Java SAMRecordIterator.next方法代码示例

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
@Nullable
private Read getReadFromBamFile(ReadQuery query, Chromosome chromosome, BamFile bamFile) throws IOException {
    try (SamReader reader = bamHelper.makeSamReader(bamFile, Collections.singletonList(chromosome),
                                                    chromosome.getReferenceId())) {
        String chromosomeName = chromosome.getName();
        if (reader.getFileHeader().getSequence(chromosomeName) == null) {
            chromosomeName = Utils.changeChromosomeName(chromosomeName);
        }

        SAMRecordIterator iterator = reader.query(chromosomeName, query.getStartIndex(), query.getEndIndex(),
                                                  true);
        while (iterator.hasNext()) {
            final SAMRecord samRecord = iterator.next();
            if (samRecord.getReadName().equals(query.getName())) {
                BamQueryOption option = new BamQueryOption();
                option.setRefID(chromosome.getReferenceId());
                option.setChromosomeName(chromosome.getName());
                SAMRecordHandler recordHandler = new SAMRecordHandler(query.getStartIndex(), query.getEndIndex(),
                                                                      referenceManager, null, option);
                List<BasePosition> diffBase = recordHandler.computeDifferentBase(samRecord);
                return BamUtil.createExtendedRead(samRecord, diffBase);
            }
        }
    }
    return null;
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
/**
 * Given a SamReader, find all reads within a region (ref:start-end) that span a splice junction and tally the number of times
 * each junction is spanned. Optionally tally the average values of "tallyTagName" tags (eg. NM).
 * 
 * @param reader
 * @param ref
 * @param start
 * @param end
 * @param orient
 * @param minOverlap
 * @param tallyTagName
 * @param separateReadCounts
 * @return
 */
public static SortedMap<GenomeSpan, MappedReadCounter> countJunctions(SamReader reader, String ref, int start, int end, Orientation orient, int minOverlap, String tallyTagName) {
    SAMRecordIterator it = reader.query(ref, start, end, true);
    SortedMap<GenomeSpan, MappedReadCounter> counters = new TreeMap<GenomeSpan, MappedReadCounter>();
    
    while (it.hasNext()) {
        SAMRecord read = it.next();
        if (read.isSecondaryOrSupplementary() || read.getDuplicateReadFlag() || read.getNotPrimaryAlignmentFlag() || read.getReadUnmappedFlag() || read.getSupplementaryAlignmentFlag()) {
            // skip all secondary / duplicate / unmapped reads
            continue;
        }
       
        if (isJunctionSpanning(read)) {
            for (GenomeSpan junction: getJunctionsForRead(read, orient, minOverlap)) {
                if (!counters.containsKey(junction)) {
                    counters.put(junction, new MappedReadCounter(tallyTagName));
                }
                
                counters.get(junction).addRead(read);
            }
        }
    }
    it.close();
    return counters;
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
private void convertFileAndVerifyRecordCount(final int expectedCount,
                   final String fastqFilename1,
                   final String fastqFilename2,
                   final FastqQualityFormat version,
                   final boolean permissiveFormat,
                   final boolean useSequentialFastqs) throws IOException {
    final File samFile = convertFile(fastqFilename1, fastqFilename2, version, permissiveFormat, useSequentialFastqs);
    final SamReader samReader = SamReaderFactory.makeDefault().open(samFile);
    final SAMRecordIterator iterator = samReader.iterator();
    int actualCount = 0;
    while (iterator.hasNext()) {
        iterator.next();
        actualCount++;
    }
    samReader.close();
    Assert.assertEquals(actualCount, expectedCount);
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
private static String compareReads(final File actualSam, final File expectedSam, final ValidationStringency validation, final File reference) throws IOException {
    try(final SamReader reader1 = getReader(actualSam, validation, reference);
        final SamReader reader2 = getReader(expectedSam, validation, reference)) {
        final SAMRecordIterator it1 = reader1.iterator();
        final SAMRecordIterator it2 = reader2.iterator();
        while (it1.hasNext() && it2.hasNext()) {
            final SAMRecord read1 = it1.next();
            final SAMRecord read2 = it2.next();
            final String eqMessage = readsEqualAllowAddingAttributes(read1, read2);
            if (eqMessage != null){
                return eqMessage;
            }
        }
        if (it1.hasNext() || it2.hasNext()) {
            //at least one has no more records (because the while loop is done) and at least one does have records. So we're not equal.
            return "Not the same number of reads";
        }
        return null;
    }
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
private void scanPureJava() throws Exception
{
long start=System.currentTimeMillis();
   final MessageDigest md = MessageDigest.getInstance("MD5");
for(int N=0;N< N_LOOP;++N)
	{
	htsjdk.samtools.SamReader r=htsjdk.samtools.SamReaderFactory.makeDefault().
			validationStringency(ValidationStringency.DEFAULT_STRINGENCY).
			open(bamFile);
	SAMRecordIterator iter=r.iterator();
	while(iter.hasNext())
		{
		SAMRecord rec=iter.next();
		md.digest((rec.getReadName()+rec.getReadString()+rec.getBaseQualityString()+rec.getAlignmentStart()).getBytes());
		}
		
	r.close();
	}
System.out.println("PureJava\t\t\tmd5="+digest(md)+" time="+(System.currentTimeMillis()-start));
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
private SAMRecord getNextRecordToReturn() {
	SAMRecord nextRecord = null;
	if (currentSortedRecords.size() > 0) {
		SamRecordAndChunkIndex currentRecordAndReaderIndex = currentSortedRecords.pollFirst();
		nextRecord = currentRecordAndReaderIndex.getRecord();
		int chunkIndex = currentRecordAndReaderIndex.getChunkIndex();
		SAMRecordIterator currentIter = iters[chunkIndex];
		if (currentIter.hasNext()) {
			SAMRecord nextChunkRecord = currentIter.next();
			if (!currentSortedRecords.add(new SamRecordAndChunkIndex(nextChunkRecord, chunkIndex))) {
				// add this point we know there is a problem just collecting more info before reporting the problem.
				SamRecordAndChunkIndex alreadyContainedRecord = null;
				for (SamRecordAndChunkIndex samRecordAndChunk : currentSortedRecords) {
					if (comparator.compare(samRecordAndChunk.getRecord(), nextChunkRecord) == 0) {
						alreadyContainedRecord = samRecordAndChunk;
					}
				}
				throw new IllegalStateException("Provided comparator does not uniquely identify the records.  Comparator failed on sam record[" + nextChunkRecord.getReadName() + " isReadOne:"
						+ nextChunkRecord.getFirstOfPairFlag() + "] in chunk[" + chunkIndex + "] which matches [" + alreadyContainedRecord.getRecord().getReadName() + " isReadOne:"
						+ alreadyContainedRecord.getRecord().getFirstOfPairFlag() + "] in chunk[" + alreadyContainedRecord.getChunkIndex() + "].");
			}
		}
	}
	return nextRecord;
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
private void scan(final SamReader in) throws IOException
 	{
 	SAMRecordIterator iter=in.iterator();
 	while(iter.hasNext())
{
 		final SAMRecord rec = iter.next();
 		String sampleName= this.partition.getPartion(rec);
 		if(sampleName==null || sampleName.isEmpty()) sampleName="__UNDEFINED_"+this.partition.name().toUpperCase()+"_";
 		
 		Counter<Integer> counter = this.lengths.get(sampleName);
 		if(counter==null) {
 			counter = new Counter<>();
 			 this.lengths.put(sampleName,counter);
 		}
 		final int len = rec.getReadLength();
 		counter.incr(len);
 		this.max_length=Math.max(max_length, len);
 		
}
 	iter.close();
 	}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
private Map<Sequence, List<SAMRecord>> getReadsFromFile(final Chromosome chromosome, final Track<Sequence> track,
                                                        final BamFile bamFile, final List<Sequence> blocks)
        throws IOException {
    final Map<Sequence, List<SAMRecord>> records = new HashMap<>();
    try (SamReader reader = makeSamReader(bamFile, Collections.singletonList(chromosome),
            chromosome.getReferenceId())) {
        LOG.debug(getMessage(MessagesConstants.DEBUG_FILE_OPENING, bamFile.getPath()));
        String chromosomeName = chromosome.getName();
        final int startIndex = track.getStartIndex();
        final int endIndex = track.getEndIndex();

        if (reader.getFileHeader().getSequence(chromosomeName) == null) {
            chromosomeName = Utils.changeChromosomeName(chromosomeName);
        }
        final SAMRecordIterator iterator = reader.queryOverlapping(chromosomeName, startIndex, endIndex);

        LOG.debug(getMessage(MessagesConstants.DEBUG_GET_ITERATOR_QUERY, iterator.toString()));
        while (iterator.hasNext()) {
            final SAMRecord samRecord = iterator.next();
            //if read unmapped
            if (!samRecord.getSAMFlags().contains(SAMFlag.READ_UNMAPPED) && !samRecord.getCigar().isEmpty() &&
                    samRecord.getEnd() > samRecord.getStart()) {
                addRecordToBlock(blocks, records, samRecord);
            }
        }
    }
    return records;
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
private static SAMRecord bufferRecord(final SAMRecordIterator iter, 
		final SAMRecord sam_record,
		final SAMRecord[] buff_record, 
		final float[] as,
		final boolean[] aln,
		final String record_id) {
	// TODO Auto-generated method stub

	final Set<SAMRecord> buffered_records = new HashSet<SAMRecord>();
	buffered_records.add(sam_record);
	SAMRecord tmp_record;
	while( (tmp_record=iter.hasNext()?iter.next():null)!=null && 
			tmp_record.getReadName().equals(record_id)) {
		buffered_records.add(tmp_record);
	}
	Arrays.fill(buff_record, null);
	Arrays.fill(as, -1.0f);
	Arrays.fill(aln, false);
	
	for(SAMRecord r : buffered_records) {
		if( r.getFirstOfPairFlag() && 
				!r.getSupplementaryAlignmentFlag() &&
				!r.getNotPrimaryAlignmentFlag() ) {
			buff_record[0] = r;	
			as[0] = r.getFloatAttribute("AS");
			aln[0] = !r.getReadUnmappedFlag();
		}
		if( r.getSecondOfPairFlag() && 
				!r.getSupplementaryAlignmentFlag() &&
				!r.getNotPrimaryAlignmentFlag() ) {
			buff_record[1] = r;
			as[1] = r.getFloatAttribute("AS");
			aln[1] = !r.getReadUnmappedFlag();
		}
	}
	
	return tmp_record;
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
private Map<Sequence, List<SAMRecord>> getReadsFromFile(
        final Chromosome chromosome, final Track<Sequence> track, final BamFile bamFile,
        final List<Sequence> blocks) throws IOException {
    final Map<Sequence, List<SAMRecord>> records = new HashMap<>();
    try (SamReader reader = makeSamReader(bamFile, Collections.singletonList(chromosome),
            chromosome.getReferenceId())) {
        LOG.debug(getMessage(MessagesConstants.DEBUG_FILE_OPENING, bamFile.getPath()));
        String chromosomeName = chromosome.getName();
        final int startIndex = track.getStartIndex();
        final int endIndex = track.getEndIndex();

        if (reader.getFileHeader().getSequence(chromosomeName) == null) {
            chromosomeName = Utils.changeChromosomeName(chromosomeName);
        }
        final SAMRecordIterator iterator = reader.queryOverlapping(chromosomeName, startIndex, endIndex);

        LOG.debug(getMessage(MessagesConstants.DEBUG_GET_ITERATOR_QUERY, iterator.toString()));
        while (iterator.hasNext()) {
            final SAMRecord samRecord = iterator.next();
            //if read unmapped
            if (!samRecord.getSAMFlags().contains(SAMFlag.READ_UNMAPPED) && !samRecord.getCigar().isEmpty() &&
                    samRecord.getEnd() > samRecord.getStart()) {
                addRecordToBlock(blocks, records, samRecord);
            }
        }
    }
    return records;
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
public static int getSamReadLength(SamReader reader, int recordsToScan) {
	int i = 0;
	int size = 0;
    SAMRecordIterator it = reader.iterator();
    while (it.hasNext() && i < recordsToScan) {
    	SAMRecord read = it.next();
    	size = Math.max(size,  read.getReadLength());
    	i++;
    }
    it.close();
    return size;
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
/** 
 * Find reads that overlap a given genomic region
 * @param reader
 * @param pos
 * @param orient
 * @param readLength
 * @param minOverlap
 * @param allowGaps
 * @return
 */
public static List<SAMRecord> findOverlappingReads(SamReader reader, GenomeSpan pos, Orientation orient, int readLength, int minOverlap, boolean allowGaps) {
	List<SAMRecord> out = new ArrayList<SAMRecord>();

	SAMRecordIterator it = reader.query(pos.ref, pos.start - readLength + minOverlap, pos.start + readLength - minOverlap, true);
    while (it.hasNext()) {
        SAMRecord read = it.next();
        if (read.isSecondaryOrSupplementary() || read.getDuplicateReadFlag() || read.getNotPrimaryAlignmentFlag() || read.getReadUnmappedFlag() || read.getSupplementaryAlignmentFlag()) {
            // skip all secondary / duplicate / unmapped reads
            continue;
        }
        
        if (!allowGaps) {
            // skip all reads with gaps
            for (CigarElement el: read.getCigar().getCigarElements()) {
                if (el.getOperator() == CigarOperator.N) {
                    continue;
                }
            }
        }
        
        if (ReadUtils.getFragmentEffectiveStrand(read, orient) != pos.strand) {
        	continue;
        }
        
        for (GenomeSpan region: ReadUtils.getJunctionFlankingRegions(read, orient, minOverlap)) {
        	if (region.start <= (pos.start - minOverlap) && region.end >= (pos.start + minOverlap)) {
        		out.add(read);
        		break;
        	}
        }
    }
    it.close();
	return out;
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
/**
 * Helper function that writes reads from iterator it into writer out, updating each SAMRecord along the way
 * according to the newOrder mapping from dictionary index -> index.  Name is used for printing only.
 */
private void writeReads(final SAMFileWriter out,
                        final SAMRecordIterator it,
                        final Map<Integer, Integer> newOrder,
                        final String name) {
    long counter = 0;
    log.info("  Processing " + name);

    while (it.hasNext()) {
        counter++;
        final SAMRecord read = it.next();
        final int oldRefIndex = read.getReferenceIndex();
        final int oldMateIndex = read.getMateReferenceIndex();
        final int newRefIndex = newOrderIndex(read, oldRefIndex, newOrder);

        read.setHeader(out.getFileHeader());
        read.setReferenceIndex(newRefIndex);

        final int newMateIndex = newOrderIndex(read, oldMateIndex, newOrder);
        if (oldMateIndex != -1 && newMateIndex == -1) { // becoming unmapped
            read.setMateAlignmentStart(0);
            read.setMateUnmappedFlag(true);
            read.setAttribute(SAMTag.MC.name(), null);      // Set the Mate Cigar String to null
        }
        read.setMateReferenceIndex(newMateIndex);

        out.addAlignment(read);
    }

    it.close();
    log.info("Wrote " + counter + " reads");
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
private void validateUq(final File input, final File reference) {
    final SamReader reader = SamReaderFactory.makeDefault().referenceSequence(reference).open(input);
    final SAMRecordIterator iterator = reader.iterator();
    while (iterator.hasNext()){
        SAMRecord rec = iterator.next();
        if (!rec.getReadUnmappedFlag())
            Assert.assertNotNull(rec.getAttribute("UQ"));
    }
}
 

import htsjdk.samtools.SAMRecordIterator; //导入方法依赖的package包/类
protected void test() {
    try {
        final SamFileValidator validator = new SamFileValidator(new PrintWriter(System.out), 8000);

        // Validate it has the expected cigar
        validator.setIgnoreWarnings(true);
        validator.setVerbose(true, 1000);
        validator.setErrorsToIgnore(Arrays.asList(SAMValidationError.Type.MISSING_READ_GROUP));
        SamReaderFactory factory = SamReaderFactory.makeDefault().validationStringency(ValidationStringency.LENIENT);
        SamReader samReader = factory.open(getOutput());
        final SAMRecordIterator iterator = samReader.iterator();
        while (iterator.hasNext()) {
            final SAMRecord rec = iterator.next();
            Assert.assertEquals(rec.getCigarString(), expectedCigar);
            if (SAMUtils.hasMateCigar(rec)) {
                Assert.assertEquals(SAMUtils.getMateCigarString(rec), expectedCigar);
            }
        }
        CloserUtil.close(samReader);

        // Run validation on the output file
        samReader = factory.open(getOutput());
        final boolean validated = validator.validateSamFileVerbose(samReader, null);
        CloserUtil.close(samReader);

        Assert.assertTrue(validated, "ValidateSamFile failed");
    } finally {
        TestUtil.recursiveDelete(getOutputDir());
    }
}