public void ParseVcfLine_NonInformativeAlleles_WithNormalAllele_NotFiltered()
{
const string vcfLine1 = "chr1 13133 . T <*>,G 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
const string vcfLine2 = "chr1 13133 . T *,C 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
const string vcfLine3 = "chr1 13133 . T <M>,A 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
const string vcfLine4 = "chr1 13133 . T A,<NON_REF> 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
var refMinorProvider = new Mock <IRefMinorProvider>();
var seqProvider = ParserTestUtils.GetSequenceProvider(13133, "T", 'A', ChromosomeUtilities.RefNameToChromosome);
var refNameToChromosome = seqProvider.RefNameToChromosome;
var variantFactory = new VariantFactory(seqProvider);
var position1 = AnnotationUtilities.ParseVcfLine(vcfLine1, refMinorProvider.Object, variantFactory, refNameToChromosome);
var position2 = AnnotationUtilities.ParseVcfLine(vcfLine2, refMinorProvider.Object, variantFactory, refNameToChromosome);
var position3 = AnnotationUtilities.ParseVcfLine(vcfLine3, refMinorProvider.Object, variantFactory, refNameToChromosome);
var position4 = AnnotationUtilities.ParseVcfLine(vcfLine4, refMinorProvider.Object, variantFactory, refNameToChromosome);
var annotatedVariants1 = Annotator.GetAnnotatedVariants(position1.Variants);
var annotatedVariants2 = Annotator.GetAnnotatedVariants(position2.Variants);
var annotatedVariants3 = Annotator.GetAnnotatedVariants(position3.Variants);
var annotatedVariants4 = Annotator.GetAnnotatedVariants(position4.Variants);
// SimplePositions
Assert.Equal(new[] { "<*>", "G" }, position1.AltAlleles);
Assert.Equal(new[] { "*", "C" }, position2.AltAlleles);
Assert.Equal(new[] { "<M>", "A" }, position3.AltAlleles);
Assert.Equal(new[] { "A", "<NON_REF>" }, position4.AltAlleles);
// Variants
Assert.Equal(new[] { "<*>", "G" }, annotatedVariants1.Select(x => x.Variant.AltAllele).ToArray());
Assert.Equal(new[] { "*", "C" }, annotatedVariants2.Select(x => x.Variant.AltAllele).ToArray());
Assert.Equal(new[] { "<M>", "A" }, annotatedVariants3.Select(x => x.Variant.AltAllele).ToArray());
Assert.Equal(new[] { "A", "<NON_REF>" }, annotatedVariants4.Select(x => x.Variant.AltAllele).ToArray());
}
public void ParseVcfLine_line_with_only_non_informative_alleles_position_unchanged_but_variants_ignored()
{
const string vcfLine1 = "chr1 13133 . T <*> 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
const string vcfLine2 = "chr1 13133 . T * 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
const string vcfLine3 = "chr1 13133 . T <M> 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
var chromosome = new Chromosome("chr1", "1", 0);
var refMinorProvider = new Mock <IRefMinorProvider>();
refMinorProvider.Setup(x => x.IsReferenceMinor(chromosome, 13133)).Returns(false);
var refNameToChromosome = new Dictionary <string, IChromosome> {
["chr1"] = chromosome
};
var variantFactory = new VariantFactory(refNameToChromosome, refMinorProvider.Object, false);
var position1 = VcfReaderUtils.ParseVcfLine(vcfLine1, variantFactory, refNameToChromosome);
var position2 = VcfReaderUtils.ParseVcfLine(vcfLine2, variantFactory, refNameToChromosome);
var position3 = VcfReaderUtils.ParseVcfLine(vcfLine3, variantFactory, refNameToChromosome);
var annotatedVariants1 = Annotator.GetAnnotatedVariants(position1.Variants);
var annotatedVariants2 = Annotator.GetAnnotatedVariants(position2.Variants);
var annotatedVariants3 = Annotator.GetAnnotatedVariants(position3.Variants);
// SimplePositions unchanged
Assert.Equal("<*>", position1.AltAlleles[0]);
Assert.Equal("*", position2.AltAlleles[0]);
Assert.Equal("<M>", position3.AltAlleles[0]);
// Variants are null
Assert.Null(annotatedVariants1);
Assert.Null(annotatedVariants2);
Assert.Null(annotatedVariants3);
}
public void ParseVcfLine_NonInformativeAlleles_Alone_NotFiltered()
{
const string vcfLine1 = "chr1 13133 . T <*> 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
const string vcfLine2 = "chr1 13133 . T * 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
const string vcfLine3 = "chr1 13133 . T <M> 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
var refMinorProvider = new Mock <IRefMinorProvider>();
var seqProvider = ParserTestUtils.GetSequenceProvider(13133, "T", 'A', ChromosomeUtilities.RefNameToChromosome);
var variantFactory = new VariantFactory(seqProvider);
var position1 = AnnotationUtilities.ParseVcfLine(vcfLine1, refMinorProvider.Object, variantFactory, seqProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.ParseVcfLine(vcfLine2, refMinorProvider.Object, variantFactory, seqProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.ParseVcfLine(vcfLine3, refMinorProvider.Object, variantFactory, seqProvider.RefNameToChromosome);
var annotatedVariants1 = Annotator.GetAnnotatedVariants(position1.Variants);
var annotatedVariants2 = Annotator.GetAnnotatedVariants(position2.Variants);
var annotatedVariants3 = Annotator.GetAnnotatedVariants(position3.Variants);
// SimplePositions unchanged
Assert.Equal("<*>", position1.AltAlleles[0]);
Assert.Equal("*", position2.AltAlleles[0]);
Assert.Equal("<M>", position3.AltAlleles[0]);
// Variants not filtered
Assert.Equal("<*>", annotatedVariants1[0].Variant.AltAllele);
Assert.Equal("*", annotatedVariants2[0].Variant.AltAllele);
Assert.Equal("<M>", annotatedVariants3[0].Variant.AltAllele);
}
public void ParseVcfLine_line_with_only_NonRef_is_refMinor()
{
const string vcfLine = "1 10628385 . C <NON_REF> . LowGQX;HighDPFRatio END=10628385;BLOCKAVG_min30p3a GT:GQX:DP:DPF 0/0:24:9:18";
var chromosome = new Chromosome("chr1", "1", 0);
var refMinorProvider = new Mock <IRefMinorProvider>();
refMinorProvider.Setup(x => x.IsReferenceMinor(chromosome, 10628385)).Returns(true);
refMinorProvider.Setup(x => x.GetGlobalMajorAlleleForRefMinor(chromosome, 10628385)).Returns("T");
var refNameToChromosome = new Dictionary <string, IChromosome> {
["1"] = chromosome
};
var variantFactory = new VariantFactory(refNameToChromosome, refMinorProvider.Object, false);
var position = VcfReaderUtils.ParseVcfLine(vcfLine, variantFactory, refNameToChromosome);
var annotatedVariants = Annotator.GetAnnotatedVariants(position.Variants);
Assert.Equal("C", position.RefAllele);
Assert.Equal(new[] { "<NON_REF>" }, position.AltAlleles);
Assert.Equal("T", position.Variants[0].RefAllele);
Assert.Equal("C", position.Variants[0].AltAllele);
// Variants
Assert.Equal(new[] { "C" }, annotatedVariants.Select(x => x.Variant.AltAllele).ToArray());
}
public void GetJsonString_DifferentOriginalChromosomeName()
{
const string originalChromosomeName = "originalChr1";
IVariant[] variants = GetVariants();
ISample[] samples = GetSamples();
IAnnotatedVariant[] annotatedVariants = Annotator.GetAnnotatedVariants(variants);
var position = GetPosition(originalChromosomeName, variants, samples);
var annotatedPosition = new AnnotatedPosition(position, annotatedVariants);
string observedResult = annotatedPosition.GetJsonString();
Assert.NotNull(observedResult);
Assert.Contains($"\"chromosome\":\"{originalChromosomeName}\"", observedResult);
}
public void ParseVcfLine_line_with_only_NonRef_is_not_refMinor()
{
const string vcfLine = "1 10005 . C <NON_REF> . LowGQX END=10034;BLOCKAVG_min30p3a GT:GQX:DP:DPF 0/0:3:1:0";
var refMinorProvider = new Mock <IRefMinorProvider>();
var seqProvider =
ParserTestUtils.GetSequenceProvider(10005, "C", 'A', ChromosomeUtilities.RefNameToChromosome);
var variantFactory = new VariantFactory(seqProvider.Sequence, _vidCreator);
var position = AnnotationUtilities.ParseVcfLine(vcfLine, refMinorProvider.Object, seqProvider, null, variantFactory);
var annotatedVariants = Annotator.GetAnnotatedVariants(position.Variants);
Assert.Equal("C", position.RefAllele);
Assert.Equal(new[] { "<NON_REF>" }, position.AltAlleles);
Assert.Null(position.Variants);
Assert.Null(annotatedVariants);
}
public void GetJsonString_fisherStrand()
{
const string vcfLine = "21\t9411410\t.\tC\tT\t9.51\tDRAGENSnpHardQUAL\tAC=2;AF=1.000;AN=2;DP=2;FS=0.000;MQ=100.00;QD=9.51;SOR=1.609";
var refMinorProvider = new Mock <IRefMinorProvider>();
var seqProvider = ParserTestUtils.GetSequenceProvider(9411410, "C", 'A', ChromosomeUtilities.RefNameToChromosome);
var variantFactory = new VariantFactory(seqProvider.Sequence, new VariantId());
var position = AnnotationUtilities.ParseVcfLine(vcfLine, refMinorProvider.Object, seqProvider, null, variantFactory);
IVariant[] variants = GetVariants();
IAnnotatedVariant[] annotatedVariants = Annotator.GetAnnotatedVariants(variants);
var annotatedPosition = new AnnotatedPosition(position, annotatedVariants);
string observedResult = annotatedPosition.GetJsonString();
Assert.NotNull(observedResult);
Assert.Contains("\"fisherStrandBias\":0", observedResult);
}
public void Test_crash_caused_by_variant_trimming()
{
const string vcfLine1 = "chr1 8021910 rs373653682 GGTGCTGGACGGTGTCCCT G . . .";
var refMinorProvider = new Mock <IRefMinorProvider>();
var seqProvider = ParserTestUtils.GetSequenceProvider(8021910, "GGTGCTGGACGGTGTCCCT", 'A', ChromosomeUtilities.RefNameToChromosome);
var variantFactory = new VariantFactory(seqProvider.Sequence, _vidCreator);
var position1 = AnnotationUtilities.ParseVcfLine(vcfLine1, refMinorProvider.Object, seqProvider, null, variantFactory);
var annotatedVariants1 = Annotator.GetAnnotatedVariants(position1.Variants);
// SimplePositions
Assert.Equal(new[] { "G" }, position1.AltAlleles);
// Variants
Assert.Equal(new[] { "" }, annotatedVariants1.Select(x => x.Variant.AltAllele).ToArray());
}
public void GetJsonString_BreakEndEventId()
{
const string vcfLine = "1\t38432782\tMantaBND:2312:0:1:0:0:0:0\tG\tG]6:28863899]\t971\tPASS\tSVTYPE=BND;MATEID=MantaBND:2312:0:1:0:0:0:1;EVENT=MantaBND:2312:0:1:0:0:0:0;JUNCTION_QUAL=716;BND_DEPTH=52;MATE_BND_DEPTH=56";
var refMinorProvider = new Mock <IRefMinorProvider>();
var seqProvider = ParserTestUtils.GetSequenceProvider(38432782, "G", 'C', ChromosomeUtilities.RefNameToChromosome);
var variantFactory = new VariantFactory(seqProvider.Sequence, new VariantId());
var position = AnnotationUtilities.ParseVcfLine(vcfLine, refMinorProvider.Object, seqProvider, null, variantFactory);
IVariant[] variants = GetVariants();
IAnnotatedVariant[] annotatedVariants = Annotator.GetAnnotatedVariants(variants);
var annotatedPosition = new AnnotatedPosition(position, annotatedVariants);
string observedResult = annotatedPosition.GetJsonString();
Assert.NotNull(observedResult);
Assert.Contains("\"breakendEventId\":\"MantaBND:2312:0:1:0:0:0:0\"", observedResult);
}
public void GetJsonString_StrelkaSomatic()
{
const string vcfLine = "chr1 13813 . T G . LowQscore SOMATIC;QSS=33;TQSS=1;NT=ref;QSS_NT=16;TQSS_NT=1;SGT=TT->GT;DP=266;MQ=23.89;MQ0=59;ALTPOS=69;ALTMAP=37;ReadPosRankSum=1.22;SNVSB=5.92;PNOISE=0.00;PNOISE2=0.00;VQSR=1.93";
var refMinorProvider = new Mock <IRefMinorProvider>();
var seqProvider = ParserTestUtils.GetSequenceProvider(13813, "T", 'C', ChromosomeUtilities.RefNameToChromosome);
var variantFactory = new VariantFactory(seqProvider.Sequence, new VariantId());
var position = AnnotationUtilities.ParseVcfLine(vcfLine, refMinorProvider.Object, seqProvider, variantFactory);
IVariant[] variants = GetVariants();
IAnnotatedVariant[] annotatedVariants = Annotator.GetAnnotatedVariants(variants);
var annotatedPosition = new AnnotatedPosition(position, annotatedVariants);
string observedResult = annotatedPosition.GetJsonString();
Assert.NotNull(observedResult);
Assert.Contains("\"jointSomaticNormalQuality\":16", observedResult);
Assert.Contains("\"recalibratedQuality\":1.93", observedResult);
}
public void ParseVcfLine_line_with_only_NonRef_is_refMinor()
{
const string vcfLine = "1 10628385 . C <NON_REF> . LowGQX;HighDPFRatio END=10628385;BLOCKAVG_min30p3a GT:GQX:DP:DPF 0/0:24:9:18";
var refMinorProvider = new Mock <IRefMinorProvider>();
refMinorProvider.Setup(x => x.GetGlobalMajorAllele(ChromosomeUtilities.Chr1, 10628385)).Returns("T");
var seqProvider =
ParserTestUtils.GetSequenceProvider(10628385, "C", 'A', ChromosomeUtilities.RefNameToChromosome);
var variantFactory = new VariantFactory(seqProvider.Sequence, _vidCreator);
var position = AnnotationUtilities.ParseVcfLine(vcfLine, refMinorProvider.Object, seqProvider, null, variantFactory);
var annotatedVariants = Annotator.GetAnnotatedVariants(position.Variants);
Assert.Equal("C", position.RefAllele);
Assert.Equal(new[] { "<NON_REF>" }, position.AltAlleles);
Assert.Equal("T", position.Variants[0].RefAllele);
Assert.Equal("C", position.Variants[0].AltAllele);
// Variants
Assert.Equal(new[] { "C" }, annotatedVariants.Select(x => x.Variant.AltAllele).ToArray());
}
public void Test_crash_caused_by_variant_trimming()
{
const string vcfLine1 = "chr1 8021910 rs373653682 GGTGCTGGACGGTGTCCCT G . . .";
var chromosome = new Chromosome("chr1", "1", 0);
var refMinorProvider = new Mock <IRefMinorProvider>();
refMinorProvider.Setup(x => x.IsReferenceMinor(chromosome, 8021910)).Returns(false);
var refNameToChromosome = new Dictionary <string, IChromosome> {
["chr1"] = chromosome
};
var variantFactory = new VariantFactory(refNameToChromosome, refMinorProvider.Object, false);
var position1 = VcfReaderUtils.ParseVcfLine(vcfLine1, variantFactory, refNameToChromosome);
var annotatedVariants1 = Annotator.GetAnnotatedVariants(position1.Variants);
// SimplePositions
Assert.Equal(new[] { "G" }, position1.AltAlleles);
// Variants
Assert.Equal(new[] { "" }, annotatedVariants1.Select(x => x.Variant.AltAllele).ToArray());
}
public void ParseVcfLine_non_informative_alleles_or_NonRef_filtered_only_in_variants()
{
const string vcfLine1 = "chr1 13133 . T <*>,G 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
const string vcfLine2 = "chr1 13133 . T *,C 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
const string vcfLine3 = "chr1 13133 . T <M>,A 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
const string vcfLine4 = "chr1 13133 . T A,<NON_REF> 36.00 PASS SNVSB=0.0;SNVHPOL=4 GT:GQ:GQX:DP:DPF:AD 0/1:62:20:7:1:3,4";
var chromosome = new Chromosome("chr1", "1", 0);
var refMinorProvider = new Mock <IRefMinorProvider>();
refMinorProvider.Setup(x => x.IsReferenceMinor(chromosome, 13133)).Returns(false);
var refNameToChromosome = new Dictionary <string, IChromosome> {
["chr1"] = chromosome
};
var variantFactory = new VariantFactory(refNameToChromosome, refMinorProvider.Object, false);
var position1 = VcfReaderUtils.ParseVcfLine(vcfLine1, variantFactory, refNameToChromosome);
var position2 = VcfReaderUtils.ParseVcfLine(vcfLine2, variantFactory, refNameToChromosome);
var position3 = VcfReaderUtils.ParseVcfLine(vcfLine3, variantFactory, refNameToChromosome);
var position4 = VcfReaderUtils.ParseVcfLine(vcfLine4, variantFactory, refNameToChromosome);
var annotatedVariants1 = Annotator.GetAnnotatedVariants(position1.Variants);
var annotatedVariants2 = Annotator.GetAnnotatedVariants(position2.Variants);
var annotatedVariants3 = Annotator.GetAnnotatedVariants(position3.Variants);
var annotatedVariants4 = Annotator.GetAnnotatedVariants(position4.Variants);
// SimplePositions
Assert.Equal(new[] { "<*>", "G" }, position1.AltAlleles);
Assert.Equal(new[] { "*", "C" }, position2.AltAlleles);
Assert.Equal(new[] { "<M>", "A" }, position3.AltAlleles);
Assert.Equal(new[] { "A", "<NON_REF>" }, position4.AltAlleles);
// Variants
Assert.Equal(new[] { "G" }, annotatedVariants1.Select(x => x.Variant.AltAllele).ToArray());
Assert.Equal(new[] { "C" }, annotatedVariants2.Select(x => x.Variant.AltAllele).ToArray());
Assert.Equal(new[] { "A" }, annotatedVariants3.Select(x => x.Variant.AltAllele).ToArray());
Assert.Equal(new[] { "A" }, annotatedVariants4.Select(x => x.Variant.AltAllele).ToArray());
}
public void ParseVcfLine_line_with_only_NonRef_is_not_refMinor()
{
const string vcfLine = "1 10005 . C <NON_REF> . LowGQX END=10034;BLOCKAVG_min30p3a GT:GQX:DP:DPF 0/0:3:1:0";
var chromosome = new Chromosome("chr1", "1", 0);
var refMinorProvider = new Mock <IRefMinorProvider>();
refMinorProvider.Setup(x => x.IsReferenceMinor(chromosome, 10005)).Returns(false);
var refNameToChromosome = new Dictionary <string, IChromosome> {
["1"] = chromosome
};
var variantFactory = new VariantFactory(refNameToChromosome, refMinorProvider.Object, false);
var position = VcfReaderUtils.ParseVcfLine(vcfLine, variantFactory, refNameToChromosome);
var annotatedVariants = Annotator.GetAnnotatedVariants(position.Variants);
Assert.Equal("C", position.RefAllele);
Assert.Equal(new[] { "<NON_REF>" }, position.AltAlleles);
Assert.Equal("C", position.Variants[0].RefAllele);
Assert.Equal("<NON_REF>", position.Variants[0].AltAllele);
// Variants
Assert.Null(annotatedVariants);
}