Java IntervalList类代码示例

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
/**
 * Prepare to iterate through the given SAM records, skipping non-primary alignments
 *
 * @param samReader    must be coordinate sorted
 * @param intervalList Either the list of desired intervals, or null.  Note that if an intervalList is
 *                     passed in that is not coordinate sorted, it will eventually be coordinated sorted by this class.
 * @param useIndex     If true, do indexed lookup to improve performance.  Not relevant if intervalList == null.
 *                     It is no longer the case the useIndex==true can make performance worse.  It should always perform at least
 *                     as well as useIndex==false, and generally will be much faster.
 */
public SamLocusIterator(final SamReader samReader, final IntervalList intervalList, final boolean useIndex) {
    //if (samReader.getFileHeader().getSortOrder() == null || samReader.getFileHeader().getSortOrder() == SAMFileHeader.SortOrder.unsorted) {
    //   LOG.warn("SamLocusIterator constructed with samReader that has SortOrder == unsorted.  ", "" +
    //            "Assuming SAM is coordinate sorted, but exceptions may occur if it is not.");
    //} else if (samReader.getFileHeader().getSortOrder() != SAMFileHeader.SortOrder.coordinate) {
    //    throw new SAMException("SamLocusIterator cannot operate on a SAM file that is not coordinate sorted.");
    //}
    this.samReader = samReader;
    this.useIndex = useIndex;
    if (intervalList != null) {
        intervals = intervalList.uniqued().getIntervals();
        this.referenceSequenceMask = new IntervalListReferenceSequenceMask(intervalList);
    } else {
        intervals = null;
        this.referenceSequenceMask = new WholeGenomeReferenceSequenceMask(samReader.getFileHeader());
    }
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
/**
 * The normal-only workflow
 */
private void runNormalOnly() {
    final BayesianHetPulldownCalculator normalHetPulldownCalculator;
    final Pulldown normalHetPulldown;

    normalHetPulldownCalculator = new BayesianHetPulldownCalculator(REFERENCE_ARGUMENTS.getReferenceFile(),
            IntervalList.fromFile(snpFile), minimumMappingQuality, minimumBaseQuality, readDepthThreshold,
            VALIDATION_STRINGENCY, errorProbabilityAdjustmentFactor,
            new BalancedHeterozygousPileupPriorModel());

    logger.info("Calculating the Het pulldown from the normal BAM file using the BALANCED prior...");
    normalHetPulldown = normalHetPulldownCalculator.getHetPulldown(normalBamFile, hetCallingStringency);

    logger.info("Writing Het pulldown from normal reads to " + normalHetOutputFile.toString());
    normalHetPulldown.write(normalHetOutputFile, AllelicCountTableColumn.AllelicCountTableVerbosity.FULL);
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
/**
 * The tumor-only workflow
 */
private void runTumorOnly() {
    final BayesianHetPulldownCalculator tumorHetPulldownCalculator;
    final Pulldown tumorHetPulldown;

    tumorHetPulldownCalculator = new BayesianHetPulldownCalculator(REFERENCE_ARGUMENTS.getReferenceFile(),
            IntervalList.fromFile(snpFile), minimumMappingQuality, minimumBaseQuality, readDepthThreshold,
            VALIDATION_STRINGENCY, errorProbabilityAdjustmentFactor,
            new HeterogeneousHeterozygousPileupPriorModel(minimumAbnormalFraction, maximumAbnormalFraction,
                    maximumCopyNumber, quadratureOrder));

    logger.info("Calculating the Het pulldown from the tumor BAM file using the HETEROGENEOUS prior...");
    tumorHetPulldown = tumorHetPulldownCalculator.getHetPulldown(tumorBamFile, hetCallingStringency);

    logger.info("Writing Het pulldown from tumor reads to " + tumorHetOutputFile.toString());
    tumorHetPulldown.write(tumorHetOutputFile, AllelicCountTableColumn.AllelicCountTableVerbosity.FULL);
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
/**
 * Constructor of {@link BayesianHetPulldownCalculator} object
 *
 * @param refFile the reference genome file
 * @param snpIntervals {@link IntervalList} of common SNPs
 * @param minMappingQuality minimum phred mapping quality
 * @param minBaseQuality minimum phred base quality
 * @param readDepthThreshold minimum read depth
 * @param validationStringency validation stringency
 * @param errorProbabilityAdjustmentFactor (experimental) multiplicative factor for read and mapping error
 *                                         probabilities
 * @param hetPrior the prior model for heterzygous pileups
 */
public BayesianHetPulldownCalculator(final File refFile, final IntervalList snpIntervals,
                                     final int minMappingQuality, final int minBaseQuality,
                                     final int readDepthThreshold, final ValidationStringency validationStringency,
                                     final double errorProbabilityAdjustmentFactor,
                                     final HeterozygousPileupPriorModel hetPrior) {
    ParamUtils.isPositiveOrZero(minMappingQuality, "Minimum mapping quality must be nonnegative.");
    ParamUtils.isPositiveOrZero(minBaseQuality, "Minimum base quality must be nonnegative.");

    this.refFile = Utils.nonNull(refFile);
    this.snpIntervals = Utils.nonNull(snpIntervals);
    this.minMappingQuality = ParamUtils.isPositive(minMappingQuality, "Minimum mapping quality must be a positive integer");
    this.minBaseQuality = ParamUtils.isPositive(minBaseQuality, "Minimum base quality must be a positive integer");
    this.readDepthThreshold = ParamUtils.isPositive(readDepthThreshold, "Read depth threshold must be a positive integer");
    this.validationStringency = Utils.nonNull(validationStringency);
    this.errorProbabilityAdjustmentFactor = ParamUtils.isPositive(errorProbabilityAdjustmentFactor,
            "Error adjustment factor must be positive.");
    this.hetPrior = Utils.nonNull(hetPrior);
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
@Override
protected Object doWork() {
    validateArguments();

    final File referenceFile = referenceArguments.getReferenceFile();
    final IntervalList siteIntervals = IntervalList.fromFile(inputSiteIntervalsFile);

    final AllelicCountCollector allelicCountCollector = new AllelicCountCollector(referenceFile, readValidationStringency);

    logger.info("Collecting allelic counts...");
    final AllelicCountCollection allelicCounts = allelicCountCollector.collect(inputBAMFile, siteIntervals, minimumMappingQuality, minimumBaseQuality);
    allelicCounts.write(outputAllelicCountsFile);
    logger.info("Allelic counts written to " + outputAllelicCountsFile.toString());

    return "SUCCESS";
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
@Override
public void onTraversalStart() {
    ParamUtils.isPositive(scatterCount, "scatter count must be > 0.");

    if (!outputDir.exists() && !outputDir.mkdir()) {
        throw new RuntimeIOException("Unable to create directory: " + outputDir.getAbsolutePath());
    }

    // in general dictionary will be from the reference, but using -I reads.bam or -F variants.vcf
    // to use the sequence dict from a bam or vcf is also supported
    final SAMSequenceDictionary sequenceDictionary = getBestAvailableSequenceDictionary();

    final List<SimpleInterval> intervals = hasIntervals() ? intervalArgumentCollection.getIntervals(sequenceDictionary)
            : IntervalUtils.getAllIntervalsForReference(sequenceDictionary);

    final IntervalList intervalList = new IntervalList(sequenceDictionary);
    intervals.stream().map(si -> new Interval(si.getContig(), si.getStart(), si.getEnd())).forEach(intervalList::add);
    final IntervalListScatterer scatterer = new IntervalListScatterer(subdivisionMode);
    final List<IntervalList> scattered = scatterer.scatter(intervalList, scatterCount, false);

    final DecimalFormat formatter = new DecimalFormat("0000");
    IntStream.range(0, scattered.size()).forEach(n -> scattered.get(n).write(new File(outputDir, formatter.format(n) + "-scattered.intervals")));
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
@DataProvider(name = "inputGetTumorHetPulldown")
public Object[][] inputGetTumorHetPulldown() {
    final Pulldown tumorHetPulldown = new Pulldown(normalHeader);
    tumorHetPulldown.add(new AllelicCount(new SimpleInterval("1", 11522, 11522), 7, 4));
    tumorHetPulldown.add(new AllelicCount(new SimpleInterval("1", 12098, 12098), 8, 6));
    tumorHetPulldown.add(new AllelicCount(new SimpleInterval("1", 14630, 14630), 9, 8));
    tumorHetPulldown.add(new AllelicCount(new SimpleInterval("2", 14689, 14689), 6, 9));
    tumorHetPulldown.add(new AllelicCount(new SimpleInterval("2", 14982, 14982), 6, 5));

    final IntervalList normalHetIntervals = new IntervalList(tumorHeader);
    normalHetIntervals.add(new Interval("1", 11522, 11522));
    normalHetIntervals.add(new Interval("1", 12098, 12098));
    normalHetIntervals.add(new Interval("1", 14630, 14630));
    normalHetIntervals.add(new Interval("2", 14689, 14689));
    normalHetIntervals.add(new Interval("2", 14982, 14982));

    return new Object[][]{
            {normalHetIntervals, tumorHetPulldown}
    };
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
public RawWgsMetrics(final IntervalList intervals,
                     final Histogram<Integer> highQualityDepthHistogram,
                     final Histogram<Integer> unfilteredDepthHistogram,
                     final double pctExcludedByMapq,
                     final double pctExcludedByDupes,
                     final double pctExcludedByPairing,
                     final double pctExcludedByBaseq,
                     final double pctExcludedByOverlap,
                     final double pctExcludedByCapping,
                     final double pctTotal,
                     final int coverageCap,
                     final Histogram<Integer> unfilteredBaseQHistogram,
                     final int sampleSize) {
    super(intervals, highQualityDepthHistogram, unfilteredDepthHistogram, pctExcludedByMapq, pctExcludedByDupes, pctExcludedByPairing, pctExcludedByBaseq,
            pctExcludedByOverlap, pctExcludedByCapping, pctTotal, coverageCap, unfilteredBaseQHistogram, sampleSize);
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
public HsMetricCollector(final Set<MetricAccumulationLevel> accumulationLevels,
                         final List<SAMReadGroupRecord> samRgRecords,
                         final ReferenceSequenceFile refFile,
                         final File perTargetCoverage,
                         final File perBaseCoverage,
                         final IntervalList targetIntervals,
                         final IntervalList probeIntervals,
                         final String probeSetName,
                         final int nearProbeDistance,
                         final int minimumMappingQuality,
                         final int minimumBaseQuality,
                         final boolean clipOverlappingReads,
                         final int coverageCap,
                         final int sampleSize) {
    super(accumulationLevels, samRgRecords, refFile, perTargetCoverage, perBaseCoverage, targetIntervals, probeIntervals, probeSetName, nearProbeDistance, minimumMappingQuality, minimumBaseQuality, clipOverlappingReads, coverageCap, sampleSize);
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
public static OverlapDetector<Interval> makeOverlapDetector(final File samFile, final SAMFileHeader header, final File ribosomalIntervalsFile, final Log log) {

        final OverlapDetector<Interval> ribosomalSequenceOverlapDetector = new OverlapDetector<Interval>(0, 0);
        if (ribosomalIntervalsFile != null) {

            final IntervalList ribosomalIntervals = IntervalList.fromFile(ribosomalIntervalsFile);
            if (ribosomalIntervals.size() == 0) {
                log.warn("The RIBOSOMAL_INTERVALS file, " + ribosomalIntervalsFile.getAbsolutePath() + " does not contain intervals");
            }
            try {
                SequenceUtil.assertSequenceDictionariesEqual(header.getSequenceDictionary(), ribosomalIntervals.getHeader().getSequenceDictionary());
            } catch (SequenceUtil.SequenceListsDifferException e) {
                throw new PicardException("Sequence dictionaries differ in " + samFile.getAbsolutePath() + " and " + ribosomalIntervalsFile.getAbsolutePath(),
                        e);
            }
            final IntervalList uniquedRibosomalIntervals = ribosomalIntervals.uniqued();
            final List<Interval> intervals = uniquedRibosomalIntervals.getIntervals();
            ribosomalSequenceOverlapDetector.addAll(intervals, intervals);
        }
        return ribosomalSequenceOverlapDetector;
    }
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
public TargetMetricsCollector(final Set<MetricAccumulationLevel> accumulationLevels,
                              final List<SAMReadGroupRecord> samRgRecords,
                              final ReferenceSequenceFile refFile,
                              final File perTargetCoverage,
                              final File perBaseCoverage,
                              final IntervalList targetIntervals,
                              final IntervalList probeIntervals,
                              final String probeSetName,
                              final int nearProbeDistance,
                              final int minimumMappingQuality,
                              final int minimumBaseQuality,
                              final boolean clipOverlappingReads,
                              final int coverageCap,
                              final int sampleSize) {
    this(accumulationLevels, samRgRecords, refFile, perTargetCoverage, perBaseCoverage, targetIntervals, probeIntervals, probeSetName, nearProbeDistance, minimumMappingQuality, minimumBaseQuality, clipOverlappingReads, false, coverageCap, sampleSize);
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
public TargetedPcrMetricsCollector(final Set<MetricAccumulationLevel> accumulationLevels,
                                   final List<SAMReadGroupRecord> samRgRecords,
                                   final ReferenceSequenceFile refFile,
                                   final File perTargetCoverage,
                                   final File perBaseCoverage,
                                   final IntervalList targetIntervals,
                                   final IntervalList probeIntervals,
                                   final String probeSetName,
                                   final int nearProbeDistance,
                                   final int minimumMappingQuality,
                                   final int minimumBaseQuality,
                                   final boolean clipOverlappingReads,
                                   final int coverageCap,
                                   final int sampleSize) {
    super(accumulationLevels, samRgRecords, refFile, perTargetCoverage, perBaseCoverage, targetIntervals, probeIntervals, probeSetName, nearProbeDistance, minimumMappingQuality, minimumBaseQuality, clipOverlappingReads, coverageCap, sampleSize);
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
public WgsMetricsWithNonZeroCoverage(final IntervalList intervals,
                                     final Histogram<Integer> highQualityDepthHistogram,
                                     final Histogram<Integer> unfilteredDepthHistogram,
                                     final double pctExcludedByMapq,
                                     final double pctExcludedByDupes,
                                     final double pctExcludedByPairing,
                                     final double pctExcludedByBaseq,
                                     final double pctExcludedByOverlap,
                                     final double pctExcludedByCapping,
                                     final double pctTotal,
                                     final int coverageCap,
                                     final Histogram<Integer> unfilteredBaseQHistogram,
                                     final int sampleSize) {
    super(intervals, highQualityDepthHistogram, unfilteredDepthHistogram, pctExcludedByMapq, pctExcludedByDupes, pctExcludedByPairing, pctExcludedByBaseq,
            pctExcludedByOverlap, pctExcludedByCapping, pctTotal, coverageCap, unfilteredBaseQHistogram, sampleSize);
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
/** Factory method to create both a SNP bitmask and an indel bitmask in a single pass of the VCF.
 * If intervals are given, consider only SNP and indel sites that overlap the intervals.  If log is given,
 * progress loading the variants will be written to the log. */
public static DbSnpBitSets createSnpAndIndelBitSets(final File dbSnpFile,
                                                    final SAMSequenceDictionary sequenceDictionary,
                                                    final IntervalList intervals,
                                                    final Optional<Log> log) {

    final DbSnpBitSets sets = new DbSnpBitSets();
    sets.snps   = new DbSnpBitSetUtil();
    sets.indels = new DbSnpBitSetUtil();

    final Map<DbSnpBitSetUtil, Set<VariantType>> map = new HashMap<>();
    map.put(sets.snps,   EnumSet.of(VariantType.SNP));
    map.put(sets.indels, EnumSet.of(VariantType.insertion, VariantType.deletion));
    loadVcf(dbSnpFile, sequenceDictionary, map, intervals, log);
    return sets;
}
 

import htsjdk.samtools.util.IntervalList; //导入依赖的package包/类
@Override
protected int doWork() {
    IOUtil.assertFileIsReadable(INPUT);
    IOUtil.assertFileIsWritable(OUTPUT);

    IntervalList intervals = IntervalList.fromFile(INPUT);
    if (SORT) intervals = intervals.sorted();

    try {
        final BufferedWriter out = IOUtil.openFileForBufferedWriting(OUTPUT);
        for (final Interval i : intervals) {
            final String strand = i.isNegativeStrand() ? "-" : "+";
            final List<?> fields = CollectionUtil.makeList(i.getContig(), i.getStart()-1, i.getEnd(), i.getName(), SCORE, strand);
            out.append(fields.stream().map(String::valueOf).collect(Collectors.joining("\t")));
            out.newLine();
        }

        out.close();
    }
    catch (IOException ioe) {
        throw new RuntimeIOException(ioe);
    }

    return 0;
}