Java SAMRecord.getAlignmentEnd方法代码示例

import net.sf.samtools.SAMRecord; //导入方法依赖的package包/类
protected void processRead(Collection<SAMRecord> records) {
      int mapcount = records.size();
      if (mapcount == 0) {
          return;
      }
      if (!useNonUnique && mapcount > 1) {
          return;
      }
	
      float weight = 1 / ((float)mapcount);
      Read currRead = new Read();
for (SAMRecord record : records) {
    int start = record.getAlignmentStart();
    int end = record.getAlignmentEnd();
    ReadHit currHit = new ReadHit(
				  record.getReferenceName().replaceFirst("^chr", ""), 
				  start, end, 
				  record.getReadNegativeStrandFlag() ? '-' : '+',
				  weight);
    currRead.addHit(currHit);
}currRead.setNumHits(mapcount);
addHits(currRead);
  }
 

import net.sf.samtools.SAMRecord; //导入方法依赖的package包/类
protected void processRead(Collection<SAMRecord> records) {
      int mapcount = records.size();
      if (mapcount == 0) {
          return;
      }
      if (!useNonUnique && mapcount > 1) {
          return;
      }
	
      float weight = 1 / ((float)mapcount);
      Read currRead = new Read((int)totalWeight);
for (SAMRecord record : records) {
	int start = record.getAlignmentStart();
    int end = record.getAlignmentEnd();
    ReadHit currHit = new ReadHit(gen, currID,
				  record.getReferenceName().replaceFirst("^chr", ""), 
				  start, end, 
				  record.getReadNegativeStrandFlag() ? '-' : '+',
				  weight);
    currRead.addHit(currHit);
    currID++;
}currRead.setNumHits(mapcount);
addHits(currRead);
totalWeight++;
  }
 

import net.sf.samtools.SAMRecord; //导入方法依赖的package包/类
/**
 * Construct an entry by parsing a SAM record for a read.
 *
 * The read name should be of the format, e.g. T100;chr1:10001-10100 i.e.
 * LABEL;CHROMOSOME;START-END
 *
 * Warning: this constructor will only set the following fields: originChr,
 * originStart, originEnd, alignChr, alignStart, alignEnd. Other fields must
 * be set via the separate set methods.
 *
 * @param record
 */
public ThesaurusEntry(SAMRecord record, GenomeInfo ginfo) {
    this.ginfo = ginfo;

    // parse the read name to get the origin location        
    String[] readelements = record.getReadName().split(";|:|-");
    //originChr = readelements[1];
    originChrIndex = ginfo.getChrIndex(readelements[1]);
    originStart = Integer.parseInt(readelements[2]);
    originEnd = Integer.parseInt(readelements[3]);

    // get the alignment location
    //alignChr = record.getReferenceName();
    alignChrIndex = ginfo.getChrIndex(record.getReferenceName());
    alignStart = record.getAlignmentStart();
    alignEnd = record.getAlignmentEnd();

    if (record.getReadNegativeStrandFlag()) {
        alignStrand = '-';
    } else {
        alignStrand = '+';
    }

    anchors = new ArrayList<ThesaurusAnchor>(2);
    // the anchor array will not be properly formed, i.e. any mismatches will not
    // be recorded either in the anchors or in the penalty field.

    ok = true;
}
 

import net.sf.samtools.SAMRecord; //导入方法依赖的package包/类
/**
 * basic constructor that copies a SAMrecord and computes minimal things
 *
 * @param record
 */
public ThesaurusSAMRecord(SAMRecord record) {
    this.record = record;
    Cigar cigar = record.getCigar();
    cigarsize = cigar.numCigarElements();
    cigarelements = new CigarElement[cigarsize];
    for (int i = 0; i < cigarsize; i++) {
        cigarelements[i] = cigar.getCigarElement(i);
    }
    bases = record.getReadBases();
    alignStart = record.getAlignmentStart();
    alignEnd = record.getAlignmentEnd();
}
 

import net.sf.samtools.SAMRecord; //导入方法依赖的package包/类
public SequenceRead(SAMRecord record) {
    super(record.getAlignmentStart(), record.getAlignmentEnd());
    this.chr = record.getReferenceName();
    if (record.getReadNegativeStrandFlag()) {
        strand = Strand.NEGATIVE;
    } else {
        strand = Strand.POSITIVE;
    }
    this.readBases = record.getReadBases();
    this.qualities = record.getBaseQualities();
    this.alignmentBlocks = record.getAlignmentBlocks();
}
 

import net.sf.samtools.SAMRecord; //导入方法依赖的package包/类
@Override
public void processSequence(SAMRecord read) {
	SAMFileHeader header = read.getHeader();
	SAMSequenceDictionary samSequenceDictionary = header.getSequenceDictionary();
	int referenceIndex = read.getReferenceIndex();
	long alignmentStart = read.getAlignmentStart();
	long alignmentEnd = read.getAlignmentEnd();

	log.debug("header = " + header);
	log.debug("referenceIndex = " + referenceIndex);
	
	readNumber++;

	if (referenceIndex > -1) {
		if (!isBinNucleotidesSet) {
			setBinNumber(samSequenceDictionary);
		}
		if (alignmentEnd > alignmentStart) {
			long referenceStart = sequenceStarts.get(referenceIndex);
			long alignmentStartAbsolute = alignmentStart + referenceStart;
			long alignmentEndAbsolute = alignmentEnd + referenceStart;

			recordCoverage(alignmentStartAbsolute, alignmentEndAbsolute);
		}
		else {
			errorReads++;
		}
	}
}
 

import net.sf.samtools.SAMRecord; //导入方法依赖的package包/类
public static SAMRecord convertToPairedEndFragment(SAMRecord rec) {
	int insertSize = Math.abs(rec.getInferredInsertSize());
	//TODO: possible to remove (insertSize > 0) clause? What does an insert size of 0 mean?
	if (rec.getReadPairedFlag() && rec.getProperPairFlag() && !rec.getReadUnmappedFlag() 
			&& (insertSize <= MAX_INSERT) && (rec.getAlignmentStart() < rec.getMateAlignmentStart())
			&& rec.getReferenceName() != "chrM") // current paired end representation doesn't do well with circular chromosomes
	{
		//We need to get the full fragment contained by read.getStart to pair.getEnd
		int readEnd=rec.getAlignmentEnd();
		int mateStart=rec.getMateAlignmentStart();
					
		//int extension = insertSize - rec.getReadLength();
		int extension=(mateStart-readEnd)+rec.getReadLength();
		if (extension <= MAX_INSERT) {
			String newRead = rec.getReadString() + StringUtils.repeat("N", extension);
			rec.setReadString(newRead);
			String newQual = StringUtils.repeat("A", newRead.length());
			if(!rec.getBaseQualityString().equals("*")) newQual = rec.getBaseQualityString() + StringUtils.repeat("A", extension);
			rec.setBaseQualityString(newQual);
			String newCigar=newRead.length()+"M";
			rec.setCigarString(newCigar);

			// Change attributes to represent single read
			rec.setMateReferenceName("*");
			rec.setMateAlignmentStart(0);
			rec.setFirstOfPairFlag(false);
			rec.setMateNegativeStrandFlag(false);
			rec.setMateUnmappedFlag(false);
			rec.setProperPairFlag(false);
			rec.setReadPairedFlag(false);
			rec.setSecondOfPairFlag(false);
		}
	} else {
		rec = null;
	}
	return rec;
}
 

import net.sf.samtools.SAMRecord; //导入方法依赖的package包/类
private boolean readMapsToProbe(SAMRecord read, SAMFileHeader header) {
	if (read.getReadUnmappedFlag()) return false;
	
	int left, right;
	if (read.getReferenceName().contains("OriginalArray")) {
		left = ORIGINAL_ARRAY_LEFT;
		right = ORIGINAL_ARRAY_RIGHT;
	} else if (read.getReferenceName().contains("MainArray")) {
		left = MAIN_ARRAY_LEFT;
		right = MAIN_ARRAY_RIGHT;
	} else if (read.getReferenceName().contains("SimpleArray")) {
		left = SIMPLE_ARRAY_LEFT;
		right = SIMPLE_ARRAY_RIGHT;
	} else if (read.getReferenceName().contains("140105")) {
		left = ARRAY_140105;
		right = ARRAY_140105;
	} else if (read.getReferenceName().contains("Mouse")) {
		left = MRNA_ARRAY_LEFT;
		right = MRNA_ARRAY_RIGHT;
	} else {
		log.error("This reference name doesn't match: " + read.getReferenceName());
		return false;
	}
	
	left = T7BASES + left;
	right = header.getSequence(read.getReferenceIndex()).getSequenceLength() - right - T7BASES;
	
	if ((read.getAlignmentStart() <= left - OVERLAP) || read.getAlignmentEnd() >= right + OVERLAP) {
		return true;
	}
	
	return false;
}
 

import net.sf.samtools.SAMRecord; //导入方法依赖的package包/类
/**
 * Removes all pairs from the collection such that one of the mates is farther than the max insert size allowed
 * @param tempCollection
 */
private Map<String, AlignmentPair> purgeByDistance(Map<String, AlignmentPair> tempCollection,int currentPosition) {
	
	Map<String, AlignmentPair> newCollection = new TreeMap<String, AlignmentPair>();
	for(String key : tempCollection.keySet()){
		AlignmentPair pair=tempCollection.get(key);
		boolean toAdd=true;
		Iterator<SAMRecord> recordIter;
		//For alignments where we are still waiting for the second one
		if(!pair.hasValue1() || !pair.hasValue2()){
			if(pair.hasValue1()){
				recordIter=pair.getValue1().iterator();
			}
			else{recordIter=pair.getValue2().iterator();}
			
			//pair.removeRecordsFartherThan(currentPosition);
			
			while(recordIter.hasNext()) {
				SAMRecord record = recordIter.next();
				//if(we are farther than the current 
				if((currentPosition-record.getAlignmentEnd()) > maxAllowableInsert){
					recordIter.remove();
					if(pair.valuesAreEmpty())
						toAdd=false;
				}
			}
		}
		if(toAdd)
			newCollection.put(key, pair);
	}
	return newCollection;
}
 

import net.sf.samtools.SAMRecord; //导入方法依赖的package包/类
/**
 * Gets a single end read.
 * 
 * @param sections The tab split sections from the SAM file
 * @param flag The binary flag field from the file
 * @return The read which was read
 * @throws SeqMonkException
 */
private SequenceReadWithChromosome getSingleEndRead (SAMRecord samRecord) throws SeqMonkException {
	int strand;
	int start;
	int end;

	start = samRecord.getAlignmentStart();
	end = samRecord.getAlignmentEnd();

	if (samRecord.getReadNegativeStrandFlag()) {
		strand = Location.REVERSE;
	}
	else {
		strand = Location.FORWARD;
	}


	if (extendBy > 0) {
		if (strand == Location.FORWARD) {
			end += extendBy;
		}
		else if (strand == Location.REVERSE) {
			start -= extendBy;
		}
	}

	ChromosomeWithOffset c;
	try {
		c = collection.genome().getChromosome(samRecord.getReferenceName());
	}
	catch (Exception iae) {
		throw new SeqMonkException(iae.getLocalizedMessage());
	}
	
	start = c.position(start);
	end = c.position(end);

	// We also don't allow readings which are beyond the end of the chromosome
	if (end > c.chromosome().length()) {
		int overrun = end - c.chromosome().length();
		throw new SeqMonkException("Reading position "+end+" was "+overrun+"bp beyond the end of chr"+c.chromosome().name()+" ("+c.chromosome().length()+")");
	}
	if (start < 1) {
		throw new SeqMonkException("Reading position "+start+" was before the start of chr"+c.chromosome().name()+" ("+c.chromosome().length()+")");			
	}

	// We can now make the new reading
	SequenceReadWithChromosome read = new SequenceReadWithChromosome(c.chromosome(),SequenceRead.packPosition(start,end,strand));

	return read;
}
 

import net.sf.samtools.SAMRecord; //导入方法依赖的package包/类
/**
 * Gets a paired end read.  This method assumes that it will only be passed reads which map
 * to the reverse strand since these are the ones which contain enough information to 
 * unambiguously locate both ends of the pair.
 * 
 * @param sections The tab split sections from the SAM file
 * @param flag The binary flag field
 * @return The read which was read
 * @throws SeqMonkException
 */
private SequenceReadWithChromosome getPairedEndRead (SAMRecord samRecord) throws SeqMonkException {
	int strand;
	int start;
	int end;

	if (!samRecord.getReadNegativeStrandFlag()) {
		throw new SeqMonkException("Read passed to parse pair was not on the negative strand");
	}
	
	if (samRecord.getMateNegativeStrandFlag()) {
		throw new SeqMonkException("Ignored discordantly stranded read pair");
	}
	
	end = samRecord.getAlignmentEnd();
	start = samRecord.getMateAlignmentStart();
	
	if (start > end) {
		throw new SeqMonkException("Ignored discordantly stranded read pair");
	}
	
	if (samRecord.getFirstOfPairFlag()) {
		strand = Location.REVERSE;
	}
	else {
		strand = Location.FORWARD;
	}
	
	if ((end - start)+1 > pairedEndDistance) {
		throw new SeqMonkException("Distance between ends "+((end - start)+1)+" was larger than cutoff ("+pairedEndDistance+")");
	}

	ChromosomeWithOffset c;

	try {
		c = dataCollection().genome().getChromosome(samRecord.getReferenceName());
	}
	catch (Exception e) {
		throw new SeqMonkException(e.getLocalizedMessage());
	}
	
	start = c.position(start);
	end = c.position(end);

	// We also don't allow readings which are beyond the end of the chromosome
	if (end > c.chromosome().length()) {
		int overrun = end - c.chromosome().length();
		throw new SeqMonkException("Reading position "+end+" was "+overrun+"bp beyond the end of chr"+c.chromosome().name()+" ("+c.chromosome().length()+")");
	}
	if (start < 1) {
		throw new SeqMonkException("Reading position "+start+" was before the start of chr"+c.chromosome().name()+" ("+c.chromosome().length()+")");			
	}

	// We can now make the new reading
	SequenceReadWithChromosome read = new SequenceReadWithChromosome(c.chromosome(),SequenceRead.packPosition(start,end,strand));

	return read;
}