private static IEnumerable <AnnotationRange> GetAnnotationRanges(NirvanaConfig config, GenomeAssembly genomeAssembly) { string cachePathPrefix = LambdaUtilities.GetCachePathPrefix(genomeAssembly); IntervalForest <IGene> geneIntervalForest; IDictionary <string, IChromosome> refNameToChromosome; List <long> blockOffsets; using (var tabixStream = PersistentStreamUtils.GetReadStream(config.tabixUrl)) using (var tabixReader = new BinaryReader(new BlockGZipStream(tabixStream, CompressionMode.Decompress))) using (var referenceStream = PersistentStreamUtils.GetReadStream(LambdaUrlHelper.GetRefUrl(genomeAssembly))) using (var sequenceProvider = new ReferenceSequenceProvider(referenceStream)) using (var taProvider = new TranscriptAnnotationProvider(cachePathPrefix, sequenceProvider, null)) { long vcfSize = HttpUtilities.GetLength(config.vcfUrl); int numPartitions = Math.Max(Math.Min((int)((vcfSize - 1) / MinPartitionSize + 1), MaxNumPartitions), MinNumPartitions); var tabixIndex = Reader.Read(tabixReader, sequenceProvider.RefNameToChromosome); blockOffsets = PartitionUtilities.GetFileOffsets(config.vcfUrl, numPartitions, tabixIndex); IntervalArray <ITranscript>[] transcriptIntervalArrays = taProvider.TranscriptIntervalArrays; geneIntervalForest = GeneForestGenerator.GetGeneForest(transcriptIntervalArrays); refNameToChromosome = sequenceProvider.RefNameToChromosome; } IEnumerable <AnnotationRange> annotationRanges = PartitionUtilities.GenerateAnnotationRanges(blockOffsets, config.vcfUrl, geneIntervalForest, refNameToChromosome); return(annotationRanges); }
private static AnnotationResources GetAnnotationResources(AnnotationConfig annotationConfig) { var genomeAssembly = GenomeAssemblyHelper.Convert(annotationConfig.genomeAssembly); string cachePathPrefix = LambdaUrlHelper.GetCacheFolder().UrlCombine(genomeAssembly.ToString()).UrlCombine(LambdaUrlHelper.DefaultCacheSource); string nirvanaS3Ref = LambdaUrlHelper.GetRefUrl(genomeAssembly); string saManifestUrl = LambdaUtilities.GetManifestUrl(annotationConfig.supplementaryAnnotations ?? "latest", genomeAssembly); var metrics = new PerformanceMetrics(); var annotationResources = new AnnotationResources(nirvanaS3Ref, cachePathPrefix, saManifestUrl == null? null: new List <string> { saManifestUrl }, annotationConfig.customAnnotations, annotationConfig.customStrUrl, false, false, false, metrics); using (var tabixStream = PersistentStreamUtils.GetReadStream(annotationConfig.tabixUrl)) { annotationResources.InputStartVirtualPosition = GetTabixVirtualPosition(annotationConfig.annotationRange, tabixStream, annotationResources.SequenceProvider.RefNameToChromosome); } Logger.WriteLine($"Tabix position :{annotationResources.InputStartVirtualPosition}"); return(annotationResources); }
public ValidationResult Run(ValidationConfig config, ILambdaContext context) { string snsTopicArn = null; try { LogUtilities.UpdateLogger(context.Logger, null); LogUtilities.LogLambdaInfo(context, CommandLineUtilities.InformationalVersion); LogUtilities.LogObject("Config", config); LogUtilities.Log(new[] { LambdaUrlHelper.UrlBaseEnvironmentVariableName, LambdaUtilities.SnsTopicKey }); LambdaUtilities.GarbageCollect(); snsTopicArn = LambdaUtilities.GetEnvironmentVariable(LambdaUtilities.SnsTopicKey); config.Validate(); GenomeAssembly genomeAssembly = GenomeAssemblyHelper.Convert(config.genomeAssembly); string nirvanaS3Ref = LambdaUrlHelper.GetRefUrl(genomeAssembly); var refProvider = ProviderUtilities.GetSequenceProvider(nirvanaS3Ref); using (var stream = PersistentStreamUtils.GetReadStream(config.customStrUrl)) TryLoadStrFile(stream, genomeAssembly, refProvider); } catch (Exception exception) { return(HandleException(config.id, exception, snsTopicArn)); } return(GetSuccessOutput(config.id)); }
private static AnnotationResources GetAnnotationResources(SingleConfig lambdaConfig) { GenomeAssembly genomeAssembly = GenomeAssemblyHelper.Convert(lambdaConfig.genomeAssembly); string cachePathPrefix = CacheUtilities.GetCachePathPrefix(lambdaConfig.vepVersion, genomeAssembly); string nirvanaS3Ref = LambdaUrlHelper.GetRefUrl(genomeAssembly); string annotatorVersion = "Nirvana " + CommandLineUtilities.GetVersion(Assembly.GetAssembly(typeof(SingleAnnotationLambda))); var metrics = new PerformanceMetrics(); Logger.WriteLine($"Cache prefix: {cachePathPrefix}"); //todo: get customStrTsv from lambdaConfig var annotationResources = new AnnotationResources(nirvanaS3Ref, cachePathPrefix, null, lambdaConfig.customAnnotations, null, false, false, false, metrics) { AnnotatorVersionTag = annotatorVersion }; return(annotationResources); }
public void GetS3RefLocation_AsExpected() { Assert.Equal(LambdaUrlHelper.GetRefPrefix("whatever") + "GRCh37" + LambdaUrlHelper.RefSuffix, LambdaUrlHelper.GetRefUrl(GenomeAssembly.GRCh37, "whatever")); }
private static VariantAnnotationsParser GetVariantAnnotationsParserFromCustomTsvStream(PersistentStream customTsvStream) { var parser = VariantAnnotationsParser.Create(new StreamReader(GZipUtilities.GetAppropriateStream(customTsvStream))); parser.SequenceProvider = new ReferenceSequenceProvider(PersistentStreamUtils.GetReadStream(LambdaUrlHelper.GetRefUrl(parser.Assembly))); return(parser); }