public void Parse_Somatic_Strelka()
{
var info = VcfInfoParser.Parse("SOMATIC;QSS=2;TQSS=1;NT=het;QSS_NT=2;TQSS_NT=1;SGT=CG->CG;DP=183;MQ=46.57;MQ0=15;ALTPOS=35;ALTMAP=24;ReadPosRankSum=-1.23;SNVSB=0.00;PNOISE=0.00;PNOISE2=0.00;VQSR=1.23");
Assert.Equal(1.23, info.RecalibratedQuality);
Assert.Equal(2, info.JointSomaticNormalQuality);
}
public void Blank_info_field_when_remove_all_info_tags()
{
var info = VcfInfoParser.Parse(
"AA=G;CSQT=1|AGRN|ENST00000379370|");
Assert.Equal("", info.UpdatedInfoField);
}
public void Parse_GATK()
{
var info = VcfInfoParser.Parse("AC=2;AF=0.250;AN=8;BaseQRankSum=1.719;DB;DP=106;Dels=0.00;FS=20.202;HaplotypeScore=0.0000;MLEAC=2;MLEAF=0.250;MQ=43.50;MQ0=52;MQRankSum=2.955;QD=4.73;ReadPosRankSum=1.024;SB=-1.368e+02;VQSLOD=-0.3503;culprit=MQ;PLF");
Assert.Equal(-136.8, info.StrandBias);
Assert.Equal(20.202, info.FisherStrandBias);
Assert.Equal(43.50, info.MappingQuality);
}
public void Info_tags_are_correctly_removed()
{
var info = VcfInfoParser.Parse(
"END=964423;SVTYPE=DEL;SVLEN=-422;IMPRECISE;CIPOS=-170,170;CIEND=-175,175;CSQT=1|AGRN|ENST00000379370|");
Assert.Equal("END=964423;SVTYPE=DEL;SVLEN=-422;IMPRECISE;CIPOS=-170,170;CIEND=-175,175",
info.UpdatedInfoField);
}
public void Info_tags_are_capturedCorrect3()
{
var info = VcfInfoParser.Parse(
"AC=2;AF=0.250;AN=8;BaseQRankSum=1.719;DB;DP=106;Dels=0.00;FS=20.202;HaplotypeScore=0.0000;MLEAC=2;MLEAF=0.250;MQ=43.50;MQ0=52;MQRankSum=2.955;QD=4.73;ReadPosRankSum=1.024;SB=-1.368e+02;VQSLOD=-0.3503;culprit=MQ;PLF");
Assert.Equal(106, info.Depth);
Assert.Equal(-136.8, info.StrandBias);
}
public void GetVariant_svDel()
{
var infoData = VcfInfoParser.Parse("SVTYPE=DEL;END=138730");
var variantFactory = new VariantFactory(Sequence, _vidCreator);
IVariant[] variants = variantFactory.CreateVariants(ChromosomeUtilities.Chr1, 69391, 138730, "A", new[] { "<DEL>" }, infoData, new[] { false }, false, null, null);
Assert.NotNull(variants);
}
public void Info_tags_are_capturedCorrect1()
{
var info = VcfInfoParser.Parse(
"SOMATIC;QSI=2;TQSI=1;NT=het;QSI_NT=2;TQSI_NT=1;VQSR=5.9;CN=6");
Assert.Equal(2, info.JointSomaticNormalQuality);
Assert.Equal(6, info.CopyNumber);
Assert.Equal(5.9, info.RecalibratedQuality);
}
public void Parse_Somatic_Manta()
{
var info = VcfInfoParser.Parse("END=1660503;SVTYPE=DEL;SVLEN=-65919;IMPRECISE;CIPOS=-285,285;CIEND=-205,205;SOMATIC;SOMATICSCORE=36;ColocalizedCanvas");
Assert.Equal(65919, info.SvLength);
Assert.Equal(1660503, info.End);
Assert.Equal(36, info.JointSomaticNormalQuality);
Assert.Equal(new[] { -285, 285 }, info.CiPos);
Assert.Equal(new[] { -205, 205 }, info.CiEnd);
}
public void GetVariant_svDel()
{
var infoData = VcfInfoParser.Parse("SVTYPE=DEL;END=138730");
var variantFactory = new VariantFactory(_sequenceProvider);
var variants = variantFactory.CreateVariants(_chromosome1, 69391, 138730, "A", new[] { "<DEL>" }, infoData, new[] { false }, false, null, null);
Assert.NotNull(variants);
Assert.Equal(2, variants[0].BreakEnds.Length);
}
public void Info_tags_are_capturedCorrect2()
{
var info = VcfInfoParser.Parse(
"END=1660503;SVTYPE=DEL;SVLEN=-65919;IMPRECISE;CIPOS=-285,285;CIEND=-205,205;SOMATIC;SOMATICSCORE=36;ColocalizedCanvas");
Assert.Equal(65919, info.SvLength);
Assert.Equal(1660503, info.End);
Assert.True(info.ColocalizedWithCnv);
Assert.Equal(36, info.JointSomaticNormalQuality);
Assert.Equal(new[] { -285, 285 }, info.CiPos);
Assert.Equal(new[] { -205, 205 }, info.CiEnd);
}
public void GetVariant_svDel()
{
var infoData = VcfInfoParser.Parse("SVTYPE=DEL;END=138730");
var chromosome1 = new Chromosome("chr1", "1", 0);
var variantFactory = new VariantFactory(new Dictionary <string, IChromosome> {
{ "1", chromosome1 }
}, null, false);
var variants = variantFactory.CreateVariants(chromosome1, null, 69391, 138730, "A", new[] { "<DEL>" }, infoData, new[] { false }, false);
Assert.NotNull(variants);
Assert.Equal(2, variants[0].BreakEnds.Length);
}
public static IPosition ToPosition(ISimplePosition simplePosition, IRefMinorProvider refMinorProvider, ISequenceProvider sequenceProvider, IMitoHeteroplasmyProvider mitoHeteroplasmyProvider, VariantFactory variantFactory, bool enableDq = false)
{
if (simplePosition == null)
{
return(null);
}
sequenceProvider.LoadChromosome(simplePosition.Chromosome);
string[] vcfFields = simplePosition.VcfFields;
string[] altAlleles = vcfFields[VcfCommon.AltIndex].OptimizedSplit(',');
bool isReference = altAlleles.Length == 1 && VcfCommon.ReferenceAltAllele.Contains(altAlleles[0]);
string globalMajorAllele = isReference
? refMinorProvider?.GetGlobalMajorAllele(simplePosition.Chromosome, simplePosition.Start)
: null;
bool isRefMinor = isReference && globalMajorAllele != null;
if (isReference && !isRefMinor)
{
return(GetReferencePosition(simplePosition));
}
var infoData = VcfInfoParser.Parse(vcfFields[VcfCommon.InfoIndex]);
int end = ExtractEnd(infoData, simplePosition.Start, simplePosition.RefAllele.Length);
double?quality = vcfFields[VcfCommon.QualIndex].GetNullableValue <double>(double.TryParse);
string[] filters = vcfFields[VcfCommon.FilterIndex].OptimizedSplit(';');
ISample[] samples = vcfFields.ToSamples(variantFactory.FormatIndices, simplePosition, mitoHeteroplasmyProvider, enableDq);
IVariant[] variants = variantFactory.CreateVariants(simplePosition.Chromosome, simplePosition.Start, end,
simplePosition.RefAllele, altAlleles, infoData, simplePosition.IsDecomposed,
simplePosition.IsRecomposed, simplePosition.LinkedVids, globalMajorAllele);
return(new Position(simplePosition.Chromosome, simplePosition.Start, end, simplePosition.RefAllele,
altAlleles, quality, filters, variants, samples, infoData, vcfFields, simplePosition.IsDecomposed,
simplePosition.IsRecomposed));
}
public static Position CreatFromSimplePosition(ISimplePosition simplePosition, VariantFactory variantFactory)
{
if (simplePosition == null)
{
return(null);
}
var vcfFields = simplePosition.VcfFields;
var infoData = VcfInfoParser.Parse(vcfFields[VcfCommon.InfoIndex]);
var id = vcfFields[VcfCommon.IdIndex];
int end = ExtractEnd(infoData, simplePosition.Start, simplePosition.RefAllele.Length); // re-calculate the end by checking INFO field
string[] altAlleles = vcfFields[VcfCommon.AltIndex].Split(',').ToArray();
double? quality = vcfFields[VcfCommon.QualIndex].GetNullableValue <double>(double.TryParse);
string[] filters = vcfFields[VcfCommon.FilterIndex].Split(';');
var samples = new SampleFieldExtractor(vcfFields, infoData.Depth).ExtractSamples();
var variants = variantFactory.CreateVariants(simplePosition.Chromosome, id, simplePosition.Start, end, simplePosition.RefAllele, altAlleles, infoData, simplePosition.IsDecomposed, simplePosition.IsRecomposed);
return(new Position(simplePosition.Chromosome, simplePosition.Start, end, simplePosition.RefAllele, altAlleles, quality, filters, variants, samples,
infoData, vcfFields, simplePosition.IsDecomposed, simplePosition.IsRecomposed));
}
public void EmptyInfoField()
{
Assert.Null(VcfInfoParser.Parse(""));
}
public void Parse_Breakend_Event_Id()
{
var info = VcfInfoParser.Parse("SVTYPE=BND;MATEID=MantaBND:2312:0:1:1:0:0:0;IMPRECISE;CIPOS=-344,344;EVENT=MantaBND:2312:0:1:0:0:0:0;JUNCTION_QUAL=204;BND_DEPTH=38;MATE_BND_DEPTH=46");
Assert.Equal("MantaBND:2312:0:1:0:0:0:0", info.BreakendEventId);
}