public void OnekGenArbitrationVcf()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chrX_129354240_129354241.nsa"));
VcfUtilities.FieldEquals(saReader, "X 129354240 rs1160681 C A 100 PASS .",
"GMAF=C|0.4713", VcfCommon.InfoIndex);
}
public void AnnotationCarryover()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr2_90472571_90472592.nsa"));
var annotationSource = ResourceUtilities.GetAnnotationSource(DataUtilities.EmptyCachePrefix, saReader);
annotationSource?.EnableReferenceNoCalls(false);
var annotatedVariant = DataUtilities.GetVariant(annotationSource,
"2 90472571 . AAAAAAAAAAAAAAAAAAGTCC AGTCT 177 PASS CIGAR=1M21D4I;RU=.;REFREP=.;IDREP=. GT:GQ:GQX:DPI:AD 0/1:220:177:46:40,7");
Assert.NotNull(annotatedVariant);
var altAllele = annotatedVariant.AnnotatedAlternateAlleles.First();
Assert.NotNull(altAllele);
Assert.False(altAllele.IsReferenceMinor);
Assert.Equal("indel", altAllele.VariantType);
Assert.Equal("2:90472572:90472592:GTCT", altAllele.VariantId);
annotatedVariant = DataUtilities.GetVariant(annotationSource,
"2 90472592 . C . . PASS RefMinor GT:GQX:DP:DPF:AD 0:96:33:15:33");
Assert.NotNull(annotatedVariant);
altAllele = annotatedVariant.AnnotatedAlternateAlleles.FirstOrDefault();
Assert.NotNull(altAllele);
Assert.True(altAllele.IsReferenceMinor);
Assert.Equal("SNV", altAllele.VariantType);
}
public void ClearingAncestralAllele()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chrX_2957282_2957284.nsa"));
VcfUtilities.FieldDoesNotContain(saReader, "chrX 2957282 . A G 100 PASS .",
"AA=", VcfCommon.InfoIndex);
}
public void MissingClinVarVcf()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr17_73512643_73512644.nsa"));
VcfUtilities.FieldEquals(saReader, "17 73512643 rs398124622 T TGGAGCC . . .",
"AF1000G=0.059105;clinvar=1|conflicting_interpretations_of_pathogenicity", VcfCommon.InfoIndex);
}
public void EmptyInputInfo()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr17_77263_77265.nsa"));
VcfUtilities.FieldEquals(saReader,
"17 77263 . TG T 428 PASS . GT:GQ:GQX:DPI:AD 1/1:33:30:12:0,11", "AA=GGG;AF1000G=1", VcfCommon.InfoIndex);
}
public void SpuriousRefMinor()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr2_190634103_190634104.nsa"));
VcfUtilities.FieldEquals(saReader, "2 190634103 . C . . HighDPFRatio .", ".",
VcfCommon.InfoIndex);
}
public void DbSnpOutputTest()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr1_115256529_115256530.nsa"));
VcfUtilities.FieldContains(saReader,
"chr1 115256529 . T C 1000 PASS . GT 0/1", "rs11554290", VcfCommon.IdIndex);
}
public void ConflictingOneKgen()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr22_17996285_17996286.nsa"));
VcfUtilities.FieldEquals(saReader,
"22 17996285 rs35048606 A ATCTC 100 PASS .", ".", VcfCommon.InfoIndex);
}
public void ClinvarSignificanceWithComma()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chrX_76937963_76937963.nsa"));
VcfUtilities.FieldContains(saReader, "X 76937963 . G C . . .",
"conflicting_interpretations_of_pathogenicity\\x2c_not_provided", VcfCommon.InfoIndex);
}
public void UnwantedRefMinor()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnotGRCh38("chr1_26213904_26213905.nsa"));
VcfUtilities.FieldContains(saReader,
"chr1 26213904 . C . . LowGQX;HighDPFRatio . GT:GQX:DP:DPF 0/0:3:1:1", "RefMinor", VcfCommon.InfoIndex);
}
public void SpuriousRefMinor2()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chrX_1619046_1619046.nsa"));
VcfUtilities.FieldEquals(saReader,
"X 1619046 . C . . LowGQX RefMinor GT:GQX:DP:DPF 0/0:8:38:12", ".", VcfCommon.InfoIndex);
}
public void OnekGenArbitrationVcf2()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chrX_534468_534469.nsa"));
VcfUtilities.FieldEquals(saReader, "X 534468 . T C 100 PASS .",
"GMAF=G|0.2891", VcfCommon.InfoIndex);
}
public void MissingRefMinorOneKgen()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr1_17639993_17639994.nsa"));
VcfUtilities.FieldEquals(saReader, "1 17639993 rs560856316 C . . . .",
"RefMinor;GMAF=C|0.002796", VcfCommon.InfoIndex);
}
public void EvsWrongAltValue()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr17_641334_641337.nsa"));
VcfUtilities.FieldEquals(saReader,
"17 641336 rs60947910 C T 9 LowGQX SNVSB=0.0;SNVHPOL=19;AA=C;GMAF=T|0.1835;AF1000G=0.183506;EVS=|22|6254;phyloP=-1.271 GT:GQ:GQX:DP:DPF:AD 0/1:17:9:3:2:1,2",
"SNVSB=0.0;SNVHPOL=19;AA=C;GMAF=T|0.1835;AF1000G=0.183506;cosmic=1|COSN6415581", VcfCommon.InfoIndex);
}
public void CosmicMultiDelete()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr17_21319650_21319651.nsa"));
VcfUtilities.FieldEquals(saReader,
"17 21319650 . CGAG C 101 PASS CIGAR=1M3D;RU=GAG;REFREP=2;IDREP=1 GT:GQ:GQX:DPI:AD 0/1:141:101:29:22,4",
"CIGAR=1M3D;RU=GAG;REFREP=2;IDREP=1;cosmic=1|COSM278475", VcfCommon.InfoIndex);
}
public void DuplicateEntryRefMinor()
{
// the following entry should not get refMinor tag. It has conflicting entries in 1kg and should have no allele frequency related info
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chrX_1389061_1389062.nsa"));
VcfUtilities.FieldDoesNotContain(saReader,
"X 1389061 . A C 100 PASS AC=3235", "RefMinor", VcfCommon.InfoIndex);
}
public void RefSiteRefMinor()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr1_789256_789257.nsa"));
VcfUtilities.FieldEquals(saReader,
"1 789256 rs3131939 T . . LowGQX END=789256 GT:GQX:DP:DPF:AD 0:.:0:0:0",
"END=789256;RefMinor;GMAF=T|0.005192", VcfCommon.InfoIndex);
}
public void MissingDbsnpId()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr17_3616153_3616154.nsa"));
VcfUtilities.FieldEquals(saReader,
"17 3616153 rs34081014 C G 48 PASS SNVSB=0.0;SNVHPOL=2;AA=C;GMAF=G|0.07029;AF1000G=0.0702875;phyloP=0.444;CSQT=1|ITGAE|ENST00000263087|downstream_gene_variant;CSQR=1|ENSR00001339304|regulatory_region_variant GT:GQ:GQX:DP:DPF:AD 0/1:47:44:6:0:2,4",
"rs34081014;rs71362546", VcfCommon.IdIndex);
}
public void NotPotentialRefMinor()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr17_77263_77265.nsa"));
VcfUtilities.FieldEquals(saReader,
"17 77264 . G . 428 PASS END=77265;CIGAR=1M1D;RU=G;REFREP=4;IDREP=3 GT:GQ:GQX:DPI:AD 1/1:33:30:12:0,11",
"END=77265;CIGAR=1M1D;RU=G;REFREP=4;IDREP=3", VcfCommon.InfoIndex);
}
public void DuplicateOneKgFreq()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr5_29786207_29786208.nsa"));
VcfUtilities.FieldEquals(saReader,
"5 29786207 rs150619197 C . . SiteConflict;LowGQX END=29786207;BLOCKAVG_min30p3a;AF1000G=.,0.994409;GMAF=A|0.9944;RefMinor GT:GQX:DP:DPF 0:24:9:0",
"END=29786207;BLOCKAVG_min30p3a;RefMinor;GMAF=C|0.005591", VcfCommon.InfoIndex);
}
public void MissingEvsValue()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr1_226259211_226259213.nsa"));
VcfUtilities.FieldEquals(saReader,
"1 226259211 rs375001380;rs397983063 TCA TA,TC 32 LowGQXHetAltDel CIGAR=1M1D1M,2M1D;RU=C,A;REFREP=1,17;IDREP=0,16;EVS=|6|5096;CSQT=1|H3F3A|ENST00000366813|3_prime_UTR_variant&feature_truncation,2|H3F3A|ENST00000366813|3_prime_UTR_variant&feature_truncation GT:GQ:GQX:DPI:AD 1/2:162:2:22:4,8,1",
"CIGAR=1M1D1M,2M1D;RU=C,A;REFREP=1,17;IDREP=0,16", VcfCommon.InfoIndex);
}
public void MissingRefMinorAnnotation()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr2_193187632_193187633.nsa"));
VcfUtilities.FieldEquals(saReader,
"2 193187632 . G . . LowGQX;HighDPFRatio . GT:GQX:DP:DPF .:.:0:2", "RefMinor;GMAF=G|0.01937",
VcfCommon.InfoIndex);
}
public void NoGlobalMinorAllele()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr1_241369_241370.nsa"));
VcfUtilities.FieldEquals(saReader,
"1 241369 . C T 77 LowGQXHomSNP SNVSB=0.0;SNVHPOL=3;CSQ=T|intron_variant&non_coding_transcript_variant|MODIFIER|AP006222.2|ENSG00000228463|Transcript|ENST00000424587|lincRNA||2/3|ENST00000424587.2:n.264-2802G>A|||||||||-1|Clone_based_vega_gene||YES|||||||||,T|upstream_gene_variant|MODIFIER|AP006222.2|ENSG00000228463|Transcript|ENST00000448958|lincRNA|||||||||||2811|-1|Clone_based_vega_gene||||||||||| GT:GQ:GQX:DP:DPF:AD 1/1:12:13:5:2:0,5",
"SNVSB=0.0;SNVHPOL=3;AF1000G=1", VcfCommon.InfoIndex);
}
public void MultiDbSnpOutput()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr17_186913_186914.nsa"));
VcfUtilities.FieldEquals(saReader,
"17 186913 rs34543275,rs11453667 A AT 111 LowGQX CIGAR=1M1I;RU=T;REFREP=11;IDREP=12;GMAF=AC|0.002995;AF1000G=0.748003;CSQT=1|RPH3AL|ENST00000331302|intron_variant&feature_elongation,1||ENST00000575743|downstream_gene_variant GT:GQ:GQX:DPI:AD 1/1:21:18:9:0,7",
"rs11453667;rs34543275", VcfCommon.IdIndex);
}
public void MissingRsid()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr1_129010_129012.nsa"));
VcfUtilities.FieldEquals(saReader,
"chr1 129010 rs377161483 AATG A 32 LowGQXHetAltDel CIGAR=1M1D1M,2M1D;RU=C,A;REFREP=1,17;IDREP=0,16 GT:GQ:GQX:DPI:AD 1/2:162:2:22:4,8,1",
"rs377161483", VcfCommon.IdIndex);
}
public void NoRefMinorForDeletion()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr17_77263_77265.nsa"));
VcfUtilities.FieldEquals(saReader,
"17 77263 . TG T 428 PASS CIGAR=1M1D;RU=G;REFREP=4;IDREP=3 GT:GQ:GQX:DPI:AD 1/1:33:30:12:0,11",
"CIGAR=1M1D;RU=G;REFREP=4;IDREP=3;AA=GGG;AF1000G=1", VcfCommon.InfoIndex);
}
public void DbSnpIds()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr1_129010_129012.nsa"));
VcfUtilities.FieldEquals(saReader,
"1 1594584 MantaDEL:164:0:1:1:0:0;rs123 C <DEL> . MGE10kb END=1660503;SVTYPE=DEL;SVLEN=-65919;IMPRECISE;CIPOS=-285,285;CIEND=-205,205;SOMATIC;SOMATICSCORE=36;Colocaliz edCanvas PR 42,0 226,9",
"MantaDEL:164:0:1:1:0:0", VcfCommon.IdIndex);
}
public void VariantSiteRefMinor()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr1_789256_789257.nsa"));
VcfUtilities.FieldEquals(saReader,
"1 789256 rs3131939 T C . LowGQX . GT:GQX:DP:DPF:AD 0:.:0:0:0", "GMAF=T|0.005192;AF1000G=0.994808",
VcfCommon.InfoIndex);
}
public void AlleleSpecificClinvarVcf()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr17_2266812_2266813.nsa"));
VcfUtilities.FieldEquals(saReader,
"17 2266812 rs2003968 T C 112 LowGQX SNVSB=-8.7;SNVHPOL=3;AA=C;GMAF=C|0.5663;AF1000G=0.566294;EVS=0.4839|27|6502;phyloP=-5.078;cosmic=COSM1563374;clinvar=1|other;CSQT=1|SGSM2|ENST00000268989|synonymous_variant GT:GQ:GQX:DP:DPF:AD 1/1:21:21:8:1:0,8",
"SNVSB=-8.7;SNVHPOL=3;AA=C;GMAF=T|0.4337;AF1000G=0.566294;EVS=0.483928|27|6502;cosmic=1|COSM1563374",
VcfCommon.InfoIndex);
}
public void MissingAFinX()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chrX_857972_857973.nsa"));
VcfUtilities.FieldEquals(saReader,
"X 857972 . A C . LowQscore SOMATIC;QSS=1;TQSS=2;NT=ref;QSS_NT=1;TQSS_NT=2;SGT=AC->AC;DP=143;MQ=58.73;MQ0=5;ALTPOS=6;ALTMAP=5;ReadPosRankSum=-2.92;SNVSB=0.00;PNOISE=0.00;PNOISE2=0.00;VQSR=1.98;phyloP=-1.187 DP:FDP:SDP:SUBDP:AU:CU:GU:TU 58:1:0:0:57,58:0,4:0,0:0,0 74:1:0:0:69,70:4,11:0,0:0,0",
"SOMATIC;QSS=1;TQSS=2;NT=ref;QSS_NT=1;TQSS_NT=2;SGT=AC->AC;DP=143;MQ=58.73;MQ0=5;ALTPOS=6;ALTMAP=5;ReadPosRankSum=-2.92;SNVSB=0.00;PNOISE=0.00;PNOISE2=0.00;VQSR=1.98;GMAF=A|0.4323;AF1000G=0.567692",
VcfCommon.InfoIndex);
}