예제 #1
0
  public static void main(String[] args) {
    args =
        new String[] {
          "/commun/data/users/cfaucheron/aln_20120329/S0529/data_S0529/S0529_sort.nodup.bam"
        };
    ReferenceSequenceFile rsf =
        ReferenceSequenceFileFactory.getReferenceSequenceFile(
            new File("/commun/data/pubdb/ucsc/hg19/chromosomes/hg19.fa"));
    int count = 0;
    for (String filename : args) {
      File file = new File(filename);
      SAMFileReader samIn = new SAMFileReader(file);
      SAMRecordIterator r = samIn.iterator();
      while (r.hasNext()) {

        SAMRecord rec = r.next();
        if (rec.getReadUnmappedFlag()) continue;

        if (++count > 10000) break;

        if (rec.getAlignmentStart() > rec.getAlignmentEnd()) throw new IllegalStateException();
        byte bases[] =
            rsf.getSubsequenceAt(
                    rec.getReferenceName(),
                    rec.getAlignmentStart(),
                    Math.max(
                        rec.getAlignmentEnd(),
                        rec.getAlignmentStart() + rec.getCigar().getPaddedReferenceLength()))
                .getBases();
        Iterator<CigarAlignment> i = CigarAlignment.iterator(rec);
        /*System.err.println(rec.getCigarString());
        System.err.println(bases.length);
        System.err.println("start:"+rec.getAlignmentStart());*/
        StringBuilder s1 = new StringBuilder();
        StringBuilder s2 = new StringBuilder();

        while (i.hasNext()) {
          CigarAlignment caln = i.next();
          /*
          System.err.println(rec.getCigarString());

          System.err.println("bases.length:"+bases.length);
          System.err.println("refpos:"+caln.getReferencePosition1());
          System.err.println("readpos:"+rec.getAlignmentStart());
          */
          if (caln.getReferencePosition1() - rec.getAlignmentStart() >= bases.length) {
            System.out.println("SHORT!");
            System.out.println("op:" + caln.getCigarOperator());
            System.out.println("read start:" + rec.getAlignmentStart());
            System.out.println("clan.pos1:" + caln.getReferencePosition1());
            System.out.println("read end:" + rec.getAlignmentEnd());
            System.out.println("bases.length:" + bases.length);
            System.out.println(
                "getPaddedReferenceLength:" + rec.getCigar().getPaddedReferenceLength());
            System.out.println("getReferenceLength:" + rec.getCigar().getReferenceLength());
            System.out.println("getReadLength:" + rec.getCigar().getReadLength());
            System.out.println(
                "cigar.read.length:" + Cigar.getReadLength(rec.getCigar().getCigarElements()));
            count = 2000;
            break;
          }
          if (caln.isInsertRef()) {
            s2.append("-");
            s1.append(caln.getReadBase());
          } else if (caln.isDeletionRef()) {
            s2.append((char) bases[caln.getReferencePosition1() - rec.getAlignmentStart()]);
            s1.append("-");
          } else {
            s2.append((char) bases[caln.getReferencePosition1() - rec.getAlignmentStart()]);
            s1.append(caln.getReadBase());
          }
          // System.out.println(s1);
          // System.out.println(s2);
          // System.out.println();
        }
        System.out.println(
            rec.getCigarString() + " " + rec.getReferenceName() + ":" + rec.getAlignmentStart());
        System.out.println("ref :" + new String(bases));
        System.out.println("read:" + new String(rec.getReadBases()));
        System.out.println();
        System.out.println(s1);
        System.out.println(s2);
        System.out.println();
      }
      samIn.close();
    }
  }
예제 #2
0
  /**
   * Asserts that files are readable and writable and then fires off an HsMetricsCalculator instance
   * to do the real work.
   */
  protected int doWork() {
    IoUtil.assertFileIsReadable(getProbeIntervals());
    IoUtil.assertFileIsReadable(TARGET_INTERVALS);
    IoUtil.assertFileIsReadable(INPUT);
    IoUtil.assertFileIsWritable(OUTPUT);
    if (PER_TARGET_COVERAGE != null) IoUtil.assertFileIsWritable(PER_TARGET_COVERAGE);

    final SAMFileReader samReader = new SAMFileReader(INPUT);

    final File probeIntervals = getProbeIntervals();

    // Validate that the targets and baits have the same references as the reads file
    SequenceUtil.assertSequenceDictionariesEqual(
        samReader.getFileHeader().getSequenceDictionary(),
        IntervalList.fromFile(TARGET_INTERVALS).getHeader().getSequenceDictionary(),
        INPUT,
        TARGET_INTERVALS);
    SequenceUtil.assertSequenceDictionariesEqual(
        samReader.getFileHeader().getSequenceDictionary(),
        IntervalList.fromFile(probeIntervals).getHeader().getSequenceDictionary(),
        INPUT,
        probeIntervals);

    ReferenceSequenceFile ref = null;
    if (REFERENCE_SEQUENCE != null) {
      IoUtil.assertFileIsReadable(REFERENCE_SEQUENCE);
      ref = ReferenceSequenceFileFactory.getReferenceSequenceFile(REFERENCE_SEQUENCE);
      SequenceUtil.assertSequenceDictionariesEqual(
          samReader.getFileHeader().getSequenceDictionary(),
          ref.getSequenceDictionary(),
          INPUT,
          REFERENCE_SEQUENCE);
    }

    final TargetMetricsCollector collector =
        makeCollector(
            METRIC_ACCUMULATION_LEVEL,
            samReader.getFileHeader().getReadGroups(),
            ref,
            PER_TARGET_COVERAGE,
            TARGET_INTERVALS,
            probeIntervals,
            getProbeSetName());

    // Add each record to the requested collectors
    final Iterator<SAMRecord> records = samReader.iterator();
    final ProgressLogger progress = new ProgressLogger(log);

    while (records.hasNext()) {
      final SAMRecord sam = records.next();
      collector.acceptRecord(sam, null);
      progress.record(sam);
    }

    // Write the output file
    final MetricsFile<HsMetrics, Integer> metrics = getMetricsFile();
    collector.finish();

    collector.addAllLevelsToFile(metrics);

    metrics.write(OUTPUT);

    return 0;
  }
예제 #3
0
파일: PhasingUtils.java 프로젝트: nh13/gatk
  static VariantContext reallyMergeIntoMNP(
      VariantContext vc1, VariantContext vc2, ReferenceSequenceFile referenceFile) {
    int startInter = vc1.getEnd() + 1;
    int endInter = vc2.getStart() - 1;
    byte[] intermediateBases = null;
    if (startInter <= endInter) {
      intermediateBases =
          referenceFile.getSubsequenceAt(vc1.getChr(), startInter, endInter).getBases();
      StringUtil.toUpperCase(intermediateBases);
    }
    MergedAllelesData mergeData =
        new MergedAllelesData(
            intermediateBases, vc1, vc2); // ensures that the reference allele is added

    GenotypesContext mergedGenotypes = GenotypesContext.create();
    for (final Genotype gt1 : vc1.getGenotypes()) {
      Genotype gt2 = vc2.getGenotype(gt1.getSampleName());

      List<Allele> site1Alleles = gt1.getAlleles();
      List<Allele> site2Alleles = gt2.getAlleles();

      List<Allele> mergedAllelesForSample = new LinkedList<Allele>();

      /* NOTE: Since merged alleles are added to mergedAllelesForSample in the SAME order as in the input VC records,
        we preserve phase information (if any) relative to whatever precedes vc1:
      */
      Iterator<Allele> all2It = site2Alleles.iterator();
      for (Allele all1 : site1Alleles) {
        Allele all2 = all2It.next(); // this is OK, since allSamplesAreMergeable()

        Allele mergedAllele = mergeData.ensureMergedAllele(all1, all2);
        mergedAllelesForSample.add(mergedAllele);
      }

      double mergedGQ = Math.max(gt1.getLog10PError(), gt2.getLog10PError());
      Set<String> mergedGtFilters =
          new HashSet<
              String>(); // Since gt1 and gt2 were unfiltered, the Genotype remains unfiltered

      Map<String, Object> mergedGtAttribs = new HashMap<String, Object>();
      PhaseAndQuality phaseQual = calcPhaseForMergedGenotypes(gt1, gt2);
      if (phaseQual.PQ != null) mergedGtAttribs.put(ReadBackedPhasingWalker.PQ_KEY, phaseQual.PQ);

      Genotype mergedGt =
          new Genotype(
              gt1.getSampleName(),
              mergedAllelesForSample,
              mergedGQ,
              mergedGtFilters,
              mergedGtAttribs,
              phaseQual.isPhased);
      mergedGenotypes.add(mergedGt);
    }

    String mergedName = mergeVariantContextNames(vc1.getSource(), vc2.getSource());
    double mergedLog10PError = Math.min(vc1.getLog10PError(), vc2.getLog10PError());
    Set<String> mergedFilters =
        new HashSet<
            String>(); // Since vc1 and vc2 were unfiltered, the merged record remains unfiltered
    Map<String, Object> mergedAttribs = mergeVariantContextAttributes(vc1, vc2);

    // ids
    List<String> mergedIDs = new ArrayList<String>();
    if (vc1.hasID()) mergedIDs.add(vc1.getID());
    if (vc2.hasID()) mergedIDs.add(vc2.getID());
    String mergedID =
        mergedIDs.isEmpty()
            ? VCFConstants.EMPTY_ID_FIELD
            : Utils.join(VCFConstants.ID_FIELD_SEPARATOR, mergedIDs);

    VariantContextBuilder mergedBuilder =
        new VariantContextBuilder(
                mergedName,
                vc1.getChr(),
                vc1.getStart(),
                vc2.getEnd(),
                mergeData.getAllMergedAlleles())
            .id(mergedID)
            .genotypes(mergedGenotypes)
            .log10PError(mergedLog10PError)
            .filters(mergedFilters)
            .attributes(mergedAttribs);
    VariantContextUtils.calculateChromosomeCounts(mergedBuilder, true);
    return mergedBuilder.make();
  }