gatk-3.8/public/testdata/sites_to_validate.vcf

44 lines
15 KiB
Plaintext

##fileformat=VCFv4.0
##ApplyRecalibration="analysis_type=ApplyRecalibration input_file=[] sample_metadata=[] read_buffer_size=null phone_home=STANDARD read_filter=[] intervals=[20] excludeIntervals=null reference_sequence=/seq/references/Homo_sapiens_assembly19/v1/Homo_sapiens_assembly19.fasta rodBind=[/humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/calls/combined.phase1.chr20.raw.snps.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 recal_file=/humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/recal/baseline.ALL.chr20.recal tranches_file=/humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/recal/baseline.ALL.chr20.tranches 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 ts_filter_level=99.9 ignore_filter=null mode=SNP"
##CombineVariants="analysis_type=CombineVariants input_file=[] sample_metadata=[] read_buffer_size=null phone_home=STANDARD read_filter=[] intervals=[20:57000001-60000000] excludeIntervals=null reference_sequence=/humgen/1kg/reference/human_g1k_v37.fasta rodBind=[/humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/calls/chr20/AFR/AFR.phase1.chr20.20.raw.snps.vcf, /humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/calls/chr20/ASN/ASN.phase1.chr20.20.raw.snps.vcf, /humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/calls/chr20/AMR/AMR.phase1.chr20.20.raw.snps.vcf, /humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/calls/chr20/EUR/EUR.phase1.chr20.20.raw.snps.vcf, /humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/calls/chr20/AFR.admix/AFR.admix.phase1.chr20.20.raw.snps.vcf, /humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/calls/chr20/ASN.admix/ASN.admix.phase1.chr20.20.raw.snps.vcf, /humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/calls/chr20/AMR.admix/AMR.admix.phase1.chr20.20.raw.snps.vcf, /humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/calls/chr20/EUR.admix/EUR.admix.phase1.chr20.20.raw.snps.vcf, /humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/calls/chr20/ALL/ALL.phase1.chr20.20.raw.snps.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=ALL,AFR.admix,AMR.admix,EUR.admix,ASN.admix,AFR,AMR,EUR,ASN printComplexMerges=false filteredAreUncalled=false minimalVCF=false setKey=pop assumeIdenticalSamples=false minimumN=1 masterMerge=false mergeInfoWithMaxAC=true"
##FILTER=<ID=TruthSensitivityTranche99.90to99.91,Description="Truth sensitivity tranche level at VSQ Lod: -0.4524 <= x < 0.0134">
##FILTER=<ID=TruthSensitivityTranche99.91to99.92,Description="Truth sensitivity tranche level at VSQ Lod: -0.7529 <= x < -0.4524">
##FILTER=<ID=TruthSensitivityTranche99.92to99.93,Description="Truth sensitivity tranche level at VSQ Lod: -1.608 <= x < -0.7529">
##FILTER=<ID=TruthSensitivityTranche99.93to99.94,Description="Truth sensitivity tranche level at VSQ Lod: -2.8478 <= x < -1.608">
##FILTER=<ID=TruthSensitivityTranche99.94to100.00+,Description="Truth sensitivity tranche level at VQS Lod < -Infinity">
##FILTER=<ID=TruthSensitivityTranche99.94to100.00,Description="Truth sensitivity tranche level at VSQ Lod: -Infinity <= x < -2.8478">
##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">
##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=VQSLOD,Number=1,Type=Float,Description="Log odds ratio of being a true variant versus being false under the trained gaussian mixture model">
##INFO=<ID=pop,Number=1,Type=String,Description="Source VCF for the merged record in CombineVariants">
##SelectVariants="analysis_type=SelectVariants input_file=[] sample_metadata=[] read_buffer_size=null phone_home=STANDARD read_filter=[] intervals=null excludeIntervals=null reference_sequence=/humgen/1kg/reference/human_g1k_v37.fasta rodBind=[/humgen/1kg/processing/production_wgs_phase1/consensus_wgs/v2b/recal/baseline.ALL.chr20.recal.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 sample=[HG00108, HG00111, HG00117, HG00118, HG00125, HG00127, HG00128, HG00136, HG00137, HG00138, HG00139, HG00141, HG00146, HG00150, HG00152, HG00156, HG00160, HG00171, HG00173, HG00174, HG00182, HG00187, HG00190, HG00234, HG00235, HG00237, HG00242, HG00244, HG00246, HG00250, HG00251, HG00254, HG00257, HG00262, HG00266, HG00268, HG00277, HG00284, HG00306, HG00313, HG00319, HG00321, HG00326, HG00327, HG00328, HG00329, HG00330, HG00331, HG00334, HG00336, HG00339, HG00342, HG00344, HG00346, HG00351, HG00353, HG00357, HG00372, HG00375, HG00419, HG00428, HG00436, HG00446, HG00448, HG00457, HG00478, HG00479, HG00524, HG00530, HG00533, HG00534, HG00537, HG00543, HG00554, HG00556, HG00557, HG00577, HG00578, HG00595, HG00596, HG00608, HG00620, HG00634, HG00635, HG00637, HG00638, HG00640, HG00650, HG00651, HG00656, HG00671, HG00672, HG00683, HG00684, HG00689, HG00690, HG00699, HG00702, HG00704, HG00708, HG01055, HG01060, HG01066, HG01070, HG01079, HG01083, HG01101, HG01102, HG01113, HG01133, HG01140, HG01148, HG01170, HG01171, HG01173, HG01174, HG01188, HG01191, HG01197, HG01204, HG01251, HG01350, HG01354, HG01356, HG01360, HG01366, HG01375, HG01389, HG01437, HG01441, HG01456, HG01462, HG01495, HG01497, HG01516, HG01521, HG01522, HG01550, HG01551, NA06989, NA06994, NA07037, NA07048, NA07051, NA07056, NA07346, NA07347, NA10851, NA11843, NA11892, NA11893, NA11894, NA11930, NA11993, NA12044, NA12046, NA12058, NA12273, NA12282, NA12286, NA12287, NA12341, NA12342, NA12399, NA12413, NA12489, NA12546, NA12717, NA12748, NA12749, NA12751, NA12777, NA12812, NA12830, NA12873, NA18487, NA18507, NA18511, NA18523, NA18535, NA18541, NA18542, NA18544, NA18546, NA18547, NA18550, NA18563, NA18573, NA18577, NA18592, NA18593, NA18602, NA18603, NA18608, NA18609, NA18610, NA18612, NA18615, NA18616, NA18621, NA18622, NA18623, NA18624, NA18627, NA18630, NA18633, NA18636, NA18637, NA18638, NA18639, NA18642, NA18740, NA18856, NA18861, NA18867, NA18868, NA18871, NA18874, NA18907, NA18910, NA18916, NA18917, NA18923, NA18933, NA18934, NA18943, NA18948, NA18950, NA18956, NA18957, NA18959, NA18960, NA18965, NA18968, NA18971, NA18973, NA18974, NA18976, NA18983, NA18984, NA18985, NA18995, NA19005, NA19007, NA19010, NA19056, NA19057, NA19064, NA19066, NA19072, NA19074, NA19077, NA19080, NA19081, NA19083, NA19085, NA19088, NA19093, NA19099, NA19107, NA19108, NA19129, NA19138, NA19150, NA19160, NA19171, NA19198, NA19200, NA19204, NA19209, NA19235, NA19236, NA19248, NA19257, NA19309, NA19311, NA19313, NA19321, NA19324, NA19331, NA19332, NA19334, NA19346, NA19347, NA19360, NA19372, NA19376, NA19382, NA19383, NA19384, NA19390, NA19394, NA19395, NA19428, NA19430, NA19436, NA19439, NA19440, NA19451, NA19453, NA19457, NA19463, NA19466, NA19468, NA19470, NA19471, NA19472, NA19660, NA19661, NA19663, NA19676, NA19684, NA19700, NA19712, NA19722, NA19725, NA19728, NA19729, NA19731, NA19740, NA19749, NA19755, NA19756, NA19758, NA19759, NA19770, NA19773, NA19777, NA19780, NA19783, NA19818, NA19835, NA19900, NA19985, NA20276, NA20278, NA20282, NA20287, NA20296, NA20314, NA20317, NA20336, NA20341, NA20342, NA20344, NA20346, NA20412, NA20502, NA20504, NA20505, NA20515, NA20516, NA20521, NA20524, NA20525, NA20528, NA20530, NA20532, NA20537, NA20538, NA20540, NA20544, NA20581, NA20589, NA20753, NA20759, NA20765, NA20768, NA20769, NA20774, NA20775, NA20783, NA20787, NA20790, NA20800, NA20802, NA20804, NA20807, NA20810, NA20812, NA20815, NA20816, NA20819, val_samples.list] select_expressions=[] excludeNonVariants=false excludeFiltered=false discordance= concordance= family_structure= mendelianViolation=false mendelianViolationQualThreshold=0.0 select_random_number=0 select_random_fraction=0.0 selectSNPs=false selectIndels=false"
##UnifiedGenotyper="analysis_type=UnifiedGenotyper input_file=[/humgen/1kg/phase1_cleaned_bams/bams/chr20/CHB.phase1.chr20.20.cleaned.bam, /humgen/1kg/phase1_cleaned_bams/bams/chr20/CHS.phase1.chr20.20.cleaned.bam, /humgen/1kg/phase1_cleaned_bams/bams/chr20/CLM.phase1.chr20.20.cleaned.bam, /humgen/1kg/phase1_cleaned_bams/bams/chr20/JPT.phase1.chr20.20.cleaned.bam, /humgen/1kg/phase1_cleaned_bams/bams/chr20/MXL.phase1.chr20.20.cleaned.bam, /humgen/1kg/phase1_cleaned_bams/bams/chr20/PUR.phase1.chr20.20.cleaned.bam] sample_metadata=[] read_buffer_size=null phone_home=STANDARD read_filter=[] intervals=[20:57000001-60000000] excludeIntervals=null reference_sequence=/humgen/1kg/reference/human_g1k_v37.fasta rodBind=[/humgen/1kg/processing/production_wgs_phase1/consensus/ALL.phase1.wgs.unionBC1.chr20.pass.sites.vcf, /humgen/gsa-hpprojects/GATK/data/dbsnp_132_b37.leftAligned.vcf] rodToIntervalTrackName=null BTI_merge_rule=UNION nonDeterministicRandomSeed=false DBSNP=null downsampling_type=null downsample_to_fraction=null downsample_to_coverage=50 baq=CALCULATE_AS_NECESSARY 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=SNP p_nonref_model=EXACT heterozygosity=0.0010 pcr_error_rate=1.0E-4 genotyping_mode=GENOTYPE_GIVEN_ALLELES output_mode=EMIT_VARIANTS_ONLY 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=0.05 min_indel_count_for_genotyping=5 indel_heterozygosity=1.25E-4 indelGapContinuationPenalty=10.0 indelGapOpenPenalty=45.0 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=[]"
##source=SelectVariants
#CHROM POS ID REF ALT QUAL FILTER INFO
20 207414 . G A 85.09 PASS .
20 792122 . TCCC T 22.24 PASS .
20 994145 . G GAAG 48.21 PASS .
20 1074230 . C T 2.29 QD .
20 1084330 . AC GT 42.21 PASS .