private Haplotype getHaplotypeFromRead(
final PileupElement p, final int contextSize, final int locus) {
final GATKSAMRecord read = p.getRead();
int readOffsetFromPileup = p.getOffset();
final byte[] haplotypeBases = new byte[contextSize];
Arrays.fill(haplotypeBases, (byte) REGEXP_WILDCARD);
final double[] baseQualities = new double[contextSize];
Arrays.fill(baseQualities, 0.0);
byte[] readBases = read.getReadBases();
readBases =
AlignmentUtils.readToAlignmentByteArray(
read.getCigar(), readBases); // Adjust the read bases based on the Cigar string
byte[] readQuals = read.getBaseQualities();
readQuals =
AlignmentUtils.readToAlignmentByteArray(
read.getCigar(),
readQuals); // Shift the location of the qual scores based on the Cigar string
readOffsetFromPileup =
AlignmentUtils.calcAlignmentByteArrayOffset(
read.getCigar(), p, read.getAlignmentStart(), locus);
final int baseOffsetStart = readOffsetFromPileup - (contextSize - 1) / 2;
for (int i = 0; i < contextSize; i++) {
final int baseOffset = i + baseOffsetStart;
if (baseOffset < 0) {
continue;
}
if (baseOffset >= readBases.length) {
break;
}
if (readQuals[baseOffset] == PileupElement.DELETION_BASE) {
readQuals[baseOffset] = PileupElement.DELETION_QUAL;
}
if (!BaseUtils.isRegularBase(readBases[baseOffset])) {
readBases[baseOffset] = (byte) REGEXP_WILDCARD;
readQuals[baseOffset] = (byte) 0;
} // N's shouldn't be treated as distinct bases
readQuals[baseOffset] = (byte) Math.min((int) readQuals[baseOffset], p.getMappingQual());
if (((int) readQuals[baseOffset]) < 5) {
readQuals[baseOffset] = (byte) 0;
} // quals less than 5 are used as codes and don't have actual probabilistic meaning behind
// them
haplotypeBases[i] = readBases[baseOffset];
baseQualities[i] = (double) readQuals[baseOffset];
}
return new Haplotype(haplotypeBases, baseQualities);
}
/**
* Hard clip the read to the variable region (from refStart to refStop)
*
* @param read the read to be clipped
* @param refStart the beginning of the variant region (inclusive)
* @param refStop the end of the variant region (inclusive)
* @return the read hard clipped to the variant region
*/
public static GATKSAMRecord hardClipToRegion(
final GATKSAMRecord read, final int refStart, final int refStop) {
final int start = read.getAlignmentStart();
final int stop = read.getAlignmentEnd();
// check if the read is contained in region
if (start <= refStop && stop >= refStart) {
if (start < refStart && stop > refStop)
return hardClipBothEndsByReferenceCoordinates(read, refStart - 1, refStop + 1);
else if (start < refStart) return hardClipByReferenceCoordinatesLeftTail(read, refStart - 1);
else if (stop > refStop) return hardClipByReferenceCoordinatesRightTail(read, refStop + 1);
return read;
} else return GATKSAMRecord.emptyRead(read);
}
/**
* Hard clips away soft clipped bases that are below the given quality threshold
*
* @param read the read
* @param minQual the mininum base quality score to revert the base (inclusive)
* @return a new read without low quality soft clipped bases
*/
public static GATKSAMRecord hardClipLowQualitySoftClips(GATKSAMRecord read, byte minQual) {
int nLeadingSoftClips = read.getAlignmentStart() - read.getSoftStart();
if (read.isEmpty() || nLeadingSoftClips > read.getReadLength())
return GATKSAMRecord.emptyRead(read);
byte[] quals = read.getBaseQualities(EventType.BASE_SUBSTITUTION);
int left = -1;
if (nLeadingSoftClips > 0) {
for (int i = nLeadingSoftClips - 1; i >= 0; i--) {
if (quals[i] >= minQual) left = i;
else break;
}
}
int right = -1;
int nTailingSoftClips = read.getSoftEnd() - read.getAlignmentEnd();
if (nTailingSoftClips > 0) {
for (int i = read.getReadLength() - nTailingSoftClips; i < read.getReadLength(); i++) {
if (quals[i] >= minQual) right = i;
else break;
}
}
GATKSAMRecord clippedRead = read;
if (right >= 0
&& right + 1
< clippedRead
.getReadLength()) // only clip if there are softclipped bases (right >= 0) and the
// first high quality soft clip is not the last base (right+1 <
// readlength)
clippedRead =
hardClipByReadCoordinates(
clippedRead,
right + 1,
clippedRead.getReadLength()
- 1); // first we hard clip the low quality soft clips on the right tail
if (left >= 0
&& left - 1
> 0) // only clip if there are softclipped bases (left >= 0) and the first high quality
// soft clip is not the last base (left-1 > 0)
clippedRead =
hardClipByReadCoordinates(
clippedRead,
0,
left - 1); // then we hard clip the low quality soft clips on the left tail
return clippedRead;
}
private ArrayList<Allele> computeConsensusAlleles(
ReferenceContext ref,
Map<String, AlignmentContext> contexts,
AlignmentContextUtils.ReadOrientation contextType) {
Allele refAllele = null, altAllele = null;
GenomeLoc loc = ref.getLocus();
ArrayList<Allele> aList = new ArrayList<Allele>();
HashMap<String, Integer> consensusIndelStrings = new HashMap<String, Integer>();
int insCount = 0, delCount = 0;
// quick check of total number of indels in pileup
for (Map.Entry<String, AlignmentContext> sample : contexts.entrySet()) {
AlignmentContext context = AlignmentContextUtils.stratify(sample.getValue(), contextType);
final ReadBackedExtendedEventPileup indelPileup = context.getExtendedEventPileup();
insCount += indelPileup.getNumberOfInsertions();
delCount += indelPileup.getNumberOfDeletions();
}
if (insCount < minIndelCountForGenotyping && delCount < minIndelCountForGenotyping)
return aList;
for (Map.Entry<String, AlignmentContext> sample : contexts.entrySet()) {
// todo -- warning, can be duplicating expensive partition here
AlignmentContext context = AlignmentContextUtils.stratify(sample.getValue(), contextType);
final ReadBackedExtendedEventPileup indelPileup = context.getExtendedEventPileup();
for (ExtendedEventPileupElement p : indelPileup.toExtendedIterable()) {
// SAMRecord read = p.getRead();
GATKSAMRecord read = ReadUtils.hardClipAdaptorSequence(p.getRead());
if (read == null) continue;
if (ReadUtils.is454Read(read)) {
continue;
}
/* if (DEBUG && p.isIndel()) {
System.out.format("Read: %s, cigar: %s, aln start: %d, aln end: %d, p.len:%d, Type:%s, EventBases:%s\n",
read.getReadName(),read.getCigar().toString(),read.getAlignmentStart(),read.getAlignmentEnd(),
p.getEventLength(),p.getType().toString(), p.getEventBases());
}
*/
String indelString = p.getEventBases();
if (p.isInsertion()) {
boolean foundKey = false;
if (read.getAlignmentEnd() == loc.getStart()) {
// first corner condition: a read has an insertion at the end, and we're right at the
// insertion.
// In this case, the read could have any of the inserted bases and we need to build a
// consensus
for (String s : consensusIndelStrings.keySet()) {
int cnt = consensusIndelStrings.get(s);
if (s.startsWith(indelString)) {
// case 1: current insertion is prefix of indel in hash map
consensusIndelStrings.put(s, cnt + 1);
foundKey = true;
break;
} else if (indelString.startsWith(s)) {
// case 2: indel stored in hash table is prefix of current insertion
// In this case, new bases are new key.
consensusIndelStrings.remove(s);
consensusIndelStrings.put(indelString, cnt + 1);
foundKey = true;
break;
}
}
if (!foundKey)
// none of the above: event bases not supported by previous table, so add new key
consensusIndelStrings.put(indelString, 1);
} else if (read.getAlignmentStart() == loc.getStart() + 1) {
// opposite corner condition: read will start at current locus with an insertion
for (String s : consensusIndelStrings.keySet()) {
int cnt = consensusIndelStrings.get(s);
if (s.endsWith(indelString)) {
// case 1: current insertion is suffix of indel in hash map
consensusIndelStrings.put(s, cnt + 1);
foundKey = true;
break;
} else if (indelString.endsWith(s)) {
// case 2: indel stored in hash table is suffix of current insertion
// In this case, new bases are new key.
consensusIndelStrings.remove(s);
consensusIndelStrings.put(indelString, cnt + 1);
foundKey = true;
break;
}
}
if (!foundKey)
// none of the above: event bases not supported by previous table, so add new key
consensusIndelStrings.put(indelString, 1);
} else {
// normal case: insertion somewhere in the middle of a read: add count to hash map
int cnt =
consensusIndelStrings.containsKey(indelString)
? consensusIndelStrings.get(indelString)
: 0;
consensusIndelStrings.put(indelString, cnt + 1);
}
} else if (p.isDeletion()) {
indelString = String.format("D%d", p.getEventLength());
int cnt =
consensusIndelStrings.containsKey(indelString)
? consensusIndelStrings.get(indelString)
: 0;
consensusIndelStrings.put(indelString, cnt + 1);
}
}
/* if (DEBUG) {
int icount = indelPileup.getNumberOfInsertions();
int dcount = indelPileup.getNumberOfDeletions();
if (icount + dcount > 0)
{
List<Pair<String,Integer>> eventStrings = indelPileup.getEventStringsWithCounts(ref.getBases());
System.out.format("#ins: %d, #del:%d\n", insCount, delCount);
for (int i=0 ; i < eventStrings.size() ; i++ ) {
System.out.format("%s:%d,",eventStrings.get(i).first,eventStrings.get(i).second);
// int k=0;
}
System.out.println();
}
} */
}
int maxAlleleCnt = 0;
String bestAltAllele = "";
for (String s : consensusIndelStrings.keySet()) {
int curCnt = consensusIndelStrings.get(s);
if (curCnt > maxAlleleCnt) {
maxAlleleCnt = curCnt;
bestAltAllele = s;
}
// if (DEBUG)
// System.out.format("Key:%s, number: %d\n",s,consensusIndelStrings.get(s) );
} // gdebug-
if (maxAlleleCnt < minIndelCountForGenotyping) return aList;
if (bestAltAllele.startsWith("D")) {
// get deletion length
int dLen = Integer.valueOf(bestAltAllele.substring(1));
// get ref bases of accurate deletion
int startIdxInReference = (int) (1 + loc.getStart() - ref.getWindow().getStart());
// System.out.println(new String(ref.getBases()));
byte[] refBases =
Arrays.copyOfRange(ref.getBases(), startIdxInReference, startIdxInReference + dLen);
if (Allele.acceptableAlleleBases(refBases)) {
refAllele = Allele.create(refBases, true);
altAllele = Allele.create(Allele.NULL_ALLELE_STRING, false);
}
} else {
// insertion case
if (Allele.acceptableAlleleBases(bestAltAllele)) {
refAllele = Allele.create(Allele.NULL_ALLELE_STRING, true);
altAllele = Allele.create(bestAltAllele, false);
}
}
if (refAllele != null && altAllele != null) {
aList.add(0, refAllele);
aList.add(1, altAllele);
}
return aList;
}
@Override
public T traverse(
final ActiveRegionWalker<M, T> walker, final LocusShardDataProvider dataProvider, T sum) {
logger.debug(String.format("TraverseActiveRegion.traverse: Shard is %s", dataProvider));
final LocusView locusView = getLocusView(walker, dataProvider);
final GenomeLocSortedSet initialIntervals = engine.getIntervals();
final LocusReferenceView referenceView = new LocusReferenceView(walker, dataProvider);
final int activeRegionExtension =
walker.getClass().getAnnotation(ActiveRegionExtension.class).extension();
final int maxRegionSize =
walker.getClass().getAnnotation(ActiveRegionExtension.class).maxRegion();
if (locusView
.hasNext()) { // trivial optimization to avoid unnecessary processing when there's nothing
// here at all
int minStart = Integer.MAX_VALUE;
ActivityProfile profile =
new ActivityProfile(engine.getGenomeLocParser(), walker.hasPresetActiveRegions());
ReferenceOrderedView referenceOrderedDataView =
getReferenceOrderedView(walker, dataProvider, locusView);
// We keep processing while the next reference location is within the interval
GenomeLoc prevLoc = null;
while (locusView.hasNext()) {
final AlignmentContext locus = locusView.next();
GenomeLoc location = locus.getLocation();
if (prevLoc != null) {
// fill in the active / inactive labels from the stop of the previous location to the
// start of this location
// TODO refactor to separate function
for (int iii = prevLoc.getStop() + 1; iii < location.getStart(); iii++) {
final GenomeLoc fakeLoc =
engine.getGenomeLocParser().createGenomeLoc(prevLoc.getContig(), iii, iii);
if (initialIntervals == null || initialIntervals.overlaps(fakeLoc)) {
profile.add(
fakeLoc,
new ActivityProfileResult(
walker.hasPresetActiveRegions()
&& walker.presetActiveRegions.overlaps(fakeLoc)
? 1.0
: 0.0));
}
}
}
dataProvider.getShard().getReadMetrics().incrementNumIterations();
// create reference context. Note that if we have a pileup of "extended events", the context
// will
// hold the (longest) stretch of deleted reference bases (if deletions are present in the
// pileup).
final ReferenceContext refContext = referenceView.getReferenceContext(location);
// Iterate forward to get all reference ordered data covering this location
final RefMetaDataTracker tracker =
referenceOrderedDataView.getReferenceOrderedDataAtLocus(
locus.getLocation(), refContext);
// Call the walkers isActive function for this locus and add them to the list to be
// integrated later
if (initialIntervals == null || initialIntervals.overlaps(location)) {
profile.add(location, walkerActiveProb(walker, tracker, refContext, locus, location));
}
// Grab all the previously unseen reads from this pileup and add them to the massive read
// list
for (final PileupElement p : locus.getBasePileup()) {
final GATKSAMRecord read = p.getRead();
if (!myReads.contains(read)) {
myReads.add(read);
}
// If this is the last pileup for this shard calculate the minimum alignment start so that
// we know
// which active regions in the work queue are now safe to process
minStart = Math.min(minStart, read.getAlignmentStart());
}
prevLoc = location;
printProgress(locus.getLocation());
}
updateCumulativeMetrics(dataProvider.getShard());
// Take the individual isActive calls and integrate them into contiguous active regions and
// add these blocks of work to the work queue
// band-pass filter the list of isActive probabilities and turn into active regions
final ActivityProfile bandPassFiltered = profile.bandPassFilter();
final List<ActiveRegion> activeRegions =
bandPassFiltered.createActiveRegions(activeRegionExtension, maxRegionSize);
// add active regions to queue of regions to process
// first check if can merge active regions over shard boundaries
if (!activeRegions.isEmpty()) {
if (!workQueue.isEmpty()) {
final ActiveRegion last = workQueue.getLast();
final ActiveRegion first = activeRegions.get(0);
if (last.isActive == first.isActive
&& last.getLocation().contiguousP(first.getLocation())
&& last.getLocation().size() + first.getLocation().size() <= maxRegionSize) {
workQueue.removeLast();
activeRegions.remove(first);
workQueue.add(
new ActiveRegion(
last.getLocation().union(first.getLocation()),
first.isActive,
this.engine.getGenomeLocParser(),
activeRegionExtension));
}
}
workQueue.addAll(activeRegions);
}
logger.debug(
"Integrated "
+ profile.size()
+ " isActive calls into "
+ activeRegions.size()
+ " regions.");
// now go and process all of the active regions
sum = processActiveRegions(walker, sum, minStart, dataProvider.getLocus().getContig());
}
return sum;
}
private double scoreReadAgainstHaplotype(
final PileupElement p, final int contextSize, final Haplotype haplotype, final int locus) {
double expected = 0.0;
double mismatches = 0.0;
// What's the expected mismatch rate under the model that this read is actually sampled from
// this haplotype? Let's assume the consensus base c is a random choice one of A, C, G, or T,
// and that
// the observed base is actually from a c with an error rate e. Since e is the rate at which
// we'd
// see a miscalled c, the expected mismatch rate is really e. So the expected number of
// mismatches
// is just sum_i e_i for i from 1..n for n sites
//
// Now, what's the probabilistic sum of mismatches? Suppose that the base b is equal to c.
// Well, it could
// actually be a miscall in a matching direction, which would happen at a e / 3 rate. If b !=
// c, then
// the chance that it is actually a mismatch is 1 - e, since any of the other 3 options would be
// a mismatch.
// so the probability-weighted mismatch rate is sum_i ( matched ? e_i / 3 : 1 - e_i ) for i = 1
// ... n
final byte[] haplotypeBases = haplotype.getBases();
final GATKSAMRecord read = p.getRead();
byte[] readBases = read.getReadBases();
readBases =
AlignmentUtils.readToAlignmentByteArray(
p.getRead().getCigar(), readBases); // Adjust the read bases based on the Cigar string
byte[] readQuals = read.getBaseQualities();
readQuals =
AlignmentUtils.readToAlignmentByteArray(
p.getRead().getCigar(),
readQuals); // Shift the location of the qual scores based on the Cigar string
int readOffsetFromPileup = p.getOffset();
readOffsetFromPileup =
AlignmentUtils.calcAlignmentByteArrayOffset(
p.getRead().getCigar(), p, read.getAlignmentStart(), locus);
final int baseOffsetStart = readOffsetFromPileup - (contextSize - 1) / 2;
for (int i = 0; i < contextSize; i++) {
final int baseOffset = i + baseOffsetStart;
if (baseOffset < 0) {
continue;
}
if (baseOffset >= readBases.length) {
break;
}
final byte haplotypeBase = haplotypeBases[i];
final byte readBase = readBases[baseOffset];
final boolean matched =
(readBase == haplotypeBase || haplotypeBase == (byte) REGEXP_WILDCARD);
byte qual = readQuals[baseOffset];
if (qual == PileupElement.DELETION_BASE) {
qual = PileupElement.DELETION_QUAL;
} // calcAlignmentByteArrayOffset fills the readQuals array with DELETION_BASE at deletions
qual = (byte) Math.min((int) qual, p.getMappingQual());
if (((int) qual)
>= 5) { // quals less than 5 are used as codes and don't have actual probabilistic meaning
// behind them
final double e = QualityUtils.qualToErrorProb(qual);
expected += e;
mismatches += matched ? e : 1.0 - e / 3.0;
}
// a more sophisticated calculation would include the reference quality, but it's nice to
// actually penalize
// the mismatching of poorly determined regions of the consensus
}
return mismatches - expected;
}
