private static ExitCodes ProgramExecution()
{
var logger = new ConsoleLogger();
var bundle = DataBundle.GetDataBundle(_inputReferencePath, _inputPrefix);
int numRefSeqs = bundle.SequenceReader.NumRefSeqs;
var chromosome = ReferenceNameUtilities.GetChromosome(bundle.SequenceReader.RefNameToChromosome, _referenceName);
bundle.Load(chromosome);
string outputStub = GetOutputStub(chromosome, bundle.Source);
var interval = new ChromosomeInterval(chromosome, _referencePosition, _referenceEndPosition);
var transcripts = GetTranscripts(logger, bundle, interval);
var sift = GetPredictionStaging(logger, "SIFT", transcripts, chromosome, bundle.SiftPredictions, bundle.SiftReader, x => x.SiftIndex, numRefSeqs);
var polyphen = GetPredictionStaging(logger, "PolyPhen", transcripts, chromosome, bundle.PolyPhenPredictions, bundle.PolyPhenReader, x => x.PolyPhenIndex, numRefSeqs);
string referenceBases = GetReferenceBases(logger, bundle.SequenceReader, interval);
var regulatoryRegionIntervalArrays = GetRegulatoryRegionIntervalArrays(logger, bundle.TranscriptCache, interval, numRefSeqs);
var transcriptIntervalArrays = PredictionUtilities.UpdateTranscripts(transcripts, bundle.SiftPredictions,
sift.Predictions, bundle.PolyPhenPredictions, polyphen.Predictions, numRefSeqs);
var transcriptStaging = GetTranscriptStaging(bundle.TranscriptCacheData.Header, transcriptIntervalArrays, regulatoryRegionIntervalArrays);
WriteCache(logger, FileUtilities.GetCreateStream(CacheConstants.TranscriptPath(outputStub)), transcriptStaging, "transcript");
WriteCache(logger, FileUtilities.GetCreateStream(CacheConstants.SiftPath(outputStub)), sift.Staging, "SIFT");
WriteCache(logger, FileUtilities.GetCreateStream(CacheConstants.PolyPhenPath(outputStub)), polyphen.Staging, "PolyPhen");
WriteReference(logger, CacheConstants.BasesPath(outputStub), bundle.SequenceReader, chromosome,
referenceBases, interval.Start);
return(ExitCodes.Success);
}
/// <summary>
/// creates the global database
/// </summary>
public void CreateTranscriptCacheFile(string outputPrefix)
{
if (!_hasData)
{
throw new GeneralException("Data was not loaded before running CreateTranscriptCacheFile");
}
Console.Write("- creating transcript cache file... ");
var createBenchmark = new Benchmark();
var globalOutputPath = CacheConstants.TranscriptPath(outputPrefix);
var customHeader = new GlobalCustomHeader(_transcriptReader.Header.VepReleaseTicks,
_transcriptReader.Header.VepVersion);
var header = new FileHeader(CacheConstants.Identifier, CacheConstants.SchemaVersion,
CacheConstants.DataVersion, _transcriptReader.Header.TranscriptSource, _currentTimeTicks, _transcriptReader.Header.GenomeAssembly, customHeader);
var genes = ConvertGenes();
using (var writer = new GlobalCacheWriter(globalOutputPath, header))
{
var cache = new VD.GlobalCache(header, _transcripts.ToArray(), _regulatoryElements.ToArray(),
genes, _introns.ToArray(), _microRnas.ToArray(), _peptideSeqs.ToArray());
writer.Write(cache);
}
Console.WriteLine("{0}", Benchmark.ToHumanReadable(createBenchmark.GetElapsedTime()));
}
private static ExitCodes ProgramExecution()
{
using (var writer = GZipUtilities.GetStreamWriter(_outputFileName))
{
string cachePath = CacheConstants.TranscriptPath(_inputPrefix);
var sequenceData = SequenceHelper.GetDictionaries(_referencePath);
// load the cache
Console.Write("- reading {0}... ", Path.GetFileName(cachePath));
var cache = TranscriptCacheHelper.GetCache(cachePath, sequenceData.refIndexToChromosome);
Console.WriteLine("found {0:N0} reference sequences. ", cache.RegulatoryRegionIntervalArrays.Length);
Console.Write("- writing GFF entries... ");
foreach (var intervalArray in cache.RegulatoryRegionIntervalArrays)
{
if (intervalArray == null)
{
continue;
}
foreach (var interval in intervalArray.Array)
{
WriteRegulatoryFeature(writer, interval.Value);
}
}
Console.WriteLine("finished.");
}
return(ExitCodes.Success);
}
public TranscriptAnnotationProvider(string pathPrefix, ISequenceProvider sequenceProvider, ProteinConservationProvider conservationProvider)
{
Name = "Transcript annotation provider";
_sequence = sequenceProvider.Sequence;
_refNameToChromosome = sequenceProvider.RefNameToChromosome;
_conservationProvider = conservationProvider;
using (var stream = PersistentStreamUtils.GetReadStream(CacheConstants.TranscriptPath(pathPrefix)))
{
(_transcriptCache, TranscriptIntervalArrays, VepVersion) = InitiateCache(stream, sequenceProvider.RefIndexToChromosome, sequenceProvider.Assembly);
}
Assembly = _transcriptCache.Assembly;
DataSourceVersions = _transcriptCache.DataSourceVersions;
// TODO: this is not great. We should not be using IEnumerables if we have to resort to strange stuff like this
if (conservationProvider != null)
{
DataSourceVersions = DataSourceVersions.Concat(new[] { conservationProvider.Version });
}
_siftStream = PersistentStreamUtils.GetReadStream(CacheConstants.SiftPath(pathPrefix));
_siftReader = new PredictionCacheReader(_siftStream, PredictionCacheReader.SiftDescriptions);
_polyphenStream = PersistentStreamUtils.GetReadStream(CacheConstants.PolyPhenPath(pathPrefix));
_polyphenReader = new PredictionCacheReader(_polyphenStream, PredictionCacheReader.PolyphenDescriptions);
}
public void TranscriptPath_NominalCase()
{
const string expectedResult = "bob.transcripts.ndb";
var observedResult = CacheConstants.TranscriptPath("bob");
Assert.Equal(expectedResult, observedResult);
}
private static ExitCodes ProgramExecution()
{
var sequenceData = SequenceHelper.GetDictionaries(_refSequencePath);
var logger = new ConsoleLogger();
var caches = LoadTranscriptCaches(logger, CacheConstants.TranscriptPath(_inputPrefix),
CacheConstants.TranscriptPath(_inputPrefix2), sequenceData.refIndexToChromosome);
if (caches.Cache.TranscriptIntervalArrays.Length != caches.Cache2.TranscriptIntervalArrays.Length)
{
throw new InvalidDataException($"Expected the number of reference sequences in cache 1 ({caches.Cache.TranscriptIntervalArrays.Length}) and cache 2 ({caches.Cache2.TranscriptIntervalArrays.Length}) to be the same.");
}
int numRefSeqs = caches.Cache.TranscriptIntervalArrays.Length;
var combinedIntervalArrays = new IntervalArray <ITranscript> [numRefSeqs];
var siftPredictionsPerRef = new Prediction[numRefSeqs][];
var polyphenPredictionsPerRef = new Prediction[numRefSeqs][];
PredictionHeader siftHeader;
PredictionHeader polyphenHeader;
using (var siftReader = new PredictionCacheReader(FileUtilities.GetReadStream(CacheConstants.SiftPath(_inputPrefix)), PredictionCacheReader.SiftDescriptions))
using (var siftReader2 = new PredictionCacheReader(FileUtilities.GetReadStream(CacheConstants.SiftPath(_inputPrefix2)), PredictionCacheReader.SiftDescriptions))
using (var polyphenReader = new PredictionCacheReader(FileUtilities.GetReadStream(CacheConstants.PolyPhenPath(_inputPrefix)), PredictionCacheReader.PolyphenDescriptions))
using (var polyphenReader2 = new PredictionCacheReader(FileUtilities.GetReadStream(CacheConstants.PolyPhenPath(_inputPrefix2)), PredictionCacheReader.PolyphenDescriptions))
{
siftHeader = siftReader.Header;
polyphenHeader = polyphenReader.Header;
for (ushort refIndex = 0; refIndex < numRefSeqs; refIndex++)
{
var chromosome = sequenceData.refIndexToChromosome[refIndex];
Console.ForegroundColor = ConsoleColor.Yellow;
logger.WriteLine($"\n{chromosome.UcscName}:");
Console.ResetColor();
var sift = CombinePredictions(logger, chromosome, "SIFT", siftReader, siftReader2);
siftPredictionsPerRef[refIndex] = sift.Predictions;
var polyphen = CombinePredictions(logger, chromosome, "PolyPhen", polyphenReader, polyphenReader2);
polyphenPredictionsPerRef[refIndex] = polyphen.Predictions;
var transcriptIntervalArray = caches.Cache.TranscriptIntervalArrays[refIndex];
var transcriptIntervalArray2 = caches.Cache2.TranscriptIntervalArrays[refIndex];
combinedIntervalArrays[refIndex] = CombineTranscripts(logger, transcriptIntervalArray,
transcriptIntervalArray2, sift.Offset, polyphen.Offset);
}
}
logger.WriteLine();
WritePredictions(logger, "SIFT", CacheConstants.SiftPath(_outputPrefix), siftHeader, siftPredictionsPerRef);
WritePredictions(logger, "PolyPhen", CacheConstants.PolyPhenPath(_outputPrefix), polyphenHeader, polyphenPredictionsPerRef);
WriteTranscripts(logger, CloneHeader(caches.Cache.Header), combinedIntervalArrays,
caches.Cache.RegulatoryRegionIntervalArrays);
return(ExitCodes.Success);
}
public PianoAnnotationProvider(string pathPrefix, ISequenceProvider sequenceProvider)
{
Name = "Transcript annotation provider";
_sequence = sequenceProvider.Sequence;
_transcriptCache = InitiateCache(FileUtilities.GetReadStream(CacheConstants.TranscriptPath(pathPrefix)), sequenceProvider.GetChromosomeIndexDictionary(), sequenceProvider.GenomeAssembly, sequenceProvider.NumRefSeqs);
GenomeAssembly = _transcriptCache.GenomeAssembly;
DataSourceVersions = _transcriptCache.DataSourceVersions;
}
private static ExitCodes ProgramExecution()
{
var cachePath = CacheConstants.TranscriptPath(_inputPrefix);
var header = GetHeaderInformation(cachePath);
Console.WriteLine($"Versions: Schema: {header.Schema}, Data: {header.Data}, VEP: {header.Vep}");
return(ExitCodes.Success);
}
/// <summary>
/// constructor
/// </summary>
public CacheCombiner(string inputPrefix1, string inputPrefix2, string outputPrefix)
{
_prefix1 = inputPrefix1;
_prefix2 = inputPrefix2;
_outPrefix = outputPrefix;
_cachePath1 = CacheConstants.TranscriptPath(inputPrefix1);
_cachePath2 = CacheConstants.TranscriptPath(inputPrefix2);
_outputCachePath = CacheConstants.TranscriptPath(outputPrefix);
}
private static void WriteTranscripts(ILogger logger, CacheHeader header,
IntervalArray <ITranscript>[] transcriptIntervalArrays,
IntervalArray <IRegulatoryRegion>[] regulatoryRegionIntervalArrays)
{
var staging = TranscriptCacheStaging.GetStaging(header, transcriptIntervalArrays, regulatoryRegionIntervalArrays);
logger.Write("- writing transcripts... ");
staging.Write(FileUtilities.GetCreateStream(CacheConstants.TranscriptPath(_outputPrefix)));
logger.WriteLine("finished.");
}
public static ExitCodes Run(string command, string[] commandArgs)
{
var ops = new OptionSet
{
{
"ref|r=",
"compressed reference sequence file",
v => _compressedReference = v
},
{
"cache|c=",
"Transcript cache prefix",
v => _transcriptCachePrefix = v
},
{
"gene|g=",
"Gene info data file from NCBI",
v => _geneInfoFile = v
},
{
"in|i=",
"input VCF file path",
v => _inputFile = v
},
{
"out|o=",
"output directory",
v => _outputDirectory = v
}
};
string commandLineExample = $"{command} [options]";
var exitCode = new ConsoleAppBuilder(commandArgs, ops)
.Parse()
.CheckInputFilenameExists(_compressedReference, "compressed reference sequence file name", "--ref")
.HasRequiredParameter(_transcriptCachePrefix, "transcript cache file", "--cache")
.CheckInputFilenameExists(CacheConstants.TranscriptPath(_transcriptCachePrefix), "transcript cache prefix", "--cache")
.HasRequiredParameter(_inputFile, "SpliceAI VCF file", "--in")
.CheckInputFilenameExists(_inputFile, "SpliceAI VCF file", "--in")
.HasRequiredParameter(_geneInfoFile, "Gene info data file from NCBI", "--gene")
.CheckInputFilenameExists(_geneInfoFile, "Gene info data file from NCBI", "--gene")
.HasRequiredParameter(_outputDirectory, "output directory", "--out")
.CheckDirectoryExists(_outputDirectory, "output directory", "--out")
.SkipBanner()
.ShowHelpMenu("Creates a supplementary database containing 1000 Genomes allele frequencies", commandLineExample)
.ShowErrors()
.Execute(ProgramExecution);
return(exitCode);
}
static int Main(string[] args)
{
var ops = new OptionSet
{
{
"cache|c=",
"input cache {prefix}",
v => ConfigurationSettings.InputCachePrefix = v
},
{
"in|i=",
"input VCF {path}",
v => ConfigurationSettings.VcfPath = v
},
{
"out|o=",
"output {file path} ",
v => ConfigurationSettings.OutputFileName = v
},
{
"ref|r=",
"input compressed reference sequence {path}",
v => ConfigurationSettings.RefSequencePath = v
},
{
"force-mt",
"forces to annotate mitochondria variants",
v => ConfigurationSettings.ForceMitochondrialAnnotation = v != null
}
};
var commandLineExample = "-i <vcf path> -d <cache dir> -r <ref path> -o <base output filename>";
var piano = new Piano();
var exitCode = new ConsoleAppBuilder(args, ops)
.UseVersionProvider(new VersionProvider())
.Parse()
.CheckInputFilenameExists(ConfigurationSettings.VcfPath, "vcf", "--in", true, "-")
.CheckInputFilenameExists(ConfigurationSettings.RefSequencePath, "reference sequence", "--ref")
.CheckInputFilenameExists(CacheConstants.TranscriptPath(ConfigurationSettings.InputCachePrefix), "transcript cache", "--cache")
.HasRequiredParameter(ConfigurationSettings.OutputFileName, "output file stub", "--out")
.ShowBanner(Constants.Authors)
.ShowHelpMenu("peptide annotation", commandLineExample)
.ShowErrors()
.Execute(piano.ProgramExecution);
return((int)exitCode);
}
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);
}
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.");
}
}
public static GlobalCache LoadCache(string cachePrefix)
{
var cachePath = CacheConstants.TranscriptPath(cachePrefix);
if (!File.Exists(cachePath))
{
return(null);
}
GlobalCache transcriptCache;
using (var reader = new GlobalCacheReader(FileUtilities.GetReadStream(cachePath)))
{
transcriptCache = reader.Read();
}
return(transcriptCache);
}
public void Create(string outputPath)
{
using (var writer = GZipUtilities.GetStreamWriter(outputPath))
{
Console.Write("- reading {0}... ", Path.GetFileName(_cachePrefix));
var cache = GetCache(CacheConstants.TranscriptPath(_cachePrefix));
Console.WriteLine("found {0:N0} transcripts.", cache.Transcripts.Length);
AddGenesToDictionary(cache.Genes);
Console.Write("- writing GFF entries... ");
foreach (var transcript in cache.Transcripts)
{
Write(writer, _referenceNames[transcript.ReferenceIndex], transcript);
}
Console.WriteLine("finished.");
}
}
public static ExitCodes Run(string command, string[] commandArgs)
{
var ops = new OptionSet
{
{
"cache|c=",
"Cache prefix",
v => _cachePrefix = v
},
{
"ref|r=",
"Reference sequence path",
v => _referenceSequncePath = v
},
{
"in|i=",
"input tsv file",
v => _inputFile = v
},
{
"out|o=",
"output directory",
v => _outputDirectory = v
}
};
string commandLineExample = $"{command} [options]";
var exitCode = new ConsoleAppBuilder(commandArgs, ops)
.Parse()
.HasRequiredParameter(_outputDirectory, "output directory", "--out")
.CheckDirectoryExists(_outputDirectory, "output directory", "--out")
.HasRequiredParameter(_cachePrefix, "transcript cache prefix", "--cache")
.CheckInputFilenameExists(CacheConstants.TranscriptPath(_cachePrefix), "transcript cache prefix", "--cache")
.HasRequiredParameter(_referenceSequncePath, "reference sequence path", "--ref")
.CheckInputFilenameExists(_referenceSequncePath, "reference sequence path", "--ref")
.CheckInputFilenameExists(_inputFile, "input TSV file", "--in")
.SkipBanner()
.ShowHelpMenu("Creates a gene annotation database from gnomAD data", commandLineExample)
.ShowErrors()
.Execute(ProgramExecution);
return(exitCode);
}
private static ExitCodes ProgramExecution()
{
Source transcriptSource = ParseVepCacheDirectoryMain.GetSource(_transcriptSource);
string cachePath = CacheConstants.TranscriptPath(_inputPrefix);
IDictionary <ushort, IChromosome> refIndexToChromosome =
SequenceHelper.GetDictionaries(_compressedReferencePath).refIndexToChromosome;
TranscriptCacheData cache = TranscriptCacheHelper.GetCache(cachePath, refIndexToChromosome);
IDictionary <IGene, int> geneToInternalId = InternalGenes.CreateDictionary(cache.Genes);
using (var writer = new GffWriter(GZipUtilities.GetStreamWriter(_outputFileName)))
{
var creator = new GffCreator(writer, geneToInternalId, transcriptSource);
creator.Create(cache.TranscriptIntervalArrays);
}
return(ExitCodes.Success);
}
public TranscriptAnnotationProvider(string pathPrefix, ISequenceProvider sequenceProvider)
{
Name = "Transcript annotation provider";
_sequence = sequenceProvider.Sequence;
var transcriptStream = PersistentStreamUtils.GetReadStream(CacheConstants.TranscriptPath(pathPrefix));
(_transcriptCache, TranscriptIntervalArrays, VepVersion) = InitiateCache(transcriptStream, sequenceProvider.RefIndexToChromosome, sequenceProvider.Assembly);
Assembly = _transcriptCache.Assembly;
DataSourceVersions = _transcriptCache.DataSourceVersions;
var siftStream = PersistentStreamUtils.GetReadStream(CacheConstants.SiftPath(pathPrefix));
_siftReader = new PredictionCacheReader(siftStream, PredictionCacheReader.SiftDescriptions);
var polyphenStream = PersistentStreamUtils.GetReadStream(CacheConstants.PolyPhenPath(pathPrefix));
_polyphenReader = new PredictionCacheReader(polyphenStream, PredictionCacheReader.PolyphenDescriptions);
}
protected override void ProgramExecution()
{
var referenceNames = GetUcscReferenceNames(ConfigurationSettings.CompressedReferencePath);
using (var writer = GZipUtilities.GetStreamWriter(ConfigurationSettings.OutputFileName))
{
var cachePath = CacheConstants.TranscriptPath(ConfigurationSettings.CachePrefix);
// load the cache
Console.Write("- reading {0}... ", Path.GetFileName(cachePath));
var cache = GetCache(cachePath);
Console.WriteLine("found {0:N0} regulatory regions. ", cache.RegulatoryElements.Length);
Console.Write("- writing GFF entries... ");
foreach (var regulatoryFeature in cache.RegulatoryElements)
{
WriteRegulatoryFeature(writer, referenceNames, regulatoryFeature);
}
Console.WriteLine("finished.");
}
}
public IAnnotationSource CreateAnnotationSource(IAnnotatorInfo annotatorInfo, IAnnotatorPaths annotatorPaths)
{
var conservationScoreReader = new PhylopReader(annotatorPaths.SupplementaryAnnotation);
var transcriptStream = FileUtilities.GetReadStream(CacheConstants.TranscriptPath(annotatorPaths.CachePrefix));
var siftStream = FileUtilities.GetReadStream(CacheConstants.SiftPath(annotatorPaths.CachePrefix));
var polyPhenStream = FileUtilities.GetReadStream(CacheConstants.PolyPhenPath(annotatorPaths.CachePrefix));
var referenceStream = FileUtilities.GetReadStream(annotatorPaths.CompressedReference);
var streams = new AnnotationSourceStreams(transcriptStream, siftStream, polyPhenStream, referenceStream);
var caProvider = annotatorPaths.CustomAnnotation.Any() ? new CustomAnnotationProvider(annotatorPaths.CustomAnnotation) : null;
var ciProvider = annotatorPaths.CustomIntervals.Any() ? new CustomIntervalProvider(annotatorPaths.CustomIntervals) : null;
var saProvider = annotatorPaths.SupplementaryAnnotation != null ? new SupplementaryAnnotationProvider(annotatorPaths.SupplementaryAnnotation) : null;
//adding the saPath because OMIM needs it
var annotationSource = new NirvanaAnnotationSource(streams, saProvider, conservationScoreReader, caProvider, ciProvider, annotatorPaths.SupplementaryAnnotation);
if (annotatorInfo.BooleanArguments.Contains(AnnotatorInfoCommon.ReferenceNoCall))
{
annotationSource.EnableReferenceNoCalls(annotatorInfo.BooleanArguments.Contains(AnnotatorInfoCommon.TranscriptOnlyRefNoCall));
}
if (annotatorInfo.BooleanArguments.Contains(AnnotatorInfoCommon.EnableMitochondrialAnnotation))
{
annotationSource.EnableMitochondrialAnnotation();
}
if (annotatorInfo.BooleanArguments.Contains(AnnotatorInfoCommon.ReportAllSvOverlappingTranscripts))
{
annotationSource.EnableReportAllSvOverlappingTranscripts();
}
if (annotatorInfo.BooleanArguments.Contains(AnnotatorInfoCommon.EnableLoftee))
{
annotationSource.AddPlugin(new Loftee());
}
return(annotationSource);
}
protected override void ValidateCommandLine()
{
if (ConfigurationSettings.VcfPath != "-")
{
CheckInputFilenameExists(ConfigurationSettings.VcfPath, "vcf", "--in");
}
CheckInputFilenameExists(ConfigurationSettings.CompressedReferencePath, "compressed reference sequence", "--ref");
CheckInputFilenameExists(CacheConstants.TranscriptPath(ConfigurationSettings.InputCachePrefix), "transcript cache", "--cache");
CheckInputFilenameExists(CacheConstants.SiftPath(ConfigurationSettings.InputCachePrefix), "SIFT cache", "--cache");
CheckInputFilenameExists(CacheConstants.PolyPhenPath(ConfigurationSettings.InputCachePrefix), "PolyPhen cache", "--cache");
CheckDirectoryExists(ConfigurationSettings.SupplementaryAnnotationDirectory, "supplementary annotation", "--sd", false);
foreach (var customAnnotationDirectory in ConfigurationSettings.CustomAnnotationDirectories)
{
CheckDirectoryExists(customAnnotationDirectory, "custom annotation", "--ca", false);
}
foreach (var customAnnotationDirectory in ConfigurationSettings.CustomIntervalDirectories)
{
CheckDirectoryExists(customAnnotationDirectory, "custom interval", "--ci", false);
}
// if we're using stdout, it doesn't make sense to output the VCF and gVCF
if (ConfigurationSettings.OutputFileName == "-")
{
ConfigurationSettings.Vcf = false;
ConfigurationSettings.Gvcf = false;
PerformanceMetrics.DisableOutput = true;
}
HasRequiredParameter(ConfigurationSettings.OutputFileName, "output file stub", "--out");
if (ConfigurationSettings.LimitReferenceNoCallsToTranscripts)
{
ConfigurationSettings.EnableReferenceNoCalls = true;
}
}
private static ExitCodes ProgramExecution()
{
Dictionary <string, string> geneIdToSymbols;
using (var cacheStream = FileUtilities.GetReadStream(CacheConstants.TranscriptPath(_cachePrefix)))
using (var transcriptCacheReader = new TranscriptCacheReader(cacheStream))
using (var refProvider = new ReferenceSequenceProvider(FileUtilities.GetReadStream(_referenceSequncePath)))
{
geneIdToSymbols = LoadGenesFromCache(refProvider, transcriptCacheReader);
Console.WriteLine($"Loaded {geneIdToSymbols.Count} gene symbols from cache.");
}
var version = DataSourceVersionReader.GetSourceVersion(_inputFile + ".version");
var outFileName = $"{version.Name}_{version.Version}";
using (var gnomadGeneParser = new GnomadGeneParser(GZipUtilities.GetAppropriateStreamReader(_inputFile), geneIdToSymbols))
using (var stream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.NgaFileSuffix)))
using (var ngaWriter = new NgaWriter(stream, version, SaCommon.GnomadGeneScoreTag, SaCommon.SchemaVersion, false))
{
ngaWriter.Write(gnomadGeneParser.GetItems());
}
return(ExitCodes.Success);
}
private static ExitCodes ProgramExecution()
{
string transcriptPath = _inputPrefix + ".transcripts.gz";
string siftPath = _inputPrefix + ".sift.gz";
string polyphenPath = _inputPrefix + ".polyphen.gz";
string regulatoryPath = _inputPrefix + ".regulatory.gz";
(var refIndexToChromosome, var refNameToChromosome, int numRefSeqs) = SequenceHelper.GetDictionaries(_inputReferencePath);
using (var transcriptReader = new MutableTranscriptReader(GZipUtilities.GetAppropriateReadStream(transcriptPath), refIndexToChromosome))
using (var regulatoryReader = new RegulatoryRegionReader(GZipUtilities.GetAppropriateReadStream(regulatoryPath), refIndexToChromosome))
using (var siftReader = new PredictionReader(GZipUtilities.GetAppropriateReadStream(siftPath), refIndexToChromosome, IntermediateIoCommon.FileType.Sift))
using (var polyphenReader = new PredictionReader(GZipUtilities.GetAppropriateReadStream(polyphenPath), refIndexToChromosome, IntermediateIoCommon.FileType.Polyphen))
using (var geneReader = new UgaGeneReader(GZipUtilities.GetAppropriateReadStream(ExternalFiles.UniversalGeneFilePath), refNameToChromosome))
{
var genomeAssembly = transcriptReader.Header.Assembly;
var source = transcriptReader.Header.Source;
long vepReleaseTicks = transcriptReader.Header.VepReleaseTicks;
ushort vepVersion = transcriptReader.Header.VepVersion;
Logger.Write("- loading universal gene archive file... ");
var genes = geneReader.GetGenes();
var geneForest = CreateGeneForest(genes, numRefSeqs, genomeAssembly);
Logger.WriteLine($"{genes.Length:N0} loaded.");
Logger.Write("- loading regulatory region file... ");
var regulatoryRegions = regulatoryReader.GetRegulatoryRegions();
Logger.WriteLine($"{regulatoryRegions.Length:N0} loaded.");
Logger.Write("- loading transcript file... ");
var transcripts = transcriptReader.GetTranscripts();
var transcriptsByRefIndex = transcripts.GetMultiValueDict(x => x.Chromosome.Index);
Logger.WriteLine($"{transcripts.Length:N0} loaded.");
MarkCanonicalTranscripts(transcripts);
var predictionBuilder = new PredictionCacheBuilder(genomeAssembly);
var predictionCaches = predictionBuilder.CreatePredictionCaches(transcriptsByRefIndex, siftReader, polyphenReader, numRefSeqs);
Logger.Write("- writing SIFT prediction cache... ");
predictionCaches.Sift.Write(FileUtilities.GetCreateStream(CacheConstants.SiftPath(_outputCacheFilePrefix)));
Logger.WriteLine("finished.");
Logger.Write("- writing PolyPhen prediction cache... ");
predictionCaches.PolyPhen.Write(FileUtilities.GetCreateStream(CacheConstants.PolyPhenPath(_outputCacheFilePrefix)));
Logger.WriteLine("finished.");
var transcriptBuilder = new TranscriptCacheBuilder(genomeAssembly, source, vepReleaseTicks, vepVersion);
var transcriptStaging = transcriptBuilder.CreateTranscriptCache(transcripts, regulatoryRegions, geneForest, numRefSeqs);
Logger.Write("- writing transcript cache... ");
transcriptStaging.Write(FileUtilities.GetCreateStream(CacheConstants.TranscriptPath(_outputCacheFilePrefix)));
Logger.WriteLine("finished.");
}
return(ExitCodes.Success);
}
public static TranscriptCacheData GetTranscriptData(IDictionary <ushort, IChromosome> refIndexToChromosome, string transcriptCachePrefix)
{
using var transcriptCacheReader = new TranscriptCacheReader(
FileUtilities.GetReadStream(CacheConstants.TranscriptPath(transcriptCachePrefix)));
return(transcriptCacheReader.Read(refIndexToChromosome));
}
public void TranscriptPath_Null_WithNullPrefix()
{
var observedResult = CacheConstants.TranscriptPath(null);
Assert.Null(observedResult);
}
private static ExitCodes ProgramExecution()
{
var referenceProvider = new ReferenceSequenceProvider(FileUtilities.GetReadStream(_compressedReference));
TranscriptCacheData transcriptData;
using (var transcriptCacheReader = new TranscriptCacheReader(FileUtilities.GetReadStream(CacheConstants.TranscriptPath(_transcriptCachePrefix))))
{
transcriptData = transcriptCacheReader.Read(referenceProvider.RefIndexToChromosome);
}
var spliceIntervals = SpliceUtilities.GetSpliceIntervals(referenceProvider, transcriptData);
var nirEnstToGeneSymbols = SpliceUtilities.GetEnstToGeneSymbols(referenceProvider, transcriptData);
Dictionary <string, string> spliceAiEnstToGeneSymbols;
using (var reader = new StreamReader(GZipUtilities.GetAppropriateReadStream(_geneInfoFile)))
{
spliceAiEnstToGeneSymbols = SpliceUtilities.GetSpliceAiGeneSymbols(reader);
}
var spliceAiToNirvanaGeneSymbols =
SpliceUtilities.GetSymbolMapping(spliceAiEnstToGeneSymbols, nirEnstToGeneSymbols);
Console.WriteLine($"Mapped {spliceAiToNirvanaGeneSymbols.Count} spliceAI gene symbols to Nirvana gene symbols (out of {spliceAiEnstToGeneSymbols.Count})");
var version = DataSourceVersionReader.GetSourceVersion(_inputFile + ".version");
string outFileName = $"{version.Name}_{version.Version}";
using (var spliceAiParser = new SpliceAiParser(
GZipUtilities.GetAppropriateReadStream(_inputFile),
referenceProvider, spliceIntervals, spliceAiToNirvanaGeneSymbols))
using (var nsaStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.SaFileSuffix)))
using (var indexStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.SaFileSuffix + SaCommon.IndexSufix)))
using (var nsaWriter = new NsaWriter(nsaStream, indexStream, version, referenceProvider, SaCommon.SpliceAiTag, true, true, SaCommon.SchemaVersion, false))
{
nsaWriter.Write(spliceAiParser.GetItems());
}
Console.WriteLine($"Total number of entries from Splice AI: {SpliceAiParser.Count}");
return(ExitCodes.Success);
}
private static ExitCodes ProgramExecution()
{
var referenceProvider = new ReferenceSequenceProvider(FileUtilities.GetReadStream(_compressedReference));
TranscriptCacheData transcriptData;
using (var transcriptCacheReader = new TranscriptCacheReader(FileUtilities.GetReadStream(CacheConstants.TranscriptPath(_transcriptCachePrefix))))
{
transcriptData = transcriptCacheReader.Read(referenceProvider.RefIndexToChromosome);
}
var spliceIntervals = SpliceUtilities.GetSpliceIntervals(referenceProvider, transcriptData);
var nirvanaGeneForest = SpliceUtilities.GetGeneForest(transcriptData);
Console.WriteLine("Loaded transcripts and generated splice intervals.");
Dictionary <string, List <string> > geneSymbolSynonyms;
using (var geneInfoParser = new GeneInfoParser(GZipUtilities.GetAppropriateStreamReader(_geneInfoFile)))
{
geneSymbolSynonyms = geneInfoParser.GetGeneSymbolSynonyms();
}
Console.WriteLine("Loaded gene symbol synonyms");
var version = DataSourceVersionReader.GetSourceVersion(_inputFile + ".version");
string outFileName = $"{version.Name}_{version.Version}";
using (var spliceAiParser = new SpliceAiParser(
GZipUtilities.GetAppropriateReadStream(_inputFile),
referenceProvider, spliceIntervals, nirvanaGeneForest, geneSymbolSynonyms))
using (var nsaStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.SaFileSuffix)))
using (var indexStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.SaFileSuffix + SaCommon.IndexSufix)))
{
var nsaWriter = new NsaWriter(new ExtendedBinaryWriter(nsaStream), new ExtendedBinaryWriter(indexStream), version, referenceProvider, SaCommon.SpliceAiTag, true, true, SaCommon.SchemaVersion, false);
nsaWriter.Write(spliceAiParser.GetItems());
}
Console.WriteLine($"Total number of entries from Splice AI: {SpliceAiParser.Count}");
return(ExitCodes.Success);
}
public static int Main(string[] args)
{
var ops = new OptionSet
{
{
"cache|c=",
"input cache {prefix}",
v => _inputCachePrefix = v
},
{
"in|i=",
"input VCF {path}",
v => _vcfPath = v
},
{
"out|o=",
"output {file path}",
v => _outputFileName = v
},
{
"ref|r=",
"input compressed reference sequence {path}",
v => _refSequencePath = v
},
{
"sd=",
"input supplementary annotation {directory}",
v => SupplementaryAnnotationDirectories.Add(v)
},
{
"force-mt",
"forces to annotate mitochondrial variants",
v => _forceMitochondrialAnnotation = v != null
},
{
"disable-recomposition",
"don't recompose function relevant variants",
v => _disableRecomposition = v != null
},
{
"legacy-vids",
"enables support for legacy VIDs",
v => _useLegacyVids = v != null
},
{
"enable-dq",
"report DQ from VCF samples field",
v => _enableDq = v != null
},
{
"str=",
"user provided STR annotation TSV file",
v => _customStrTsv = v
}
};
var exitCode = new ConsoleAppBuilder(args, ops)
.UseVersionProvider(new VersionProvider())
.Parse()
.CheckInputFilenameExists(_vcfPath, "vcf", "--in", true, "-")
.CheckInputFilenameExists(_refSequencePath, "reference sequence", "--ref")
.CheckInputFilenameExists(CacheConstants.TranscriptPath(_inputCachePrefix), "transcript cache", "--cache")
.CheckInputFilenameExists(CacheConstants.SiftPath(_inputCachePrefix), "SIFT cache", "--cache")
.CheckInputFilenameExists(CacheConstants.PolyPhenPath(_inputCachePrefix), "PolyPhen cache", "--cache")
.CheckInputFilenameExists(_customStrTsv, "custom STR annotation TSV", "--str", false)
.HasRequiredParameter(_outputFileName, "output file stub", "--out")
.DisableOutput(_outputFileName == "-")
.ShowBanner(Constants.Authors)
.ShowHelpMenu("Annotates a set of variants", "-i <vcf path> -c <cache prefix> --sd <sa dir> -r <ref path> -o <base output filename>")
.ShowErrors()
.Execute(ProgramExecution);
return((int)exitCode);
}
public static IRecomposer Create(ISequenceProvider sequenceProvider,
string inputCachePrefix)
{
var transcriptIntervalArrays = ReadWriteUtilities.ReadCache(FileUtilities.GetReadStream(CacheConstants.TranscriptPath(inputCachePrefix)), sequenceProvider.RefIndexToChromosome);
var(geneIntervalForest, _) = ReadWriteUtilities.GetIntervalAndTranscriptsForeachGene(transcriptIntervalArrays);
var codonInfoProvider = CodonInfoProvider.CreateCodonInfoProvider(transcriptIntervalArrays);
var variantGenerator = new VariantGenerator(sequenceProvider);
var positionBuffer = new PositionBuffer(codonInfoProvider, geneIntervalForest);
return(new Recomposer(new PositionProcessor(positionBuffer, codonInfoProvider, variantGenerator), sequenceProvider));
}