public void AnnotationSourceConstructor()
{
var saPath = Resources.TopPath("DirectoryIntegrity");
var cacheStub = Resources.CacheGRCh37("ENST00000579787_chr1_Ensembl84");
var customAnnoPath = Resources.TopPath("DirectoryIntegrity");
var customIntervalsPath = Resources.TopPath("DirectoryIntegrity");
var conservationScoreReader = new PhylopReader(saPath);
var transcriptStream = ResourceUtilities.GetReadStream(cacheStub + ".ndb");
var siftStream = ResourceUtilities.GetReadStream(cacheStub + ".sift");
var polyPhenStream = ResourceUtilities.GetReadStream(cacheStub + ".polyphen");
var referenceStream = ResourceUtilities.GetReadStream(cacheStub + ".bases");
var streams = new AnnotationSourceStreams(transcriptStream, siftStream, polyPhenStream, referenceStream);
var customAnnotationProvider = new CustomAnnotationProvider(new[] { customAnnoPath });
var customIntervalProvider = new CustomIntervalProvider(new[] { customIntervalsPath });
var saProvider = new SupplementaryAnnotationProvider(saPath);
var annotationSource = new NirvanaAnnotationSource(streams, saProvider, conservationScoreReader,
customAnnotationProvider, customIntervalProvider, null);
Assert.NotNull(annotationSource);
}
public void EmptySamplesTest()
{
using (var reader = new LiteVcfReader(ResourceUtilities.GetReadStream(Resources.InputFiles("Nirvana_unified_json_format.vcf"))))
{
// getting the 4th variant
VcfUtilities.GetNextVariant(reader, _renamer);
VcfUtilities.GetNextVariant(reader, _renamer);
VcfUtilities.GetNextVariant(reader, _renamer);
var variant = VcfUtilities.GetNextVariant(reader, _renamer);
// GT:GQ:GQX:DPI:AD
// 0/1:124:19:5:11,8:PASS:.
// .
// 1/2:55:59:.:0,21:LowGQX:20
// the unified json will call this function to get all the samples and can print them out using GetEntry as shown below
var sampleVariants = variant.ExtractSampleInfo();
var expectedEntry =
"{\"variantFreq\":0.4211,\"genotypeQuality\":124,\"alleleDepths\":[11,8],\"genotype\":\"0/1\"}";
var observedEntry = sampleVariants[0].ToString();
Assert.Equal(expectedEntry, observedEntry);
expectedEntry = "{\"isEmpty\":true}";
observedEntry = sampleVariants[1].ToString();
Assert.Equal(expectedEntry, observedEntry);
expectedEntry =
"{\"variantFreq\":1,\"totalDepth\":20,\"genotypeQuality\":55,\"alleleDepths\":[0,21],\"genotype\":\"1/2\",\"failedFilter\":true}";
observedEntry = sampleVariants[2].ToString();
Assert.Equal(expectedEntry, observedEntry);
}
}
public void JsonSamplesOutput()
{
using (var reader = new LiteVcfReader(ResourceUtilities.GetReadStream(Resources.InputFiles("Nirvana_unified_json_format.vcf"))))
{
// LP2000021 LP2000022 LP2000023
Assert.Equal("LP2000021", reader.SampleNames[0]);
Assert.Equal("LP2000022", reader.SampleNames[1]);
Assert.Equal("LP2000023", reader.SampleNames[2]);
var variant = VcfUtilities.GetNextVariant(reader, _renamer);
// chr9 138685463 . A C . PASS BaseQRankSum=-1.61165;GQ=120;DP=43;ReadPosRankSum=0;MQ=60;SNVHPOL=3;SNVSB=-65.7;MQRankSum=0 GT:GQX:GQ:DP:DPF:AD 0/0:90:0:31:0:. 0/0:75:0:26:0:. 0/1:161:194:36:0:20,16
// the unified json will call this function to get all the samples and can print them out using GetEntry as shown below
var sampleVariants = variant.ExtractSampleInfo();
Assert.Equal("0/0", sampleVariants[0].Genotype);
Assert.Equal("0/0", sampleVariants[1].Genotype);
Assert.Equal("0/1", sampleVariants[2].Genotype);
const string expectedEntry1 = "{\"totalDepth\":31,\"genotypeQuality\":90,\"genotype\":\"0/0\"}";
const string expectedEntry2 = "{\"totalDepth\":26,\"genotypeQuality\":75,\"genotype\":\"0/0\"}";
const string expectedEntry3 = "{\"variantFreq\":0.4444,\"totalDepth\":36,\"genotypeQuality\":161,\"alleleDepths\":[20,16],\"genotype\":\"0/1\"}";
Assert.Equal(expectedEntry1, sampleVariants[0].ToString());
Assert.Equal(expectedEntry2, sampleVariants[1].ToString());
Assert.Equal(expectedEntry3, sampleVariants[2].ToString());
}
}
public void IndexCreation_multiChromosome()
{
var jsonStream = new BlockGZipStream(ResourceUtilities.GetReadStream(Resources.TopPath("cosmicv72.indels.json.gz")), CompressionMode.Decompress);
var writeStream = new MemoryStream();
using (var indexCreator = new IndexCreator(jsonStream, writeStream))
{
indexCreator.CreateIndex();
}
JasixIndex readBackIndex;
var readStream = new MemoryStream(writeStream.ToArray());
readStream.Seek(0, SeekOrigin.Begin);
using (readStream)
{
readBackIndex = new JasixIndex(readStream);
}
Assert.Equal(2268, readBackIndex.GetFirstVariantPosition("chr1", 9775924, 9775924));
Assert.Equal(14035925971, readBackIndex.GetFirstVariantPosition("chr2", 16081096, 16081096));
Assert.Equal(433156622693, readBackIndex.GetFirstVariantPosition("chr20", 36026164, 36026164));
Assert.Equal(439602269527, readBackIndex.GetFirstVariantPosition("chrX", 66765044, 66765044));
}
public void GetGeneSection()
{
var readStream = new BlockGZipStream(ResourceUtilities.GetReadStream(Resources.TopPath("Clinvar20150901.json.gz")), CompressionMode.Decompress);
var indexStream = ResourceUtilities.GetReadStream(Resources.TopPath("Clinvar20150901.json.gz.jsi"));
var outStream = new MemoryStream();
using (var writer = new StreamWriter(outStream, Encoding.UTF8, 512, true))
using (var qp = new QueryProcessor(new StreamReader(readStream), indexStream, writer))
{
writer.NewLine = "\r\n";
qp.PrintSection("genes");
}
Assert.NotEqual(0, outStream.Length);
outStream.Position = 0;
using (var reader = new StreamReader(outStream))
{
var count = 0;
var line = reader.ReadLine();
while (line != null)
{
count++;
line = reader.ReadLine();
}
Assert.Equal(127, count);
}
}
public void NoSamples()
{
using (var reader = new LiteVcfReader(ResourceUtilities.GetReadStream(Resources.InputFiles("NoSamples.vcf"))))
{
Assert.Null(reader.SampleNames);
}
}
/// <summary>
/// constructor
/// </summary>
public ChromosomeRenamerFixture()
{
var referenceStream = ResourceUtilities.GetReadStream(Resources.CacheGRCh37("ENSR00001584270_chr1_Ensembl84_reg.bases"));
Sequence = new CompressedSequence();
Reader = new CompressedSequenceReader(referenceStream, Sequence);
Renamer = Sequence.Renamer;
}
public void CopyNumberExtractionNormal()
{
using (var reader = new LiteVcfReader(ResourceUtilities.GetReadStream(Resources.InputFiles("canvas.vcf"))))
{
Assert.Equal(9, VcfCommon.GenotypeIndex);
Assert.Equal("SAMPLE", reader.SampleNames[0]);
}
}
public void CopyNumberExtractionTumor()
{
using (var reader = new LiteVcfReader(ResourceUtilities.GetReadStream(Resources.InputFiles("tumor.vcf"))))
{
Assert.Equal(9, VcfCommon.GenotypeIndex);
Assert.Equal("TUMOR", reader.SampleNames[1]);
}
}
public void GetColumnIndices_missing_column()
{
const string header = @"CNV_ID ID_GENE gene_name ID_SAMPLE ID_TUMOUR Primary site Site subtype 1 Site subtype 2 Site subtype 3 Primary histology Histology subtype 1 Histology subtype 2 Histology subtype 3 SAMPLE_NAME TOTAL_CN MINOR_ALLELE MUT_TYPE ID_STUDY Chromosome:G_Start..G_Stop";
var readStream = ResourceUtilities.GetReadStream(Resources.SaPath("CosmicCNV.tsv"));
var cnvReader = new CosmicCnvReader(readStream,
ChromosomeUtilities.RefNameToChromosome,
GenomeAssembly.GRCh37);
Assert.Throws <InvalidDataException>(() => cnvReader.GetColumnIndices(header));
}
public void MultiSampleVcf()
{
using (var reader = new LiteVcfReader(ResourceUtilities.GetReadStream(Resources.TopPath("OneKMultiSample.vcf"))))
{
// HG00096 HG00097 HG00099 HG00100 HG00101 HG00102......
Assert.Equal("HG00096", reader.SampleNames[0]);
Assert.Equal("HG00097", reader.SampleNames[1]);
Assert.Equal("HG00099", reader.SampleNames[2]);
Assert.Equal("HG00100", reader.SampleNames[3]);
Assert.Equal("HG00101", reader.SampleNames[4]);
}
}
public void GetEntries()
{
var readStream = ResourceUtilities.GetReadStream(Resources.SaPath("CosmicCNV.tsv"));
var cnvReader = new CosmicCnvReader(readStream,
ChromosomeUtilities.RefNameToChromosome,
GenomeAssembly.GRCh37);
var cnvItems = cnvReader.GetEntries();
Assert.Equal(5, cnvItems.Count());
}
public void GetColumnIndices_valid_header()
{
const string header = @"CNV_ID ID_GENE gene_name ID_SAMPLE ID_TUMOUR Primary site Site subtype 1 Site subtype 2 Site subtype 3 Primary histology Histology subtype 1 Histology subtype 2 Histology subtype 3 SAMPLE_NAME TOTAL_CN MINOR_ALLELE MUT_TYPE ID_STUDY GRCh Chromosome:G_Start..G_Stop";
var readStream = ResourceUtilities.GetReadStream(Resources.SaPath("CosmicCNV.tsv"));
var cnvReader = new CosmicCnvReader(readStream,
ChromosomeUtilities.RefNameToChromosome,
GenomeAssembly.GRCh37);
cnvReader.GetColumnIndices(header);
//we do not need an assert because not getting an exception in the last line means pass
}
public void GetColumnIndices_missing_column()
{
var header = @"CNV_ID ID_GENE gene_name ID_SAMPLE ID_TUMOUR Primary site Site subtype 1 Site subtype 2 Site subtype 3 Primary histology Histology subtype 1 Histology subtype 2 Histology subtype 3 SAMPLE_NAME TOTAL_CN MINOR_ALLELE MUT_TYPE ID_STUDY Chromosome:G_Start..G_Stop";
var readStream = ResourceUtilities.GetReadStream(Resources.TopPath("SA\\CosmicCNV.tsv"));
var cnvReader = new CosmicCnvReader(readStream,
new Dictionary <string, IChromosome>()
{
{ "W", new Chromosome("chrW", "W", 1) }
},
GenomeAssembly.GRCh37);
Assert.Throws <InvalidDataException>(() => cnvReader.GetColumnIndices(header));
}
public void BasicCustomIntervalOutput()
{
var customIntervalProvider = new MockCustomIntervalProvider(ResourceUtilities.GetReadStream(Resources.CustomIntervals("chr1_IcslIntervals_69090_69091.nci")), _renamer);
var annotationSource = ResourceUtilities.GetAnnotationSource(DataUtilities.EmptyCachePrefix, null, null, customIntervalProvider);
var annotatedVariant = DataUtilities.GetVariant(annotationSource,
"chr1 69092 . T C . LowGQX;HighDPFRatio END=10244;BLOCKAVG_min30p3a GT:GQX:DP:DPF .:.:0:1");
Assert.NotNull(annotatedVariant);
const string expectedJson = "{\"altAllele\":\"C\",\"refAllele\":\"T\",\"begin\":69092,\"chromosome\":\"chr1\",\"end\":69092,\"variantType\":\"SNV\",\"vid\":\"1:69092:C\",\"IcslIntervals\":[{\"Start\":69091,\"End\":70008,\"gene\":\"OR4F5\",\"assesment\":\"Some_evidence_of_constraint\",\"score\":0.0,\"exacScore\":3.60208899915}]}";
var observedJson = JsonUtilities.GetFirstAlleleJson(annotatedVariant);
Assert.Equal(expectedJson, observedJson);
}
public void BgzipTestReader_basic()
{
var stream = ResourceUtilities.GetReadStream(Resources.TopPath("TinyAnnotated.json"));
var lineCount = 0;
using (var jasixReader = new StreamReader(stream))
{
while (jasixReader.ReadLine() != null)
{
lineCount++;
}
}
Assert.Equal(4, lineCount);
}
public void ConservationScoreTest2()
{
var saReader = ResourceUtilities.GetSupplementaryAnnotationReader(Resources.MiniSuppAnnot("chr1_13528_13529.nsa"));
var csReader = new MockConservationScoreReader(ResourceUtilities.GetReadStream(Resources.TopPath("chr1_10918_150000.npd")));
var annotatedVariant = DataUtilities.GetVariant(DataUtilities.EmptyCachePrefix, saReader,
"1 13528 . C G,CT 1771.54 VQSRTrancheSNP99.60to99.80 AC=21,11;AC_AFR=12,0", csReader);
Assert.NotNull(annotatedVariant);
var altAllele = JsonUtilities.GetAllele(annotatedVariant);
Assert.NotNull(altAllele);
var altAllele2 = JsonUtilities.GetAllele(annotatedVariant, 1);
Assert.NotNull(altAllele2);
Assert.Contains("\"phylopScore\":0.81", altAllele);
Assert.DoesNotContain("\"phylopScore\"", altAllele2);
}
public void GetEntries()
{
var readStream = ResourceUtilities.GetReadStream(Resources.TopPath("SA\\CosmicCNV.tsv"));
var cnvReader = new CosmicCnvReader(readStream,
new Dictionary <string, IChromosome>()
{
{ "17", new Chromosome("chr17", "17", 1) },
{ "Y", new Chromosome("chrY", "Y", 2) },
{ "MT", new Chromosome("chrM", "MT", 3) }
},
GenomeAssembly.GRCh37);
var cnvItems = cnvReader.GetEntries();
Assert.Equal(5, cnvItems.Count());
}
public void GetCompressedSequence()
{
using (var reader = new CompressedSequenceReader(
ResourceUtilities.GetReadStream(Resources.TopPath("TestSeq_reference.dat"))))
{
var sequence = reader.Sequence;
var chromosome = new Chromosome("chrBob", "Bob", 0);
reader.GetCompressedSequence(chromosome);
Assert.Equal(0, sequence.Length);
chromosome = new Chromosome("chrTestSeq", "TestSeq", 0);
reader.GetCompressedSequence(chromosome);
Assert.NotNull(reader.CytogeneticBands);
Assert.Equal(GenomeAssembly.GRCh37, reader.Assembly);
Assert.Equal(53, sequence.Length);
}
}
public void MultipleAllelesMultipleSamples()
{
using (var reader = new LiteVcfReader(ResourceUtilities.GetReadStream(Resources.InputFiles("Nirvana_unified_json_format.vcf"))))
{
// LP2000021 LP2000022 LP2000023
Assert.Equal("LP2000021", reader.SampleNames[0]);
Assert.Equal("LP2000022", reader.SampleNames[1]);
Assert.Equal("LP2000023", reader.SampleNames[2]);
// skip the first variant
VcfUtilities.GetNextVariant(reader, _renamer);
var variant = VcfUtilities.GetNextVariant(reader, _renamer);
// GT:GQ:GQX:DPI:AD
// 1/2:46:1:32:0,22,3
// 1/1:147:4:27:0,12,5
// 0/0:365:9:29:0,8,10
// the unified json will call this function to get all the samples and can print them out using GetEntry as shown below
var sampleVariants = variant.ExtractSampleInfo();
Assert.Equal("1/2", sampleVariants[0].Genotype);
Assert.Equal("1/1", sampleVariants[1].Genotype);
Assert.Equal("0/0", sampleVariants[2].Genotype);
// 1/2 - A
var expectedEntry =
"{\"variantFreq\":1,\"totalDepth\":32,\"genotypeQuality\":1,\"alleleDepths\":[0,22,3],\"genotype\":\"1/2\"}";
var observedEntry = sampleVariants[0].ToString();
Assert.Equal(expectedEntry, observedEntry);
// 1/1 - T
expectedEntry = "{\"variantFreq\":1,\"totalDepth\":27,\"genotypeQuality\":4,\"alleleDepths\":[0,12,5],\"genotype\":\"1/1\"}";
observedEntry = sampleVariants[1].ToString();
Assert.Equal(expectedEntry, observedEntry);
// 0/0 - A
expectedEntry = "{\"variantFreq\":1,\"totalDepth\":29,\"genotypeQuality\":9,\"alleleDepths\":[0,8,10],\"genotype\":\"0/0\"}";
observedEntry = sampleVariants[2].ToString();
Assert.Equal(expectedEntry, observedEntry);
}
}
public void SamplesWithFilterAndGq()
{
using (var reader = new LiteVcfReader(ResourceUtilities.GetReadStream(Resources.InputFiles("Nirvana_unified_json_format.vcf"))))
{
// skip the first two variants
VcfUtilities.GetNextVariant(reader, _renamer);
VcfUtilities.GetNextVariant(reader, _renamer);
var variant = VcfUtilities.GetNextVariant(reader, _renamer);
// GT:GQ:DP:DPF:AD:FT:DPI
// 0/1:124:19:5:11,8:PASS:.
// 2/2:58:55:.:0,23:LowGQX:21
// 1/2:55:59:.:0,21:LowGQX:20
// the unified json will call this function to get all the samples and can print them out using GetEntry as shown below
var sampleVariants = variant.ExtractSampleInfo();
Assert.Equal("0/1", sampleVariants[0].Genotype);
Assert.Equal("2/2", sampleVariants[1].Genotype);
Assert.Equal("1/2", sampleVariants[2].Genotype);
var expectedEntry =
"{\"variantFreq\":0.4211,\"genotypeQuality\":124,\"alleleDepths\":[11,8],\"genotype\":\"0/1\"}";
var observedEntry = sampleVariants[0].ToString();
Assert.Equal(expectedEntry, observedEntry);
// 1/1 - T
expectedEntry =
"{\"variantFreq\":1,\"totalDepth\":21,\"genotypeQuality\":58,\"alleleDepths\":[0,23],\"genotype\":\"2/2\",\"failedFilter\":true}";
observedEntry = sampleVariants[1].ToString();
Assert.Equal(expectedEntry, observedEntry);
// 0/0 - A
expectedEntry =
"{\"variantFreq\":1,\"totalDepth\":20,\"genotypeQuality\":55,\"alleleDepths\":[0,21],\"genotype\":\"1/2\",\"failedFilter\":true}";
observedEntry = sampleVariants[2].ToString();
Assert.Equal(expectedEntry, observedEntry);
}
}
public void GetHeaderOnly()
{
var readStream = new BlockGZipStream(ResourceUtilities.GetReadStream(Resources.TopPath("Clinvar20150901.json.gz")), CompressionMode.Decompress);
var indexStream = ResourceUtilities.GetReadStream(Resources.TopPath("Clinvar20150901.json.gz.jsi"));
var outStream = new MemoryStream();
using (var writer = new StreamWriter(outStream, Encoding.UTF8, 512, true))
using (var qp = new QueryProcessor(new StreamReader(readStream), indexStream, writer))
{
qp.PrintHeaderOnly();
}
Assert.NotEqual(0, outStream.Length);
outStream.Position = 0;
using (var reader = new StreamReader(outStream))
{
string headerLine = reader.ReadToEnd();
Assert.Equal("{\"header\":{\"annotator\":\"Nirvana 2.0.9.0\",\"creationTime\":\"2018-04-30 17:17:23\",\"genomeAssembly\":\"GRCh37\",\"schemaVersion\":6,\"dataVersion\":\"91.26.45\",\"dataSources\":[{\"name\":\"VEP\",\"version\":\"91\",\"description\":\"Ensembl\",\"releaseDate\":\"2018-03-05\"},{\"name\":\"ClinVar\",\"version\":\"20180129\",\"description\":\"A freely accessible, public archive of reports of the relationships among human variations and phenotypes, with supporting evidence\",\"releaseDate\":\"2018-01-29\"},{\"name\":\"COSMIC\",\"version\":\"84\",\"description\":\"somatic mutation and related details and information relating to human cancers\",\"releaseDate\":\"2018-02-13\"},{\"name\":\"dbSNP\",\"version\":\"150\",\"description\":\"Identifiers for observed variants\",\"releaseDate\":\"2017-04-03\"},{\"name\":\"gnomAD_exome\",\"version\":\"2.0.2\",\"description\":\"Exome allele frequencies from Genome Aggregation Database (gnomAD)\",\"releaseDate\":\"2017-10-05\"},{\"name\":\"gnomAD\",\"version\":\"2.0.2\",\"description\":\"Whole genome allele frequencies from Genome Aggregation Database (gnomAD)\",\"releaseDate\":\"2017-10-05\"},{\"name\":\"MITOMAP\",\"version\":\"20180228\",\"description\":\"Small variants in the MITOMAP human mitochondrial genome database\",\"releaseDate\":\"2018-02-28\"},{\"name\":\"1000 Genomes Project\",\"version\":\"Phase 3 v5a\",\"description\":\"A public catalogue of human variation and genotype data\",\"releaseDate\":\"2013-05-27\"},{\"name\":\"TOPMed\",\"version\":\"freeze_5\",\"description\":\"Allele frequencies from TOPMed data lifted over using dbSNP ids.\",\"releaseDate\":\"2017-08-28\"},{\"name\":\"ClinGen\",\"version\":\"20160414\",\"releaseDate\":\"2016-04-14\"},{\"name\":\"DGV\",\"version\":\"20160515\",\"description\":\"Provides a comprehensive summary of structural variation in the human genome\",\"releaseDate\":\"2016-05-15\"},{\"name\":\"MITOMAP\",\"version\":\"20180228\",\"description\":\"Large structural variants in the MITOMAP human mitochondrial genome database\",\"releaseDate\":\"2018-02-28\"},{\"name\":\"ExAC\",\"version\":\"0.3.1\",\"description\":\"Gene scores from the ExAC project\",\"releaseDate\":\"2016-03-16\"},{\"name\":\"OMIM\",\"version\":\"20180213\",\"description\":\"An Online Catalog of Human Genes and Genetic Disorders\",\"releaseDate\":\"2018-02-13\"},{\"name\":\"phyloP\",\"version\":\"hg19\",\"description\":\"46 way conservation score between humans and 45 other vertebrates\",\"releaseDate\":\"2009-11-10\"}]}}\r\n", headerLine);
}
}
public void GetChromosomeList()
{
var readStream = new BlockGZipStream(ResourceUtilities.GetReadStream(Resources.TopPath("Clinvar20150901.json.gz")), CompressionMode.Decompress);
var indexStream = ResourceUtilities.GetReadStream(Resources.TopPath("Clinvar20150901.json.gz.jsi"));
var outStream = new MemoryStream();
using (var writer = new StreamWriter(outStream, Encoding.UTF8, 512, true))
using (var qp = new QueryProcessor(new StreamReader(readStream), indexStream, writer))
{
qp.PrintChromosomeList();
}
Assert.NotEqual(0, outStream.Length);
outStream.Position = 0;
using (var reader = new StreamReader(outStream))
{
string chromList = reader.ReadToEnd();
Assert.Equal("1\r\n2\r\n3\r\n4\r\n5\r\n6\r\n7\r\n8\r\n9\r\n10\r\n11\r\n12\r\n13\r\n14\r\n15\r\n16\r\n17\r\n18\r\n19\r\n20\r\n21\r\nX\r\nY\r\n", chromList);
}
}
public void GetCompressedSequence()
{
using (var reader = new CompressedSequenceReader(ResourceUtilities.GetReadStream(Resources.TopPath("TestSeq_reference.dat"))))
{
Assert.Equal(GenomeAssembly.GRCh37, reader.Assembly);
var sequence = reader.Sequence;
var chromosome = new Chromosome("chrBob", "Bob", null, null, 1, 1);
reader.GetCompressedSequence(chromosome);
Assert.Null(sequence.CytogeneticBands);
Assert.Equal(0, sequence.Length);
chromosome = new Chromosome("chrTestSeq", "TestSeq", null, null, 1, 0);
reader.GetCompressedSequence(chromosome);
var bases = sequence.Substring(0, 100);
Assert.NotNull(sequence.CytogeneticBands);
Assert.Equal(53, sequence.Length);
Assert.Equal("NNATGTTTCCACTTTCTCCTCATTAGANNNTAACGAATGGGTGATTTCCCTAN", bases);
}
}
public void ReadDataVersionFromFile()
{
var versionFile = ResourceUtilities.GetReadStream(Resources.TopPath("dbSNP.version"));
DataSourceVersion version;
using (var reader = new DataSourceVersionReader(versionFile))
{
version = reader.GetVersion();
}
Assert.Equal("dbSNP", version.Name);
Assert.Equal("147", version.Version);
Assert.Equal(DateTime.Parse("2016-04-08").Ticks, version.ReleaseDateTicks);
Assert.True(string.IsNullOrEmpty(version.Description));
Assert.Contains("dataSource=dbSNP", version.ToString()); //vcf output
var sb = StringBuilderCache.Acquire();
version.SerializeJson(sb);
Assert.Contains("name\":\"dbSNP", StringBuilderCache.GetStringAndRelease(sb)); //json output
}
public void TestIndexCreation()
{
var readStream = new BlockGZipStream(ResourceUtilities.GetReadStream(Resources.TopPath("cosmicv72.indels.json.gz")), CompressionMode.Decompress);
var tempFile = Path.Combine(Path.GetTempPath(), Path.GetRandomFileName());
using (var indexCreator = new IndexCreator(readStream, FileUtilities.GetCreateStream(tempFile)))
{
indexCreator.CreateIndex();
}
JasixIndex readBackIndex;
using (var stream = FileUtilities.GetReadStream(tempFile))
{
readBackIndex = new JasixIndex(stream);
}
Assert.Equal(1591, readBackIndex.GetFirstVariantPosition("chr1", 9775924, 9775924));
Assert.Equal(11500956299, readBackIndex.GetFirstVariantPosition("chr2", 16081096, 16081096));
Assert.Equal(372100991296, readBackIndex.GetFirstVariantPosition("chr20", 36026164, 36026164));
Assert.Equal(377682846863, readBackIndex.GetFirstVariantPosition("chrX", 66765044, 66765044));
File.Delete(tempFile);
}
public BlockGZipStreamTests()
{
// TODO: Fix fragile constructor
_expectedDecompressedBuffer = GrabBytes(ResourceUtilities.GetReadStream(Resources.TopPath("HelloWorld_original.dat")));
}
//constructor
public PhylopGetScoreTests()
{
_npdReader = new PhylopReader(ResourceUtilities.GetReadStream(Resources.TopPath("chr1_10918_150000.npd")));
}
/// <summary>
/// constructor
/// </summary>
public PhylopGetScoreTests()
{
// TODO: Fix fragile constructor
_npdReader = new PhylopReader(ResourceUtilities.GetReadStream(Resources.TopPath("chr1_10918_150000.npd")));
}