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub debug_file=null metrics_file=null annotation=[]"
+##VariantAnnotator="analysis_type=VariantAnnotator input_file=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpYvqW3G/gatk_input.bam] sample_metadata=[] read_buffer_size=null phone_home=NO_ET read_filter=[] intervals=null excludeIntervals=null reference_sequence=/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpYvqW3G/gatk_input.fasta rodBind=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpYvqW3G/input_variant.vcf, /var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpYvqW3G/input_dbsnp_0.bed] rodToIntervalTrackName=null BTI_merge_rule=UNION nonDeterministicRandomSeed=false DBSNP=null downsampling_type=null downsample_to_fraction=null downsample_to_coverage=null baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=1 interval_merging=ALL read_group_black_list=null processingTracker=null restartProcessingTracker=false processingTrackerStatusFile=null processingTrackerID=-1 allow_intervals_with_unindexed_bam=false disable_experimental_low_memory_sharding=false logging_level=INFO log_to_file=null help=false out=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub NO_HEADER=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub sites_only=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub sampleName=null annotation=[AlleleBalance, BaseQualityRankSumTest, DepthOfCoverage, HomopolymerRun, MappingQualityRankSumTest, MappingQualityZero, QualByDepth, RMSMappingQuality, SpanningDeletions, HaplotypeScore] group=[] expression=[] useAllAnnotations=false list=false assume_single_sample_reads=null vcfContainsOnlyIndels=false"
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	A Fake phiX Sample
+phiX174	1443	.	AC	.	37.27	.	AC=0;AF=0.00;AN=2;DP=10;MQ=37.74;MQ0=0	GT:DP:GQ:PL	0/0:7:0:0,0,0

File test-data/gatk/gatk_variant_combine/gatk_variant_combine_out_1.log.contains

View file
  • Ignore whitespace
+HelpFormatter - Program Args: -T CombineVariants
+GenomeAnalysisEngine - Strictness is SILENT
+TraversalEngine - [INITIALIZATION COMPLETE; TRAVERSAL STARTING]
+TraversalEngine -        Location processed.sites  runtime per.1M.sites completed total.runtime remaining
+TraversalEngine - Total runtime

File test-data/gatk/gatk_variant_combine/gatk_variant_combine_out_1.vcf

View file
  • Ignore whitespace
+##fileformat=VCFv4.1
+##CombineVariants="analysis_type=CombineVariants input_file=[] sample_metadata=[] read_buffer_size=null phone_home=NO_ET read_filter=[] intervals=null excludeIntervals=null reference_sequence=/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpNWtPhs/gatk_input.fasta rodBind=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpNWtPhs/input_variant_from_variant_annotator.vcf] rodToIntervalTrackName=null BTI_merge_rule=UNION nonDeterministicRandomSeed=false DBSNP=null downsampling_type=null downsample_to_fraction=null downsample_to_coverage=null baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=1 interval_merging=ALL read_group_black_list=null processingTracker=null restartProcessingTracker=false processingTrackerStatusFile=null processingTrackerID=-1 allow_intervals_with_unindexed_bam=false disable_experimental_low_memory_sharding=false logging_level=INFO log_to_file=null help=false out=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub NO_HEADER=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub sites_only=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub genotypemergeoption=PRIORITIZE filteredrecordsmergetype=KEEP_IF_ANY_UNFILTERED rod_priority_list=from_variant_annotator printComplexMerges=false filteredAreUncalled=false minimalVCF=false setKey=set assumeIdenticalSamples=false minimumN=1 masterMerge=false mergeInfoWithMaxAC=false"
+##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth (only filtered reads used for calling)">
+##FORMAT=<ID=GQ,Number=1,Type=Float,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##INFO=<ID=AB,Number=1,Type=Float,Description="Allele Balance for hets (ref/(ref+alt))">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP Membership">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Filtered Depth">
+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">
+##INFO=<ID=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">
+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=HRun,Number=1,Type=Integer,Description="Largest Contiguous Homopolymer Run of Variant Allele In Either Direction">
+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">
+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQ0,Number=1,Type=Integer,Description="Total Mapping Quality Zero Reads">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##INFO=<ID=SB,Number=1,Type=Float,Description="Strand Bias">
+##INFO=<ID=set,Number=1,Type=String,Description="Source VCF for the merged record in CombineVariants">
+##UnifiedGenotyper="analysis_type=UnifiedGenotyper input_file=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpXqIddV/gatk_input_0.bam] sample_metadata=[] read_buffer_size=null phone_home=NO_ET read_filter=[] intervals=null excludeIntervals=null reference_sequence=/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpXqIddV/gatk_input.fasta rodBind=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpXqIddV/input_dbsnp_0.bed] rodToIntervalTrackName=null BTI_merge_rule=UNION nonDeterministicRandomSeed=false DBSNP=null downsampling_type=null downsample_to_fraction=null downsample_to_coverage=null baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=1 interval_merging=ALL read_group_black_list=null processingTracker=null restartProcessingTracker=false processingTrackerStatusFile=null processingTrackerID=-1 allow_intervals_with_unindexed_bam=false disable_experimental_low_memory_sharding=false logging_level=INFO log_to_file=null help=false genotype_likelihoods_model=BOTH p_nonref_model=EXACT heterozygosity=0.0010 pcr_error_rate=1.0E-4 genotyping_mode=DISCOVERY output_mode=EMIT_ALL_CONFIDENT_SITES standard_min_confidence_threshold_for_calling=4.0 standard_min_confidence_threshold_for_emitting=4.0 noSLOD=false assume_single_sample_reads=null abort_at_too_much_coverage=-1 min_base_quality_score=17 min_mapping_quality_score=20 max_deletion_fraction=-1.0 min_indel_count_for_genotyping=2 indel_heterozygosity=1.25E-4 indelGapContinuationPenalty=10.0 indelGapOpenPenalty=3.0 indelHaplotypeSize=80 doContextDependentGapPenalties=true getGapPenaltiesFromData=false indel_recal_file=indel.recal_data.csv indelDebug=false dovit=false GSA_PRODUCTION_ONLY=false exactCalculation=LINEAR_EXPERIMENTAL ignoreSNPAlleles=false output_all_callable_bases=false genotype=false out=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub NO_HEADER=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub sites_only=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub debug_file=null metrics_file=null annotation=[]"
+##VariantAnnotator="analysis_type=VariantAnnotator input_file=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpYvqW3G/gatk_input.bam] sample_metadata=[] read_buffer_size=null phone_home=NO_ET read_filter=[] intervals=null excludeIntervals=null reference_sequence=/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpYvqW3G/gatk_input.fasta rodBind=[/var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpYvqW3G/input_variant.vcf, /var/folders/78/786YaG3QH58XnzrWynoDBk+++TI/-Tmp-/tmpYvqW3G/input_dbsnp_0.bed] rodToIntervalTrackName=null BTI_merge_rule=UNION nonDeterministicRandomSeed=false DBSNP=null downsampling_type=null downsample_to_fraction=null downsample_to_coverage=null baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=1 interval_merging=ALL read_group_black_list=null processingTracker=null restartProcessingTracker=false processingTrackerStatusFile=null processingTrackerID=-1 allow_intervals_with_unindexed_bam=false disable_experimental_low_memory_sharding=false logging_level=INFO log_to_file=null help=false out=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub NO_HEADER=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub sites_only=org.broadinstitute.sting.gatk.io.stubs.VCFWriterStub sampleName=null annotation=[AlleleBalance, BaseQualityRankSumTest, DepthOfCoverage, HomopolymerRun, MappingQualityRankSumTest, MappingQualityZero, QualByDepth, RMSMappingQuality, SpanningDeletions, HaplotypeScore] group=[] expression=[] useAllAnnotations=false list=false assume_single_sample_reads=null vcfContainsOnlyIndels=false"
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	A Fake phiX Sample
+phiX174	1443	.	AC	.	.	PASS	AC=0;AF=0.00;AN=2;DP=10;MQ=37.74;MQ0=0;set=ReferenceInAll	GT:DP:GQ:PL	0/0:7:0:0,0,0

File test-data/gatk/gatk_variant_eval/gatk_variant_eval_out_1.log.contains

View file
  • Ignore whitespace
+HelpFormatter - Program Args: -T VariantEval
+GenomeAnalysisEngine - Strictness is SILENT
+TraversalEngine -        Location processed.sites  runtime per.1M.sites completed total.runtime remaining
+VariantEvalWalker - Finalizing variant report
+TraversalEngine - Total runtime

File test-data/gatk/gatk_variant_eval/gatk_variant_eval_out_1.tabular

View file
  • Ignore whitespace
+##:GATKReport.v0.1 CompOverlap : The overlap between eval and comp sites
+CompOverlap  CompRod  EvalRod  JexlExpression  Novelty  nEvalVariants  nCompVariants  novelSites  nVariantsAtComp  compRate  nConcordant  concordantRate
+CompOverlap  dbsnp    eval     none            all      0              0              0           0                0.00000000  0            0.00000000    
+CompOverlap  dbsnp    eval     none            known    0              0              0           0                0.00000000  0            0.00000000    
+CompOverlap  dbsnp    eval     none            novel    0              0              0           0                0.00000000  0            0.00000000    
+
+##:GATKReport.v0.1 CountVariants : Counts different classes of variants in the sample
+CountVariants  CompRod  EvalRod  JexlExpression  Novelty  nProcessedLoci  nCalledLoci  nRefLoci  nVariantLoci  variantRate  variantRatePerBp  nSNPs  nMNPs  nInsertions  nDeletions  nComplex  nNoCalls  nHets  nHomRef  nHomVar  nSingletons  nHomDerived  heterozygosity  heterozygosityPerBp  hetHomRatio  indelRate  indelRatePerBp  deletionInsertionRatio
+CountVariants  dbsnp    eval     none            all      5386            1            1         0             0.00000000   0.00000000        0      0      0            0           0         0         0      1        0        0            0            0.00000000      0.00000000           0.00000000   0.00000000  0.00000000      0.00000000            
+CountVariants  dbsnp    eval     none            known    5386            0            0         0             0.00000000   0.00000000        0      0      0            0           0         0         0      0        0        0            0            0.00000000      0.00000000           0.00000000   0.00000000  0.00000000      0.00000000            
+CountVariants  dbsnp    eval     none            novel    5386            1            1         0             0.00000000   0.00000000        0      0      0            0           0         0         0      1        0        0            0            0.00000000      0.00000000           0.00000000   0.00000000  0.00000000      0.00000000            
+
+##:GATKReport.v0.1 SimpleMetricsByAC.metrics : TiTv by allele count
+SimpleMetricsByAC.metrics  CompRod  EvalRod  JexlExpression  Novelty  row  AC  nTi  nTv  n  TiTv
+SimpleMetricsByAC.metrics  dbsnp    eval     none            all      ac0  0   0    0    0  0.0 
+SimpleMetricsByAC.metrics  dbsnp    eval     none            all      ac1  1   0    0    0  0.0 
+SimpleMetricsByAC.metrics  dbsnp    eval     none            all      ac2  2   0    0    0  0.0 
+SimpleMetricsByAC.metrics  dbsnp    eval     none            known    ac0  0   0    0    0  0.0 
+SimpleMetricsByAC.metrics  dbsnp    eval     none            known    ac1  1   0    0    0  0.0 
+SimpleMetricsByAC.metrics  dbsnp    eval     none            known    ac2  2   0    0    0  0.0 
+SimpleMetricsByAC.metrics  dbsnp    eval     none            novel    ac0  0   0    0    0  0.0 
+SimpleMetricsByAC.metrics  dbsnp    eval     none            novel    ac1  1   0    0    0  0.0 
+SimpleMetricsByAC.metrics  dbsnp    eval     none            novel    ac2  2   0    0    0  0.0 
+
+##:GATKReport.v0.1 TiTvVariantEvaluator : Ti/Tv Variant Evaluator
+TiTvVariantEvaluator  CompRod  EvalRod  JexlExpression  Novelty  nTi  nTv  tiTvRatio  nTiInComp  nTvInComp  TiTvRatioStandard  nTiDerived  nTvDerived  tiTvDerivedRatio
+TiTvVariantEvaluator  dbsnp    eval     none            all      0    0    0.00000000  0          0          0.00000000         0           0           0.00000000      
+TiTvVariantEvaluator  dbsnp    eval     none            known    0    0    0.00000000  0          0          0.00000000         0           0           0.00000000      
+TiTvVariantEvaluator  dbsnp    eval     none            novel    0    0    0.00000000  0          0          0.00000000         0           0           0.00000000      
+
+##:GATKReport.v0.1 ValidationReport : Assess site accuracy and sensitivity of callset against follow-up validation assay
+ValidationReport  CompRod  EvalRod  JexlExpression  Novelty  nComp  TP  FP  FN  TN  sensitivity  specificity  PPV  FDR  CompMonoEvalNoCall  CompMonoEvalFiltered  CompMonoEvalMono  CompMonoEvalPoly  CompPolyEvalNoCall  CompPolyEvalFiltered  CompPolyEvalMono  CompPolyEvalPoly  CompFiltered  nDifferentAlleleSites
+ValidationReport  dbsnp    eval     none            all      0      0   0   0   0   NaN          100.00000000  NaN  NaN  0                   0                     0                 0                 0                   0                     0                 0                 0             0                    
+ValidationReport  dbsnp    eval     none            known    0      0   0   0   0   NaN          100.00000000  NaN  NaN  0                   0                     0                 0                 0                   0                     0                 0                 0             0                    
+ValidationReport  dbsnp    eval     none            novel    0      0   0   0   0   NaN          100.00000000  NaN  NaN  0                   0                     0                 0                 0                   0                     0                 0                 0             0                    
+

File test-data/gatk/gatk_variant_filtration/gatk_variant_filtration_out_1.log.contains

View file
  • Ignore whitespace
+GenomeAnalysisEngine - Strictness is SILENT 
+TraversalEngine - [INITIALIZATION COMPLETE; TRAVERSAL STARTING] 
+TraversalEngine -        Location processed.sites  runtime per.1M.sites completed total.runtime remaining 
+TraversalEngine - Total runtime 

File tool_conf.xml.sample

View file
  • Ignore whitespace
      <tool file="gatk/analyze_covariates.xml" />
    <label text="Genotyping" id="gatk_genotyping" />
      <tool file="gatk/unified_genotyper.xml" />
+   <label text="Annotation" id="gatk_annotation" />
+     <tool file="gatk/variant_annotator.xml" />
+   <label text="Filtration" id="gatk_filtration" />
+     <tool file="gatk/variant_filtration.xml" />
+     <tool file="gatk/variant_filtration.xml" />
+   <label text="Variant Quality Score Recalibration" id="gatk_variant_quality_score_recalibration" />
+     <tool file="gatk/variant_recalibrator.xml" />
+     <tool file="gatk/variant_apply_recalibration.xml" />
+   <label text="Variant Utilities" id="gatk_variant_utilities"/>
+     <tool file="gatk/variants_validate.xml" />
+     <tool file="gatk/variant_eval.xml" />
+     <tool file="gatk/variant_combine.xml" />
   </section>
   <section name="NGS: Peak Calling" id="peak_calling">
    <tool file="peak_calling/macs_wrapper.xml" />

File tools/gatk/analyze_covariates.xml

View file
  • Ignore whitespace
-<tool id="gatk_analyze_covariates" name="Analyze Covariates" version="0.0.1">
-  <description>- perform local realignment</description>
+<tool id="gatk_analyze_covariates" name="Analyze Covariates" version="0.0.2">
+  <description>- draw plots</description>
 <command interpreter="python">gatk_wrapper.py
+   --max_jvm_heap_fraction "2"
    --stdout "${output_log}"
    --html_report_from_directory "${output_html}" "${output_html.files_path}"
    -p 'java 
         <param name="ignore_q" type="integer" value="5" label="Ignore bases with reported quality less than this number."/>
         <param name="num_read_groups" type="integer" value="-1" label="Only process N read groups."/>
         <param name="max_quality_score" type="integer" value="50" label="Max quality score"/>
-        <param name="max_histogram_value" type="integer" value="0" label="Max quality score"/>
-        <param name="do_indel_quality" type="boolean" truevalue="--do_indel_quality" falsevalue="" label="Max quality score"/>
+        <param name="max_histogram_value" type="integer" value="0" label="Max histogram value"/>
+        <param name="do_indel_quality" type="boolean" truevalue="--do_indel_quality" falsevalue="" label="Do indel quality"/>
       </when>
     </conditional>
   </inputs>
   <help>
 **What it does**
 
-     Create collapsed versions of the recal csv file and call R scripts to plot residual error versus the various covariates.
+Create collapsed versions of the recal csv file and call R scripts to plot residual error versus the various covariates.
 
+For more information on base quality score recalibration using the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Base_quality_score_recalibration&gt;`_.
+
+To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3&gt;`_.
+
+If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.
 
 ------
 
-Please cite the website "http://addlink.here" as well as:
-
-Add citation here 2011.
-
-------
-
-**Input formats**
+**Inputs**
 
 GenomeAnalysisTK: AnalyzeCovariates accepts an recal CSV file.
 
-------
 
 **Outputs**
 
-The output is in and HTML file with links to PDF graphs and a data files, see http://addlink.here for more details.
+The output is in and HTML file with links to PDF graphs and a data files.
+
+
+Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.
 
 -------
 
 **Settings**::
 
- recal_file                   The input recal csv file to analyze
- output_dir                   The directory in which to output all the plots and intermediate data files
- path_to_Rscript           The path to your implementation of Rscript. For Broad users this is maybe /broad/tools/apps/R-2.6.0/bin/Rscript
- path_to_resources     Path to resources folder holding the Sting R scripts.
- ignoreQ                           Ignore bases with reported quality less than this number.
- numRG                                 Only process N read groups. Default value: -1 (process all read groups)
- max_quality_score          The integer value at which to cap the quality scores, default is 50
- max_histogram_value   If supplied, this value will be the max value of the histogram plots
- do_indel_quality                             If supplied, this value will be the max value of the histogram plots
+ recal_file             The input recal csv file to analyze
+ output_dir             The directory in which to output all the plots and intermediate data files
+ path_to_Rscript        The path to your implementation of Rscript. For Broad users this is maybe /broad/tools/apps/R-2.6.0/bin/Rscript
+ path_to_resources      Path to resources folder holding the Sting R scripts.
+ ignoreQ                Ignore bases with reported quality less than this number.
+ numRG                  Only process N read groups. Default value: -1 (process all read groups)
+ max_quality_score      The integer value at which to cap the quality scores, default is 50
+ max_histogram_value    If supplied, this value will be the max value of the histogram plots
+ do_indel_quality       If supplied, this value will be the max value of the histogram plots
+
+------
+
+**Citation**
+
+For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. &lt;http://www.ncbi.nlm.nih.gov/pubmed/21478889&gt;`_
 
   </help>
 </tool>

File tools/gatk/count_covariates.xml

View file
  • Ignore whitespace
-<tool id="gatk_count_covariates" name="Count Covariates" version="0.0.1">
+<tool id="gatk_count_covariates" name="Count Covariates" version="0.0.2">
   <description>on BAM files</description>
   <command interpreter="python">gatk_wrapper.py
+   --max_jvm_heap_fraction "2"
    --stdout "${output_log}"
    -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
    -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
    '
     
     #set $snp_dataset_provided = False
-    #if str( $input_dbsnp_rod ) != "None":
-        -d "-D" "${input_dbsnp_rod}" "${input_dbsnp_rod.ext}" "dbsnp_rod"
-        #set $snp_dataset_provided = True
-    #end if
     #set $rod_binding_names = dict()
     #for $rod_binding in $rod_bind:
         #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
         #else
             #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector
         #end if
-        #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'snps':
+        #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'dbsnp':
             #set $snp_dataset_provided = True
         #end if
         #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
       <option value="QualityScoreCovariate" />
       <option value="CycleCovariate" />
       <option value="DinucCovariate" />
-      <!-- covariates below were pull from source code, since the list option doesn't seem to work (when tried) -->
+      <!-- covariates below were pulled from list option -->
       <option value="HomopolymerCovariate" />
+      <option value="GCContentCovariate" />
       <option value="MappingQualityCovariate" />
       <option value="MinimumNQSCovariate" />
       <option value="PositionCovariate" />
       <option value="PrimerRoundCovariate" />
       <option value="TileCovariate" />
     </param>
-    <param name="input_dbsnp_rod" type="data" format="gatk_dbsnp" optional="True" label="dbSNP reference ordered data (ROD)" />
+    
     <repeat name="rod_bind" title="Binding for reference-ordered data">
         <conditional name="rod_bind_type">
 	      <param name="rod_bind_type_selector" type="select" label="Binding Type">
-	        <option value="snps" selected="True">SNPs</option>
+	        <option value="dbsnp" selected="True">dbSNP</option>
+	        <option value="snps">SNPs</option>
 	        <option value="indels">INDELs</option>
 	        <option value="mask">Mask</option>
 	        <option value="custom">Custom</option>
 	      </param>
+          <when value="dbsnp">
+              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
+              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
+          </when>
           <when value="snps">
               <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
               <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
               <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
               <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
           </when>
+          <when value="mask">
+              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
+              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
+          </when>
           <when value="custom">
               <param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/>
               <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
           <param name="reference_source_selector" value="history" />
           <param name="ref_file" value="phiX.fasta" ftype="fasta" />
           <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" />
-          <param name="input_dbsnp_rod"  />
-          <param name="rod_bind_type_selector" value="snps" />
+          <param name="rod_bind_type_selector" value="dbsnp" />
           <param name="rodToIntervalTrackName" />
           <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" />
           <param name="standard_covs" value="True" />
   
 **What it does**
 
-     This walker is designed to work as the first pass in a two-pass processing step. It does a by-locus traversal 
-     operating only at sites that are not in dbSNP. We assume that all reference mismatches we see are therefore errors 
-     and indicative of poor base quality. This walker generates tables based on various user-specified covariates (such 
-     as read group, reported quality score, cycle, and dinucleotide) Since there is a large amount of data one can then 
-     calculate an empirical probability of error given the particular covariates seen at this site, where p(error) = num 
-     mismatches / num observations The output file is a CSV list of (the several covariate values, num observations, num 
-     mismatches, empirical quality score) The first non-comment line of the output file gives the name of the covariates 
-     that were used for this calculation.  Note: ReadGroupCovariate and QualityScoreCovariate are required covariates 
-     and will be added for the user regardless of whether or not they were specified Note: This walker is designed to be 
-     used in conjunction with TableRecalibrationWalker.
+This walker is designed to work as the first pass in a two-pass processing step. It does a by-locus traversal operating only at sites that are not in dbSNP. We assume that all reference mismatches we see are therefore errors and indicative of poor base quality. This walker generates tables based on various user-specified covariates (such as read group, reported quality score, cycle, and dinucleotide) Since there is a large amount of data one can then calculate an empirical probability of error given the particular covariates seen at this site, where p(error) = num mismatches / num observations The output file is a CSV list of (the several covariate values, num observations, num mismatches, empirical quality score) The first non-comment line of the output file gives the name of the covariates that were used for this calculation.  Note: ReadGroupCovariate and QualityScoreCovariate are required covariates and will be added for the user regardless of whether or not they were specified Note: This walker is designed to be used in conjunction with TableRecalibrationWalker.
 
+For more information on base quality score recalibration using the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Base_quality_score_recalibration&gt;`_.
+
+To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3&gt;`_.
+
+If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.
 
 ------
 
-Please cite the website "http://addlink.here" as well as:
-
-Add citation here 2011.
-
-------
-
-**Input formats**
+**Inputs**
 
 GenomeAnalysisTK: CountCovariates accepts an aligned BAM input file.
 
-------
 
 **Outputs**
 
-The output is in CSV format, see http://addlink.here for more details.
+The output is in CSV format.
+
+
+Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.
 
 -------
 
 **Settings**::
 
 
- default_read_group                           If a read has no read group then default to the provided String.
- default_platform                                If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid.
- force_read_group                               If provided, the read group ID of EVERY read will be forced to be the provided String. This is useful to collapse all data into a single read group.
- force_platform                                    If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid.
- window_size_nqs                                 The window size used by MinimumNQSCovariate for its calculation
- homopolymer_nback                           The number of previous bases to look at in HomopolymerCovariate
- exception_if_no_tile                               If provided, TileCovariate will throw an exception when no tile can be found. The default behavior is to use tile = -1
- solid_recal_mode                             How should we recalibrate solid bases in whichthe reference was inserted? Options = DO_NOTHING, SET_Q_ZERO, SET_Q_ZERO_BASE_N, or REMOVE_REF_BIAS (DO_NOTHING|SET_Q_ZERO|SET_Q_ZERO_BASE_N|REMOVE_REF_BIAS)
- 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 (THROW_EXCEPTION|LEAVE_READ_UNRECALIBRATED|PURGE_READ)
- recal_file                                     Filename for the input covariates table recalibration .csv file
- out                                                           The output CSV file
- recal_file                                                     Filename for the outputted covariates table recalibration file
- standard_covs                                                                Use the standard set of covariates in addition to the ones listed using the -cov argument
- 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.
+ default_read_group                               If a read has no read group then default to the provided String.
+ default_platform                                 If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid.
+ force_read_group                                 If provided, the read group ID of EVERY read will be forced to be the provided String. This is useful to collapse all data into a single read group.
+ force_platform                                   If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid.
+ window_size_nqs                                  The window size used by MinimumNQSCovariate for its calculation
+ homopolymer_nback                                The number of previous bases to look at in HomopolymerCovariate
+ exception_if_no_tile                             If provided, TileCovariate will throw an exception when no tile can be found. The default behavior is to use tile = -1
+ solid_recal_mode                                 How should we recalibrate solid bases in whichthe reference was inserted? Options = DO_NOTHING, SET_Q_ZERO, SET_Q_ZERO_BASE_N, or REMOVE_REF_BIAS (DO_NOTHING|SET_Q_ZERO|SET_Q_ZERO_BASE_N|REMOVE_REF_BIAS)
+ 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 (THROW_EXCEPTION|LEAVE_READ_UNRECALIBRATED|PURGE_READ)
+ recal_file                                       Filename for the input covariates table recalibration .csv file
+ out                                              The output CSV file
+ recal_file                                       Filename for the outputted covariates table recalibration file
+ standard_covs                                    Use the standard set of covariates in addition to the ones listed using the -cov argument
+ 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.
+
+------
+
+**Citation**
+
+For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. &lt;http://www.ncbi.nlm.nih.gov/pubmed/21478889&gt;`_
 
   </help>
 </tool>

File tools/gatk/gatk_wrapper.py

View file
  • Ignore whitespace
     parser = optparse.OptionParser()
     parser.add_option( '-p', '--pass_through', dest='pass_through_options', action='append', type="string", help='These options are passed through directly to GATK, without any modification.' )
     parser.add_option( '-d', '--dataset', dest='datasets', action='append', type="string", nargs=4, help='"-argument" "original_filename" "galaxy_filetype" "name_prefix"' )
+    parser.add_option( '', '--max_jvm_heap', dest='max_jvm_heap', action='store', type="string", default=None, help='If specified, the maximum java virtual machine heap size will be set to the provide value.' )
+    parser.add_option( '', '--max_jvm_heap_fraction', dest='max_jvm_heap_fraction', action='store', type="int", default=0, help='If specified, the maximum java virtual machine heap size will be set to the provide value as a fraction of total physical memory.' )
     parser.add_option( '', '--stdout', dest='stdout', action='store', type="string", default=None, help='If specified, the output of stdout will be written to this file.' )
     parser.add_option( '', '--stderr', dest='stderr', action='store', type="string", default=None, help='If specified, the output of stderr will be written to this file.' )
     parser.add_option( '', '--html_report_from_directory', dest='html_report_from_directory', action='append', type="string", nargs=2, help='"Target HTML File" "Directory"')
         cmd = ' '.join( options.pass_through_options )
     else:
         cmd = ''
+    if options.max_jvm_heap:
+        cmd.replace( 'java ', 'java -Xmx%s ' % ( options.max_jvm_heap ), 1 )
+    elif options.max_jvm_heap_fraction:
+        cmd.replace( 'java ', 'java -XX:DefaultMaxRAMFraction=%s  -XX:+UseParallelGC ' % ( options.max_jvm_heap_fraction ), 1 )
     if options.datasets:
         for ( dataset_arg, filename, galaxy_ext, prefix ) in options.datasets:
             gatk_filename = gatk_filename_from_galaxy( filename, galaxy_ext, target_dir = tmp_dir, prefix = prefix )

File tools/gatk/indel_realigner.xml

View file
  • Ignore whitespace
-<tool id="gatk_indel_realigner" name="Indel Realigner" version="0.0.1">
+<tool id="gatk_indel_realigner" name="Indel Realigner" version="0.0.2">
   <description>- perform local realignment</description>
   <command interpreter="python">gatk_wrapper.py
+   --max_jvm_heap_fraction "2"
    --stdout "${output_log}"
    -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
    -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
    -p 'java 
     -jar "${GALAXY_DATA_INDEX_DIR}/shared/jars/gatk/GenomeAnalysisTK.jar"
     -T "IndelRealigner"
-    ##-quiet ##this appears to have no effect...confirmed by gatk programmers
     -o "${output_bam}"
     -et "NO_ET" ##ET no phone home
     ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
    '
    
     #set $rod_binding_names = dict()
-    #if str( $input_dbsnp_rod ) != "None":
-        -d "-D" "${input_dbsnp_rod}" "${input_dbsnp_rod.ext}" "dbsnp_rod"
-    #end if
     #for $rod_binding in $rod_bind:
         #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
             #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name
         -p '
         --entropyThreshold "${analysis_param_type.entropy_threshold}"
         ${analysis_param_type.simplify_bam}
+        --consensusDeterminationModel "${analysis_param_type.consensus_determination_model}"
         --maxIsizeForMovement "${analysis_param_type.max_insert_size_for_movement}"
         --maxPositionalMoveAllowed "${analysis_param_type.max_positional_move_allowed}"
         --maxConsensuses "${analysis_param_type.max_consensuses}"
         --maxReadsForConsensuses "${analysis_param_type.max_reads_for_consensuses}"
         --maxReadsForRealignment "${analysis_param_type.max_reads_for_realignment}"
-        "${analysis_param_type.no_original_alignment_tags}"
+        ${analysis_param_type.no_original_alignment_tags}
         '
     #end if
   </command>
       </when>
     </conditional>
     <param name="target_intervals" type="data" format="gatk_interval,bed,picard_interval_list" label="Restrict realignment to provided intervals" />
-    <param name="input_dbsnp_rod" type="data" format="gatk_dbsnp" optional="True" label="dbSNP reference ordered data (ROD)" />
     <repeat name="rod_bind" title="Binding for reference-ordered data">
         <conditional name="rod_bind_type">
 	      <param name="rod_bind_type_selector" type="select" label="Binding Type">
-	        <option value="snps" selected="True">SNPs</option>
+	        <option value="dbsnp" selected="True">dbSNP</option>
+	        <option value="snps">SNPs</option>
 	        <option value="indels">INDELs</option>
 	        <option value="custom">Custom</option>
 	      </param>
+          <when value="dbsnp">
+              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
+              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
+          </when>
           <when value="snps">
               <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
               <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
         
         <param name="entropy_threshold" type="float" value="0.15" label="percentage of mismatching base quality scores at a position to be considered having high entropy" />
         <param name="simplify_bam" type="boolean" checked="False" truevalue="-simplifyBAM" falsevalue="" label="Simplify BAM"/>
-        
+        <param name="consensus_determination_model" type="select" label="Consensus Determination Model">
+          <option value="KNOWNS_ONLY">KNOWNS_ONLY</option>
+          <option value="USE_READS" selected="True">USE_READS</option>
+          <option value="USE_SW">USE_SW</option>
+        </param>
         <param name="max_insert_size_for_movement" type="integer" value="3000" label="Maximum insert size of read pairs that we attempt to realign" />
         <param name="max_positional_move_allowed" type="integer" value="200" label="Maximum positional move in basepairs that a read can be adjusted during realignment" />
         <param name="max_consensuses" type="integer" value="30" label="Max alternate consensuses to try" />
           <param name="ref_file" value="phiX.fasta" ftype="fasta" />
           <param name="target_intervals" value="gatk/gatk_realigner_target_creator/gatk_realigner_target_creator_out_1.gatk_interval" ftype="gatk_interval" />
           <param name="input_bam" value="gatk/fake_phiX_reads_1.bam" ftype="bam" />
-          <param name="input_dbsnp_rod"  />
           <param name="rod_bind_type_selector" value="snps" />
           <param name="rodToIntervalTrackName" />
           <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" />
           <param name="lod_threshold" value="5.0" />
           <param name="knowns_only" />
           <param name="gatk_param_type_selector" value="basic" />
-          <param name="analysis_param_type_selector" value="basic" />
+          <param name="analysis_param_type_selector" value="advanced" />
+          <param name="entropy_threshold" value="0.15" />
+          <param name="simplify_bam" />
+          <param name="consensus_determination_model" value="USE_SW" />
+          <param name="max_insert_size_for_movement" value="3000" />
+          <param name="max_positional_move_allowed" value="200" />
+          <param name="max_consensuses" value="30" />
+          <param name="max_reads_for_consensuses" value="120" />
+          <param name="max_reads_for_realignment" value="20000" />
+          <param name="no_original_alignment_tags" />
           <output name="output_bam" file="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" lines_diff="2" /> 
           <output name="output_log" file="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.log.contains" compare="contains" />
       </test>
   <help>
 **What it does**
 
-     Performs local realignment of reads based on misalignments due to the presence of indels. Unlike most mappers, this 
-     walker uses the full alignment context to determine whether an appropriate alternate reference (i.e. indel) exists 
-     and updates SAMRecords accordingly.
+Performs local realignment of reads based on misalignments due to the presence of indels. Unlike most mappers, this walker uses the full alignment context to determine whether an appropriate alternate reference (i.e. indel) exists and updates SAMRecords accordingly.
+
+For more information on local realignment around indels using the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Local_realignment_around_indels&gt;`_.
+
+To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3&gt;`_.
+
+If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.
 
 ------
 
-Please cite the website "http://addlink.here" as well as:
-
-Add citation here 2011.
-
-------
-
-**Input formats**
+**Inputs**
 
 GenomeAnalysisTK: IndelRealigner accepts an aligned BAM and a list of intervals to realign as input files.
 
-------
 
 **Outputs**
 
-The output is in the BAM format, see http://addlink.here for more details.
+The output is in the BAM format.
+
+
+Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.
 
 -------
 
 **Settings**::
 
- targetIntervals                intervals file output from RealignerTargetCreator
- LODThresholdForCleaning            LOD threshold above which the cleaner will clean
- entropyThreshold                      percentage of mismatches at a locus to be considered having high entropy
- out                                                      Output bam
- bam_compression                       Compression level to use for writing BAM files
- disable_bam_indexing                                              Turn off on-the-fly creation of indices for output BAM files.
- simplifyBAM                                          If provided, output BAM files will be simplified to include just key reads for downstream variation discovery analyses (removing duplicates, PF-, non-primary reads), as well stripping all extended tags from the kept reads except the read group identifier
- useOnlyKnownIndels                                    Don't run 'Smith-Waterman' to generate alternate consenses; use only known indels provided as RODs for constructing the alternate references.
- maxReadsInMemory                  max reads allowed to be kept in memory at a time by the SAMFileWriter. Keep it low to minimize memory consumption (but the tool may skip realignment on regions with too much coverage.  If it is too low, it may generate errors during realignment); keep it high to maximize realignment (but make sure to give Java enough memory).
- maxIsizeForMovement               maximum insert size of read pairs that we attempt to realign
- maxPositionalMoveAllowed   maximum positional move in basepairs that a read can be adjusted during realignment
- maxConsensuses                   max alternate consensuses to try (necessary to improve performance in deep coverage)
- maxReadsForConsensuses           max reads used for finding the alternate consensuses (necessary to improve performance in deep coverage)
- maxReadsForRealignment         max reads allowed at an interval for realignment; if this value is exceeded, realignment is not attempted and the reads are passed to the output file(s) as-is
- noOriginalAlignmentTags                                   Don't output the original cigar or alignment start tags for each realigned read in the output bam.
- targetIntervalsAreNotSorted                      This tool assumes that the target interval list is sorted; if the list turns out to be unsorted, it will throw an exception.  Use this argument when your interval list is not sorted to instruct the Realigner to first sort it in memory.
+ targetIntervals              intervals file output from RealignerTargetCreator
+ LODThresholdForCleaning      LOD threshold above which the cleaner will clean
+ entropyThreshold             percentage of mismatches at a locus to be considered having high entropy
+ out                          Output bam
+ bam_compression              Compression level to use for writing BAM files
+ disable_bam_indexing         Turn off on-the-fly creation of indices for output BAM files.
+ simplifyBAM                  If provided, output BAM files will be simplified to include just key reads for downstream variation discovery analyses (removing duplicates, PF-, non-primary reads), as well stripping all extended tags from the kept reads except the read group identifier
+ useOnlyKnownIndels           Don't run 'Smith-Waterman' to generate alternate consenses; use only known indels provided as RODs for constructing the alternate references.
+ maxReadsInMemory             max reads allowed to be kept in memory at a time by the SAMFileWriter. Keep it low to minimize memory consumption (but the tool may skip realignment on regions with too much coverage.  If it is too low, it may generate errors during realignment); keep it high to maximize realignment (but make sure to give Java enough memory).
+ maxIsizeForMovement          maximum insert size of read pairs that we attempt to realign
+ maxPositionalMoveAllowed     maximum positional move in basepairs that a read can be adjusted during realignment
+ maxConsensuses               max alternate consensuses to try (necessary to improve performance in deep coverage)
+ maxReadsForConsensuses       max reads used for finding the alternate consensuses (necessary to improve performance in deep coverage)
+ maxReadsForRealignment       max reads allowed at an interval for realignment; if this value is exceeded, realignment is not attempted and the reads are passed to the output file(s) as-is
+ noOriginalAlignmentTags      Don't output the original cigar or alignment start tags for each realigned read in the output bam.
+ targetIntervalsAreNotSorted  This tool assumes that the target interval list is sorted; if the list turns out to be unsorted, it will throw an exception.  Use this argument when your interval list is not sorted to instruct the Realigner to first sort it in memory.
 
+------
+
+**Citation**
+
+For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. &lt;http://www.ncbi.nlm.nih.gov/pubmed/21478889&gt;`_
 
   </help>
 </tool>

File tools/gatk/realigner_target_creator.xml

View file
  • Ignore whitespace
-<tool id="gatk_realigner_target_creator" name="Realigner Target Creator" version="0.0.1">
+<tool id="gatk_realigner_target_creator" name="Realigner Target Creator" version="0.0.2">
   <description>for use in local realignment</description>
   <command interpreter="python">gatk_wrapper.py
+   --max_jvm_heap_fraction "2"
    --stdout "${output_log}"
    -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
    -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
     #end if
    '
     #set $rod_binding_names = dict()
-    #if str( $input_dbsnp_rod ) != "None":
-        -d "-D" "${input_dbsnp_rod}" "${input_dbsnp_rod.ext}" "dbsnp_rod"
-    #end if
     #for $rod_binding in $rod_bind:
         #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
             #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name
       </when>
     </conditional>
     
-    <param name="input_dbsnp_rod" type="data" format="gatk_dbsnp" optional="True" label="dbSNP reference ordered data (ROD)" />
     <repeat name="rod_bind" title="Binding for reference-ordered data">
         <conditional name="rod_bind_type">
 	      <param name="rod_bind_type_selector" type="select" label="Binding Type">
-	        <option value="snps" selected="True">SNPs</option>
+	        <option value="dbsnp" selected="True">dbSNP</option>
+	        <option value="snps">SNPs</option>
 	        <option value="indels">INDELs</option>
 	        <option value="custom">Custom</option>
 	      </param>
+          <when value="dbsnp">
+              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
+              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
+          </when>
           <when value="snps">
               <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
               <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
           <param name="reference_source_selector" value="history" />
           <param name="ref_file" value="phiX.fasta" ftype="fasta" />
           <param name="input_bam" value="gatk/fake_phiX_reads_1.bam" ftype="bam" />
-          <param name="input_dbsnp_rod"  />
-          <param name="rod_bind_type_selector" value="snps" />
+          <param name="rod_bind_type_selector" value="dbsnp" />
           <param name="rodToIntervalTrackName" />
           <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" />
           <param name="gatk_param_type_selector" value="basic" />
 
 Emits intervals for the Local Indel Realigner to target for cleaning.  Ignores 454 reads, MQ0 reads, and reads with consecutive indel operators in the CIGAR string.
 
-------
+For more information on local realignment around indels using the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Local_realignment_around_indels&gt;`_.
 
-Please cite the website "http://addlink.here" as well as:
+To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3&gt;`_.
 
-Add citation here 2011.
+If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.
 
 ------
 
-**Input formats**
+**Inputs**
 
 GenomeAnalysisTK: RealignerTargetCreator accepts an aligned BAM input file.
 
-------
 
 **Outputs**
 
-The output is in GATK Interval format, see http://addlink.here for more details.
+The output is in GATK Interval format.
+
+
+Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.
 
 -------
 
  minReadsAtLocus     minimum reads at a locus to enable using the entropy calculation
  maxIntervalSize     maximum interval size
 
+------
+
+**Citation**
+
+For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. &lt;http://www.ncbi.nlm.nih.gov/pubmed/21478889&gt;`_
+
   </help>
 </tool>

File tools/gatk/table_recalibration.xml

View file
  • Ignore whitespace
-<tool id="gatk_table_recalibration" name="Table Recalibration" version="0.0.1">
+<tool id="gatk_table_recalibration" name="Table Recalibration" version="0.0.2">
   <description>on BAM files</description>
   <command interpreter="python">gatk_wrapper.py
+   --max_jvm_heap_fraction "2"
    --stdout "${output_log}"
    -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
    -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
           <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" />
           <param name="gatk_param_type_selector" value="basic" />
           <param name="analysis_param_type_selector" value="basic" />
-          <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" lines_diff="2" />
+          <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" lines_diff="4" />
           <output name="output_log" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.log.contains" compare="contains" />
       </test>
   </tests>
   <help>
 **What it does**
 
-     This walker is designed to work as the second pass in a two-pass processing step, doing a by-read traversal.  For 
-     each base in each read this walker calculates various user-specified covariates (such as read group, reported 
-     quality score, cycle, and dinuc) Using these values as a key in a large hashmap the walker calculates an empirical 
-     base quality score and overwrites the quality score currently in the read. This walker then outputs a new bam file 
-     with these updated (recalibrated) reads.  Note: This walker expects as input the recalibration table file generated 
-     previously by CovariateCounterWalker. Note: This walker is designed to be used in conjunction with 
-     CovariateCounterWalker.
+This walker is designed to work as the second pass in a two-pass processing step, doing a by-read traversal.  For each base in each read this walker calculates various user-specified covariates (such as read group, reported quality score, cycle, and dinuc) Using these values as a key in a large hashmap the walker calculates an empirical base quality score and overwrites the quality score currently in the read. This walker then outputs a new bam file with these updated (recalibrated) reads.  Note: This walker expects as input the recalibration table file generated previously by CovariateCounterWalker. Note: This walker is designed to be used in conjunction with CovariateCounterWalker.
+
+For more information on base quality score recalibration using the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Base_quality_score_recalibration&gt;`_.
+
+To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3&gt;`_.
+
+If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.
 
 ------
 
-Please cite the website "http://addlink.here" as well as:
-
-Add citation here 2011.
-
-------
-
-**Input formats**
+**Inputs**
 
 GenomeAnalysisTK: TableRecalibration accepts an aligned BAM and a recalibration CSV input files.
 
-------
 
 **Outputs**
 
-The output is in BAM format, see http://addlink.here for more details.
+The output is in BAM format.
+
+
+Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.
 
 -------
 
 **Settings**::
 
- default_read_group                           If a read has no read group then default to the provided String.
- default_platform                                If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid.
- force_read_group                               If provided, the read group ID of EVERY read will be forced to be the provided String. This is useful to collapse all data into a single read group.
- force_platform                                    If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid.
- window_size_nqs                                 The window size used by MinimumNQSCovariate for its calculation
- homopolymer_nback                           The number of previous bases to look at in HomopolymerCovariate
- exception_if_no_tile                               If provided, TileCovariate will throw an exception when no tile can be found. The default behavior is to use tile = -1
- solid_recal_mode                             How should we recalibrate solid bases in whichthe reference was inserted? Options = DO_NOTHING, SET_Q_ZERO, SET_Q_ZERO_BASE_N, or REMOVE_REF_BIAS (DO_NOTHING|SET_Q_ZERO|SET_Q_ZERO_BASE_N|REMOVE_REF_BIAS)
- 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 (THROW_EXCEPTION|LEAVE_READ_UNRECALIBRATED|PURGE_READ)
- recal_file                                     Filename for the input covariates table recalibration .csv file
- out                                                           The output BAM file
- bam_compression                            Compression level to use for writing BAM files
- disable_bam_indexing                                                   Turn off on-the-fly creation of indices for output BAM files.
- simplifyBAM                                               If provided, output BAM files will be simplified to include just key reads for downstream variation discovery analyses (removing duplicates, PF-, non-primary reads), as well stripping all extended tags from the kept reads except the read group identifier
- preserve_qscores_less_than            Bases with quality scores less than this threshold won't be recalibrated, default=5. In general it's unsafe to change qualities scores below &lt; 5, since base callers use these values to indicate random or bad bases
- smoothing                                              Number of imaginary counts to add to each bin bin order to smooth out bins with few data points, default=1
- max_quality_score                            The integer value at which to cap the quality scores, default=50
- doNotWriteOriginalQuals                                         If true, we will not write the original quality (OQ) tag for each read
+ default_read_group             If a read has no read group then default to the provided String.
+ default_platform               If a read has no platform then default to the provided String. Valid options are illumina, 454, and solid.
+ force_read_group               If provided, the read group ID of EVERY read will be forced to be the provided String. This is useful to collapse all data into a single read group.
+ force_platform                 If provided, the platform of EVERY read will be forced to be the provided String. Valid options are illumina, 454, and solid.
+ window_size_nqs                The window size used by MinimumNQSCovariate for its calculation
+ homopolymer_nback              The number of previous bases to look at in HomopolymerCovariate
+ exception_if_no_tile           If provided, TileCovariate will throw an exception when no tile can be found. The default behavior is to use tile = -1
+ solid_recal_mode               How should we recalibrate solid bases in whichthe reference was inserted? Options = DO_NOTHING, SET_Q_ZERO, SET_Q_ZERO_BASE_N, or REMOVE_REF_BIAS (DO_NOTHING|SET_Q_ZERO|SET_Q_ZERO_BASE_N|REMOVE_REF_BIAS)
+ 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 (THROW_EXCEPTION|LEAVE_READ_UNRECALIBRATED|PURGE_READ)
+ recal_file                     Filename for the input covariates table recalibration .csv file
+ out                            The output BAM file
+ bam_compression                Compression level to use for writing BAM files
+ disable_bam_indexing           Turn off on-the-fly creation of indices for output BAM files.
+ simplifyBAM                    If provided, output BAM files will be simplified to include just key reads for downstream variation discovery analyses (removing duplicates, PF-, non-primary reads), as well stripping all extended tags from the kept reads except the read group identifier
+ preserve_qscores_less_than     Bases with quality scores less than this threshold won't be recalibrated, default=5. In general it's unsafe to change qualities scores below &lt; 5, since base callers use these values to indicate random or bad bases
+ smoothing                      Number of imaginary counts to add to each bin bin order to smooth out bins with few data points, default=1
+ max_quality_score              The integer value at which to cap the quality scores, default=50
+ doNotWriteOriginalQuals        If true, we will not write the original quality (OQ) tag for each read
+
+------
+
+**Citation**
+
+For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. &lt;http://www.ncbi.nlm.nih.gov/pubmed/21478889&gt;`_
 
   </help>
 </tool>

File tools/gatk/unified_genotyper.xml

View file
  • Ignore whitespace
-<tool id="gatk_unified_genotyper" name="Unified Genotyper" version="0.0.1">
+<tool id="gatk_unified_genotyper" name="Unified Genotyper" version="0.0.2">
   <description>SNP and indel caller</description>
   <command interpreter="python">gatk_wrapper.py
+   --max_jvm_heap_fraction "2"
    --stdout "${output_log}"
    #for $i, $input_bam in enumerate( $reference_source.input_bams ):
        -d "-I" "${input_bam.input_bam}" "${input_bam.input_bam.ext}" "gatk_input_${i}"
     --standard_min_confidence_threshold_for_emitting "${standard_min_confidence_threshold_for_emitting}"
    '
     #set $rod_binding_names = dict()
-    #if str( $input_dbsnp_rod ) != "None":
-        -d "-D" "${input_dbsnp_rod}" "${input_dbsnp_rod.ext}" "dbsnp_rod"
-    #end if
     #for $rod_binding in $rod_bind:
         #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
             #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name
       </when>
     </conditional>
     
-    <param name="input_dbsnp_rod" type="data" format="gatk_dbsnp" optional="True" label="dbSNP reference ordered data (ROD)" />
     <repeat name="rod_bind" title="Binding for reference-ordered data">
         <conditional name="rod_bind_type">
 	      <param name="rod_bind_type_selector" type="select" label="Binding Type">
-	        <option value="snps" selected="True">SNPs</option>
+	        <option value="dbsnp" selected="True">dbSNP</option>
+	        <option value="snps">SNPs</option>
 	        <option value="indels">INDELs</option>
 	        <option value="custom">Custom</option>
 	      </param>
+          <when value="dbsnp">
+              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
+              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
+          </when>
           <when value="snps">
               <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
               <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
     <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (VCF)" />
     <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
   </outputs>
+  <!-- FIXME! <trackster_conf/> -->
   <tests>
       <test>
           <param name="reference_source_selector" value="history" />
           <param name="ref_file" value="phiX.fasta" ftype="fasta" />
           <param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" />
-          <param name="input_dbsnp_rod"  />
-          <param name="rod_bind_type_selector" value="snps" />
+          <param name="rod_bind_type_selector" value="dbsnp" />
           <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" />
           <param name="rodToIntervalTrackName" />
           <param name="standard_min_confidence_threshold_for_calling" value="4" />
           <param name="doContextDependentGapPenalties" />
           <!-- <param name="annotation" value="" />
           <param name="group" value="" /> -->
-          <output name="output_interval" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.vcf" lines_diff="2"/> 
+          <output name="output_vcf" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.vcf" lines_diff="2"/> 
           <output name="output_log" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.log.contains" compare="contains"/>
       </test>
   </tests>
   <help>
 **What it does**
 
-     A variant caller which unifies the approaches of several disparate callers.  Works for single-sample and 
-     multi-sample data.  The user can choose from several different incorporated calculation models.
+A variant caller which unifies the approaches of several disparate callers.  Works for single-sample and multi-sample data.  The user can choose from several different incorporated calculation models.
+
+For more information on the GATK Unified Genotyper, see this `tool specific page &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Unified_genotyper&gt;`_.
+
+To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3&gt;`_.
+
+If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.
 
 ------
 
-Please cite the website "http://addlink.here" as well as:
-
-Add citation here 2011.
-
-------
-
-**Input formats**
+**Inputs**
 
 GenomeAnalysisTK: UnifiedGenotyper accepts an aligned BAM input file.
 
-------
 
 **Outputs**
 
-The output is in VCF format, see http://addlink.here for more details.
+The output is in VCF format.
+
+
+Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.
 
 -------
 
 **Settings**::
 
- genotype_likelihoods_model                           Genotype likelihoods calculation model to employ -- BOTH is the default option, while INDEL is also available for calling indels and SNP is available for calling SNPs only (SNP|INDEL|BOTH)
- p_nonref_model                                                  Non-reference probability calculation model to employ -- EXACT is the default option, while GRID_SEARCH is also available. (EXACT|GRID_SEARCH)
- heterozygosity                                                  Heterozygosity value used to compute prior likelihoods for any locus
- pcr_error_rate                                             The PCR error rate to be used for computing fragment-based likelihoods
- genotyping_mode                                             Should we output confident genotypes (i.e. including ref calls) or just the variants? (DISCOVERY|GENOTYPE_GIVEN_ALLELES)
- output_mode                                                    Should we output confident genotypes (i.e. including ref calls) or just the variants? (EMIT_VARIANTS_ONLY|EMIT_ALL_CONFIDENT_SITES|EMIT_ALL_SITES)
- standard_min_confidence_threshold_for_calling                         The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be called
- standard_min_confidence_threshold_for_emitting                        The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be emitted (and filtered if less than the calling threshold)
- noSLOD                                                                            If provided, we will not calculate the SLOD
- min_base_quality_score                                   Minimum base quality required to consider a base for calling
- min_mapping_quality_score                             Minimum read mapping quality required to consider a read for calling
- max_deletion_fraction                               Maximum fraction of reads with deletions spanning this locus for it to be callable [to disable, set to &lt; 0 or &gt; 1; default:0.05]
- min_indel_count_for_genotyping           Minimum number of consensus indels required to trigger genotyping run
- indel_heterozygosity                       Heterozygosity for indel calling
- indelGapContinuationPenalty                    Indel gap continuation penalty
- indelGapOpenPenalty                                    Indel gap open penalty
- indelHaplotypeSize                                    Indel haplotype size
- doContextDependentGapPenalties                                                  Vary gap penalties by context
- indel_recal_file                                         Filename for the input covariates table recalibration .csv file - EXPERIMENTAL, DO NO USE
- indelDebug                                                                 Output indel debug info
- out                                                                           File to which variants should be written
- annotation                                                             One or more specific annotations to apply to variant calls
- group                                                                       One or more classes/groups of annotations to apply to variant calls
+ genotype_likelihoods_model                        Genotype likelihoods calculation model to employ -- BOTH is the default option, while INDEL is also available for calling indels and SNP is available for calling SNPs only (SNP|INDEL|BOTH)
+ p_nonref_model                                    Non-reference probability calculation model to employ -- EXACT is the default option, while GRID_SEARCH is also available. (EXACT|GRID_SEARCH)
+ heterozygosity                                    Heterozygosity value used to compute prior likelihoods for any locus
+ pcr_error_rate                                    The PCR error rate to be used for computing fragment-based likelihoods
+ genotyping_mode                                   Should we output confident genotypes (i.e. including ref calls) or just the variants? (DISCOVERY|GENOTYPE_GIVEN_ALLELES)
+ output_mode                                       Should we output confident genotypes (i.e. including ref calls) or just the variants? (EMIT_VARIANTS_ONLY|EMIT_ALL_CONFIDENT_SITES|EMIT_ALL_SITES)
+ standard_min_confidence_threshold_for_calling     The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be called
+ standard_min_confidence_threshold_for_emitting    The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be emitted (and filtered if less than the calling threshold)
+ noSLOD                                            If provided, we will not calculate the SLOD
+ min_base_quality_score                            Minimum base quality required to consider a base for calling
+ min_mapping_quality_score                         Minimum read mapping quality required to consider a read for calling
+ max_deletion_fraction                             Maximum fraction of reads with deletions spanning this locus for it to be callable [to disable, set to &lt; 0 or &gt; 1; default:0.05]
+ min_indel_count_for_genotyping                    Minimum number of consensus indels required to trigger genotyping run
+ indel_heterozygosity                              Heterozygosity for indel calling
+ indelGapContinuationPenalty                       Indel gap continuation penalty
+ indelGapOpenPenalty                               Indel gap open penalty
+ indelHaplotypeSize                                Indel haplotype size
+ doContextDependentGapPenalties                    Vary gap penalties by context
+ indel_recal_file                                  Filename for the input covariates table recalibration .csv file - EXPERIMENTAL, DO NO USE
+ indelDebug                                        Output indel debug info
+ out                                               File to which variants should be written
+ annotation                                        One or more specific annotations to apply to variant calls
+ group                                             One or more classes/groups of annotations to apply to variant calls
+
+------
+
+**Citation**
+
+For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. &lt;http://www.ncbi.nlm.nih.gov/pubmed/21478889&gt;`_
 
   </help>
 </tool>

File tools/gatk/variant_annotator.xml

View file
  • Ignore whitespace
+<tool id="gatk_variant_annotator" name="Variant Annotator" version="0.0.1">
+  <description></description>
+  <command interpreter="python">gatk_wrapper.py
+   --max_jvm_heap_fraction "2"
+   --stdout "${output_log}"
+   #if str( $reference_source.input_bam ) != "None":
+       -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
+       -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
+   #end if
+   -d "-B:variant,%(file_type)s" "${reference_source.input_variant}" "${reference_source.input_variant.ext}" "input_variant"
+   -p 'java 
+    -jar "${GALAXY_DATA_INDEX_DIR}/shared/jars/gatk/GenomeAnalysisTK.jar"
+    -T "VariantAnnotator"
+    ##--num_threads 4 ##hard coded, for now
+    -et "NO_ET" ##ET no phone home
+    ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
+    #if $reference_source.reference_source_selector != "history":
+        -R "${reference_source.ref_file.fields.path}"
+    #end if
+    -o "${output_vcf}"
+    #if str( $annotations_type.annotations_type_selector ) == "use_all_annotations":
+        --useAllAnnotations
+    #else:
+        #if $annotations_type.annotations.value:
+            #for $annotation in str( $annotations_type.annotations ).split( ',' ):
+                --annotation "${annotation}"
+            #end for
+        #end if
+    #end if
+##    #for $additional_annotation in $additional_annotations:
+##        --annotation "${additional_annotation.additional_annotation_type.additional_annotation_type_selector}"
+##        #for $name, $param in $additional_annotation.additional_annotation_type.iteritems():
+##            #if $name not in [ "__current_case__", "additional_annotation_type_selector" ]:
+##                --${name} "${param}"
+##            #end if
+##        #end for
+##    #end for
+    #if str( $reference_source.input_variant_name ):
+        --sampleName "${reference_source.input_variant_name}"
+    #end if
+    ${reference_source.input_variant_bti}
+   '
+    
+    #set $rod_binding_names = dict()
+    #for $rod_binding in $rod_bind:
+        #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
+            #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name
+        #elif str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'comp':
+            #set $rod_bind_name = "comp" + str( $rod_binding.rod_bind_type.custom_rod_name )
+        #else 
+            #set $rod_bind_name = $rod_binding.rod_bind_type.rod_bind_type_selector
+        #end if
+        #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
+        -d "-B:${rod_bind_name},%(file_type)s" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}"
+        #if str( $rod_binding.rod_bind_type.rodToIntervalTrackName ):
+            -p '--rodToIntervalTrackName "${rod_bind_name}"'
+        #end if
+    #end for
+    
+    ##start standard gatk options
+    #if $gatk_param_type.gatk_param_type_selector == "advanced":
+        #for $sample_metadata in $gatk_param_type.sample_metadata:
+            -p '--sample_metadata "${sample_metadata.sample_metadata_file}"'
+        #end for
+        #for $read_filter in $gatk_param_type.read_filter:
+            -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}"
+            ###raise Exception( str( dir( $read_filter ) ) )
+            #for $name, $param in $read_filter.read_filter_type.iteritems():
+                #if $name not in [ "__current_case__", "read_filter_type_selector" ]:
+                    --${name} "${param}"
+                #end if
+            #end for
+            '
+        #end for
+        #if str( $gatk_param_type.input_intervals ) != "None":
+            -d "-L" "${gatk_param_type.input_intervals}" "${gatk_param_type.input_intervals.ext}" "input_intervals"
+        #end if
+        #if str( $gatk_param_type.input_exclude_intervals ) != "None":
+            -d "-XL" "${gatk_param_type.input_exclude_intervals}" "${gatk_param_type.input_exclude_intervals.ext}" "input_intervals"
+        #end if
+        
+        -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"'
+        -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"'
+        #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE":
+            -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"'
+        #end if
+        -p '
+        --baq "${gatk_param_type.baq}"
+        --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}"
+        ${gatk_param_type.use_original_qualities}
+        --defaultBaseQualities "${gatk_param_type.default_base_qualities}"
+        --validation_strictness "${gatk_param_type.validation_strictness}"
+        --interval_merging "${gatk_param_type.interval_merging}"
+        '
+        #if str( $gatk_param_type.read_group_black_list ) != "None":
+            -d "-read_group_black_list" "${gatk_param_type.read_group_black_list}" "txt" "input_read_group_black_list"
+        #end if
+    #end if
+    #if str( $reference_source.reference_source_selector ) == "history":
+        -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input"
+    #end if
+    ##end standard gatk options
+    
+    ##start analysis specific options
+    #if $analysis_param_type.analysis_param_type_selector == "advanced":
+        -p '
+        #if $analysis_param_type.group.value:
+            #for $annotation_group in str( $analysis_param_type.group ).split( ',' ):
+                --group "${annotation_group}"
+            #end for
+        #end if
+        '
+    #end if
+  </command>
+  <inputs>
+    <conditional name="reference_source">
+      <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
+        <option value="cached">Locally cached</option>
+        <option value="history">History</option>
+      </param>
+      <when value="cached">
+        <param name="input_variant" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file to annotate" />
+        <param name="input_variant_name" type="text" value="" label="Variant Name" help="Not needed for VCF inputs."/>
+        <param name="input_variant_bti" type="boolean" truevalue="-BTI variant" falsevalue="" label="Increase efficiency for small variant files." />
+        <param name="input_bam" type="data" format="bam" label="BAM file" optional="True" help="Not needed for all annotations." >
+          <validator type="unspecified_build" />
+          <validator type="dataset_metadata_in_file" filename="picard_index.loc" metadata_name="dbkey" metadata_column="1" message="Sequences are not currently available for the specified build." /> <!-- fixme!!! this needs to be a select -->
+        </param>
+        <param name="ref_file" type="select" label="Using reference genome">
+          <options from_data_table="picard_indexes">
+            <filter type="data_meta" key="dbkey" ref="input_variant" column="dbkey"/>
+          </options>
+        </param>
+      </when>
+      <when value="history"> <!-- FIX ME!!!! -->
+        <param name="input_variant" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file to annotate" />
+        <param name="input_variant_name" type="text" value="" label="Variant Name" help="Not needed for VCF inputs."/>
+        <param name="input_variant_bti" type="boolean" truevalue="-BTI variant" falsevalue="" label="Increase efficiency for small variant files." />
+        <param name="input_bam" type="data" format="bam" label="BAM file" optional="True" />
+        <param name="ref_file" type="data" format="fasta" label="Using reference file" />
+      </when>
+    </conditional>
+    <conditional name="annotations_type">
+      <param name="annotations_type_selector" type="select" label="Use all possible annotations">
+        <option value="use_all_annotations">Use all</option>
+        <option value="choose" selected="True">Use selected</option>
+      </param>
+      <when value="use_all_annotations">
+          <!-- no extra options here -->
+      </when>
+      <when value="choose">
+        <param name="annotations" type="select" multiple="True" display="checkboxes" label="Annotations to apply" >
+          <!-- might we want to load the available annotations from an external configuration file, since additional ones can be added to local installs? -->
+          <option value="AlleleBalance" />
+          <option value="BaseQualityRankSumTest" />
+          <option value="DepthOfCoverage" />
+          <option value="HomopolymerRun" />
+          <option value="MappingQualityRankSumTest" />
+          <option value="MappingQualityZero" />
+          <option value="QualByDepth" />
+          <option value="RMSMappingQuality" />
+          <option value="SpanningDeletions" />
+          <option value="HaplotypeScore" />
+          <!-- annotations below were pulled from list option -->
+          <option value="ChromosomeCounts" />
+          <option value="IndelType" />
+          <option value="HardyWeinberg" />
+          <option value="BaseCounts" />
+          <option value="LowMQ" />
+          <option value="FisherStrand" />
+          <option value="GenomicAnnotation" />
+          <option value="GCContent" />
+          <option value="ReadPosRankSumTest" />
+          <option value="SBByDepth" />
+          <option value="ReadDepthAndAllelicFractionBySample" />
+          <option value="AlleleBalanceBySample" />
+          <option value="DepthPerAlleleBySample" />
+          <option value="MappingQualityZeroBySample" />
+          <option value="NBaseCount" />
+          <option value="GLstats" />
+          <option value="SampleList" />
+          <option value="MappingQualityZeroFraction" />
+        </param>
+      </when>
+    </conditional>
+    <!-- <repeat name="additional_annotations" title="Additional annotation">
+        <conditional name="additional_annotation_type">
+          <param name="additional_annotation_type_selector" type="select" label="Choose annotation type">
+            <option value="SnpEff">snpEff</option>
+          </param>
+          <when value="SnpEff">
+            <param name="snpEffFile" type="data" format="snpEff" label="snpEff output file" />
+          </when>
+        </conditional>
+    </repeat> -->
+    <repeat name="rod_bind" title="Binding for reference-ordered data">
+        <conditional name="rod_bind_type">
+          <param name="rod_bind_type_selector" type="select" label="Binding Type">
+            <option value="variant">Variants</option>
+	        <option value="dbsnp">dbSNP</option>
+	        <option value="snps">SNPs</option>
+            <option value="comp" selected="True">Comps</option>
+            <option value="indels">INDELs</option>
+            <option value="mask">Mask</option>
+            <option value="custom">Custom</option>
+          </param>
+          <when value="variant">
+              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant ROD file" />
+              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
+          </when>
+          <when value="comp">
+              <param name="input_rod" type="data" format="vcf,gatk_dbsnp" label="ROD file" />
+              <param name="custom_rod_name" type="text" value="Unnamed" label="ROD Name"/>
+              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
+          </when>
+          <when value="dbsnp">
+              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
+              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
+          </when>
+          <when value="snps">
+              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
+              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
+          </when>
+          <when value="indels">
+              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
+              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
+          </when>
+          <when value="mask">
+              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
+              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
+          </when>
+          <when value="custom">
+              <param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/>
+              <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" />
+              <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" />
+          </when>
+        </conditional>
+    </repeat>
+    
+    <conditional name="gatk_param_type">
+      <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options">
+        <option value="basic" selected="True">Basic</option>
+        <option value="advanced">Advanced</option>
+      </param>
+      <when value="basic">
+        <!-- Do nothing here -->
+      </when>
+      <when value="advanced">
+        <repeat name="sample_metadata" title="Sample Metadata">
+            <param name="sample_metadata_file" type="data" format="txt" label="Sample file(s) in JSON format" />
+        </repeat>
+        <repeat name="read_filter" title="Read Filter">
+            <conditional name="read_filter_type">
+              <param name="read_filter_type_selector" type="select" label="Read Filter Type">
+                <option value="MaxReadLength" selected="True">MaxReadLength</option>
+                <option value="ZeroMappingQualityRead">ZeroMappingQualityRead</option>
+              </param>
+              <when value="ZeroMappingQualityRead">
+                  <!-- no extra options -->
+              </when>
+              <when value="MaxReadLength">
+                  <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/>
+              </when>
+            </conditional>
+        </repeat>
+        <param name="input_intervals" type="data" format="picard_interval_list" optional="True" label="A list of genomic intervals over which to operate" />
+        <param name="input_exclude_intervals" type="data" format="picard_interval_list" optional="True" label="A list of genomic intervals to exclude from processing" />
+        <param name="BTI_merge_rule" type="select" label="BTI merge rule">
+          <option value="UNION" selected="True">UNION</option>
+          <option value="INTERSECTION">INTERSECTION</option>
+        </param>
+        <conditional name="downsampling_type">
+          <param name="downsampling_type_selector" type="select" label="Type of reads downsampling to employ at a given locus" help="Downsampling Type">
+            <option value="NONE" selected="True">NONE</option>
+            <option value="ALL_READS">ALL_READS</option>
+            <option value="BY_SAMPLE">BY_SAMPLE</option>
+          </param>
+          <when value="NONE">
+              <!-- no more options here -->
+          </when>
+          <when value="ALL_READS">
+              <conditional name="downsample_to_type">
+                  <param name="downsample_to_type_selector" type="select" label="Type of reads downsampling to employ at a given locus" help="Downsampling Type">
+                      <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
+                      <option value="downsample_to_coverage">Downsample by Coverage</option>
+                  </param>
+                  <when value="downsample_to_fraction">
+                      <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="0.1"/>
+                  </when>
+                  <when value="downsample_to_coverage">
+                      <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0"/>
+                  </when>
+              </conditional>
+          </when>
+          <when value="BY_SAMPLE">
+              <conditional name="downsample_to_type">
+                  <param name="downsample_to_type_selector" type="select" label="Type of reads downsampling to employ at a given locus" help="Downsampling Type">
+                      <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
+                      <option value="downsample_to_coverage">Downsample by Coverage</option>
+                  </param>
+                  <when value="downsample_to_fraction">
+                      <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="0.1"/>
+                  </when>
+                  <when value="downsample_to_coverage">
+                      <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0"/>
+                  </when>
+              </conditional>
+          </when>
+        </conditional>
+        <param name="baq" type="select" label="Type of BAQ calculation to apply in the engine">
+          <option value="OFF" selected="True">OFF</option>
+          <option value="CALCULATE_AS_NECESSARY">CALCULATE_AS_NECESSARY</option>
+          <option value="RECALCULATE">RECALCULATE</option>
+        </param>
+        <param name="baq_gap_open_penalty" type="integer" label="BAQ gap open penalty (Phred Scaled)" value="40" help="Default value is 40. 30 is perhaps better for whole genome call sets."/>
+        <param name="use_original_qualities" type="boolean" truevalue="--useOriginalQualities" falsevalue="" label="Use the original base quality scores from the OQ tag" />
+        <param name="default_base_qualities" type="integer" label="Value to be used for all base quality scores, when some are missing" value="-1"/>
+        <param name="validation_strictness" type="select" label="How strict should we be with validation">
+          <option value="STRICT" selected="True">STRICT</option>
+          <option value="LENIENT">LENIENT</option>
+          <option value="SILENT">SILENT</option>
+        </param>
+        <param name="interval_merging" type="select" label="Interval merging rule">
+          <option value="ALL" selected="True">ALL</option>
+          <option value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option>
+        </param>
+        <param name="read_group_black_list" type="data" format="txt" optional="True" label="Read group black list" />
+      </when>
+    </conditional>
+    
+    <conditional name="analysis_param_type">
+      <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
+        <option value="basic" selected="True">Basic</option>
+        <option value="advanced">Advanced</option>
+      </param>
+      <when value="basic">
+        <!-- Do nothing here -->
+      </when>
+      <when value="advanced">
+        <param name="group" type="select" multiple="True" display="checkboxes" label="annotation interfaces/groups to apply to variant calls">
+          <option value="Standard">Standard</option>
+          <option value="Experimental">Experimental</option>
+          <option value="WorkInProgress">WorkInProgress</option>
+        </param>
+
+      </when>
+    </conditional>
+  </inputs>
+  <outputs>
+    <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (Variant File)" />
+    <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
+  </outputs>
+  <tests>
+      <test>
+          <param name="reference_source_selector" value="history" />
+          <param name="ref_file" value="phiX.fasta" ftype="fasta" />
+          <param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" />
+          <param name="input_variant" value="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.vcf" ftype="vcf" />
+          <param name="annotations_type_selector" value="choose" />
+          <param name="annotations" value="AlleleBalance,BaseQualityRankSumTest,DepthOfCoverage,HomopolymerRun,MappingQualityRankSumTest,MappingQualityZero,QualByDepth,RMSMappingQuality,SpanningDeletions,HaplotypeScore" />
+          <!-- <param name="additional_annotation_type_selector" value="snpEff" />
+          <param name="snpEffFile" value="single_comment.dat" ftype="snpEff" /> -->
+          <param name="rod_bind_type_selector" value="dbsnp" />
+          <param name="rodToIntervalTrackName" />
+          <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" />
+          <param name="gatk_param_type_selector" value="basic" />
+          <param name="analysis_param_type_selector" value="basic" />
+          <output name="output_vcf" file="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" lines_diff="2" /> 
+          <output name="output_log" file="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.log.contains" compare="contains" />
+      </test>
+  </tests>
+  <help>
+**What it does**
+
+Annotates variant calls with context information.  Users can specify which of the available annotations to use.
+
+For more information on using the VariantAnnotator, see this `tool specific page &lt;http://www.broadinstitute.org/gsa/wiki/index.php/VariantAnnotator&gt;`_.
+
+To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3&gt;`_.
+
+If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.
+
+------
+
+
+**Inputs**
+
+GenomeAnalysisTK: VariantAnnotator accepts a variant input file.
+
+
+**Outputs**
+
+The output is in VCF format.
+
+
+Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.
+
+-------
+
+**Settings**::
+
+
+ sampleName           The sample (NA-ID) corresponding to the variant input (for non-VCF input only)
+ annotation           One or more specific annotations to apply to variant calls
+ group                One or more classes/groups of annotations to apply to variant calls
+ expression           One or more specific expressions to apply to variant calls; see documentation for more details
+ useAllAnnotations    Use all possible annotations (not for the faint of heart)
+
+------
+
+**Citation**
+
+For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. &lt;http://www.ncbi.nlm.nih.gov/pubmed/21478889&gt;`_
+
+  </help>
+</tool>

File tools/gatk/variant_apply_recalibration.xml

View file
  • Ignore whitespace
+<tool id="gatk_variant_apply_recalibration" name="Apply Variant Recalibration" version="0.0.1">
+  <description></description>
+  <command interpreter="python">gatk_wrapper.py
+   --max_jvm_heap_fraction "2"
+   --stdout "${output_log}"
+   -d "-B:input,%(file_type)s" "${reference_source.input_variants}" "${reference_source.input_variants.ext}" "input_variants"
+   -p 'java 
+    -jar "${GALAXY_DATA_INDEX_DIR}/shared/jars/gatk/GenomeAnalysisTK.jar"
+    -T "ApplyRecalibration"
+    ##--num_threads 4 ##hard coded, for now
+    -et "NO_ET" ##ET no phone home
+    #if $reference_source.reference_source_selector != "history":
+        -R "${reference_source.ref_file.fields.path}"
+    #end if
+    --recal_file "${reference_source.input_recal}"
+    --tranches_file "${reference_source.input_tranches}"
+    --out "${output_variants}"
+   '
+    
+    ##start standard gatk options
+    #if $gatk_param_type.gatk_param_type_selector == "advanced":
+        #for $sample_metadata in $gatk_param_type.sample_metadata:
+            -p '--sample_metadata "${sample_metadata.sample_metadata_file}"'
+        #end for
+        #for $read_filter in $gatk_param_type.read_filter:
+            -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}"
+            ###raise Exception( str( dir( $read_filter ) ) )
+            #for $name, $param in $read_filter.read_filter_type.iteritems():
+                #if $name not in [ "__current_case__", "read_filter_type_selector" ]:
+                    --${name} "${param}"
+                #end if
+            #end for
+            '
+        #end for
+        #if str( $gatk_param_type.input_intervals ) != "None":
+            -d "-L" "${gatk_param_type.input_intervals}" "${gatk_param_type.input_intervals.ext}" "input_intervals"
+        #end if
+        #if str( $gatk_param_type.input_exclude_intervals ) != "None":
+            -d "-XL" "${gatk_param_type.input_exclude_intervals}" "${gatk_param_type.input_exclude_intervals.ext}" "input_intervals"
+        #end if
+        
+        -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"'
+        -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"'
+        #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE":
+            -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"'
+        #end if
+        -p '
+        --baq "${gatk_param_type.baq}"
+        --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}"
+        ${gatk_param_type.use_original_qualities}
+        --defaultBaseQualities "${gatk_param_type.default_base_qualities}"
+        --validation_strictness "${gatk_param_type.validation_strictness}"
+        --interval_merging "${gatk_param_type.interval_merging}"
+        '
+        #if str( $gatk_param_type.read_group_black_list ) != "None":
+            -d "-read_group_black_list" "${gatk_param_type.read_group_black_list}" "txt" "input_read_group_black_list"
+        #end if
+    #end if
+    #if str( $reference_source.reference_source_selector ) == "history":
+        -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input"
+    #end if
+    ##end standard gatk options
+    
+    ##start analysis specific options
+    
+    #if $analysis_param_type.analysis_param_type_selector == "advanced":
+        -p '
+        --mode "${analysis_param_type.mode}"
+        
+        #for $ignore_filter in $analysis_param_type.ignore_filters:
+            #set $ignore_filter_name = str( $ignore_filter.ignore_filter_type.ignore_filter_type_selector )
+            #if $ignore_filter_name == "custom":
+              #set $ignore_filter_name = str( $ignore_filter.ignore_filter_type.filter_name )
+            #end if
+            --ignore_filter "${ignore_filter_name}"
+        #end for
+        '
+    #end if
+    -p '--ts_filter_level "${ts_filter_level}"'
+  </command>
+  <inputs>
+    <conditional name="reference_source">
+      <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
+        <option value="cached">Locally cached</option>
+        <option value="history">History</option>
+      </param>
+      <when value="cached">
+        <param name="input_variants" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file to annotate" />
+        <param name="input_recal" type="data" format="gatk_recal" label="Variant Recalibration file" />
+        <param name="input_tranches" type="data" format="gatk_tranche" label="Variant Tranches file" />
+        <param name="ref_file" type="select" label="Using reference genome">
+          <options from_data_table="picard_indexes">
+            <filter type="data_meta" key="dbkey" ref="input_variants" column="dbkey"/>
+          </options>
+        </param>
+      </when>
+      <when value="history"> <!-- FIX ME!!!! -->
+        <param name="input_variants" type="data" format="vcf,gatk_dbsnp,bed" label="Variant file to annotate" />
+        <param name="input_recal" type="data" format="gatk_recal" label="Variant Recalibration file" />
+        <param name="input_tranches" type="data" format="gatk_tranche" label="Variant Tranches file" />
+        <param name="ref_file" type="data" format="fasta" label="Using reference file" />
+      </when>
+    </conditional>
+    
+    <conditional name="gatk_param_type">
+      <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options">
+        <option value="basic" selected="True">Basic</option>
+        <option value="advanced">Advanced</option>
+      </param>
+      <when value="basic">
+        <!-- Do nothing here -->
+      </when>
+      <when value="advanced">
+        <repeat name="sample_metadata" title="Sample Metadata">
+            <param name="sample_metadata_file" type="data" format="txt" label="Sample file(s) in JSON format" />
+        </repeat>
+        <repeat name="read_filter" title="Read Filter">
+            <conditional name="read_filter_type">
+              <param name="read_filter_type_selector" type="select" label="Read Filter Type">
+                <option value="MaxReadLength" selected="True">MaxReadLength</option>
+                <option value="ZeroMappingQualityRead">ZeroMappingQualityRead</option>
+              </param>
+              <when value="ZeroMappingQualityRead">
+                  <!-- no extra options -->
+              </when>