예제 #1
0
  private void writeRecord(VariantContext vc, RefMetaDataTracker tracker, GenomeLoc loc) {
    if (!wroteHeader) {
      wroteHeader = true;

      // setup the header fields
      Set<VCFHeaderLine> hInfo = new HashSet<VCFHeaderLine>();
      hInfo.addAll(GATKVCFUtils.getHeaderFields(getToolkit(), Arrays.asList(variants.getName())));
      hInfo.add(VCFStandardHeaderLines.getFormatLine(VCFConstants.GENOTYPE_KEY));

      allowedGenotypeFormatStrings.add(VCFConstants.GENOTYPE_KEY);
      for (VCFHeaderLine field : hInfo) {
        if (field instanceof VCFFormatHeaderLine) {
          allowedGenotypeFormatStrings.add(((VCFFormatHeaderLine) field).getID());
        }
      }

      samples = new LinkedHashSet<String>();
      if (sampleName != null) {
        samples.add(sampleName);
      } else {
        // try VCF first
        samples =
            SampleUtils.getSampleListWithVCFHeader(getToolkit(), Arrays.asList(variants.getName()));

        if (samples.isEmpty()) {
          List<Feature> features = tracker.getValues(variants, loc);
          if (features.size() == 0)
            throw new IllegalStateException(
                "No rod data is present, but we just created a VariantContext");

          Feature f = features.get(0);
          if (f instanceof RawHapMapFeature)
            samples.addAll(Arrays.asList(((RawHapMapFeature) f).getSampleIDs()));
          else samples.addAll(vc.getSampleNames());
        }
      }

      vcfwriter.writeHeader(new VCFHeader(hInfo, samples));
    }

    vc = GATKVariantContextUtils.purgeUnallowedGenotypeAttributes(vc, allowedGenotypeFormatStrings);
    vcfwriter.add(vc);
  }
예제 #2
0
  /**
   * Gets the header lines for the VCF writer
   *
   * @return A set of VCF header lines
   */
  private static Set<VCFHeaderLine> getHeaderInfo() {
    Set<VCFHeaderLine> headerLines = new HashSet<>();

    // INFO fields for overall data
    headerLines.add(VCFStandardHeaderLines.getInfoLine(VCFConstants.END_KEY));
    headerLines.add(GATKVCFHeaderLines.getInfoLine(GATKVCFConstants.AVG_INTERVAL_DP_KEY));
    headerLines.add(GATKVCFHeaderLines.getInfoLine(GATKVCFConstants.INTERVAL_GC_CONTENT_KEY));
    headerLines.add(
        new VCFInfoHeaderLine(
            "Diagnose Targets", 0, VCFHeaderLineType.Flag, "DiagnoseTargets mode"));

    // FORMAT fields for each genotype
    headerLines.add(VCFStandardHeaderLines.getFormatLine(VCFConstants.GENOTYPE_FILTER_KEY));
    headerLines.add(
        GATKVCFHeaderLines.getFormatLine(GATKVCFConstants.AVG_INTERVAL_DP_BY_SAMPLE_KEY));
    headerLines.add(GATKVCFHeaderLines.getFormatLine(GATKVCFConstants.LOW_COVERAGE_LOCI));
    headerLines.add(GATKVCFHeaderLines.getFormatLine(GATKVCFConstants.ZERO_COVERAGE_LOCI));

    // FILTER fields
    for (CallableStatus stat : CallableStatus.values())
      headerLines.add(new VCFFilterHeaderLine(stat.name(), stat.description));

    return headerLines;
  }