/// <summary>
/// executes the program
/// </summary>
protected override void ProgramExecution()
{
var renamer = ChromosomeRenamer.GetChromosomeRenamer(FileUtilities.GetReadStream(ConfigurationSettings.CompressedReference));
var customIntervalDbCreator = new CustomIntervalDbCreator(ConfigurationSettings.BedFile, ConfigurationSettings.OutputDirectory, renamer);
customIntervalDbCreator.Create();
}
/// <summary>
/// executes the program
/// </summary>
protected override void ProgramExecution()
{
var transcriptPath = ConfigurationSettings.InputPrefix + ".transcripts.gz";
var regulatoryPath = ConfigurationSettings.InputPrefix + ".regulatory.gz";
var genePath = ConfigurationSettings.InputPrefix + ".genes.gz";
var intronPath = ConfigurationSettings.InputPrefix + ".introns.gz";
var mirnaPath = ConfigurationSettings.InputPrefix + ".mirnas.gz";
var siftPath = ConfigurationSettings.InputPrefix + ".sift.dat";
var polyphenPath = ConfigurationSettings.InputPrefix + ".polyphen.dat";
var peptidePath = ConfigurationSettings.InputPrefix + ".peptides.gz";
var renamer = ChromosomeRenamer.GetChromosomeRenamer(FileUtilities.GetReadStream(ConfigurationSettings.InputReferencePath));
using (var transcriptReader = new VepTranscriptReader(transcriptPath))
using (var regulatoryReader = new VepRegulatoryReader(regulatoryPath))
using (var geneReader = new VepGeneReader(genePath))
using (var mergedGeneReader = new VepCombinedGeneReader(ConfigurationSettings.InputMergedGenesPath))
using (var intronReader = new VepSimpleIntervalReader(intronPath, "intron", GlobalImportCommon.FileType.Intron))
using (var mirnaReader = new VepSimpleIntervalReader(mirnaPath, "miRNA", GlobalImportCommon.FileType.MicroRna))
using (var peptideReader = new VepSequenceReader(peptidePath, "peptide", GlobalImportCommon.FileType.Peptide))
{
var converter = new NirvanaDatabaseCreator(transcriptReader, regulatoryReader, geneReader,
mergedGeneReader, intronReader, mirnaReader, peptideReader, renamer);
converter.LoadData();
converter.MarkCanonicalTranscripts(ConfigurationSettings.InputLrgPath);
converter.CreateTranscriptCacheFile(ConfigurationSettings.OutputCacheFilePrefix);
converter.CopyPredictionCacheFile("SIFT", siftPath, CacheConstants.SiftPath(ConfigurationSettings.OutputCacheFilePrefix));
converter.CopyPredictionCacheFile("PolyPhen", polyphenPath, CacheConstants.PolyPhenPath(ConfigurationSettings.OutputCacheFilePrefix));
}
}
/// <summary>
/// creates a new annotation source with data from the micro-cache file
/// </summary>
internal static IAnnotationSource GetAnnotationSource(string cachePath, ISupplementaryAnnotationReader saReader,
IConservationScoreReader conservationScoreReader = null,
ISupplementaryAnnotationProvider customAnnotationProvider = null,
ISupplementaryAnnotationProvider customIntervalProvider = null)
{
var streams = GetAnnotationSourceStreams(cachePath);
var renamer = ChromosomeRenamer.GetChromosomeRenamer(GetReadStream($"{cachePath}.bases"));
var saProvider = new MockSupplementaryAnnotationProvider(saReader, renamer);
PerformanceMetrics.DisableOutput = true;
return(new NirvanaAnnotationSource(streams, saProvider, conservationScoreReader, customAnnotationProvider,
customIntervalProvider, null));
}
private void ProcessGenomeAssemblyDir(string gaDir)
{
var genomeAssembly = Path.GetFileName(gaDir);
var compressedSequencePath = GetCompressedSequencePath(_referenceDir, genomeAssembly);
var renamer = ChromosomeRenamer.GetChromosomeRenamer(FileUtilities.GetReadStream(compressedSequencePath));
var cacheFiles = GetCacheFiles(gaDir, renamer);
var transcriptDataSources = GetTranscriptDataSources(cacheFiles);
Console.WriteLine("GenomeAssembly dir: {0}", gaDir);
foreach (var ds in transcriptDataSources)
{
ProcessTranscriptDataSource(cacheFiles, genomeAssembly, ds);
Console.WriteLine();
}
}
public SuppAnnotExtractor(string compressedRefFile, string inputSuppAnnotFile, int begin, int end,
string datasourceName = null, string outDirectory = null)
{
_renamer = ChromosomeRenamer.GetChromosomeRenamer(FileUtilities.GetReadStream(compressedRefFile));
long intervalsPosition;
var saHeader = SupplementaryAnnotationReader.GetHeader(inputSuppAnnotFile, out intervalsPosition);
_begin = begin;
_end = end;
string miniSuppAnnotFile;
if (datasourceName == null)
{
miniSuppAnnotFile = _renamer.GetUcscReferenceName(saHeader.ReferenceSequenceName)
+ '_' + begin.ToString(CultureInfo.InvariantCulture) + '_' +
end.ToString(CultureInfo.InvariantCulture) + ".nsa";
if (outDirectory != null)
{
miniSuppAnnotFile = Path.Combine(outDirectory, miniSuppAnnotFile);
}
}
else
{
miniSuppAnnotFile = _renamer.GetUcscReferenceName(saHeader.ReferenceSequenceName)
+ '_' + begin.ToString(CultureInfo.InvariantCulture) + '_' +
end.ToString(CultureInfo.InvariantCulture) + '_' + datasourceName + ".nsa";
if (outDirectory != null)
{
miniSuppAnnotFile = Path.Combine(outDirectory, miniSuppAnnotFile);
}
}
_writer = new SupplementaryAnnotationWriter(miniSuppAnnotFile, saHeader.ReferenceSequenceName, saHeader.DataSourceVersions);
Console.WriteLine("MiniSA output to: " + miniSuppAnnotFile);
}
static void Main(string[] args)
{
if (args.Length != 2)
{
Console.WriteLine("USAGE: {0} <reference path> <input vcf file>", Path.GetFileName(Environment.GetCommandLineArgs()[0]));
Environment.Exit(1);
}
var referencePath = args[0];
var vcfPath = args[1];
if (!File.Exists(vcfPath))
{
Console.WriteLine($"ERROR: {vcfPath} does not exist.");
Environment.Exit(1);
}
if (!File.Exists(referencePath))
{
Console.WriteLine($"ERROR: {referencePath} does not exist.");
Environment.Exit(1);
}
var renamer = ChromosomeRenamer.GetChromosomeRenamer(FileUtilities.GetReadStream(referencePath));
var vid = new VID();
var counts = new Dictionary <VariantType, int>();
using (var reader = new LiteVcfReader(vcfPath))
{
while (true)
{
var vcfLine = reader.ReadLine();
if (vcfLine == null)
{
break;
}
if (vcfLine.StartsWith("#"))
{
continue;
}
VcfVariant vcfVariant = null;
try
{
vcfVariant = CreateVcfVariant(vcfLine);
}
catch (Exception e)
{
Console.WriteLine($"ERROR: Could not parse the VCF line:\n{vcfLine}");
Console.WriteLine(e.Message);
Environment.Exit(1);
}
if (vcfVariant == null)
{
continue;
}
var variant = new VariantFeature(vcfVariant, renamer, vid);
if (variant.IsReference)
{
continue;
}
variant.AssignAlternateAlleles();
bool hasMnv = false;
foreach (var altAllele in variant.AlternateAlleles)
{
AddVariantType(altAllele.NirvanaVariantType, counts);
if (altAllele.NirvanaVariantType == VariantType.MNV)
{
hasMnv = true;
}
}
if (hasMnv)
{
Console.WriteLine(vcfLine);
}
}
}
const int keyFieldLength = 15;
const int valueFieldLength = 9;
Console.WriteLine("VariantType counts:");
Console.WriteLine($"{new string('-', keyFieldLength)} {new string('-', valueFieldLength)}");
foreach (var kvp in counts.OrderBy(x => x.Key.ToString()))
{
var spaceLeft = keyFieldLength - kvp.Key.ToString().Length - 1;
var filler = new string(' ', spaceLeft);
Console.WriteLine($"{kvp.Key}:{filler} {kvp.Value,9:N0}");
}
}
