zzh
/
gatk-3.8
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merging active regions across shard boundries if they are contiguous, have the same active status and don't grow too big.

This commit is contained in:
Ryan Poplin 2012-05-01 15:51:36 -04:00
parent 0cf3603c73
commit 20a0078f23
3 changed files with 19 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
public/java/src/org/broadinstitute/sting/gatk/traversals/TraverseActiveRegions.java
View File

@ -28,7 +28,7 @@ public class TraverseActiveRegions <M,T> extends TraversalEngine<M,T,ActiveRegio
*/
protected static Logger logger = Logger.getLogger(TraversalEngine.class);
private final Queue<ActiveRegion> workQueue = new LinkedList<ActiveRegion>();
private final LinkedList<ActiveRegion> workQueue = new LinkedList<ActiveRegion>();
private final LinkedHashSet<GATKSAMRecord> myReads = new LinkedHashSet<GATKSAMRecord>();
@Override
@ -112,7 +112,20 @@ public class TraverseActiveRegions <M,T> extends TraversalEngine<M,T,ActiveRegio
final List<ActiveRegion> activeRegions = bandPassFiltered.createActiveRegions( activeRegionExtension, maxRegionSize );
// add active regions to queue of regions to process
workQueue.addAll( activeRegions );
// 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

2
public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/HaplotypeScore.java
View File

@ -376,7 +376,7 @@ public class HaplotypeScore extends InfoFieldAnnotation implements StandardAnnot
}
}
// indel likelihoods are stric log-probs, not phred scored
// indel likelihoods are strict log-probs, not phred scored
double overallScore = 0.0;
for (final double[] readHaplotypeScores : haplotypeScores) {
overallScore += MathUtils.arrayMin(readHaplotypeScores);

4
public/java/src/org/broadinstitute/sting/utils/activeregion/ActivityProfile.java
View File

@ -158,7 +158,9 @@ public class ActivityProfile {
// find the best place to break up the large active region
Double minProb = Double.MAX_VALUE;
int cutPoint = -1;
for( int iii = curStart + 50; iii < curEnd - 50; iii++ ) { // BUGBUG: assumes maxRegionSize >> 50
final int size = curEnd - curStart + 1;
for( int iii = curStart + (int)(size*0.25); iii < curEnd - (int)(size*0.25); iii++ ) {
if( isActiveList.get(iii) < minProb ) { minProb = isActiveList.get(iii); cutPoint = iii; }
}
final List<ActiveRegion> leftList = createActiveRegion(isActive, curStart, cutPoint, activeRegionExtension, maxRegionSize, new ArrayList<ActiveRegion>());