public void CompareOneOutput_batch_channel()
{
var position = 1234689;
var variant1 = AnnotatedVariant.Create(position);
var variant2 = AnnotatedVariant.Create(position);
SerialAnnotator.Annotate(variant1);
var serialJson = Utf8Json.JsonSerializer.ToJsonString(variant1);
var annotator = new BatchChannelAnnotator();
var annotatorTask = Task.Run(async() =>
{
await annotator.Submit(new List <AnnotatedVariant>()
{
variant2
});
annotator.Complete();
});
annotatorTask.Wait();
var parallelJson = Utf8Json.JsonSerializer.ToJsonString(variant2);
Assert.Equal(serialJson, parallelJson);
}
public static void Annotate(AnnotatedVariant variant)
{
_countToDelay--;
if (_countToDelay == 0)
{
_countToDelay = RateLimit;
Thread.Sleep(1);
}
var position = variant.Position;
var refAllele = variant.RefAllele;
var altAllele = variant.AltAllele;
var random = position ^ refAllele.GetHashCode() ^ altAllele.GetHashCode() ^ Utilities.Prime9;
if (random < 0)
{
random = -random;
}
var pathogenicity = PathogenicitySet[random % PathogenicitySet.Length];
var reviewStatus = ReviewStatusSet[random % ReviewStatusSet.Length];
var pubmedIds = new int[1 + random % 11];
for (int i = 0; i < pubmedIds.Length; i++)
{
pubmedIds[i] = 1 + random % Utilities.Prime4;
random ^= Utilities.Prime9;
}
variant.ClinicalAnnotation = new ClinicalAnnotation(pathogenicity, pubmedIds, reviewStatus);
}
public void regulatory_region_is_added()
{
var mockedRegulatory = new Mock <IAnnotatedRegulatoryRegion>();
mockedRegulatory.SetupGet(x => x.Consequences).Returns(new List <ConsequenceTag> {
ConsequenceTag.regulatory_region_variant
});
mockedRegulatory.SetupGet(x => x.RegulatoryRegion.Id).Returns(CompactId.Convert("ENSR12345"));
var vcfFields = "chr1 101 sa123 A . . . . .".Split("\t");
var chrom = new Chromosome("chr1", "1", 0);
var inforData = new InfoData(null, null, VariantType.SNV, null, null, null, null, null, false, null, null,
false, false, "Test=abc", null, null);
var position = new Position(chrom, 101, 101, "A", new[] { "." }, 100, null, null, null, inforData, vcfFields, new[] { false }, false);
var variant = new Variant(chrom, 101, 101, "A", ".", VariantType.reference, null, false, false, false, null, null, new AnnotationBehavior(true, false, false, true, false, false));
var annotatedVariant = new AnnotatedVariant(variant);
annotatedVariant.RegulatoryRegions.Add(mockedRegulatory.Object);
IAnnotatedVariant[] annotatedVariants = { annotatedVariant };
var annotatedPosition = new AnnotatedPosition(position, annotatedVariants);
var converter = new VcfConversion();
var observedVcf = converter.Convert(annotatedPosition).Split("\t")[VcfCommon.InfoIndex];
Assert.Equal("Test=abc;CSQR=1|ENSR12345|regulatory_region_variant", observedVcf);
}
public static void Annotate(AnnotatedVariant variant)
{
CoreAnnotationProvider.Annotate(variant);
VariantIdProvider.Annotate(variant);
AlleleFreqProvider.Annotate(variant);
ClinicalAnnotationProvider.Annotate(variant);
}
public void GenotypeIndex_is_correct_w_refMinor_allele()
{
var vcfFields1 =
"1 10628385 . C <NON_REF> . LowGQX;HighDPFRatio END=10628385;BLOCKAVG_min30p3a GT:GQX:DP:DPF 0/0:24:9:18".Split('\t');
var vcfFields2 =
"1 10628385 . C <NON_REF> . LowGQX;HighDPFRatio END=10628385;BLOCKAVG_min30p3a GT:GQX:DP:DPF 0/0:24:9:18".Split('\t');
var chromosome = new Chromosome("chr1", "1", 0);
var inforData = new InfoData(null, null, VariantType.SNV, null, null, null, null, null, false, null, null,
false, false, "", null, null);
var position1 = new Position(chromosome, 10628385, 10628385, "C", new[] { "." }, 100, null, null, null, inforData, vcfFields1, new[] { false }, false);
var position2 = new Position(chromosome, 10628385, 10628385, "C", new[] { "." }, 100, null, null, null, inforData, vcfFields2, new[] { false }, false);
var variant = new Variant(chromosome, 10628385, 10628385, "C", "<NON_REF>", VariantType.reference, null, true, false, false, null, null, new AnnotationBehavior(true, false, false, true, false, false));
var annotatedVariant = new AnnotatedVariant(variant);
annotatedVariant.SupplementaryAnnotations.Add(new AnnotatedSaDataSource(new SaDataSource("testSource", "Test", "C", false, true, "pathogenic", null), "C"));
var annotatedPosition1 = new AnnotatedPosition(position1, new IAnnotatedVariant[] { annotatedVariant });
var annotatedPosition2 = new AnnotatedPosition(position2, new IAnnotatedVariant[] { annotatedVariant });
var converter = new VcfConversion();
var observedVcf1 = converter.Convert(annotatedPosition1).Split("\t")[VcfCommon.InfoIndex];
var observedVcf2 = converter.Convert(annotatedPosition2).Split("\t")[VcfCommon.InfoIndex];
Assert.Equal("RefMinor;Test=1|pathogenic", observedVcf1);
Assert.Equal("RefMinor;Test=1|pathogenic", observedVcf2);
}
public void Add(AnnotatedVariant variant)
{
var coreSubmit = Task.Run(() =>
{
_coreProducer.Wait();
_coreQueue.Enqueue(variant);
_coreConsumer.Release();
});
var alleleSubmit = Task.Run(() =>
{
_alleleProducer.Wait();
_alleleFreqQueue.Enqueue(variant);
_alleleConsumer.Release();
});
var idSubmit = Task.Run(() =>
{
_idProducer.Wait();
_idQueue.Enqueue(variant);
_idConsumer.Release();
});
var clinicalSubmit = Task.Run(() =>
{
_clinicalProducer.Wait();
_clinicalQueue.Enqueue(variant);
_clinicalConsumer.Release();
});
coreSubmit.Wait();
alleleSubmit.Wait();
idSubmit.Wait();
clinicalSubmit.Wait();
}
public static void Annotate(AnnotatedVariant variant)
{
_countToDelay--;
if (_countToDelay == 0)
{
_countToDelay = RateLimit;
Thread.Sleep(1);
}
var position = variant.Position;
var refAllele = variant.RefAllele;
var altAllele = variant.AltAllele;
var random = position ^ refAllele.GetHashCode() ^ altAllele.GetHashCode() ^ Utilities.Prime9;
if (random < 0)
{
random = -random;
}
var count = random % 13 + 1;
var ids = new string[count];
for (int i = 0; i < count; i++)
{
ids[i] = $"rs{random:0000000000}";
random ^= Utilities.Prime9;
}
variant.Ids = ids;
}
public async ValueTask Submit(AnnotatedVariant variant)
{
await _coreChannel.Writer.WriteAsync(variant);
await _alleleFreqChannel.Writer.WriteAsync(variant);
await _idChannel.Writer.WriteAsync(variant);
await _clinicalChannel.Writer.WriteAsync(variant);
}
public void GenotypeIndex_is_correct_w_nonInformative_altAlleles_filtered()
{
var vcfFields1 = "chr1 101 sa123 A <*>,T . . .".Split("\t");
var vcfFields2 = "chr1 101 sa123 A <M>,T . . .".Split("\t");
var vcfFields3 = "chr1 101 sa123 A *,T . . .".Split("\t");
var vcfFields4 = "chr1 101 sa123 A <NON_REF>,T . . .".Split("\t");
var vcfFields5 = "chr1 101 sa123 A T,<*> . . .".Split("\t");
var vcfFields6 = "chr1 101 sa123 A T,<M> . . .".Split("\t");
var vcfFields7 = "chr1 101 sa123 A T,* . . .".Split("\t");
var vcfFields8 = "chr1 101 sa123 A T,<NON_REF> . . .".Split("\t");
var chrom = new Chromosome("chr1", "1", 0);
var inforData = new InfoData(null, null, VariantType.SNV, null, null, null, null, null, false, null, null,
false, false, "", null, null);
var position1 = new Position(chrom, 101, 101, "A", new[] { "<*>", "T" }, 100, null, null, null, inforData, vcfFields1, new[] { false }, false);
var position2 = new Position(chrom, 101, 101, "A", new[] { "<M>", "T" }, 100, null, null, null, inforData, vcfFields2, new[] { false }, false);
var position3 = new Position(chrom, 101, 101, "A", new[] { "*", "T" }, 100, null, null, null, inforData, vcfFields3, new[] { false }, false);
var position4 = new Position(chrom, 101, 101, "A", new[] { "<NON_REF>", "T" }, 100, null, null, null, inforData, vcfFields4, new[] { false }, false);
var position5 = new Position(chrom, 101, 101, "A", new[] { "T", "<*>" }, 100, null, null, null, inforData, vcfFields5, new[] { false }, false);
var position6 = new Position(chrom, 101, 101, "A", new[] { "T", "<M>" }, 100, null, null, null, inforData, vcfFields6, new[] { false }, false);
var position7 = new Position(chrom, 101, 101, "A", new[] { "T", "*" }, 100, null, null, null, inforData, vcfFields7, new[] { false }, false);
var position8 = new Position(chrom, 101, 101, "A", new[] { "T", "<NON_REF>" }, 100, null, null, null, inforData, vcfFields8, new[] { false }, false);
var variant = new Variant(chrom, 101, 101, "A", "T", VariantType.SNV, null, false, false, false, null, null, new AnnotationBehavior(true, false, false, true, false, false));
var annotatedVariant = new AnnotatedVariant(variant);
annotatedVariant.SupplementaryAnnotations.Add(new AnnotatedSaDataSource(new SaDataSource("testSource", "Test", "T", false, true, "pathogenic", null), "T"));
IAnnotatedVariant[] annotatedVariants = { annotatedVariant };
var annotatedPosition1 = new AnnotatedPosition(position1, annotatedVariants);
var annotatedPosition2 = new AnnotatedPosition(position2, annotatedVariants);
var annotatedPosition3 = new AnnotatedPosition(position3, annotatedVariants);
var annotatedPosition4 = new AnnotatedPosition(position4, annotatedVariants);
var annotatedPosition5 = new AnnotatedPosition(position5, annotatedVariants);
var annotatedPosition6 = new AnnotatedPosition(position6, annotatedVariants);
var annotatedPosition7 = new AnnotatedPosition(position7, annotatedVariants);
var annotatedPosition8 = new AnnotatedPosition(position8, annotatedVariants);
var converter = new VcfConversion();
var observedVcf1 = converter.Convert(annotatedPosition1).Split("\t")[VcfCommon.InfoIndex];
var observedVcf2 = converter.Convert(annotatedPosition2).Split("\t")[VcfCommon.InfoIndex];
var observedVcf3 = converter.Convert(annotatedPosition3).Split("\t")[VcfCommon.InfoIndex];
var observedVcf4 = converter.Convert(annotatedPosition4).Split("\t")[VcfCommon.InfoIndex];
var observedVcf5 = converter.Convert(annotatedPosition5).Split("\t")[VcfCommon.InfoIndex];
var observedVcf6 = converter.Convert(annotatedPosition6).Split("\t")[VcfCommon.InfoIndex];
var observedVcf7 = converter.Convert(annotatedPosition7).Split("\t")[VcfCommon.InfoIndex];
var observedVcf8 = converter.Convert(annotatedPosition8).Split("\t")[VcfCommon.InfoIndex];
Assert.Equal("Test=2|pathogenic", observedVcf1);
Assert.Equal("Test=2|pathogenic", observedVcf2);
Assert.Equal("Test=2|pathogenic", observedVcf3);
Assert.Equal("Test=2|pathogenic", observedVcf4);
Assert.Equal("Test=1|pathogenic", observedVcf5);
Assert.Equal("Test=1|pathogenic", observedVcf6);
Assert.Equal("Test=1|pathogenic", observedVcf7);
Assert.Equal("Test=1|pathogenic", observedVcf8);
}
public void GetJsonString_RecomposedSnvAfterTrimming_IsRecomposedTrue()
{
IVariant variant = new Variant(ChromosomeUtilities.Bob, 100, 200, "A", "G", VariantType.SNV, "bob-100-A-G", false, false, true,
new[] { "bob-100-A-G" }, AnnotationBehavior.SmallVariants, false);
var annotatedVariant = new AnnotatedVariant(variant);
const string expectedResult = "{\"vid\":\"bob-100-A-G\",\"chromosome\":\"BoB\",\"begin\":100,\"end\":200,\"refAllele\":\"A\",\"altAllele\":\"G\",\"variantType\":\"SNV\",\"isRecomposedVariant\":true,\"linkedVids\":[\"bob-100-A-G\"]}";
string observedResult = annotatedVariant.GetJsonString(OriginalChromosomeName);
Assert.Equal(expectedResult, observedResult);
}
public static AnnotatedVariant[] CreateAnnotatedVariants(int count)
{
var annoVariants = new AnnotatedVariant[count];
for (int i = 0; i < count; i++)
{
annoVariants[i] = AnnotatedVariant.Create();
}
return(annoVariants);
}
public static List <AnnotatedVariant> DeepCopy(List <AnnotatedVariant> variants)
{
var newVariants = new List <AnnotatedVariant>(variants.Count);
for (int i = 0; i < variants.Count; i++)
{
newVariants.Add(AnnotatedVariant.Create(variants[i].Position));
}
return(newVariants);
}
private static IAnnotatedPosition GetAnnotatedPosition(IVariant variant)
{
IVariant[] variants = { variant };
var position = new Position(ChromosomeUtilities.Chr3, Start, End, null, null, null, null, variants, null, null, null, null,
false);
var annotatedVariant = new AnnotatedVariant(variant);
IAnnotatedVariant[] annotatedVariants = { annotatedVariant };
return(new AnnotatedPosition(position, annotatedVariants));
}
public void Only_canonical_transcripts_are_reported_in_vcf()
{
var mockedTranscript1 = new Mock <IAnnotatedTranscript>();
mockedTranscript1.Setup(x => x.Transcript.IsCanonical).Returns(true);
mockedTranscript1.Setup(x => x.Transcript.Id).Returns(CompactId.Convert("ENST12345", 1));
mockedTranscript1.Setup(x => x.Transcript.Gene.Symbol).Returns("testGene1");
mockedTranscript1.SetupGet(x => x.Consequences)
.Returns(new List <ConsequenceTag> {
ConsequenceTag.five_prime_UTR_variant
});
var mockedTranscript2 = new Mock <IAnnotatedTranscript>();
mockedTranscript2.Setup(x => x.Transcript.IsCanonical).Returns(false);
mockedTranscript2.Setup(x => x.Transcript.Id).Returns(CompactId.Convert("ENST23456", 2));
mockedTranscript2.Setup(x => x.Transcript.Gene.Symbol).Returns("testGene2");
mockedTranscript2.SetupGet(x => x.Consequences)
.Returns(new List <ConsequenceTag> {
ConsequenceTag.missense_variant
});
var mockedTranscript3 = new Mock <IAnnotatedTranscript>();
mockedTranscript3.Setup(x => x.Transcript.IsCanonical).Returns(true);
mockedTranscript3.Setup(x => x.Transcript.Id).Returns(CompactId.Convert("NM_1234", 3));
mockedTranscript3.Setup(x => x.Transcript.Gene.Symbol).Returns("testGene3");
mockedTranscript3.SetupGet(x => x.Consequences)
.Returns(new List <ConsequenceTag> {
ConsequenceTag.missense_variant, ConsequenceTag.splice_region_variant
});
var vcfFields = "chr1 101 sa123 A T . . .".Split("\t");
var chrom = new Chromosome("chr1", "1", 0);
var inforData = new InfoData(null, null, VariantType.SNV, null, null, null, null, null, false, null, null,
false, false, "", null, null);
var position = new Position(chrom, 101, 101, "A", new[] { "T" }, 100, null, null, null, inforData, vcfFields, new[] { false }, false);
var variant = new Variant(chrom, 101, 101, "A", "T", VariantType.SNV, null, false, false, false, null, null, new AnnotationBehavior(true, false, false, true, false, false));
var annotatedVariant = new AnnotatedVariant(variant);
annotatedVariant.EnsemblTranscripts.Add(mockedTranscript1.Object);
annotatedVariant.EnsemblTranscripts.Add(mockedTranscript2.Object);
annotatedVariant.RefSeqTranscripts.Add(mockedTranscript3.Object);
IAnnotatedVariant[] annotatedVariants = { annotatedVariant };
var annotatedPosition = new AnnotatedPosition(position, annotatedVariants);
var converter = new VcfConversion();
var observedVcf = converter.Convert(annotatedPosition).Split("\t")[VcfCommon.InfoIndex];
Assert.Equal("CSQT=1|testGene1|ENST12345.1|5_prime_UTR_variant,1|testGene3|NM_1234.3|missense_variant&splice_region_variant", observedVcf);
}
public void GetJsonString_RefMinor_WithTranscripts()
{
IVariant variant = GetRefMinorVariant();
var annotatedVariant = new AnnotatedVariant(variant);
AddRegulatoryRegion(annotatedVariant);
AddTranscript(annotatedVariant);
const string expectedResult = "{\"vid\":\"bob:100:G\",\"chromosome\":\"BoB\",\"begin\":100,\"end\":200,\"isReferenceMinorAllele\":true,\"refAllele\":\"A\",\"altAllele\":\"G\",\"variantType\":\"SNV\",\"linkedVids\":[\"bob:100:102:TAT\"],\"regulatoryRegions\":[{\"id\":\"7157\",\"type\":\"TF_binding_site\",\"consequence\":[\"regulatory_region_amplification\"]}],\"transcripts\":[]}";
var observedResult = annotatedVariant.GetJsonString(OriginalChromosomeName);
Assert.Equal(expectedResult, observedResult);
}
public void Test1()
{
var variant = AnnotatedVariant.Create();
var nirvanaJson = variant.SerializeJson();
var newtonsoftJson = JsonConvert.SerializeObject(variant);
var utf8Json = Utf8Json.JsonSerializer.ToJsonString(variant);
var utf8Bytes = Utf8Json.JsonSerializer.Serialize(variant);
var systemJson = JsonSerializer.Serialize(variant);
Assert.Equal(nirvanaJson, newtonsoftJson);
Assert.Equal(nirvanaJson, utf8Json);
Assert.Equal(nirvanaJson, Encoding.UTF8.GetString(utf8Bytes));
Assert.Equal(nirvanaJson, systemJson);
}
internal static IAnnotatedVariant[] GetAnnotatedVariants(IVariant[] variants)
{
if (variants?[0].Behavior == null)
{
return(null);
}
var numVariants = variants.Length;
var annotatedVariants = new IAnnotatedVariant[numVariants];
for (var i = 0; i < numVariants; i++)
{
annotatedVariants[i] = new AnnotatedVariant(variants[i]);
}
return(annotatedVariants);
}
public static List <AnnotatedVariant> GetVariants(int n)
{
var delta = new Random();
var variants = new List <AnnotatedVariant>(n);
var position = delta.Next(1000, 5000);
for (int i = 0; i < n; i++)
{
position += delta.Next(0, 500);
variants.Add(AnnotatedVariant.Create(position));
}
return(variants);
}
public void GetJsonString_Variant_WithSupplementaryAnnotation()
{
IVariant variant = GetVariant();
var annotatedVariant = new AnnotatedVariant(variant);
const string originalChromosomeName = "BoB";
AddRegulatoryRegion(annotatedVariant);
AddSupplementaryAnnotation(annotatedVariant);
annotatedVariant.PhylopScore = -0.314;
const string expectedResult = "{\"vid\":\"bob:100:G\",\"chromosome\":\"BoB\",\"begin\":100,\"end\":200,\"refAllele\":\"A\",\"altAllele\":\"G\",\"variantType\":\"SNV\",\"phylopScore\":-0.314,\"regulatoryRegions\":[{\"id\":\"7157\",\"type\":\"TF_binding_site\",\"consequence\":[\"regulatory_region_amplification\"]}],\"clinVar\":{\"good\":\"result\"},\"exac\":[{\"bad\":\"temper\"},{\"brutal\":\"kangaroo\"}]}";
var observedResult = annotatedVariant.GetJsonString(originalChromosomeName);
Assert.Equal(expectedResult, observedResult);
}
public void original_updated_info_is_added_to_info_field()
{
var vcfFields = "chr1 101 sa123 A . . . . .".Split("\t");
var chrom = new Chromosome("chr1", "1", 0);
var inforData = new InfoData(null, null, VariantType.SNV, null, null, null, null, null, false, null, null,
false, false, "Test=abc", null, null);
var position = new Position(chrom, 101, 101, "A", new[] { "." }, 100, null, null, null, inforData, vcfFields, new[] { false }, false);
var variant = new Variant(chrom, 101, 101, "A", ".", VariantType.reference, null, true, false, false, null, null, new AnnotationBehavior(true, false, false, true, false, false));
var annotatedVariant = new AnnotatedVariant(variant);
IAnnotatedVariant[] annotatedVariants = { annotatedVariant };
var annotatedPosition = new AnnotatedPosition(position, annotatedVariants);
var converter = new VcfConversion();
var observedVcf = converter.Convert(annotatedPosition).Split("\t")[VcfCommon.InfoIndex];
Assert.Equal("Test=abc;RefMinor", observedVcf);
}
public void CompareOneOutput_conQ()
{
var position = 1234689;
var variant1 = AnnotatedVariant.Create(position);
var variant2 = AnnotatedVariant.Create(position);
SerialAnnotator.Annotate(variant1);
var serialJson = Utf8Json.JsonSerializer.ToJsonString(variant1);
var conQAnnotator = new ConQAnnotator(50);
conQAnnotator.Add(variant2);
conQAnnotator.Complete();
var conqJson = Utf8Json.JsonSerializer.ToJsonString(variant2);
Assert.Equal(serialJson, conqJson);
}
public void CompareOneOutput_channel()
{
var position = 1234689;
var variant1 = AnnotatedVariant.Create(position);
var variant2 = AnnotatedVariant.Create(position);
SerialAnnotator.Annotate(variant1);
var serialJson = Utf8Json.JsonSerializer.ToJsonString(variant1);
var channelAnnotator = new ChannelAnnotator();
channelAnnotator.Submit(variant2);
channelAnnotator.Complete();
var parallelJson = Utf8Json.JsonSerializer.ToJsonString(variant2);
Assert.Equal(serialJson, parallelJson);
}
public void Original_dbsnp_nonrsid_get_kept()
{
var vcfFields = "chr1 101 sa123 A T . . .".Split("\t");
var chrom = new Chromosome("chr1", "1", 0);
var inforData = new InfoData(null, null, VariantType.SNV, null, null, null, null, null, false, null, null,
false, false, "", null, null);
var position = new Position(chrom, 101, 101, "A", new[] { "T" }, 100, null, null, null, inforData, vcfFields, new[] { false }, false);
var variant = new Variant(chrom, 101, 101, "A", "T", VariantType.SNV, null, false, false, false, null, null, new AnnotationBehavior(true, false, false, true, false, false));
var annotatedVariant = new AnnotatedVariant(variant);
IAnnotatedVariant[] annotatedVariants = { annotatedVariant };
var annotatedPosition = new AnnotatedPosition(position, annotatedVariants);
var converter = new VcfConversion();
var observedVcf = converter.Convert(annotatedPosition).Split("\t")[VcfCommon.IdIndex];
Assert.Equal("sa123", observedVcf);
}
public void Annotate(AnnotatedVariant variant)
{
if (_isComplete)
{
return;
}
_variant = variant;
_coreSemaphore.Release();
_alleleFreqSemaphore.Release();
_idSemaphore.Release();
_clinicalSemaphore.Release();
//now wait for the annotations to be done
_coreDone.Wait();
_alleleFreqDone.Wait();
_idDone.Wait();
_clinicalDone.Wait();
}
public void Gmaf_outputed()
{
var vcfFields = "chr1 101 sa123 A T . . .".Split("\t");
var chrom = new Chromosome("chr1", "1", 0);
var inforData = new InfoData(null, null, VariantType.SNV, null, null, null, null, null, false, null, null,
false, false, "", null, null);
var position = new Position(chrom, 101, 101, "A", new[] { "T" }, 100, null, null, null, inforData, vcfFields, new[] { false }, false);
var variant = new Variant(chrom, 101, 101, "A", "T", VariantType.SNV, null, false, false, false, null, null, new AnnotationBehavior(true, false, false, true, false, false));
var annotatedVariant = new AnnotatedVariant(variant);
annotatedVariant.SupplementaryAnnotations.Add(new AnnotatedSaDataSource(new SaDataSource("globalAllele", "GMAF", "N", false, false, "G|0.002", null), "N"));
IAnnotatedVariant[] annotatedVariants = { annotatedVariant };
var annotatedPosition = new AnnotatedPosition(position, annotatedVariants);
var converter = new VcfConversion();
var observedVcf = converter.Convert(annotatedPosition).Split("\t")[VcfCommon.InfoIndex];
Assert.Equal("GMAF=G|0.002", observedVcf);
}
public void Original_dbsnp_nonrsid_merged_with_rsid_from_dbsnp()
{
var vcfFields = "chr1 101 sa123 A T . . .".Split("\t");
var chrom = new Chromosome("chr1", "1", 0);
var inforData = new InfoData(null, null, VariantType.SNV, null, null, null, null, null, false, null, null,
false, false, "", null, null);
var position = new Position(chrom, 101, 101, "A", new[] { "T" }, 100, null, null, null, inforData, vcfFields, new[] { false }, false);
var variant = new Variant(chrom, 101, 101, "A", "T", VariantType.SNV, null, false, false, false, null, null, new AnnotationBehavior(true, false, false, true, false, false));
var annotatedVariant = new AnnotatedVariant(variant);
annotatedVariant.SupplementaryAnnotations.Add(new AnnotatedSaDataSource(new SaDataSource("dbsnp", "", "T", true, false, "rs456", null), "T"));
IAnnotatedVariant[] annotatedVariants = { annotatedVariant };
var annotatedPosition = new AnnotatedPosition(position, annotatedVariants);
var converter = new VcfConversion();
var observedVcf = converter.Convert(annotatedPosition).Split("\t")[VcfCommon.IdIndex];
Assert.Equal("sa123;rs456", observedVcf);
}
public void OneKGAnnotation_is_handled()
{
var vcfFields = "chr1 101 sa123 A T . . .".Split("\t");
var chrom = new Chromosome("chr1", "1", 0);
var inforData = new InfoData(null, null, VariantType.SNV, null, null, null, null, null, false, null, null,
false, false, "", null, null);
var position = new Position(chrom, 101, 101, "A", new[] { "T" }, 100, null, null, null, inforData, vcfFields, new[] { false }, false);
var variant = new Variant(chrom, 101, 101, "A", "T", VariantType.SNV, null, false, false, false, null, null, new AnnotationBehavior(true, false, false, true, false, false));
var annotatedVariant = new AnnotatedVariant(variant);
annotatedVariant.SupplementaryAnnotations.Add(new AnnotatedSaDataSource(new SaDataSource("oneKg", "AF1000G", "T", true, false, "0.000599;t", null), "T"));
IAnnotatedVariant[] annotatedVariants = { annotatedVariant };
var annotatedPosition = new AnnotatedPosition(position, annotatedVariants);
var converter = new VcfConversion();
var observedVcf = converter.Convert(annotatedPosition).Split("\t")[VcfCommon.InfoIndex];
Assert.Equal("AA=t;AF1000G=0.000599", observedVcf);
}
public void Only_allele_specific_entry_for_annotation_not_matched_by_allele_is_output()
{
var vcfFields = "chr1 101 sa123 A T . . .".Split("\t");
var chrom = new Chromosome("chr1", "1", 0);
var inforData = new InfoData(null, null, VariantType.SNV, null, null, null, null, null, false, null, null,
false, false, "", null, null);
var position = new Position(chrom, 101, 101, "A", new[] { "T" }, 100, null, null, null, inforData, vcfFields, new[] { false }, false);
var variant = new Variant(chrom, 101, 101, "A", "T", VariantType.SNV, null, false, false, false, null, null, new AnnotationBehavior(true, false, false, true, false, false));
var annotatedVariant = new AnnotatedVariant(variant);
annotatedVariant.SupplementaryAnnotations.Add(new AnnotatedSaDataSource(new SaDataSource("testSource", "Test", "T", false, true, "pathogenic", null), "T"));
annotatedVariant.SupplementaryAnnotations.Add(new AnnotatedSaDataSource(new SaDataSource("testSource", "Test", "G", false, true, "benign", null), "T"));
IAnnotatedVariant[] annotatedVariants = { annotatedVariant };
var annotatedPosition = new AnnotatedPosition(position, annotatedVariants);
var converter = new VcfConversion();
var observedVcf = converter.Convert(annotatedPosition).Split("\t")[VcfCommon.InfoIndex];
Assert.Equal("Test=1|pathogenic", observedVcf);
}
public static void Annotate(AnnotatedVariant variant)
{
_countToDelay--;
if (_countToDelay == 0)
{
_countToDelay = RateLimit;
Thread.Sleep(1);
}
var position = variant.Position;
var n = 1 + position % 13;// that its never 0
var transcripts = new AnnotatedTranscript[n];
for (int i = 0; i < n; i++)
{
transcripts[i] = AnnotatedTranscript.Create(position, i);
}
variant.Transcripts = transcripts;
}
public static void Annotate(AnnotatedVariant variant)
{
_countToDelay--;
if (_countToDelay == 0)
{
_countToDelay = RateLimit;
Thread.Sleep(1);
}
var position = variant.Position;
var refAllele = variant.RefAllele;
var altAllele = variant.AltAllele;
var random = position ^ refAllele.GetHashCode() ^ altAllele.GetHashCode() ^ Utilities.Prime9;
var count = 15;
var frequencies = new double[count];
for (int i = 0; i < count; i++)
{
frequencies[i] = (random % Utilities.Prime6) * 1.0 / 1_000_000;
random ^= Utilities.Prime9;
}
variant.AlleleFrequencies = frequencies;
}
