annotate test-data/filtered_Mutect2-out6.vcf @ 0:c51c08cc9fcc draft

"planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/gatk4 commit 408454e8d10befcc76f38ab446091778537d4f31"

##fileformat=VCFv4.2
##FILTER=<ID=FAIL,Description="Fail the site if all alleles fail but for different reasons.">
##FILTER=<ID=PASS,Description="Site contains at least one allele that passes filters">
##FILTER=<ID=base_qual,Description="alt median base quality">
##FILTER=<ID=clustered_events,Description="Clustered events observed in the tumor">
##FILTER=<ID=contamination,Description="contamination">
##FILTER=<ID=duplicate,Description="evidence for alt allele is overrepresented by apparent duplicates">
##FILTER=<ID=fragment,Description="abs(ref - alt) median fragment length">
##FILTER=<ID=germline,Description="Evidence indicates this site is germline, not somatic">
##FILTER=<ID=haplotype,Description="Variant near filtered variant on same haplotype.">
##FILTER=<ID=low_allele_frac,Description="Allele fraction is below specified threshold">
##FILTER=<ID=map_qual,Description="ref - alt median mapping quality">
##FILTER=<ID=multiallelic,Description="Site filtered because too many alt alleles pass tumor LOD">
##FILTER=<ID=n_ratio,Description="Ratio of N to alt exceeds specified ratio">
##FILTER=<ID=normal_artifact,Description="artifact_in_normal">
##FILTER=<ID=orientation,Description="orientation bias detected by the orientation bias mixture model">
##FILTER=<ID=panel_of_normals,Description="Blacklisted site in panel of normals">
##FILTER=<ID=position,Description="median distance of alt variants from end of reads">
##FILTER=<ID=possible_numt,Description="Allele depth is below expected coverage of NuMT in autosome">
##FILTER=<ID=slippage,Description="Site filtered due to contraction of short tandem repeat region">
##FILTER=<ID=strand_bias,Description="Evidence for alt allele comes from one read direction only">
##FILTER=<ID=strict_strand,Description="Evidence for alt allele is not represented in both directions">
##FILTER=<ID=weak_evidence,Description="Mutation does not meet likelihood threshold">
##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
##FORMAT=<ID=AF,Number=A,Type=Float,Description="Allele fractions of alternate alleles in the tumor">
##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
##FORMAT=<ID=F1R2,Number=R,Type=Integer,Description="Count of reads in F1R2 pair orientation supporting each allele">
##FORMAT=<ID=F2R1,Number=R,Type=Integer,Description="Count of reads in F2R1 pair orientation supporting each allele">
##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another; will always be heterozygous and is not intended to describe called alleles">
##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Phasing set (typically the position of the first variant in the set)">
##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias.">
##GATKCommandLine=<ID=FilterMutectCalls,CommandLine="FilterMutectCalls  --output filtered.vcf --variant input.vcf --reference reference.fa --QUIET true  --threshold-strategy OPTIMAL_F_SCORE --f-score-beta 1.0 --false-discovery-rate 0.05 --initial-threshold 0.1 --mitochondria-mode false --max-events-in-region 2 --max-alt-allele-count 1 --unique-alt-read-count 0 --min-median-mapping-quality 30 --min-median-base-quality 20 --max-median-fragment-length-difference 10000 --min-median-read-position 1 --max-n-ratio Infinity --min-reads-per-strand 0 --min-allele-fraction 0.0 --contamination-estimate 0.0 --log-snv-prior -13.815510557964275 --log-indel-prior -16.11809565095832 --log-artifact-prior -2.302585092994046 --normal-p-value-threshold 0.001 --min-slippage-length 8 --pcr-slippage-rate 0.1 --distance-on-haplotype 100 --long-indel-length 5 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false",Version="4.1.7.0",Date="December 29, 2021 1:18:10 AM CET">
##GATKCommandLine=<ID=Mutect2,CommandLine="Mutect2  --tumor-sample NA12891 --output output.vcf --input tumor.bam --input normal.bam --reference reference.fa --QUIET true  --f1r2-median-mq 50 --f1r2-min-bq 20 --f1r2-max-depth 200 --genotype-pon-sites false --genotype-germline-sites false --af-of-alleles-not-in-resource -1.0 --mitochondria-mode false --tumor-lod-to-emit 3.0 --initial-tumor-lod 2.0 --pcr-snv-qual 40 --pcr-indel-qual 40 --max-population-af 0.01 --downsampling-stride 1 --callable-depth 10 --max-suspicious-reads-per-alignment-start 0 --normal-lod 2.2 --ignore-itr-artifacts false --gvcf-lod-band -2.5 --gvcf-lod-band -2.0 --gvcf-lod-band -1.5 --gvcf-lod-band -1.0 --gvcf-lod-band -0.5 --gvcf-lod-band 0.0 --gvcf-lod-band 0.5 --gvcf-lod-band 1.0 --minimum-allele-fraction 0.0 --independent-mates false --disable-adaptive-pruning false --kmer-size 10 --kmer-size 25 --dont-increase-kmer-sizes-for-cycles false --allow-non-unique-kmers-in-ref false --num-pruning-samples 1 --min-dangling-branch-length 4 --recover-all-dangling-branches false --max-num-haplotypes-in-population 128 --min-pruning 2 --adaptive-pruning-initial-error-rate 0.001 --pruning-lod-threshold 2.302585092994046 --max-unpruned-variants 100 --linked-de-bruijn-graph false --disable-artificial-haplotype-recovery false --debug-assembly false --debug-graph-transformations false --capture-assembly-failure-bam false --error-correction-log-odds -Infinity --error-correct-reads false --kmer-length-for-read-error-correction 25 --min-observations-for-kmer-to-be-solid 20 --base-quality-score-threshold 18 --pair-hmm-gap-continuation-penalty 10 --pair-hmm-implementation FASTEST_AVAILABLE --pcr-indel-model CONSERVATIVE --phred-scaled-global-read-mismapping-rate 45 --native-pair-hmm-threads 4 --native-pair-hmm-use-double-precision false --bam-writer-type CALLED_HAPLOTYPES --dont-use-soft-clipped-bases false --min-base-quality-score 10 --smith-waterman JAVA --emit-ref-confidence NONE --max-mnp-distance 1 --force-call-filtered-alleles false --allele-informative-reads-overlap-margin 2 --min-assembly-region-size 50 --max-assembly-region-size 300 --active-probability-threshold 0.002 --max-prob-propagation-distance 50 --force-active false --assembly-region-padding 100 --padding-around-indels 75 --padding-around-snps 20 --padding-around-strs 75 --max-reads-per-alignment-start 50 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false --max-read-length 2147483647 --min-read-length 30 --minimum-mapping-quality 20 --disable-tool-default-annotations false --enable-all-annotations false",Version="4.1.7.0",Date="May 8, 2020 3:34:24 PM CEST">
##INFO=<ID=AS_FilterStatus,Number=A,Type=String,Description="Filter status for each allele, as assessed by ApplyRecalibration. Note that the VCF filter field will reflect the most lenient/sensitive status across all alleles.">
##INFO=<ID=AS_SB_TABLE,Number=1,Type=String,Description="Allele-specific forward/reverse read counts for strand bias tests. Includes the reference and alleles separated by |.">
##INFO=<ID=AS_UNIQ_ALT_READ_COUNT,Number=A,Type=Integer,Description="Number of reads with unique start and mate end positions for each alt at a variant site">
##INFO=<ID=CONTQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to contamination">
##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
##INFO=<ID=ECNT,Number=1,Type=Integer,Description="Number of events in this haplotype">
##INFO=<ID=GERMQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not germline variants">
##INFO=<ID=MBQ,Number=R,Type=Integer,Description="median base quality">
##INFO=<ID=MFRL,Number=R,Type=Integer,Description="median fragment length">
##INFO=<ID=MMQ,Number=R,Type=Integer,Description="median mapping quality">
##INFO=<ID=MPOS,Number=A,Type=Integer,Description="median distance from end of read">
##INFO=<ID=NALOD,Number=A,Type=Float,Description="Negative log 10 odds of artifact in normal with same allele fraction as tumor">
##INFO=<ID=NCount,Number=1,Type=Integer,Description="Count of N bases in the pileup">
##INFO=<ID=NLOD,Number=A,Type=Float,Description="Normal log 10 likelihood ratio of diploid het or hom alt genotypes">
##INFO=<ID=OCM,Number=1,Type=Integer,Description="Number of alt reads whose original alignment doesn't match the current contig.">
##INFO=<ID=PON,Number=0,Type=Flag,Description="site found in panel of normals">
##INFO=<ID=POPAF,Number=A,Type=Float,Description="negative log 10 population allele frequencies of alt alleles">
##INFO=<ID=ROQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to read orientation artifact">
##INFO=<ID=RPA,Number=R,Type=Integer,Description="Number of times tandem repeat unit is repeated, for each allele (including reference)">
##INFO=<ID=RU,Number=1,Type=String,Description="Tandem repeat unit (bases)">
##INFO=<ID=SEQQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not sequencing errors">
##INFO=<ID=STR,Number=0,Type=Flag,Description="Variant is a short tandem repeat">
##INFO=<ID=STRANDQ,Number=1,Type=Integer,Description="Phred-scaled quality of strand bias artifact">
##INFO=<ID=STRQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles in STRs are not polymerase slippage errors">
##INFO=<ID=TLOD,Number=A,Type=Float,Description="Log 10 likelihood ratio score of variant existing versus not existing">
##MutectVersion=2.2
##contig=<ID=chr20,length=63025520>
##filtering_status=These calls have been filtered by FilterMutectCalls to label false positives with a list of failed filters and true positives with PASS.
##source=FilterMutectCalls
##source=Mutect2
##tumor_sample=NA12891
##tumor_sample=NA12892
#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA12891	NA12892
chr20	862991	.	C	G	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=10,7|4,1;DP=22;ECNT=1;GERMQ=56;MBQ=39,37;MFRL=340,366;MMQ=60,60;MPOS=19;POPAF=7.30;TLOD=11.91	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:5,5:0.491:10:4,3:1,1:1,4,4,1	0/1:12,0:0.071:12:6,0:6,0:9,3,0,0
chr20	863148	.	C	CTAT	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=19,18|4,5;DP=50;ECNT=1;GERMQ=72;MBQ=38,39;MFRL=351,362;MMQ=60,60;MPOS=34;POPAF=7.30;RPA=1,2;RU=TAT;STR;STRQ=93;TLOD=29.75	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:11,9:0.454:20:4,4:6,4:5,6,4,5	0/1:26,0:0.034:26:14,0:11,0:14,12,0,0
chr20	863271	.	A	G	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=24,10|5,4;DP=44;ECNT=1;GERMQ=74;MBQ=36,37;MFRL=347,359;MMQ=60,60;MPOS=31;POPAF=7.30;TLOD=26.85	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:8,9:0.526:17:4,5:4,4:7,1,5,4	0/1:26,0:0.035:26:15,0:10,0:17,9,0,0
chr20	863508	.	A	G	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=24,20|6,6;DP=59;ECNT=1;GERMQ=82;MBQ=39,40;MFRL=343,355;MMQ=60,60;MPOS=32;POPAF=7.30;TLOD=36.80	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:11,12:0.524:23:6,6:4,6:4,7,6,6	0/1:33,0:0.028:33:16,0:16,0:20,13,0,0
chr20	863706	.	C	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=7,25|9,11;DP=53;ECNT=2;GERMQ=40;MBQ=37,39;MFRL=341,345;MMQ=60,60;MPOS=21;POPAF=7.30;TLOD=65.75	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:0,20:0.955:20:0,12:0,7:0,0,9,11	0/1:32,0:0.029:32:9,0:23,0:7,25,0,0
chr20	863744	.	C	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=10,24|6,6;DP=48;ECNT=2;GERMQ=64;MBQ=39,38;MFRL=341,347;MMQ=60,60;MPOS=27;POPAF=7.30;TLOD=38.56	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:8,12:0.591:20:5,7:3,5:4,4,6,6	0/1:26,0:0.035:26:10,0:16,0:6,20,0,0
chr20	863846	.	C	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=28,10|4,3;DP=48;ECNT=2;GERMQ=88;MBQ=40,38;MFRL=348,343;MMQ=60,60;MPOS=27;POPAF=7.30;TLOD=20.26	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:17,7:0.309:24:11,5:5,2:14,3,4,3	0/1:21,0:0.042:21:9,0:12,0:14,7,0,0
chr20	863873	.	C	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=23,11|7,3;DP=48;ECNT=2;GERMQ=70;MBQ=39,37;MFRL=353,337;MMQ=60,60;MPOS=26;POPAF=7.30;TLOD=30.15	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:21,0:0.041:21:14,0:6,0:15,6,0,0	0/1:13,10:0.440:23:8,3:5,7:8,5,7,3
chr20	864074	.	T	C	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=19,20|8,3;DP=53;ECNT=1;GERMQ=76;MBQ=38,36;MFRL=344,355;MMQ=60,60;MPOS=17;POPAF=7.30;TLOD=31.98	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:13,11:0.465:24:7,9:5,2:5,8,8,3	0/1:26,0:0.035:26:13,0:13,0:14,12,0,0
chr20	864199	.	G	A	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=30,18|4,9;DP=63;ECNT=1;GERMQ=86;MBQ=36,39;MFRL=343,361;MMQ=60,60;MPOS=24;POPAF=7.30;TLOD=37.97	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:15,13:0.470:28:7,7:7,6:13,2,4,9	0/1:33,0:0.028:33:23,0:10,0:17,16,0,0
chr20	864301	.	G	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=20,17|12,6;DP=57;ECNT=1;GERMQ=52;MBQ=35,35;MFRL=344,358;MMQ=60,60;MPOS=28;POPAF=7.30;TLOD=56.37	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:12,18:0.594:30:9,12:3,6:6,6,12,6	0/1:25,0:0.036:25:11,0:14,0:14,11,0,0
chr20	864455	.	T	C	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=11,17|15,17;DP=63;ECNT=2;GERMQ=33;MBQ=35,39;MFRL=343,360;MMQ=60,60;MPOS=27;POPAF=7.30;TLOD=115.14	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:0,32:0.971:32:0,16:0,16:0,0,15,17	0/1:28,0:0.033:28:19,0:8,0:11,17,0,0
chr20	864512	.	A	G	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=17,22|11,15;DP=71;ECNT=2;GERMQ=39;MBQ=38,37;MFRL=344,364;MMQ=60,60;MPOS=19;POPAF=7.30;TLOD=88.07	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:14,26:0.647:40:8,12:5,14:9,5,11,15	0/1:25,0:0.035:25:12,0:12,0:8,17,0,0
chr20	864640	.	C	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=16,18|14,14;DP=64;ECNT=2;GERMQ=34;MBQ=38,35;MFRL=339,354;MMQ=60,60;MPOS=22;POPAF=7.30;TLOD=94.78	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:0,28:0.968:28:0,11:0,17:0,0,14,14	0/1:34,0:0.028:34:22,0:12,0:16,18,0,0
chr20	864660	.	G	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=16,15|11,11;DP=55;ECNT=2;GERMQ=37;MBQ=37,38;MFRL=340,358;MMQ=60,60;MPOS=29;POPAF=7.30;TLOD=69.72	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:0,22:0.960:22:0,8:0,12:0,0,11,11	0/1:31,0:0.030:31:17,0:13,0:16,15,0,0
chr20	865054	.	G	C	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=10,8|6,4;DP=30;ECNT=1;GERMQ=43;MBQ=35,34;MFRL=347,347;MMQ=60,60;MPOS=23;POPAF=7.30;TLOD=30.15	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:9,10:0.524:19:7,6:2,4:6,3,6,4	0/1:9,0:0.092:9:3,0:5,0:4,5,0,0
chr20	865366	.	G	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=13,13|15,11;DP=54;ECNT=1;GERMQ=33;MBQ=39,37;MFRL=343,353;MMQ=60,60;MPOS=24;POPAF=7.30;TLOD=88.44	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:0,26:0.965:26:0,14:0,10:0,0,15,11	0/1:26,0:0.035:26:10,0:16,0:13,13,0,0
chr20	865537	.	C	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=17,29|6,3;DP=58;ECNT=1;GERMQ=93;MBQ=35,35;MFRL=350,358;MMQ=60,60;MPOS=21;POPAF=7.30;TLOD=24.37	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:19,9:0.333:28:10,4:9,5:8,11,6,3	0/1:27,0:0.034:27:13,0:13,0:9,18,0,0
chr20	865664	.	TC	T	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=20,20|7,10;DP=59;ECNT=1;GERMQ=52;MBQ=35,34;MFRL=348,359;MMQ=60,60;MPOS=25;POPAF=7.30;RPA=4,3;RU=C;STR;STRQ=93;TLOD=42.63	GT:AD:AF:DP:F1R2:F2R1:SB	0/1:19,17:0.474:36:10,11:9,4:11,8,7,10	0/1:21,0:0.043:21:7,0:10,0:9,12,0,0