Added mapq as part of the scoring of duplicate reads.

Added filtering of unmapped reads and reads with unmapped mates in the consensus calling iterator.
fulcrumgenomics · Oct 25, 2023 · a637753 · a637753
1 parent 126009b
commit a637753
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/src/main/scala/com/fulcrumgenomics/umi/ConsensusCallingIterator.scala b/src/main/scala/com/fulcrumgenomics/umi/ConsensusCallingIterator.scala
@@ -53,7 +53,9 @@ class ConsensusCallingIterator[ConsensusRead <: SimpleRead](sourceIterator: Iter
   private var collectedStats: Boolean = false
 
   protected val iter: Iterator[SamRecord] = {
-    val filteredIterator = sourceIterator.filterNot(r => r.secondary || r.supplementary)
+    val filteredIterator = sourceIterator.filterNot { r =>
+      r.secondary || r.supplementary || r.unmapped || (r.paired && r.mateUnmapped)
+    }
 
     // Wrap our input iterator in a progress logging iterator if we have a progress logger
     val progressIterator = progress match {

diff --git a/src/main/scala/com/fulcrumgenomics/umi/GroupReadsByUmi.scala b/src/main/scala/com/fulcrumgenomics/umi/GroupReadsByUmi.scala
@@ -766,7 +766,7 @@ class GroupReadsByUmi
   private def setDuplicateFlags(group: Seq[Template]): Unit = {
     val nonDuplicateTemplate = group.maxBy { template =>
       template.primaryReads.sumBy { r =>
-        DuplicateScoringStrategy.computeDuplicateScore(r.asSam, ScoringStrategy.SUM_OF_BASE_QUALITIES)
+        r.mapq + DuplicateScoringStrategy.computeDuplicateScore(r.asSam, ScoringStrategy.SUM_OF_BASE_QUALITIES)
       }
     }