Java SAMFileReader.getFileHeader方法代码示例

import net.sf.samtools.SAMFileReader; //导入方法依赖的package包/类
/**
 * Creates a collection of SAMFileWriters, one for each chromosome.
 *
 * The definition of the chromosomes is taken from the header of a template
 * bamfile.
 *
 * @param template
 */
private void setupChromBamWriters(File template) {

    SAMFileReader inputSam = new SAMFileReader(template);
    SAMFileHeader inputHeader = inputSam.getFileHeader();
    ArrayList<SAMSequenceRecord> samchroms;
    samchroms = new ArrayList<SAMSequenceRecord>(inputSam.getFileHeader().getSequenceDictionary().getSequences());

    // create another list of just chromosome names
    ArrayList<String> chroms = new ArrayList<String>();
    for (int i = 0; i < samchroms.size(); i++) {
        chroms.add(samchroms.get(i).getSequenceName());
    }
    chroms.add("unmapped");

    // create a filewriter for each chromosome
    for (int i = 0; i < chroms.size(); i++) {
        String nowchrom = chroms.get(i);
        SAMFileHeader nowheader = inputHeader.clone();
        nowheader.addComment("Merged data using GeneticThesaurus merge2chrom: chromosome " + nowchrom);
        SAMFileWriter nowWriter = new SAMFileWriterFactory().makeSAMOrBAMWriter(
                nowheader, true, new File(prefix + "." + nowchrom + ".bam"));
        chrombams.put(nowchrom, nowWriter);
    }

}
 

import net.sf.samtools.SAMFileReader; //导入方法依赖的package包/类
protected BAMFile (File file, boolean onlyMapped) throws SequenceFormatException, IOException {
	this.file = file;
	fileSize = file.length();
	name = file.getName();
	this.onlyMapped = onlyMapped;

	SAMFileReader.setDefaultValidationStringency(SAMFileReader.ValidationStringency.SILENT);

	fis = new FileInputStream(file);
	
	br = new SAMFileReader(fis);
	
	header = br.getFileHeader();
	
	it = br.iterator();
	readNext();
}
 

import net.sf.samtools.SAMFileReader; //导入方法依赖的package包/类
@Override
public String apply(File f) {
    if (!detectable(f)) {
        throw new IllegalArgumentException("Cannot detect sample name for file: " + f.getPath());
    }
    final SAMFileReader in = new SAMFileReader(f);
    try {
        final SAMFileHeader header = in.getFileHeader();
        final List<SAMReadGroupRecord> rgs = header.getReadGroups();
        assertFalse(rgs.isEmpty(), "Cannot determine sample name: missing read group information for file: " + f.getPath());
        assertFalse(rgs.size() > 1, "Cannot determine sample name: more than one read group detected for file: " + f.getPath());
        final String sample = rgs.get(0).getSample();
        assertFalse(sample == null, "Cannot determine sample name: missing sample name in read group for file: " + f.getPath());
        return sample;
    } finally {
        in.close();
    }
}
 

import net.sf.samtools.SAMFileReader; //导入方法依赖的package包/类
public BamToSingleEndIterator(File bamFile)
{
	reader = new SAMFileReader(bamFile);
	header = reader.getFileHeader();
	iter = reader.iterator();
	nextAlignment=_next();
}
 

import net.sf.samtools.SAMFileReader; //导入方法依赖的package包/类
/**
 * @param bamFile Input SAM or BAM file to extract header and/or reads from.
 * @param 
 */
 

public BamToPairedEndIterator(File bamFile, TranscriptionRead txnRead, String flag, int maxAllowableInsert) {
	/**
	 * @param bamFile Input SAM or BAM file to extract header and/or reads from.
	 * @param  txnRead  if first read or second read is in direction of trasncription.
	 *         default: first read. TranscriptionRead.FIRST_OF_PAIR
	 * @param flag  "a" to report paired end reads and unpaired end reads
	 *        "p" to only report the paired end reads.
	 * @generator an PairedEndAlignment iterator.
	 *      
	 */
	
	this.flag=flag;
	reader = new SAMFileReader(bamFile);
	header = reader.getFileHeader();
	
	//set header to pairedEnd
	//header.setAttribute(mateLineFlag, "mergedPairedEndFormat");
	iter = reader.iterator();
	bufferCollection = new TreeMap<String,Alignment>();
	this.txnRead=txnRead;
	this.maxAllowableInsert=maxAllowableInsert;
	nextAlignment=advance();
	
}
 

import net.sf.samtools.SAMFileReader; //导入方法依赖的package包/类
@Override
protected int doWork() {
	
	try {
		
        IoUtil.assertFileIsReadable(INPUT);
        IoUtil.assertFileIsWritable(OUTPUT);
		
        final SAMFileReader reader = new SAMFileReader(INPUT);
        final SAMFileHeader header = reader.getFileHeader();
        final SAMFileWriter writer = new SAMFileWriterFactory().makeSAMOrBAMWriter(header, true, OUTPUT);
        SAMRecordIterator itr = reader.iterator();
        while (itr.hasNext()) {
        	SAMRecord record = itr.next();
        	record.setDuplicateReadFlag(false);
        	writer.addAlignment(record);
        }
        itr.close();
        writer.close();
        reader.close();
        
	} catch (Exception e) {
		log.error(e);
	}
	
	return 0;
}
 

import net.sf.samtools.SAMFileReader; //导入方法依赖的package包/类
public static Map<String, Integer> getSizesFromSAM(String samFileName) {
	final SAMFileReader inputSam = new SAMFileReader(new File(samFileName));
	SAMFileHeader header = inputSam.getFileHeader();
	SAMSequenceDictionary dictionary = header.getSequenceDictionary();
	List<SAMSequenceRecord> references = dictionary.getSequences();
	Map<String, Integer> sizes = new LinkedHashMap<String, Integer>(references.size());
	for(SAMSequenceRecord r : references) {
		sizes.put(r.getSequenceName(), r.getSequenceLength());
	}
	inputSam.close();
	
	return sizes;
}
 

import net.sf.samtools.SAMFileReader; //导入方法依赖的package包/类
@Override
protected int doWork() {
    IoUtil.assertFileIsReadable(INPUT);
    IoUtil.assertFileIsWritable(OUTPUT);
    IoUtil.assertFileIsWritable(STATS);

    try {
    	// Read and filter
    	SAMFileReader reader = new SAMFileReader(INPUT);
    	final SAMFileHeader header = reader.getFileHeader();

    	// In our current pipeline, unsorted BAM files output by BWA alignment have read pairs next to each other.
    	if (header.getSortOrder() == SAMFileHeader.SortOrder.unsorted) {
    		log.warn("Treating unsorted SAM file as queryname-sorted.  Check that this produces correct behavior.");
    	}
    	header.setSortOrder(SAMFileHeader.SortOrder.queryname);
    	
    	PairedEndReadIterator itr = new PairedEndReadIterator(reader);
    	
    	header.setSortOrder(SAMFileHeader.SortOrder.unsorted);
    	SAMFileWriter writer = new SAMFileWriterFactory().makeSAMOrBAMWriter(header, false, OUTPUT);
    	
    	while (itr.hasNext()) {
    		Pair<SAMRecord> pair = itr.next();
    		SAMRecord first = pair.getValue1();
    		SAMRecord second = pair.getValue2();
    		
    		if (readMapsToProbe(first, header) || readMapsToProbe(second, header)) {
    			writer.addAlignment(first);
    			writer.addAlignment(second);
    			addStartEndIndices(first, second);
    		}
    	}
    	
    	reader.close();
    	writer.close();
    	
    	BufferedWriter bw = new BufferedWriter(new FileWriter(STATS));
		bw.write("index\tstart\tend\n");
    	for (int i = 0; i < startIndex.length; i++) {
    		bw.write(i + "\t" + startIndex[i] + "\t"+ endIndex[i] + "\n");
    	}
    	bw.close();
    	
    } catch (Exception e) {
    	log.error(e);
    }

    return 0;
}
 

import net.sf.samtools.SAMFileReader; //导入方法依赖的package包/类
public static void main (String [] args) throws IOException {
	ArgumentMap argMap = CLUtil.getParameters(args,USAGE , "default");
	String alnFile = argMap.getInput();
	String out = argMap.getOutput();
	List<String> seqsToChange = new ArrayList<String>();
	if(argMap.containsKey("seqsToFix")) {
		seqsToChange = CLUtil.listFromArray(argMap.getMandatory("seqsToFix").split(","));
	}

	SAMFileReader reader = new SAMFileReader(new File(alnFile));
	SAMFileWriterFactory samfwf = new SAMFileWriterFactory();
	SAMFileHeader oldHeader = reader.getFileHeader();
	SAMFileHeader header = oldHeader.clone();
	header.setSortOrder(oldHeader.getSortOrder());
	oldHeader.getAttributes();
	for (Map.Entry<String, String> he : oldHeader.getAttributes()) { 
		header.setAttribute(he.getKey(), he.getValue());
	}
	
	
	
	header.addProgramRecord(new SAMProgramRecord("nextgen.core.programs.FixChromosomeNames -in " + alnFile + " -out " + out));
	SAMSequenceDictionary ssd = header.getSequenceDictionary();
	SAMSequenceDictionary newSSD = new SAMSequenceDictionary();
	List<SAMSequenceRecord > sequences = ssd.getSequences();
	for (SAMSequenceRecord s : sequences) {
		if(seqsToChange.isEmpty() || seqsToChange.contains(s.getSequenceName())) {
			SAMSequenceRecord ns = new SAMSequenceRecord("chr" + s.getSequenceName(), s.getSequenceLength());
			ns.setAssembly(s.getAssembly());
			ns.setSpecies(ns.getSpecies());
			for (Map.Entry<String, String> e : s.getAttributes()) { 
				ns.setAttribute(e.getKey(), e.getValue());
			}
			newSSD.addSequence(ns);
		} else {
			newSSD.addSequence(s);
		}
	}
	header.setSequenceDictionary(newSSD);
	
	samfwf.setCreateIndex(true);
	SAMFileWriter writer = samfwf.makeBAMWriter(header, true, new File(out))  ;
	
	Iterator<SAMRecord> alnIt = reader.iterator();
	while (alnIt.hasNext()) {
		SAMRecord a = alnIt.next();
		if(seqsToChange.isEmpty() || seqsToChange.contains(a.getReferenceName())) {
			a.setReferenceName("chr"+a.getReferenceName());
			a.setHeader(header);
		}
		writer.addAlignment(a);
	}
	
	reader.close();
	writer.close();

}