Examples with DuplicateReadFilter htsjdk.samtools.filter.DuplicateReadFilter used on opensource projects

Example 6 with DuplicateReadFilter

use of htsjdk.samtools.filter.DuplicateReadFilter in project gatk by broadinstitute.

the class BayesianHetPulldownCalculator method getSamLocusIteratorWithDefaultFilters.

/**
     * Returns a {@link SamLocusIterator} object for a given {@link SamReader} and {@link IntervalList} with filters
     * on minimum base quality and minimum mapping quality
     *
     * @param samReader a SamReader object
     * @return a SamLocusIterator object
     */
private SamLocusIterator getSamLocusIteratorWithDefaultFilters(final SamReader samReader) {
    final SamLocusIterator locusIterator = new SamLocusIterator(samReader, snpIntervals, false);
    /* set read and locus filters */
    final List<SamRecordFilter> samFilters = Arrays.asList(new NotPrimaryAlignmentFilter(), new DuplicateReadFilter());
    locusIterator.setSamFilters(samFilters);
    locusIterator.setEmitUncoveredLoci(false);
    locusIterator.setIncludeNonPfReads(false);
    locusIterator.setMappingQualityScoreCutoff(minMappingQuality);
    locusIterator.setQualityScoreCutoff(minBaseQuality);
    return locusIterator;
}

Example 7 with DuplicateReadFilter

use of htsjdk.samtools.filter.DuplicateReadFilter in project gatk by broadinstitute.

the class HetPulldownCalculator method getHetPulldown.

/**
     * For a normal or tumor sample, returns a data structure giving (intervals, reference counts, alternate counts),
     * where intervals give positions of likely heterozygous SNP sites.
     *
     * <p>
     *     For a normal sample:
     *     <ul>
     *         The IntervalList snpIntervals gives common SNP sites in 1-based format.
     *     </ul>
     *     <ul>
     *         The p-value threshold must be specified for a two-sided binomial test,
     *         which is used to determine SNP sites from snpIntervals that are
     *         compatible with a heterozygous SNP, given the sample.  Only these sites are output.
     *     </ul>
     * </p>
     * <p>
     *     For a tumor sample:
     *     <ul>
     *         The IntervalList snpIntervals gives heterozygous SNP sites likely to be present in the normal sample.
     *         This should be from {@link HetPulldownCalculator#getNormal} in 1-based format.
     *         Only these sites are output.
     *     </ul>
     * </p>
     * @param bamFile           sorted BAM file for sample
     * @param snpIntervals      IntervalList of SNP sites
     * @param sampleType        flag indicating type of sample (SampleType.NORMAL or SampleType.TUMOR)
     *                          (determines whether to perform binomial test)
     * @param pvalThreshold     p-value threshold for two-sided binomial test, used for normal sample
     * @param minimumRawReads   minimum number of total reads that must be present at a het site
     * @return                  Pulldown of heterozygous SNP sites in 1-based format
     */
private Pulldown getHetPulldown(final File bamFile, final IntervalList snpIntervals, final SampleType sampleType, final double pvalThreshold, final int minimumRawReads) {
    try (final SamReader bamReader = SamReaderFactory.makeDefault().validationStringency(validationStringency).referenceSequence(refFile).open(bamFile);
        final ReferenceSequenceFileWalker refWalker = new ReferenceSequenceFileWalker(refFile)) {
        if (bamReader.getFileHeader().getSortOrder() != SAMFileHeader.SortOrder.coordinate) {
            throw new UserException.BadInput("BAM file " + bamFile.toString() + " must be coordinate sorted.");
        }
        final Pulldown hetPulldown = new Pulldown(bamReader.getFileHeader());
        final int totalNumberOfSNPs = snpIntervals.size();
        final SamLocusIterator locusIterator = new SamLocusIterator(bamReader, snpIntervals, totalNumberOfSNPs < MAX_INTERVALS_FOR_INDEX);
        //set read and locus filters [note: read counts match IGV, but off by a few from pysam.mpileup]
        final List<SamRecordFilter> samFilters = Arrays.asList(new NotPrimaryAlignmentFilter(), new DuplicateReadFilter());
        locusIterator.setSamFilters(samFilters);
        locusIterator.setEmitUncoveredLoci(false);
        locusIterator.setIncludeNonPfReads(false);
        locusIterator.setMappingQualityScoreCutoff(minMappingQuality);
        locusIterator.setQualityScoreCutoff(minBaseQuality);
        logger.info("Examining " + totalNumberOfSNPs + " sites in total...");
        int locusCount = 0;
        for (final SamLocusIterator.LocusInfo locus : locusIterator) {
            if (locusCount % NUMBER_OF_SITES_PER_LOGGED_STATUS_UPDATE == 0) {
                logger.info("Examined " + locusCount + " covered sites.");
            }
            locusCount++;
            //include N, etc. reads here
            final int totalReadCount = locus.getRecordAndOffsets().size();
            if (totalReadCount < minimumRawReads) {
                continue;
            }
            final Nucleotide.Counter baseCounts = getPileupBaseCounts(locus);
            //only include total ACGT counts in binomial test (exclude N, etc.)
            final int totalBaseCount = Arrays.stream(BASES).mapToInt(b -> (int) baseCounts.get(b)).sum();
            if (sampleType == SampleType.NORMAL && !isPileupHetCompatible(baseCounts, totalBaseCount, pvalThreshold)) {
                continue;
            }
            final Nucleotide refBase = Nucleotide.valueOf(refWalker.get(locus.getSequenceIndex()).getBases()[locus.getPosition() - 1]);
            final int refReadCount = (int) baseCounts.get(refBase);
            final int altReadCount = totalBaseCount - refReadCount;
            hetPulldown.add(new AllelicCount(new SimpleInterval(locus.getSequenceName(), locus.getPosition(), locus.getPosition()), refReadCount, altReadCount));
        }
        logger.info(locusCount + " covered sites out of " + totalNumberOfSNPs + " total sites were examined.");
        return hetPulldown;
    } catch (final IOException | SAMFormatException e) {
        throw new UserException(e.getMessage());
    }
}