Attempt to remove altcontigs if they somehow made it into the coverag…

…e files.

NEWS

@@ -2,6 +2,7 @@ Changes in version 2.2.0
 ------------------------
 
 NEW FEATURES
+
     o Added chunks parameter to Coverage.R and calculateBamCoverageByInterval
       to reduce memory usage (#218)
 
@@ -11,15 +12,19 @@ SIGNIFICANT USER-VISIBLE CHANGES
       calculate the minimum number of supporting reads (instead of assuming a
       default BQ of 30). By default BQ is capped at 50 and variants below 25
       are ignored. Set min.supporting.reads to 0 to turn this off (#206).
-    o More robust annotation of intervals with gene symbols 
+    o More robust annotation of intervals with gene symbols
+    o Remove chrosomes not present in the centromeres GRanges object; useful
+      to remove altcontigs somehow present (should not happen with intervals
+      generated by IntervalFile.R)
 
 BUGFIXES
 
     o Fixed an issue with old R versions where factors were not converted to 
       strings, resulting in numbers instead of gene symbols
     o Fix for a crash when there are no off-target reads in off-target regions
-      (#209). 
-
+      (#209).
+    o Fixed parsing of base quality scores in Mutect 2.2   
+
 
 Changes in version 2.0.0
 ------------------------

R/filterIntervals.R

@@ -171,6 +171,20 @@ normalDB.min.coverage, normalDB.max.missing) {
     intervalsUsed
 }
 
+.filterIntervalsCentromeres <- function(intervalsUsed, tumor, centromeres) {
+    if (is.null(centromeres)) return(intervalsUsed)
+    nBefore <- sum(intervalsUsed)
+    intervalsUsed <- intervalsUsed & seqnames(tumor) %in% seqlevels(centromeres)
+    nAfter <- sum(intervalsUsed)
+
+    if (nAfter < nBefore) {
+        flog.info("Removing %i intervals on non-standard chromosomes not listed in centromeres (%s).",
+            nBefore - nAfter,
+            paste(seqlevels(tumor)[!seqlevels(tumor) %in% seqlevels(centromeres)], collapse = ","))
+    }
+    intervalsUsed
+}
+
 .filterIntervalsTargetedBase <- function(intervalsUsed, tumor, min.targeted.base) {
     if (is.null(min.targeted.base)) return(intervalsUsed)
     nBefore <- sum(intervalsUsed)

R/runAbsoluteCN.R

@@ -421,6 +421,10 @@ runAbsoluteCN <- function(normal.coverage.file = NULL,
     if (!is.null(interval.file)) {
         tumor <- .addGCData(tumor, interval.file)
     }
+    if (is.null(centromeres) && !missing(genome)) {
+        centromeres <- .getCentromerePositions(centromeres, genome,
+            if (is.null(tumor)) NULL else .getSeqlevelsStyle(tumor))
+    }
 
     args.filterIntervals <- c(list(normal = normal, tumor = tumor,
         log.ratio = log.ratio, seg.file = seg.file,
@@ -437,6 +441,7 @@ runAbsoluteCN <- function(normal.coverage.file = NULL,
 
     # chr.hash is an internal data structure, so we need to do this separately.
     intervalsUsed <- .filterIntervalsChrHash(intervalsUsed, tumor, chr.hash)
+    intervalsUsed <- .filterIntervalsCentromeres(intervalsUsed, tumor, centromeres)
     intervalsUsed <- which(intervalsUsed)
     if (length(tumor) != length(normal) ||
         length(tumor) != length(log.ratio)) {
@@ -573,10 +578,8 @@ runAbsoluteCN <- function(normal.coverage.file = NULL,
 
     flog.info("Sample sex: %s", sex)
     flog.info("Segmenting data...")
-    segProvided <- readSegmentationFile(seg.file, sampleid, model.homozygous = model.homozygous)
 
-    centromeres <- .getCentromerePositions(centromeres, genome,
-        if (is.null(vcf)) NULL else .getSeqlevelsStyle(vcf))
+    segProvided <- readSegmentationFile(seg.file, sampleid, model.homozygous = model.homozygous)
 
     args.segmentation <- c(list(normal = normal, tumor = tumor, log.ratio = log.ratio, 
         seg = segProvided, plot.cnv = plot.cnv,