public void TwoStudyCosmicCoding()
{
var vcfReader = GZipUtilities.GetAppropriateStreamReader(Resources.TopPath("cosm5428243.vcf"));
var tsvReader = GZipUtilities.GetAppropriateStreamReader(Resources.TopPath("cosm5428243.tsv"));
var cosmicReader = new MergedCosmicReader(vcfReader, tsvReader, _refChromDict);
var cosmicItems = cosmicReader.GetCosmicItems();
var count = 0;
foreach (var cosmicItem in cosmicItems)
{
switch (count)
{
case 0:
foreach (var study in cosmicItem.Studies)
{
Assert.Equal("544", study.Id);
Assert.Equal(new [] { "haematopoietic_and_lymphoid_tissue" }, study.Sites);
Assert.Equal(new [] { "haematopoietic_neoplasm", "acute_myeloid_leukaemia" }, study.Histologies);
}
break;
case 1:
foreach (var study in cosmicItem.Studies)
{
Assert.Equal("544", study.Id);
Assert.Equal(new[] { "haematopoietic;lymphoid_tissue" }, study.Sites);
Assert.Equal(new[] { "haematopoietic_neoplasm", "acute_myeloid_leukaemia" }, study.Histologies);
}
break;
}
count++;
}
}
public void TwoStudyCosmicCoding()
{
var cosmicReader = new MergedCosmicReader(Resources.TopPath("cosm5428243.vcf"), Resources.TopPath("cosm5428243.tsv"), _renamer);
var enumerator = cosmicReader.GetEnumerator();
enumerator.MoveNext();
var cosmicItem = enumerator.Current;
foreach (var study in cosmicItem.Studies)
{
Assert.Equal("544", study.ID);
Assert.Equal("haematopoietic_and_lymphoid_tissue", study.PrimarySite);
Assert.Equal("haematopoietic_neoplasm", study.Histology);
}
enumerator.MoveNext();
cosmicItem = enumerator.Current;
foreach (var study in cosmicItem.Studies)
{
Assert.Equal("544", study.ID);
Assert.Equal("haematopoietic;lymphoid_tissue", study.PrimarySite);
Assert.Equal("haematopoietic_neoplasm", study.Histology);
}
enumerator.Dispose();
}
public void CosmicAlleleSpecificIndel()
{
var vcfReader = GZipUtilities.GetAppropriateStreamReader(Resources.TopPath("COSM18152.vcf"));
var tsvReader = GZipUtilities.GetAppropriateStreamReader(Resources.TopPath("COSM18152.tsv"));
var cosmicReader = new MergedCosmicReader(vcfReader, tsvReader, _refChromDict);
var items = cosmicReader.GetCosmicItems();
Assert.Single(items);
}
public void CosmicAlleleSpecificIndel()
{
//10188320
var seqProvider = ParserTestUtils.GetSequenceProvider(10188320, "G", 'A', ChromosomeUtilities.RefNameToChromosome);
var cosmicReader = new MergedCosmicReader(Resources.TopPath("COSM18152.vcf"), Resources.TopPath("COSM18152.tsv"), seqProvider);
var items = cosmicReader.GetItems();
Assert.Single(items);
}
public void CosmicAltAllele()
{
var seqProvider = ParserTestUtils.GetSequenceProvider(6928019, "C", 'A', ChromosomeUtilities.RefNameToChromosome);
var cosmicReader = new MergedCosmicReader(Resources.TopPath("COSM983708.vcf"), Resources.TopPath("COSM983708.tsv"), seqProvider);
var items = cosmicReader.GetItems().ToList();
Assert.Single((IEnumerable)items);
Assert.Contains("\"refAllele\":\"-\"", items[0].GetJsonString());
}
public void CosmicAltAllele()
{
var vcfReader = GZipUtilities.GetAppropriateStreamReader(Resources.TopPath("COSM983708.vcf"));
var tsvReader = GZipUtilities.GetAppropriateStreamReader(Resources.TopPath("COSM983708.tsv"));
var cosmicReader = new MergedCosmicReader(vcfReader, tsvReader, _refChromDict);
var items = cosmicReader.GetCosmicItems().ToList();
Assert.Single(items);
Assert.Contains("\"refAllele\":\"C\"", items[0].GetJsonString());
}
private static ExitCodes ProgramExecution()
{
var referenceProvider = new ReferenceSequenceProvider(FileUtilities.GetReadStream(_compressedReference));
var cosmicReader = new MergedCosmicReader(_vcfFile, _tsvFile, referenceProvider);
var version = DataSourceVersionReader.GetSourceVersion(_vcfFile + ".version");
string outFileName = $"{version.Name}_{version.Version}";
using (var nsaStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.SaFileSuffix)))
using (var indexStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.SaFileSuffix + SaCommon.IndexSufix)))
using (var nsaWriter = new NsaWriter(new ExtendedBinaryWriter(nsaStream), new ExtendedBinaryWriter(indexStream), version, referenceProvider, SaCommon.CosmicTag, false, true, SaCommon.SchemaVersion, false))
{
nsaWriter.Write(cosmicReader.GetItems());
}
return(ExitCodes.Success);
}
public void TwoStudyCosmicCoding()
{
var seqProvider = ParserTestUtils.GetSequenceProvider(35416, "A", 'C', ChromosomeUtilities.RefNameToChromosome);
var cosmicReader = new MergedCosmicReader(Resources.TopPath("cosm5428243.vcf"), Resources.TopPath("cosm5428243.tsv"), seqProvider);
var cosmicItem = cosmicReader.GetItems().ToList()[0];
var studies = cosmicItem.Studies.ToList();
Assert.Equal("544", studies[0].Id);
Assert.Equal(new[] { "haematopoietic and lymphoid tissue" }, studies[0].Sites);
Assert.Equal(new[] { "haematopoietic neoplasm" }, studies[0].Histologies);
//Assert.Equal(new [] { "haematopoietic neoplasm", "acute myeloid leukaemia" }, study.Histologies);
Assert.Equal("544", studies[1].Id);
Assert.Equal(new[] { "haematopoietic;lymphoid tissue" }, studies[1].Sites);
Assert.Equal(new[] { "haematopoietic neoplasm" }, studies[1].Histologies);
//Assert.Equal(new[] { "haematopoietic_neoplasm", "acute_myeloid_leukaemia" }, study.Histologies);
}
public void IndelWithNoLeadingBase()
{
var tsvReader = new StreamReader(new MemoryStream());
var vcfReader = new StreamReader(new MemoryStream());
var cosmicReader = new MergedCosmicReader(vcfReader, tsvReader, _refChromDict);
const string vcfLine1 = "3 10188320 COSM14426 GGTACTGAC A . . GENE=VHL;STRAND=+;CDS=c.463G>A;AA=p.?;CNT=2";
const string vcfLine2 = "3 10188320 COSM18152 G A . . GENE=VHL;STRAND=+;CDS=c.463G>A;AA=p.V155M;CNT=7";
var items = cosmicReader.ExtractCosmicItems(vcfLine1);
Assert.Equal("GGTACTGAC", items[0].ReferenceAllele);
Assert.Equal("A", items[0].AlternateAllele);
Assert.Equal(10188320, items[0].Start);
var items2 = cosmicReader.ExtractCosmicItems(vcfLine2);
Assert.Equal("G", items2[0].ReferenceAllele);
Assert.Equal("A", items2[0].AlternateAllele);
Assert.Equal(10188320, items2[0].Start);
}
public void IndelWithNoLeadingBase()
{
var seqProvider = ParserTestUtils.GetSequenceProvider(10188320, "GGTACTGAC", 'A', ChromosomeUtilities.RefNameToChromosome);
//the files provided are just for the sake of construction. The main aim is to test the VCF line parsing capabilities
var cosmicReader = new MergedCosmicReader(Resources.TopPath("cosm5428243.vcf"), Resources.TopPath("cosm5428243.tsv"), seqProvider);
const string vcfLine1 = "3 10188320 COSM14426 GGTACTGAC A . . GENE=VHL;STRAND=+;CDS=c.463G>A;AA=p.?;CNT=2";
const string vcfLine2 = "3 10188320 COSM18152 G A . . GENE=VHL;STRAND=+;CDS=c.463G>A;AA=p.V155M;CNT=7";
var items = cosmicReader.ExtractCosmicItems(vcfLine1);
Assert.Equal("GGTACTGAC", items[0].RefAllele);
Assert.Equal("A", items[0].AltAllele);
Assert.Equal(10188320, items[0].Position);
var items2 = cosmicReader.ExtractCosmicItems(vcfLine2);
Assert.Equal("G", items2[0].RefAllele);
Assert.Equal("A", items2[0].AltAllele);
Assert.Equal(10188320, items2[0].Position);
}
public void IndelWithNoLeadingBase()
{
var cosmicReader = new MergedCosmicReader();
const string vcfLine1 = "3 10188320 COSM14426 GGTACTGAC A . . GENE=VHL;STRAND=+;CDS=c.463G>A;AA=p.?;CNT=2";
const string vcfLine2 = "3 10188320 COSM18152 G A . . GENE=VHL;STRAND=+;CDS=c.463G>A;AA=p.V155M;CNT=7";
var sa = new SupplementaryAnnotationPosition(10188320);
var saCreator = new SupplementaryPositionCreator(sa);
foreach (var cosmicItem in cosmicReader.ExtractCosmicItems(vcfLine1))
{
cosmicItem.SetSupplementaryAnnotations(saCreator);
}
Assert.Equal("9A", sa.CosmicItems[0].SaAltAllele);
foreach (var cosmicItem in cosmicReader.ExtractCosmicItems(vcfLine2))
{
cosmicItem.SetSupplementaryAnnotations(saCreator);
}
Assert.Equal("A", sa.CosmicItems[1].SaAltAllele);
}
private void CreateCosmicTsv(string vcfFile, string tsvFile)
{
if (string.IsNullOrEmpty(tsvFile) || string.IsNullOrEmpty(vcfFile))
{
return;
}
var benchMark = new Benchmark();
var version = DataSourceVersionReader.GetSourceVersion(vcfFile);
using (var writer = new CosmicTsvWriter(version, _outputDirectory, _genomeAssembly, new ReferenceSequenceProvider(FileUtilities.GetReadStream(_compressedReferencePath))))
{
var tsvReader = GZipUtilities.GetAppropriateStreamReader(tsvFile);
var vcfReader = GZipUtilities.GetAppropriateStreamReader(vcfFile);
var reader = new MergedCosmicReader(vcfReader, tsvReader, _refNamesDictionary);
TsvWriterUtilities.WriteSortedItems(reader.GetCosmicItems(), writer);
}
var timeSpan = Benchmark.ToHumanReadable(benchMark.GetElapsedTime());
TsvWriterUtilities.WriteCompleteInfo("COSMIC", version.Version, timeSpan);
}
// constructor
public CreateSupplementaryDatabase(
string compressedReferencePath,
string nsdBaseFileName,
string dbSnpFileName = null,
string cosmicVcfFile = null,
string cosmicTsvFile = null,
string clinVarFileName = null,
string oneKGenomeAfFileName = null,
string evsFileName = null,
string exacFileName = null,
List <string> customFiles = null,
string dgvFileName = null,
string oneKSvFileName = null,
string clinGenFileName = null,
string chrWhiteList = null)
{
_nsdBaseFileName = nsdBaseFileName;
_dataSources = new List <DataSourceVersion>();
_iSupplementaryDataItemList = new List <IEnumerator <SupplementaryDataItem> >();
_supplementaryIntervalList = new List <SupplementaryInterval>();
Console.WriteLine("Creating supplementary annotation files... Data version: {0}, schema version: {1}", SupplementaryAnnotationCommon.DataVersion, SupplementaryAnnotationCommon.SchemaVersion);
_compressedSequence = new CompressedSequence();
var compressedSequenceReader = new CompressedSequenceReader(FileUtilities.GetReadStream(compressedReferencePath), _compressedSequence);
_renamer = _compressedSequence.Renamer;
_dataFileManager = new DataFileManager(compressedSequenceReader, _compressedSequence);
if (!string.IsNullOrEmpty(chrWhiteList))
{
Console.WriteLine("Creating SA for the following chromosomes only:");
foreach (var refSeq in chrWhiteList.Split(','))
{
InputFileParserUtilities.ChromosomeWhiteList.Add(_renamer.GetEnsemblReferenceName(refSeq));
Console.Write(refSeq + ",");
}
Console.WriteLine();
}
else
{
InputFileParserUtilities.ChromosomeWhiteList = null;
}
if (dbSnpFileName != null)
{
AddSourceVersion(dbSnpFileName);
var dbSnpReader = new DbSnpReader(new FileInfo(dbSnpFileName), _renamer);
var dbSnpEnumerator = dbSnpReader.GetEnumerator();
_iSupplementaryDataItemList.Add(dbSnpEnumerator);
}
if (cosmicVcfFile != null && cosmicTsvFile != null)
{
AddSourceVersion(cosmicVcfFile);
var cosmicReader = new MergedCosmicReader(cosmicVcfFile, cosmicTsvFile, _renamer);
var cosmicEnumerator = cosmicReader.GetEnumerator();
_iSupplementaryDataItemList.Add(cosmicEnumerator);
}
if (oneKGenomeAfFileName != null)
{
AddSourceVersion(oneKGenomeAfFileName);
var oneKGenReader = new OneKGenReader(new FileInfo(oneKGenomeAfFileName), _renamer);
var oneKGenEnumerator = oneKGenReader.GetEnumerator();
_iSupplementaryDataItemList.Add(oneKGenEnumerator);
}
if (oneKSvFileName != null)
{
if (oneKGenomeAfFileName == null)
{
AddSourceVersion(oneKSvFileName);
}
var oneKGenSvReader = new OneKGenSvReader(new FileInfo(oneKSvFileName), _renamer);
var oneKGenSvEnumerator = oneKGenSvReader.GetEnumerator();
_iSupplementaryDataItemList.Add(oneKGenSvEnumerator);
}
if (evsFileName != null)
{
AddSourceVersion(evsFileName);
var evsReader = new EvsReader(new FileInfo(evsFileName), _renamer);
var evsEnumerator = evsReader.GetEnumerator();
_iSupplementaryDataItemList.Add(evsEnumerator);
}
if (exacFileName != null)
{
AddSourceVersion(exacFileName);
var exacReader = new ExacReader(new FileInfo(exacFileName), _renamer);
var exacEnumerator = exacReader.GetEnumerator();
_iSupplementaryDataItemList.Add(exacEnumerator);
}
if (clinVarFileName != null)
{
AddSourceVersion(clinVarFileName);
var clinVarReader = new ClinVarXmlReader(new FileInfo(clinVarFileName), compressedSequenceReader, _compressedSequence);
var clinVarList = clinVarReader.ToList();
clinVarList.Sort();
Console.WriteLine($"{clinVarList.Count} clinvar items read form XML file");
IEnumerator <ClinVarItem> clinVarEnumerator = clinVarList.GetEnumerator();
_iSupplementaryDataItemList.Add(clinVarEnumerator);
}
if (dgvFileName != null)
{
AddSourceVersion(dgvFileName);
var dgvReader = new DgvReader(new FileInfo(dgvFileName), _renamer);
var dgvEnumerator = dgvReader.GetEnumerator();
_iSupplementaryDataItemList.Add(dgvEnumerator);
}
if (clinGenFileName != null)
{
AddSourceVersion(clinGenFileName);
var clinGenReader = new ClinGenReader(new FileInfo(clinGenFileName), _renamer);
var clinGenEnumerator = clinGenReader.GetEnumerator();
_iSupplementaryDataItemList.Add(clinGenEnumerator);
}
if (customFiles != null)
{
foreach (var customFile in customFiles)
{
AddSourceVersion(customFile);
var customReader = new CustomAnnotationReader(new FileInfo(customFile), _renamer);
var customEnumerator = customReader.GetEnumerator();
_iSupplementaryDataItemList.Add(customEnumerator);
}
}
// initializing the IEnumerators in the list
foreach (var iDataEnumerator in _iSupplementaryDataItemList)
{
if (!iDataEnumerator.MoveNext())
{
_iSupplementaryDataItemList.Remove(iDataEnumerator);
}
}
_additionalItemsList = new List <SupplementaryDataItem>();
}