Mercurial > repos > iuc > gemini_mendel_errors
diff test-data/util/build-data/test.de_novo.vcf @ 4:00c2734b3bea draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gemini commit 283362494058ed64143b1f27afb447b8a1cb4313
| author | iuc |
|---|---|
| date | Fri, 14 Dec 2018 12:45:48 -0500 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/util/build-data/test.de_novo.vcf Fri Dec 14 12:45:48 2018 -0500 @@ -0,0 +1,127 @@ +##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="Approximate read depth (reads with MQ=255 or with bad mates are filtered)"> +##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=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=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered"> +##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"> +##UnifiedGenotyper="analysis_type=UnifiedGenotyper input_file=[bam/M10478.conc.on.pos.realigned.bam, bam/M10475.conc.on.pos.realigned.bam, bam/M10500.conc.on.pos.realigned.bam, bam/M128215.conc.on.pos.realigned.bam] read_buffer_size=null phone_home=STANDARD read_filter=[] intervals=null excludeIntervals=null interval_set_rule=UNION interval_merging=ALL reference_sequence=/m/cphg-quinlan/cphg-quinlan/shared/genomes/hg19/bwa/gatk/hg19_gatk.fa rodBind=[] nonDeterministicRandomSeed=false downsampling_type=BY_SAMPLE downsample_to_fraction=null downsample_to_coverage=250 baq=OFF baqGapOpenPenalty=40.0 performanceLog=null useOriginalQualities=false defaultBaseQualities=-1 validation_strictness=SILENT unsafe=null num_threads=10 num_cpu_threads=null num_io_threads=null num_bam_file_handles=null read_group_black_list=null pedigree=[] pedigreeString=[] pedigreeValidationType=STRICT allow_intervals_with_unindexed_bam=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_VARIANTS_ONLY standard_min_confidence_threshold_for_calling=30.0 standard_min_confidence_threshold_for_emitting=30.0 computeSLOD=false alleles=(RodBinding name= source=UNBOUND) min_base_quality_score=17 max_deletion_fraction=0.05 multiallelic=false max_alternate_alleles=5 min_indel_count_for_genotyping=5 indel_heterozygosity=1.25E-4 indelGapContinuationPenalty=10.0 indelGapOpenPenalty=45.0 indelHaplotypeSize=80 bandedIndel=false indelDebug=false ignoreSNPAlleles=false dbsnp=(RodBinding name= source=UNBOUND) 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=[] excludeAnnotation=[] filter_mismatching_base_and_quals=false" +##contig=<ID=chr1,length=249250621,assembly=hg19> +##contig=<ID=chr10,length=135534747,assembly=hg19> +##contig=<ID=chr11,length=135006516,assembly=hg19> +##contig=<ID=chr11_gl000202_random,length=40103,assembly=hg19> +##contig=<ID=chr12,length=133851895,assembly=hg19> +##contig=<ID=chr13,length=115169878,assembly=hg19> +##contig=<ID=chr14,length=107349540,assembly=hg19> +##contig=<ID=chr15,length=102531392,assembly=hg19> +##contig=<ID=chr16,length=90354753,assembly=hg19> +##contig=<ID=chr17,length=81195210,assembly=hg19> +##contig=<ID=chr17_ctg5_hap1,length=1680828,assembly=hg19> +##contig=<ID=chr17_gl000203_random,length=37498,assembly=hg19> +##contig=<ID=chr17_gl000204_random,length=81310,assembly=hg19> +##contig=<ID=chr17_gl000205_random,length=174588,assembly=hg19> +##contig=<ID=chr17_gl000206_random,length=41001,assembly=hg19> +##contig=<ID=chr18,length=78077248,assembly=hg19> +##contig=<ID=chr18_gl000207_random,length=4262,assembly=hg19> +##contig=<ID=chr19,length=59128983,assembly=hg19> +##contig=<ID=chr19_gl000208_random,length=92689,assembly=hg19> +##contig=<ID=chr19_gl000209_random,length=159169,assembly=hg19> +##contig=<ID=chr1_gl000191_random,length=106433,assembly=hg19> +##contig=<ID=chr1_gl000192_random,length=547496,assembly=hg19> +##contig=<ID=chr2,length=243199373,assembly=hg19> +##contig=<ID=chr20,length=63025520,assembly=hg19> +##contig=<ID=chr21,length=48129895,assembly=hg19> +##contig=<ID=chr21_gl000210_random,length=27682,assembly=hg19> +##contig=<ID=chr22,length=51304566,assembly=hg19> +##contig=<ID=chr3,length=198022430,assembly=hg19> +##contig=<ID=chr4,length=191154276,assembly=hg19> +##contig=<ID=chr4_ctg9_hap1,length=590426,assembly=hg19> +##contig=<ID=chr4_gl000193_random,length=189789,assembly=hg19> +##contig=<ID=chr4_gl000194_random,length=191469,assembly=hg19> +##contig=<ID=chr5,length=180915260,assembly=hg19> +##contig=<ID=chr6,length=171115067,assembly=hg19> +##contig=<ID=chr6_apd_hap1,length=4622290,assembly=hg19> +##contig=<ID=chr6_cox_hap2,length=4795371,assembly=hg19> +##contig=<ID=chr6_dbb_hap3,length=4610396,assembly=hg19> +##contig=<ID=chr6_mann_hap4,length=4683263,assembly=hg19> +##contig=<ID=chr6_mcf_hap5,length=4833398,assembly=hg19> +##contig=<ID=chr6_qbl_hap6,length=4611984,assembly=hg19> +##contig=<ID=chr6_ssto_hap7,length=4928567,assembly=hg19> +##contig=<ID=chr7,length=159138663,assembly=hg19> +##contig=<ID=chr7_gl000195_random,length=182896,assembly=hg19> +##contig=<ID=chr8,length=146364022,assembly=hg19> +##contig=<ID=chr8_gl000196_random,length=38914,assembly=hg19> +##contig=<ID=chr8_gl000197_random,length=37175,assembly=hg19> +##contig=<ID=chr9,length=141213431,assembly=hg19> +##contig=<ID=chr9_gl000198_random,length=90085,assembly=hg19> +##contig=<ID=chr9_gl000199_random,length=169874,assembly=hg19> +##contig=<ID=chr9_gl000200_random,length=187035,assembly=hg19> +##contig=<ID=chr9_gl000201_random,length=36148,assembly=hg19> +##contig=<ID=chrM,length=16571,assembly=hg19> +##contig=<ID=chrUn_gl000211,length=166566,assembly=hg19> +##contig=<ID=chrUn_gl000212,length=186858,assembly=hg19> +##contig=<ID=chrUn_gl000213,length=164239,assembly=hg19> +##contig=<ID=chrUn_gl000214,length=137718,assembly=hg19> +##contig=<ID=chrUn_gl000215,length=172545,assembly=hg19> +##contig=<ID=chrUn_gl000216,length=172294,assembly=hg19> +##contig=<ID=chrUn_gl000217,length=172149,assembly=hg19> +##contig=<ID=chrUn_gl000218,length=161147,assembly=hg19> +##contig=<ID=chrUn_gl000219,length=179198,assembly=hg19> +##contig=<ID=chrUn_gl000220,length=161802,assembly=hg19> +##contig=<ID=chrUn_gl000221,length=155397,assembly=hg19> +##contig=<ID=chrUn_gl000222,length=186861,assembly=hg19> +##contig=<ID=chrUn_gl000223,length=180455,assembly=hg19> +##contig=<ID=chrUn_gl000224,length=179693,assembly=hg19> +##contig=<ID=chrUn_gl000225,length=211173,assembly=hg19> +##contig=<ID=chrUn_gl000226,length=15008,assembly=hg19> +##contig=<ID=chrUn_gl000227,length=128374,assembly=hg19> +##contig=<ID=chrUn_gl000228,length=129120,assembly=hg19> +##contig=<ID=chrUn_gl000229,length=19913,assembly=hg19> +##contig=<ID=chrUn_gl000230,length=43691,assembly=hg19> +##contig=<ID=chrUn_gl000231,length=27386,assembly=hg19> +##contig=<ID=chrUn_gl000232,length=40652,assembly=hg19> +##contig=<ID=chrUn_gl000233,length=45941,assembly=hg19> +##contig=<ID=chrUn_gl000234,length=40531,assembly=hg19> +##contig=<ID=chrUn_gl000235,length=34474,assembly=hg19> +##contig=<ID=chrUn_gl000236,length=41934,assembly=hg19> +##contig=<ID=chrUn_gl000237,length=45867,assembly=hg19> +##contig=<ID=chrUn_gl000238,length=39939,assembly=hg19> +##contig=<ID=chrUn_gl000239,length=33824,assembly=hg19> +##contig=<ID=chrUn_gl000240,length=41933,assembly=hg19> +##contig=<ID=chrUn_gl000241,length=42152,assembly=hg19> +##contig=<ID=chrUn_gl000242,length=43523,assembly=hg19> +##contig=<ID=chrUn_gl000243,length=43341,assembly=hg19> +##contig=<ID=chrUn_gl000244,length=39929,assembly=hg19> +##contig=<ID=chrUn_gl000245,length=36651,assembly=hg19> +##contig=<ID=chrUn_gl000246,length=38154,assembly=hg19> +##contig=<ID=chrUn_gl000247,length=36422,assembly=hg19> +##contig=<ID=chrUn_gl000248,length=39786,assembly=hg19> +##contig=<ID=chrUn_gl000249,length=38502,assembly=hg19> +##contig=<ID=chrX,length=155270560,assembly=hg19> +##contig=<ID=chrY,length=59373566,assembly=hg19> +##reference=file:///m/cphg-quinlan/cphg-quinlan/shared/genomes/hg19/bwa/gatk/hg19_gatk.fa +##INFO=<ID=CSQ,Number=.,Type=String,Description="Consequence type as predicted by VEP. Format: Consequence|Codons|Amino_acids|Gene|HGNC|Feature|EXON|PolyPhen|SIFT"> +##SnpEffVersion="SnpEff 3.0g (build 2012-08-31), by Pablo Cingolani" +##SnpEffCmd="SnpEff -i vcf -o vcf GRCh37.66 test4.vep.vcf " +##INFO=<ID=EFF,Number=.,Type=String,Description="Predicted effects for this variant.Format: 'Effect ( Effect_Impact | Functional_Class | Codon_Change | Amino_Acid_change| Amino_Acid_length | Gene_Name | Gene_BioType | Coding | Transcript | Exon [ | ERRORS | WARNINGS ] )' "> +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT 1_dad 1_mom 1_kid 2_dad 2_mom 2_kid 3_dad 3_mom 3_kid +chr10 1142208 . T C 3404.3 . AC=8;AF=1.00;AN=8;DP=122;Dels=0.00;FS=0.000;HRun=0;HaplotypeScore=2.6747;MQ=36.00;MQ0=0;QD=27.90;CSQ=intron_variant|||ENSG00000047056|WDR37|ENST00000263150|||,downstream_gene_variant|||ENSG00000047056|WDR37|ENST00000436154|||,intron_variant|||ENSG00000047056|WDR37|ENST00000358220|||,stop_lost|Tga/Cga|*/R|ENSG00000047056|WDR37|ENST00000381329|9/9||;EFF=DOWNSTREAM(MODIFIER||||208|WDR37|protein_coding|CODING|ENST00000436154|),INTRON(MODIFIER||||494|WDR37|protein_coding|CODING|ENST00000263150|),INTRON(MODIFIER||||494|WDR37|protein_coding|CODING|ENST00000358220|),STOP_LOST(HIGH|MISSENSE|Tga/Cga|*250R|249|WDR37|protein_coding|CODING|ENST00000381329|exon_10_1142110_1142566) GT:AD:DP:GQ:PL 0/0:1,37:39:87.16:940,87,0 0/0:0,29:29:78.20:899,78,0 0/1:0,23:24:66.14:729,66,0 0/0:1,37:59:87.16:940,87,0 0/0:0,29:49:78.20:899,78,0 0/0:0,22:64:66.14:729,66,0 0/0:1,37:39:87.16:940,87,0 0/0:0,29:29:78.20:899,78,0 1/1:0,24:24:66.14:729,66,0 +chr10 48003992 . C T 1047.87 . AC=4;AF=0.50;AN=8;BaseQRankSum=-0.053;DP=165;Dels=0.00;FS=6.377;HRun=0;HaplotypeScore=4.3830;MQ=20.94;MQ0=0;MQRankSum=-0.368;QD=9.53;ReadPosRankSum=1.346;CSQ=missense_variant|tGt/tAt|C/Y|ENSG00000072444|ASAH2C|ENST00000420079|16/17|benign(0)|tolerated(1),missense_variant|tGt/tAt|C/Y|ENSG00000072444|ASAH2C|ENST00000426610|17/18|benign(0)|tolerated(1);EFF=NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|tGt/tAt|C540Y|610|ASAH2C|protein_coding|CODING|ENST00000420079|exon_10_48003968_48004056),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|tGt/tAt|C552Y|622|ASAH2C|protein_coding|CODING|ENST00000426610|exon_10_48003968_48004056) GT:AD:DP:GQ:PL 0/1:1,37:39:87.16:940,87,0 0/1:0,29:29:78.20:899,78,0 1/1:0,23:24:66.14:729,66,0 0/0:1,37:39:87.16:940,87,0 0/0:0,29:29:78.20:899,78,0 0/1:0,23:24:66.14:729,66,0 0/1:1,37:39:87.16:940,87,0 0/1:0,29:29:78.20:899,78,0 0/1:0,23:24:66.14:729,66,0 +chr10 48004992 . C T 1047.87 . AC=4;AF=0.50;AN=8;BaseQRankSum=-0.053;DP=165;Dels=0.00;FS=6.377;HRun=0;HaplotypeScore=4.3830;MQ=20.94;MQ0=0;MQRankSum=-0.368;QD=9.53;ReadPosRankSum=1.346;CSQ=missense_variant|tGt/tAt|C/Y|ENSG00000072444|ASAH2C|ENST00000420079|16/17|benign(0)|tolerated(1),missense_variant|tGt/tAt|C/Y|ENSG00000072444|ASAH2C|ENST00000426610|17/18|benign(0)|tolerated(1);EFF=NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|tGt/tAt|C540Y|610|ASAH2C|protein_coding|CODING|ENST00000420079|exon_10_48003968_48004056),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|tGt/tAt|C552Y|622|ASAH2C|protein_coding|CODING|ENST00000426610|exon_10_48003968_48004056) GT:AD:DP:GQ:PL 0/1:1,37:39:87.16:940,87,0 0/1:0,29:29:78.20:899,78,0 0/1:0,23:24:66.14:729,66,0 0/1:1,37:39:87.16:940,87,0 0/1:0,29:29:78.20:899,78,0 1/1:0,23:24:66.14:729,66,0 0/0:1,37:39:87.16:940,87,0 0/0:0,29:29:78.20:899,78,0 0/1:0,23:24:66.14:729,66,0 +chr10 135336656 . G A 38.34 . AC=4;AF=1.00;AN=4;DP=2;Dels=0.00;FS=0.000;HRun=4;HaplotypeScore=0.0000;MQ=37.00;MQ0=0;QD=19.17;CSQ=upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000418356|||,intron_variant&nc_transcript_variant|||ENSG00000214279||ENST00000488261|||,intron_variant|||ENSG00000203772|SPRN|ENST00000541506|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000541261|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000421586|||,intron_variant|||ENSG00000130649|CYP2E1|ENST00000463117|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000252945|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000541080|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000477500|||,upstream_gene_variant|||ENSG00000130649|CYP2E1|ENST00000480558|||,intron_variant|||ENSG00000214279||ENST00000356567|||;EFF=INTRON(MODIFIER||||151|SPRN|protein_coding|CODING|ENST00000541506|),INTRON(MODIFIER||||493|CYP2E1|protein_coding|CODING|ENST00000463117|),INTRON(MODIFIER||||693|RP11-108K14.4.1|protein_coding|CODING|ENST00000356567|),INTRON(MODIFIER|||||RP11-108K14.4.1|retained_intron|CODING|ENST00000488261|),UPSTREAM(MODIFIER||||305|CYP2E1|protein_coding|CODING|ENST00000418356|),UPSTREAM(MODIFIER||||355|CYP2E1|protein_coding|CODING|ENST00000421586|),UPSTREAM(MODIFIER||||493|CYP2E1|protein_coding|CODING|ENST00000252945|),UPSTREAM(MODIFIER||||85|CYP2E1|protein_coding|CODING|ENST00000541261|),UPSTREAM(MODIFIER|||||CYP2E1|processed_transcript|CODING|ENST00000477500|),UPSTREAM(MODIFIER|||||CYP2E1|processed_transcript|CODING|ENST00000480558|) GT:AD:DP:GQ:PL 0/0:1,37:39:87.16:940,87,0 0/0:0,29:29:78.20:899,78,0 0/1:0,24:24:66.14:729,66,0 0/0:1,37:39:87.16:940,87,0 0/0:0,29:29:78.20:899,78,0 0/1:0,24:24:66.14:729,66,0 0/1:1,37:39:87.16:940,87,0 0/1:0,29:29:78.20:899,78,0 0/1:0,24:24:66.14:729,66,0 +chr10 135369532 . T C 122.62 . AC=2;AF=0.25;AN=8;BaseQRankSum=2.118;DP=239;Dels=0.00;FS=5.194;HRun=2;HaplotypeScore=5.7141;MQ=36.02;MQ0=0;MQRankSum=0.082;QD=2.31;ReadPosRankSum=-0.695;CSQ=missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000303903|9/13|benign(0.001)|tolerated(1),missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000432597|10/14|benign(0)|tolerated(1),downstream_gene_variant|||ENSG00000171772|SYCE1|ENST00000460441|||,missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000343131|9/13|benign(0.001)|tolerated(1),intron_variant|||ENSG00000203772|SPRN|ENST00000541506|||,non_coding_exon_variant&nc_transcript_variant|||ENSG00000171772|SYCE1|ENST00000479535|6/10||,downstream_gene_variant|||ENSG00000171772|SYCE1|ENST00000482127|||,non_coding_exon_variant&nc_transcript_variant|||ENSG00000130649|CYP2E1|ENST00000368520|6/6||,missense_variant|aAg/aGg|K/R|ENSG00000171772|SYCE1|ENST00000368517|9/13|benign(0)|tolerated(1);EFF=DOWNSTREAM(MODIFIER|||||SYCE1|processed_transcript|CODING|ENST00000460441|),DOWNSTREAM(MODIFIER|||||SYCE1|processed_transcript|CODING|ENST00000482127|),EXON(MODIFIER|||||CYP2E1|retained_intron|CODING|ENST00000368520|),EXON(MODIFIER|||||SYCE1|processed_transcript|CODING|ENST00000479535|),INTRON(MODIFIER||||151|SPRN|protein_coding|CODING|ENST00000541506|),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K147R|282|SYCE1|protein_coding|CODING|ENST00000368517|exon_10_135369485_135369551),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K147R|282|SYCE1|protein_coding|CODING|ENST00000432597|exon_10_135369485_135369551),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K183R|318|SYCE1|protein_coding|CODING|ENST00000303903|exon_10_135369485_135369551),NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|aAg/aGg|K183R|351|SYCE1|protein_coding|CODING|ENST00000343131|exon_10_135369485_135369551) GT:AD:DP:GQ:PL 0/0:1,37:39:87.16:940,87,0 0/0:0,29:29:78.20:899,78,0 0/1:0,22:24:66.14:729,66,0 0/0:1,37:39:87.16:940,87,0 0/0:0,29:29:78.20:899,78,0 0/1:0,21:24:66.14:729,66,0 0/0:1,37:50:87.16:940,87,0 0/0:0,29:50:78.20:899,78,0 0/1:0,24:50:66.14:729,66,0