Java SAMSequenceDictionary类代码示例

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
public static StaticData getStaticDataInstance(RefContigInfo refContigInfo,
                                               boolean useGVCF,
                                               SamHeaderInfo samHeaderInfo,
                                               VcfHeaderInfo vcfHeaderInfo) {
    StaticData data = new StaticData();
    SAMSequenceDictionary samSequenceDictionary = SAMSequenceDictTransfer.transfer(refContigInfo);
    data.genomeLocParser = new GenomeLocParser(samSequenceDictionary);
    samHeaderInfo.addReadGroupInfo(ReadGroupInfo.apply("rg1", "sample1"));
    SAMFileHeader header = SAMHeaderTransfer.transfer(samHeaderInfo);
    List<SAMReadGroupRecord> readGroupInfos = header.getReadGroups();
    List<String> samples = new ArrayList<>();
    for (SAMReadGroupRecord readGroup : readGroupInfos) {
        samples.add(readGroup.getSample());
    }
    data.haplotypeCaller = new HaplotypeCaller(data.genomeLocParser, samples, useGVCF);
    data.basic2SAMRecordTransfer = new Basic2SAMRecordTransfer(header);

    VCFCodec codec = new VCFCodec();
    VCFHeaderLineIterable headerLineIterable = new VCFHeaderLineIterable(vcfHeaderInfo);
    data.vcfFileHeader = (VCFHeader) codec.readActualHeader(headerLineIterable);
    data.codec = codec;
    return data;
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
public static List<String> getRecalTableLines(RefContigInfo refContigInfo,
                                              SamRecordPartition samRecordPartition,
                                              FastaPartition refPartition,
                                              List<VcfRecordPartition> rodPartitions) {
    SAMSequenceDictionary samSequenceDictionary = SAMSequenceDictTransfer.transfer(refContigInfo);
    GenomeLocParser parser = new GenomeLocParser(samSequenceDictionary);

    SamContentProvider samContentProvider = new SamContentProvider(samRecordPartition);
    RefContentProvider refContentProvider = new RefContentProvider(samSequenceDictionary, refPartition);

    List<RODContentProvider> rodContentProviders = new java.util.ArrayList<>();
    rodPartitions.forEach(
            rodPartition -> rodContentProviders.add(
                    new RODContentProvider(RODNames.KNOWN_ALLELES + rodPartition.key(), rodPartition, parser))
    );

    // 生成recal table
    BaseRecalibrator baseRecalibrator = new BaseRecalibrator(
            parser, refContentProvider, samContentProvider, rodContentProviders);
    baseRecalibrator.run();

    GATKReport bqsrTable = baseRecalibrator.getReport();

    return GATKReportTransfer.report2Lines(bqsrTable);
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
public static final int compareLocatables(GenomeLocation first, GenomeLocation second, SAMSequenceDictionary dictionary) {
    Utils.nonNull(first);
    Utils.nonNull(second);
    Utils.nonNull(dictionary);

    int result = 0;
    if(first != second) {
        // compare the contigs
        result = compareContigs(first, second, dictionary);
        if (result == 0) {
            // compare start position
            result = Integer.compare(first.getStart(), second.getStart());
            if (result == 0) {
                // compare end position
                result = Integer.compare(first.getStop(), second.getStop());
            }
        }
    }
    return result;
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
public void writeOutRecalibrationTable(final VariantContextWriter recalWriter,
		final SAMSequenceDictionary seqDictionary) {
	// we need to sort in coordinate order in order to produce a valid VCF
	Collections.sort(data, VariantDatum.getComparator(seqDictionary));

	// create dummy alleles to be used
	List<Allele> alleles = Arrays.asList(Allele.create("N", true), Allele.create("<VQSR>", false));

	for (final VariantDatum datum : data) {
		if (VRAC.useASannotations)
			alleles = Arrays.asList(datum.referenceAllele, datum.alternateAllele); 
		VariantContextBuilder builder = new VariantContextBuilder("VQSR", datum.loc.getContig(),
				datum.loc.getStart(), datum.loc.getStop(), alleles);
		builder.attribute(VCFConstants.END_KEY, datum.loc.getStop());
		builder.attribute(GaeaVCFConstants.VQS_LOD_KEY, String.format("%.4f", datum.lod));
		builder.attribute(GaeaVCFConstants.CULPRIT_KEY,
				(datum.worstAnnotation != -1 ? annotationKeys.get(datum.worstAnnotation) : "NULL"));

		if (datum.atTrainingSite)
			builder.attribute(GaeaVCFConstants.POSITIVE_LABEL_KEY, true);
		if (datum.atAntiTrainingSite)
			builder.attribute(GaeaVCFConstants.NEGATIVE_LABEL_KEY, true);

		recalWriter.add(builder.make());
	}
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
public static VariantContextWriter createVCFWriter(final File outFile,
		final SAMSequenceDictionary referenceDictionary, final boolean createMD5, final Options... options) {
	Utils.nonNull(outFile);

	VariantContextWriterBuilder vcWriterBuilder = new VariantContextWriterBuilder().clearOptions()
			.setOutputFile(outFile);

	if (createMD5) {
		vcWriterBuilder.setCreateMD5();
	}

	if (null != referenceDictionary) {
		vcWriterBuilder = vcWriterBuilder.setReferenceDictionary(referenceDictionary);
	}

	for (Options opt : options) {
		vcWriterBuilder = vcWriterBuilder.setOption(opt);
	}

	return vcWriterBuilder.build();
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
static void parseGFF(File gffFile, File outfile, String genome, String genomeFile) {		
	
		try {
			
			SAMSequenceDictionary dict = ReadDict(new File(genomeFile));				
			
			FileRead.readGFF(gffFile, outfile.getCanonicalPath(), dict);
		}
		catch(Exception e) {
			e.printStackTrace();
		}
		/*	Main.addGenome
			Main.genomehash.get(genome).add(outfile);	
			JMenuItem additem = new JMenuItem(outfile.getName().substring(0,outfile.getName().indexOf(".gff")));
			additem.setName(outfile.getName().substring(0,outfile.getName().indexOf(".gff")));
			additem.addMouseListener(Main.frame);
			Main.addMenu.add(additem);
			
			break;
		*/
		
	
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
private void addIntervalFeatureTrackFromVCF(String sourceName, GenomicCoords gc, String trackTag) throws ClassNotFoundException, IOException, InvalidGenomicCoordsException, InvalidRecordException, SQLException {
	
	int idForTrack= this.getNextTrackId();
	// String trackId= new File(sourceName).getName() + "#" + idForTrack;
	String trackId= sourceName + "#" + idForTrack;
	
	// If this VCF file has sequence dictionary, check the coordinates in gc are compatible
	// If they are not, throw an exception which force resetting the coords.
	SAMSequenceDictionary seqDict = Utils.getVCFHeader(sourceName).getSequenceDictionary();
	
	if(seqDict != null && seqDict.getSequence(gc.getChrom()) == null){
		throw new InvalidGenomicCoordsException();
	}
	TrackIntervalFeature tif= new TrackIntervalFeature(sourceName, gc);
	tif.setTrackTag(trackId);
	this.trackList.add(tif);
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
private boolean setSamSeqDictFromBam(String bamfile) {

		/*  ------------------------------------------------------ */
		/* This chunk prepares SamReader from local bam            */
		SamReaderFactory srf=SamReaderFactory.make();
		srf.validationStringency(ValidationStringency.SILENT);
		SamReader samReader;
		samReader= srf.open(new File(bamfile));
		/*  ------------------------------------------------------ */
		
		SAMSequenceDictionary seqDict = samReader.getFileHeader().getSequenceDictionary();
		if(seqDict != null && !seqDict.isEmpty()){
			this.setSamSeqDictSource(new File(bamfile).getAbsolutePath());
			this.setSamSeqDict(seqDict);
			return true;
		}
		return false;
	}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
/** Return true if the GenomicCoords object is valid given the SAMSequenceDictionary. I.e.
 * gc contig and position is part of the dictionary.   
 * */
private boolean isValidPosition(GenomicCoords gc, SAMSequenceDictionary samSeqDict){

	if(samSeqDict == null || gc == null){
		return true;
	}
	
	HashMap<String, Integer> chromLen= new HashMap<String, Integer>();
	for(SAMSequenceRecord x : gc.getSamSeqDict().getSequences()){
		chromLen.put(x.getSequenceName(), x.getSequenceLength());
	}
	boolean isValid= false;
	if( chromLen.containsKey(gc.getChrom()) ){
		int len= chromLen.get(gc.getChrom());
		if(gc.getTo() <= len){
			isValid= true; 
		}
	} 
	return isValid;
	
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
@Override
public Map<String, Object> encodeAll(OutputStream outputStream, Iterator<? extends VCFVariant> features) throws IOException {

    SAMSequenceDictionary seqDict = new SAMSequenceDictionary();
    EnumSet<Options> options = VariantContextWriterFactory.DEFAULT_OPTIONS;
    options.add(Options.ALLOW_MISSING_FIELDS_IN_HEADER);
    options.remove(Options.INDEX_ON_THE_FLY);
    VariantContextWriter writer = VariantContextWriterFactory.create(outputStream, seqDict, options);

    writer.writeHeader(this.header);

    while(features.hasNext()){
        writer.add(features.next().getVariantContext());
    }

    return null;
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
@Override
protected void setupPipeline(final Pipeline pipeline) {
    final ReadsDataflowSource readsSource = new ReadsDataflowSource(bam, pipeline);
    final SAMFileHeader header = readsSource.getHeader();
    final SAMSequenceDictionary sequenceDictionary = header.getSequenceDictionary();
    final List<SimpleInterval> intervals = intervalArgumentCollection.intervalsSpecified() ? intervalArgumentCollection.getIntervals(sequenceDictionary):
            IntervalUtils.getAllIntervalsForReference(sequenceDictionary);

    final PCollectionView<SAMFileHeader> headerPcolView = pipeline.apply(Create.of(header)).apply(View.<SAMFileHeader>asSingleton());

    final PCollection<GATKRead> preads = readsSource.getReadPCollection(intervals);

    final OpticalDuplicateFinder finder = opticalDuplicatesArgumentCollection.READ_NAME_REGEX != null ?
        new OpticalDuplicateFinder(opticalDuplicatesArgumentCollection.READ_NAME_REGEX, opticalDuplicatesArgumentCollection.OPTICAL_DUPLICATE_PIXEL_DISTANCE, null) : null;
    final PCollectionView<OpticalDuplicateFinder> finderPcolView = pipeline.apply(Create.of(finder)).apply(View.<OpticalDuplicateFinder>asSingleton());

    final PCollection<GATKRead> results = preads.apply(new MarkDuplicates(headerPcolView, finderPcolView));

    // TODO: support writing large output files (need a sharded BAM writer)
    SmallBamWriter.writeToFile(pipeline, results, header, outputFile);

    if (metricsFile != null) {
        final PCollection<KV<String,DuplicationMetrics>> metrics = results.apply(new MarkDuplicatesDataflowUtils.GenerateMetricsTransform(headerPcolView));
        MarkDuplicatesDataflowUtils.writeMetricsToFile(pipeline, metrics, header, metricsFile);
    }
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
@Override
protected void setupPipeline(Pipeline pipeline) {
    if (readArguments.getReadFilesNames().size()>1) {
        throw new UserException("Sorry, we only support a single input file for now.");
    }
    final String filename = readArguments.getReadFilesNames().get(0);
    final ReadsDataflowSource readsSource = new ReadsDataflowSource(filename, pipeline);
    final SAMFileHeader header = readsSource.getHeader();
    final PCollectionView<SAMFileHeader> headerView = pipeline.apply(Create.of(header)).apply(View.asSingleton());
    final SAMSequenceDictionary sequenceDictionary = header.getSequenceDictionary();
    final List<SimpleInterval> intervals = intervalArgumentCollection.intervalsSpecified() ? intervalArgumentCollection.getIntervals(sequenceDictionary)
            : IntervalUtils.getAllIntervalsForReference(sequenceDictionary);
    final PCollectionView<BaseRecalOutput> recalInfoSingletonView = BaseRecalOutputSource.loadFileOrRemote(pipeline, BQSR_RECAL_FILE_NAME).apply(View.asSingleton());
    final PCollection<GATKRead> output = readsSource.getReadPCollection(intervals, ValidationStringency.SILENT, false)
            .apply(new ApplyBQSRTransform(headerView, recalInfoSingletonView, bqsrOpts));
    intermediateRemoteBam = OUTPUT;
    if (needsIntermediateCopy()) {
        // The user specified remote execution and provided a local file name. So we're going to have to save to remote storage as a go-between.
        // Note that this may require more permissions
        intermediateRemoteBam = BucketUtils.randomRemotePath(stagingLocation, "temp-applyBqsr-output-", ".bam");
        logger.info("Staging results at " + intermediateRemoteBam);
    }
    SmallBamWriter.writeToFile(pipeline, output, header, intermediateRemoteBam);
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入依赖的package包/类
/**
 * Builds the target collection given the values of user arguments.
 *
 * @throws UserException if there is some inconsistency in user arguments and inputs.
 * @throws GATKException if there was any problem parsing the content of the targets file.
 * @return never {@code null}.
 */
private TargetCollection<Target> resolveTargetCollection() {
    final TargetCollection<Target> result;
    if (targetsFile != null) {
        result = resolveTargetsFromFile();
    } else if (hasIntervals()) {
        final SAMSequenceDictionary sequenceDictionary = getBestAvailableSequenceDictionary();
        final List<SimpleInterval> intervals = intervalArgumentCollection.getIntervals(sequenceDictionary);

        //this constructor automatically generates target names from the intervals
        final List<Target> targets = intervals.stream().map(Target::new).collect(Collectors.toList());
        result = new HashedListTargetCollection<>(targets);
    } else {
        throw new UserException(String.format("You must indicate the set of target as input intervals (e.g. -L target-intervals.list) or a target feature file (e.g. -%s my-targets.tsv) ", TARGET_FILE_SHORT_NAME));
    }
    if (targetOutInfo.requiresUniqueTargetName()) {
        checkAllTargetsHaveName(result);
    }
    return result;
}
 

import htsjdk.samtools.SAMSequenceDictionary; //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.SAMSequenceDictionary; //导入依赖的package包/类
/**
 * Create a VCF or GVCF writer as appropriate, given our arguments
 *
 * @param outputVCF location to which the vcf should be written
 * @param readsDictionary sequence dictionary for the reads
 * @return a VCF or GVCF writer as appropriate, ready to use
 */
public VariantContextWriter makeVCFWriter( final String outputVCF, final SAMSequenceDictionary readsDictionary ) {
    Utils.nonNull(outputVCF);
    Utils.nonNull(readsDictionary);

    VariantContextWriter writer = GATKVariantContextUtils.createVCFWriter(new File(outputVCF), readsDictionary, false);

    if ( hcArgs.emitReferenceConfidence == ReferenceConfidenceMode.GVCF ) {
        try {
            writer = new GVCFWriter(writer, hcArgs.GVCFGQBands, hcArgs.genotypeArgs.samplePloidy);
        } catch ( IllegalArgumentException e ) {
            throw new CommandLineException.BadArgumentValue("GQBands", "are malformed: " + e.getMessage());
        }
    }

    return writer;
}