private void WriteRemappedEntry(string chrom, int pos, string vcfLine)
{
if (!_writers.ContainsKey(chrom))
{
_writers[chrom] = GZipUtilities.GetStreamWriter(chrom + ".vcf.gz");
}
var splits = vcfLine.Split('\t', 3);
_writers[chrom].WriteLine($"{chrom}\t{Math.Abs(pos)}\t{splits[2]}");
}
/// <summary>
/// constructor
/// </summary>
public HgncReader(string filePath)
{
// sanity check
if (!File.Exists(filePath))
{
throw new FileNotFoundException($"The specified gene_info file ({filePath}) does not exist.");
}
// open the file and parse the header
_reader = GZipUtilities.GetAppropriateStreamReader(filePath);
_reader.ReadLine();
}
/// <summary>
/// constructor
/// </summary>
public TempPredictionReader(string filePath, string description, GlobalImportCommon.FileType fileType)
{
// sanity check
if (!File.Exists(filePath))
{
throw new FileNotFoundException($"The specified protein function prediction file ({filePath}) does not exist.");
}
// open the vcf file and parse the header
_reader = GZipUtilities.GetAppropriateBinaryReader(filePath);
Header = GetHeader(description, filePath, fileType, _reader);
}
/// <summary>
/// constructor
/// </summary>
public VepRegulatoryReader(string filePath)
{
// sanity check
if (!File.Exists(filePath))
{
throw new FileNotFoundException($"The specified exon file ({filePath}) does not exist.");
}
// open the vcf file and parse the header
_reader = GZipUtilities.GetAppropriateStreamReader(filePath);
VepReaderCommon.GetHeader("regulatory element", filePath, GlobalImportCommon.FileType.Regulatory, _reader);
}
public static IVcfReader GetVcfReader(string vcfPath, IDictionary <string, IChromosome> chromosomeDictionary,
IRefMinorProvider refMinorProvider, bool verboseTranscript, IRecomposer recomposer)
{
var useStdInput = vcfPath == "-";
var peekStream =
new PeekStream(useStdInput
? Console.OpenStandardInput()
: GZipUtilities.GetAppropriateReadStream(vcfPath));
return(new VcfReader(peekStream, chromosomeDictionary, refMinorProvider, verboseTranscript, recomposer));
}
/// <summary>
/// constructor
/// </summary>
public VepSimpleIntervalReader(string filePath, string description, GlobalImportCommon.FileType fileType)
{
// sanity check
if (!File.Exists(filePath))
{
throw new FileNotFoundException($"The specified intron file ({filePath}) does not exist.");
}
// open the vcf file and parse the header
_reader = GZipUtilities.GetAppropriateStreamReader(filePath);
VepReaderCommon.GetHeader(description, filePath, fileType, _reader);
}
private static ExitCodes ProgramExecution()
{
using var mitoHeteroplasmyParser = new MitoHeteroplasmyParser(GZipUtilities.GetAppropriateReadStream(_inputFile));
using var tsvStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, OutFileName));
using var tsvWriter = new StreamWriter(tsvStream);
tsvWriter.WriteLine(HeaderLine);
foreach (var line in mitoHeteroplasmyParser.GetOutputLines())
{
tsvWriter.WriteLine(line);
}
return(ExitCodes.Success);
}
/// <summary>
/// constructor
/// </summary>
public VepTranscriptReader(string filePath)
{
// sanity check
if (!File.Exists(filePath))
{
throw new FileNotFoundException($"The specified transcripts file ({filePath}) does not exist.");
}
// open the vcf file and parse the header
_filePath = filePath;
_reader = GZipUtilities.GetAppropriateStreamReader(filePath);
Header = GetHeader();
}
private void ExtractFromClinVar()
{
if (_clinvarReader == null)
{
return;
}
using (var writer = GZipUtilities.GetStreamWriter(IsisClinicalIndelFileName))
{
string line;
while ((line = _clinvarReader.ReadLine()) != null)
{
// Skip empty lines.
if (string.IsNullOrWhiteSpace(line))
{
continue;
}
//copy required header lines
if (line.StartsWith("#"))
{
ProcessHeaderLine(writer, line);
continue;
}
var fields = line.Split('\t');
if (IsSnv(fields[VcfCommon.RefIndex], fields[VcfCommon.AltIndex]))
{
continue;
}
_clinvarCount++;
var chrName = GetChrName(fields[VcfCommon.ChromIndex]);
//skip mito for hg19
if (_assembly == GenomeAssembly.hg19 && (chrName == "chrM" || chrName == "MT"))
{
continue;
}
writer.Write(chrName + '\t' +
fields[VcfCommon.PosIndex] + '\t' +
fields[VcfCommon.IdIndex] + '\t' +
fields[VcfCommon.RefIndex] + '\t' +
fields[VcfCommon.AltIndex] + '\t' +
".\t.\t.\n");
}
}
}
private static void WriteDictionary(ILogger logger, IEnumerable <GenbankEntry> entries)
{
var header = new IntermediateIoHeader(0, 0, Source.None, GenomeAssembly.Unknown, 0);
logger.Write($"- writing Genbank file ({Path.GetFileName(GenbankFilePath)})... ");
using (var writer = new GenbankWriter(GZipUtilities.GetStreamWriter(GenbankFilePath), header))
{
foreach (var entry in entries)
{
writer.Write(entry);
}
}
logger.WriteLine("finished.");
}
public static RefSeqGff Create(string gcfGffPath, string refGffPath, IDictionary <string, IChromosome> accessionToChromosome)
{
var refSeqGenes = LoadRefSeqGffGenes(GZipUtilities.GetAppropriateStreamReader(gcfGffPath),
GZipUtilities.GetAppropriateStreamReader(refGffPath), accessionToChromosome);
var entrezGeneIdToGene = refSeqGenes
.GetMultiValueDict(x => x.GeneId)
.FlattenGeneList()
.GetMultiValueDict(x => x.GeneId);
var entrezGeneIdToSymbol = refSeqGenes.GetKeyValueDict(x => x.GeneId, x => x.Symbol);
return(new RefSeqGff(entrezGeneIdToGene, entrezGeneIdToSymbol));
}
private static IEnumerable <ISupplementaryDataItem> GetItems(IEnumerable <string> filePaths,
ISequenceProvider referenceProvider)
{
IEnumerable <ISupplementaryDataItem> items = null;
foreach (string filePath in filePaths)
{
var fileStreamReader = GZipUtilities.GetAppropriateStreamReader(filePath);
var reader = new GnomadReader(fileStreamReader, referenceProvider);
items = items == null?reader.GetItems() : items.Concat(reader.GetItems());
}
return(items);
}
private ExitCodes ProgramExecution()
{
var sequenceProvider = ProviderUtilities.GetSequenceProvider(ConfigurationSettings.RefSequencePath);
var transcriptAnnotationProvider =
ProviderUtilities.GetTranscriptAnnotationProvider(ConfigurationSettings.InputCachePrefix, sequenceProvider);
var annotator = ProviderUtilities.GetAnnotator(transcriptAnnotationProvider, sequenceProvider);
var dataSourceVesions = new List <IDataSourceVersion>();
dataSourceVesions.AddRange(transcriptAnnotationProvider.DataSourceVersions);
using (var outputWriter = new StreamWriter(ConfigurationSettings.OutputFileName))
using (var vcfReader = new VcfReader(GZipUtilities.GetAppropriateReadStream(ConfigurationSettings.VcfPath), sequenceProvider.GetChromosomeDictionary(), null, false))
{
try
{
if (vcfReader.IsRcrsMitochondrion && annotator.GenomeAssembly == GenomeAssembly.GRCh37 ||
annotator.GenomeAssembly == GenomeAssembly.GRCh38 ||
ConfigurationSettings.ForceMitochondrialAnnotation)
{
annotator.EnableMitochondrialAnnotation();
}
int previousChromIndex = -1;
IPosition position;
// var sortedVcfChecker = new SortedVcfChecker();
outputWriter.WriteLine(OutHeader);
while ((position = vcfReader.GetNextPosition()) != null)
{
// sortedVcfChecker.CheckVcfOrder(position.Chromosome.UcscName);
previousChromIndex = UpdatePerformanceMetrics(previousChromIndex, position.Chromosome);
var annotatedPosition = annotator.Annotate(position);
WriteAnnotatedPostion(annotatedPosition, outputWriter);
}
}
catch (Exception e)
{
e.Data[ExitCodeUtilities.VcfLine] = vcfReader.VcfLine;
throw;
}
}
return(ExitCodes.Success);
}
private static HashSet <int>[] GetIntronFlankingRegionStarts(string gffFile)
{
var flankingRegionStarts = new HashSet <int> [NumChrs];
for (var i = 0; i < NumChrs; i++)
{
flankingRegionStarts[i] = new HashSet <int>();
}
using (var gffReader = GZipUtilities.GetAppropriateStreamReader(gffFile))
{
string line;
var previousChrIndex = ushort.MaxValue;
var exonBoundaries = new List <Interval>();
var flankingRegionStartsthisChr = new HashSet <int>();
while ((line = gffReader.ReadLine()) != null)
{
var info = line.Split('\t');
if (info[GffFeatureColumn] == "gene")
{
ushort chrIndex = GetChrIndex(info[GffChrColumn]);
if (previousChrIndex != ushort.MaxValue && chrIndex != previousChrIndex)
{
ProcessBufferedBoundaries(exonBoundaries, flankingRegionStartsthisChr);
flankingRegionStarts[previousChrIndex] = flankingRegionStartsthisChr;
flankingRegionStartsthisChr = new HashSet <int>();
}
previousChrIndex = chrIndex;
}
else if (info[GffFeatureColumn] == "transcript")
{
ProcessBufferedBoundaries(exonBoundaries, flankingRegionStartsthisChr);
exonBoundaries = new List <Interval>();
}
else if (info[GffFeatureColumn] == "exon")
{
int start = int.Parse(info[GffStartColumn]);
int end = int.Parse(info[GffEndColumn]);
exonBoundaries.Add(new Interval(start, end));
}
}
if (previousChrIndex != ushort.MaxValue)
{
ProcessBufferedBoundaries(exonBoundaries, flankingRegionStartsthisChr);
flankingRegionStarts[previousChrIndex] = flankingRegionStartsthisChr;
}
}
return(flankingRegionStarts);
}
private static ExitCodes ProgramExecution()
{
if (_createIndex)
{
using (var indexCreator = new IndexCreator(_inputJson))
{
indexCreator.CreateIndex();
}
return(ExitCodes.Success);
}
string indexFileName = _inputJson + JasixCommons.FileExt;
ValidateIndexFile(indexFileName);
var writer = string.IsNullOrEmpty(_outputFile)
? null : GZipUtilities.GetStreamWriter(_outputFile);
using (var queryProcessor = new QueryProcessor(GZipUtilities.GetAppropriateStreamReader(_inputJson),
FileUtilities.GetReadStream(indexFileName), writer))
{
if (_list)
{
queryProcessor.ListChromosomesAndSections();
return(ExitCodes.Success);
}
if (_printHeaderOnly)
{
queryProcessor.PrintHeaderOnly();
return(ExitCodes.Success);
}
if (!string.IsNullOrEmpty(_section))
{
queryProcessor.PrintSection(_section);
return(ExitCodes.Success);
}
if (Queries == null)
{
Console.WriteLine("Please specify query region(s)");
return(ExitCodes.BadArguments);
}
queryProcessor.ProcessQuery(Queries, _printHeader);
}
return(ExitCodes.Success);
}
private static ExitCodes ProgramExecution()
{
var referenceProvider = new ReferenceSequenceProvider(FileUtilities.GetReadStream(_compressedReference));
List <CustomInterval> intervals;
SaJsonSchema intervalJsonSchema;
string jsonTag;
DataSourceVersion version;
string outputPrefix = GetOutputPrefix(_inputFile);
string nsaFileName = Path.Combine(_outputDirectory, outputPrefix + SaCommon.SaFileSuffix);
string nsaIndexFileName = nsaFileName + SaCommon.IndexSufix;
string nsaSchemaFileName = nsaFileName + SaCommon.JsonSchemaSuffix;
ReportFor reportFor;
var nsaItemCount = 0;
using (var parser = VariantAnnotationsParser.Create(GZipUtilities.GetAppropriateStreamReader(_inputFile), referenceProvider))
using (var nsaStream = FileUtilities.GetCreateStream(nsaFileName))
using (var indexStream = FileUtilities.GetCreateStream(nsaIndexFileName))
using (var nsaWriter = CaUtilities.GetNsaWriter(nsaStream, indexStream, parser, CaUtilities.GetInputFileName(_inputFile), referenceProvider, out version))
using (var saJsonSchemaStream = FileUtilities.GetCreateStream(nsaSchemaFileName))
using (var schemaWriter = new StreamWriter(saJsonSchemaStream))
{
(jsonTag, nsaItemCount, intervalJsonSchema, intervals) = CaUtilities.WriteSmallVariants(parser, nsaWriter, schemaWriter);
reportFor = parser.ReportFor;
if (intervals == null)
{
return(ExitCodes.Success);
}
}
if (nsaItemCount == 0)
{
File.Delete(nsaFileName);
File.Delete(nsaIndexFileName);
File.Delete(nsaSchemaFileName);
}
using (var nsiStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outputPrefix + SaCommon.IntervalFileSuffix)))
using (var nsiWriter = CaUtilities.GetNsiWriter(nsiStream, version, referenceProvider.Assembly, jsonTag, reportFor))
using (var siJsonSchemaStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outputPrefix + SaCommon.IntervalFileSuffix + SaCommon.JsonSchemaSuffix)))
using (var schemaWriter = new StreamWriter(siJsonSchemaStream))
{
nsiWriter.Write(intervals);
schemaWriter.Write(intervalJsonSchema);
}
return(ExitCodes.Success);
}
/// <summary>
/// Parses a ClinVar file and return an enumeration object containing all the ClinVar objects
/// that have been extracted
/// </summary>
private IEnumerable <ClinVarItem> GetItems()
{
using (var reader = GZipUtilities.GetAppropriateStreamReader(_clinVarXmlFileInfo.FullName))
using (var xmlReader = XmlTextReader.Create(reader, new XmlReaderSettings {
DtdProcessing = DtdProcessing.Prohibit, IgnoreWhitespace = true
}))
{
string elementName = null;
//skipping the top level element to go down to its children
xmlReader.ReadToDescendant("ClinVarSet");
do
{
LiteXmlElement xmlElement = null;
switch (xmlReader.NodeType)
{
case XmlNodeType.Element: // The node is an element.
elementName = xmlReader.Name;
xmlElement = ParseXmlElement(xmlReader);
break;
case XmlNodeType.EndElement: //Display the end of the element.
// Release set is the top level element we skipped. So, we will encounter this mismatch.
if (xmlReader.Name != "ReleaseSet" && xmlReader.Name != elementName)
{
throw new InvalidDataException("WARNING!! encountered unexpected endElement tag:" + xmlReader.Name);
}
break;
default:
continue;
}
var clinVarItems = ExtractClinVarItems(xmlElement);
if (clinVarItems == null)
{
continue;
}
foreach (var clinVarItem in clinVarItems)
{
yield return(clinVarItem);
}
} while (xmlReader.Read());
}
}
public void VcfHeaderCheck()
{
var randomPath = Path.Combine(Path.GetTempPath(), Path.GetRandomFileName());
var outputVcfPath = randomPath + ".vcf.gz";
var dataSourceVersions = new List <DataSourceVersion>
{
new DataSourceVersion("VEP", "84", 0, "Ensembl"),
new DataSourceVersion("dbSNP", "147", Convert.ToDateTime("06/01/2016").Ticks),
new DataSourceVersion("COSMIC", "78", Convert.ToDateTime("09/05/2016").Ticks)
};
using (new LiteVcfWriter(outputVcfPath, new List <string> {
"##source=SpliceGirl 1.0.0.28", "##reference=file:/illumina/scratch/Zodiac/Software/Jenkins/R2/Genomes/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta"
}, "84.22.34", dataSourceVersions))
{
}
var observedHeader = new List <string>();
using (var reader = GZipUtilities.GetAppropriateStreamReader(outputVcfPath))
{
string line;
while ((line = reader.ReadLine()) != null)
{
observedHeader.Add(line);
}
}
var expectedHeader = new List <string>
{
"##source=SpliceGirl 1.0.0.28",
"##reference=file:/illumina/scratch/Zodiac/Software/Jenkins/R2/Genomes/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta",
"##annotator=Illumina Annotation Engine",
"##annotatorDataVersion=84.22.34",
"##annotatorTranscriptSource=Ensembl",
"##dataSource=dbSNP,version:147,release date:2016-06-01",
"##dataSource=COSMIC,version:78,release date:2016-09-05"
};
Assert.Equal(expectedHeader.Count + 10, observedHeader.Count); //for info tags added by default
for (var i = 0; i < expectedHeader.Count; i++)
{
if (expectedHeader[i].StartsWith("##annotator=Illumina"))
{
Assert.Contains(expectedHeader[i], observedHeader[i]);
continue;
}
Assert.Equal(expectedHeader[i], observedHeader[i]);
}
}
private static ExitCodes ProgramExecution()
{
var referenceProvider = new ReferenceSequenceProvider(FileUtilities.GetReadStream(_compressedReference));
var version = DataSourceVersionReader.GetSourceVersion(_inputFileName + ".version");
string outFileName = $"{version.Name}_{version.Version}";
using (var clinGenReader = new ClinGenReader(GZipUtilities.GetAppropriateStreamReader(_inputFileName), referenceProvider.RefNameToChromosome))
using (var nsaStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.SiFileSuffix)))
using (var nsiWriter = new NsiWriter(new ExtendedBinaryWriter(nsaStream), version, referenceProvider.Assembly, SaCommon.ClinGenTag, ReportFor.StructuralVariants, SaCommon.SchemaVersion))
{
nsiWriter.Write(clinGenReader.GetItems());
}
return(ExitCodes.Success);
}
private static ExitCodes ProgramExecution()
{
var refProvider = new ReferenceSequenceProvider(FileUtilities.GetReadStream(_referenceSequencePath));
var version = DataSourceVersionReader.GetSourceVersion(_inputFile + ".version");
var outFileName = $"{version.Name}_{version.Version}";
using (var parser = new LcrRegionParser(GZipUtilities.GetAppropriateStreamReader(_inputFile), refProvider))
using (var stream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.LcrFileSuffix)))
using (var writer = new NsiWriter(stream, version, refProvider.Assembly, SaCommon.LowComplexityRegionTag, ReportFor.AllVariants, SaCommon.NsiSchemaVersion))
{
writer.Write(parser.GetItems());
}
return(ExitCodes.Success);
}
private static ExitCodes ProgramExecution()
{
var dosageMapRegionVersion = DataSourceVersionReader.GetSourceVersion(_dosageMapRegionFile + ".version");
string outFileName = $"{dosageMapRegionVersion.Name.Replace(' ', '_')}_{dosageMapRegionVersion.Version}";
var referenceProvider = new ReferenceSequenceProvider(GZipUtilities.GetAppropriateReadStream(_inputReferencePath));
using (var dosageSensitivityParser = new DosageMapRegionParser(GZipUtilities.GetAppropriateReadStream(_dosageMapRegionFile), referenceProvider.RefNameToChromosome))
using (var stream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.SiFileSuffix)))
using (var nsiWriter = new NsiWriter(stream, dosageMapRegionVersion, referenceProvider.Assembly, SaCommon.DosageSensitivityTag, ReportFor.StructuralVariants, SaCommon.SchemaVersion))
{
nsiWriter.Write(dosageSensitivityParser.GetItems());
}
return(ExitCodes.Success);
}
private static ExitCodes ProgramExecution()
{
var dosageSensitivityVersion = DataSourceVersionReader.GetSourceVersion(_dosageSensitivityFile + ".version");
string outFileName = $"{dosageSensitivityVersion.Name.Replace(' ','_')}_{dosageSensitivityVersion.Version}";
using (var dosageSensitivityParser = new DosageSensitivityParser(GZipUtilities.GetAppropriateReadStream(_dosageSensitivityFile)))
using (var stream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.NgaFileSuffix)))
using (var ngaWriter = new NgaWriter(stream, dosageSensitivityVersion, SaCommon.DosageSensitivityTag, SaCommon.SchemaVersion, false))
{
ngaWriter.Write(dosageSensitivityParser.GetItems());
}
return(ExitCodes.Success);
}
public IEnumerable <ISupplementaryInterval> GetItems(string refName)
{
if (!_refNameOffsets.ContainsKey(refName))
{
yield break;
}
var offset = _refNameOffsets[refName];
using (var reader = GZipUtilities.GetAppropriateStreamReader(_fileName))
{
reader.BaseStream.Position = offset;
string line;
//getting to the chromosome
while ((line = reader.ReadLine()) != null)
{
if (string.IsNullOrWhiteSpace(line) || line.StartsWith("#"))
{
continue;
}
// finding desired chromosome. We need this because the GetLocation for GZipStream may return a position a few lines before the start of the chromosome
if (line.StartsWith(refName + "\t"))
{
break;
}
}
if (line == null)
{
yield break;
}
do
{
//next chromosome
if (!line.StartsWith(refName + "\t"))
{
yield break;
}
var annotationItem = ExtractItem(line);
if (annotationItem == null)
{
continue;
}
yield return(annotationItem);
} while ((line = reader.ReadLine()) != null);
}
}
private static ExitCodes ProgramExecution()
{
string cachePath = CacheConstants.TranscriptPath(_inputPrefix);
var(refIndexToChromosome, _, _) = SequenceHelper.GetDictionaries(_compressedReferencePath);
var cache = TranscriptCacheHelper.GetCache(cachePath, refIndexToChromosome);
var geneToInternalId = InternalGenes.CreateDictionary(cache.Genes);
using (var writer = new GffWriter(GZipUtilities.GetStreamWriter(_outputFileName)))
{
var creator = new GffCreator(writer, geneToInternalId);
creator.Create(cache.TranscriptIntervalArrays);
}
return(ExitCodes.Success);
}
private static ExitCodes ProgramExecution()
{
var version = DataSourceVersionReader.GetSourceVersion(_inputFile + ".version");
string outFileName = $"{version.Name}_{version.Version}";
//create universal gene archive
using (var exacParser = new ExacScoresParser(GZipUtilities.GetAppropriateStreamReader(_inputFile)))
using (var stream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.NgaFileSuffix)))
using (var ngaWriter = new NgaWriter(stream, version, SaCommon.ExacScoreTag, SaCommon.SchemaVersion, false))
{
ngaWriter.Write(exacParser.GetItems());
}
return(ExitCodes.Success);
}
private ExitCodes ProgramExecution()
{
var version = DataSourceVersionReader.GetSourceVersion(_cnvTsv + ".version");
var referenceProvider = new ReferenceSequenceProvider(FileUtilities.GetReadStream(_compressedReference));
var cnvStream = _cnvTsv == null? null: GZipUtilities.GetAppropriateReadStream(_cnvTsv);
var breakendStream = _breakendTsv == null ? null : GZipUtilities.GetAppropriateReadStream(_breakendTsv);
using (var cosmicSvExtractor = new CosmicSvReader(cnvStream, breakendStream, version, _outputDir,
referenceProvider.GenomeAssembly, referenceProvider.RefNameToChromosome))
{
cosmicSvExtractor.CreateTsv();
}
return(ExitCodes.Success);
}
private static ExitCodes ProgramExecution()
{
var referenceProvider = new ReferenceSequenceProvider(FileUtilities.GetReadStream(_compressedReference));
var version = DataSourceVersionReader.GetSourceVersion(_inputFile + ".version");
string outFileName = $"{version.Name}_{version.Version}_{SaCommon.RefMinorTag}".Replace(' ', '_');
using (var refMinorReader = new RefMinorReader(GZipUtilities.GetAppropriateStreamReader(_inputFile), referenceProvider))
using (var nsaStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.RefMinorFileSuffix)))
using (var indexStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.RefMinorFileSuffix + SaCommon.IndexSufix)))
using (var writer = new RefMinorDbWriter(new ExtendedBinaryWriter(nsaStream), new ExtendedBinaryWriter(indexStream), version, referenceProvider, SaCommon.SchemaVersion))
{
writer.Write(refMinorReader.GetItems());
}
return(ExitCodes.Success);
}
private static ExitCodes ProgramExecution()
{
var dosageSensitivityVersion = DataSourceVersionReader.GetSourceVersion(_diseaseValidityFile + ".version");
string outFileName = $"{dosageSensitivityVersion.Name.Replace(' ', '_')}_{dosageSensitivityVersion.Version}";
// read uga file to get hgnc id to gene symbols dictionary
using (var diseaseValidityParser = new GeneDiseaseValidityParser(GZipUtilities.GetAppropriateReadStream(_diseaseValidityFile), GetHgncIdToGeneSymbols()))
using (var stream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.GeneFileSuffix)))
using (var ngaWriter = new NgaWriter(stream, dosageSensitivityVersion, SaCommon.DiseaseValidityTag, SaCommon.SchemaVersion, true))
{
ngaWriter.Write(diseaseValidityParser.GetItems());
}
return(ExitCodes.Success);
}
private static ExitCodes ProgramExecution()
{
var referenceProvider = new ReferenceSequenceProvider(FileUtilities.GetReadStream(_compressedReference));
var version = DataSourceVersionReader.GetSourceVersion(_inputFile + ".version");
string outFileName = $"{version.Name}_{version.Version}";
using (var primateAiParser = new MitoHeteroplasmyParser(GZipUtilities.GetAppropriateReadStream(_inputFile), referenceProvider))
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(nsaStream, indexStream, version, referenceProvider, SaCommon.MitoHeteroplasmyTag, true, false, SaCommon.SchemaVersion, false))
{
nsaWriter.Write(primateAiParser.GetItems());
}
return(ExitCodes.Success);
}
public void Create()
{
using (var reader = new GlobalCacheReader(CacheConstants.TranscriptPath(_inputPrefix)))
using (var writer = GZipUtilities.GetStreamWriter(_outPath))
{
WriteVcfHeader(writer);
var cache = reader.Read();
Console.Write("- found {0} transcripts... ", cache.Transcripts.Length);
foreach (var transcript in cache.Transcripts)
{
CreateVcf(writer, transcript);
}
Console.WriteLine("finished.");
}
}
