Merge pull request #52 from c-mertes/fraser2

Move to the improved version FRASER 2.0 using a new splice metric, the Intron Jaccard Index

.github/workflows/check-bioc.yml

@@ -249,7 +249,7 @@ jobs:
           rcmdcheck::rcmdcheck(
               args = c("--no-manual", "--no-vignettes", "--timings"),
               build_args = c("--no-manual", "--keep-empty-dirs", "--no-resave-data"),
-              error_on = "warning",
+              error_on = "error",
               check_dir = "check"
           )
         shell: Rscript {0}

DESCRIPTION

@@ -1,12 +1,13 @@
 Package: FRASER
 Type: Package
 Title: Find RAre Splicing Events in RNA-Seq Data
-Version: 1.11.0
-Date: 2021-04-05
+Version: 1.99.0
+Date: 2022-11-25
 Authors@R: c(
     person("Christian", "Mertes", role=c("aut", "cre"), 
             email="[email protected]"),
     person("Ines", "Scheller",  role=c("aut"), email="[email protected]"),
+    person("Karoline", "Lutz", role=c("aut")),
     person("Vicente", "Yepez", role=c("ctb"), email="[email protected]"),
     person("Julien", "Gagneur", role=c("aut"), email="[email protected]"))
 Description: Detection of rare aberrant splicing events in transcriptome 
@@ -28,7 +29,7 @@ biocViews:
 License: MIT + file LICENSE
 URL: https://github.com/gagneurlab/FRASER
 BugRepots: https://github.com/gagneurlab/FRASER/issues
-RoxygenNote: 7.1.2
+RoxygenNote: 7.2.2
 Encoding: UTF-8
 VignetteBuilder: knitr
 Depends:
@@ -82,9 +83,13 @@ Suggests:
     covr,
     TxDb.Hsapiens.UCSC.hg19.knownGene,
     org.Hs.eg.db,
+    rtracklayer,
+    SGSeq,
+    ggbio,
+    biovizBase
 LinkingTo:
-    Rcpp,
-    RcppArmadillo
+    RcppArmadillo,
+    Rcpp
 Collate:
     variables.R
     getNSetterFuns.R
@@ -114,3 +119,4 @@ Collate:
     fitCorrectionMethods.R
     plotMethods.R
     zzz.R
+    resultAnnotations.R

NAMESPACE

@@ -6,6 +6,7 @@ export("condition<-")
 export("currentType<-")
 export("dontWriteHDF5<-")
 export("featureExclusionMask<-")
+export("fitMetrics<-")
 export("name<-")
 export("nonSplicedReads<-")
 export("pairedEnd<-")
@@ -22,12 +23,16 @@ export(K)
 export(N)
 export(aberrant)
 export(addCountsToFraserDataSet)
+export(annotateIntronReferenceOverlap)
+export(annotatePotentialImpact)
 export(annotateRanges)
 export(annotateRangesWithTxDb)
+export(availableFDRsubsets)
 export(bamFile)
 export(bestQ)
 export(calculatePSIValues)
 export(calculatePadjValues)
+export(calculatePadjValuesOnSubset)
 export(calculatePvalues)
 export(calculateZscore)
 export(condition)
@@ -44,6 +49,8 @@ export(filterExpression)
 export(filterExpressionAndVariability)
 export(filterVariability)
 export(fit)
+export(fitMetrics)
+export(flagBlacklistRegions)
 export(getNonSplitReadCountsForAllSamples)
 export(getSplitReadCountsForAllSamples)
 export(hyperParams)
@@ -60,19 +67,22 @@ export(pVals)
 export(padjVals)
 export(pairedEnd)
 export(plotAberrantPerSample)
+export(plotBamCoverage)
+export(plotBamCoverageFromResultTable)
 export(plotCountCorHeatmap)
 export(plotEncDimSearch)
 export(plotExpectedVsObservedPsi)
 export(plotExpression)
 export(plotFilterExpression)
 export(plotFilterVariability)
+export(plotManhattan)
 export(plotQQ)
+export(plotSpliceMetricRank)
 export(plotVolcano)
 export(predictedMeans)
 export(pseudocount)
 export(psiTypes)
 export(results)
-export(resultsByGenes)
 export(rho)
 export(samples)
 export(saveFraserDataSet)
@@ -98,13 +108,15 @@ exportMethods(assays)
 exportMethods(bamFile)
 exportMethods(condition)
 exportMethods(filterExpression)
+exportMethods(filterVariability)
 exportMethods(length)
 exportMethods(name)
 exportMethods(nonSplicedReads)
 exportMethods(pairedEnd)
 exportMethods(plotAberrantPerSample)
 exportMethods(plotCountCorHeatmap)
 exportMethods(plotEncDimSearch)
+exportMethods(plotManhattan)
 exportMethods(plotQQ)
 exportMethods(plotVolcano)
 exportMethods(results)
@@ -158,27 +170,40 @@ importFrom(GenomeInfoDb,seqlengths)
 importFrom(GenomeInfoDb,seqlevels)
 importFrom(GenomeInfoDb,seqlevelsStyle)
 importFrom(GenomeInfoDb,seqnames)
+importFrom(GenomeInfoDb,sortSeqlevels)
 importFrom(GenomeInfoDb,standardChromosomes)
 importFrom(GenomicAlignments,junctions)
 importFrom(GenomicAlignments,readGAlignmentPairs)
 importFrom(GenomicAlignments,readGAlignments)
 importFrom(GenomicAlignments,summarizeJunctions)
+importFrom(GenomicFeatures,exons)
+importFrom(GenomicFeatures,fiveUTRsByTranscript)
 importFrom(GenomicFeatures,genes)
 importFrom(GenomicFeatures,intronsByTranscript)
 importFrom(GenomicFeatures,makeTxDbFromGFF)
+importFrom(GenomicFeatures,seqlevels0)
+importFrom(GenomicFeatures,threeUTRsByTranscript)
+importFrom(GenomicRanges,"end<-")
+importFrom(GenomicRanges,"seqinfo<-")
+importFrom(GenomicRanges,"start<-")
 importFrom(GenomicRanges,GRanges)
 importFrom(GenomicRanges,GRangesList)
+importFrom(GenomicRanges,end)
 importFrom(GenomicRanges,findOverlaps)
 importFrom(GenomicRanges,granges)
 importFrom(GenomicRanges,invertStrand)
 importFrom(GenomicRanges,makeGRangesFromDataFrame)
+importFrom(GenomicRanges,start)
 importFrom(HDF5Array,HDF5Array)
 importFrom(HDF5Array,loadHDF5SummarizedExperiment)
 importFrom(HDF5Array,path)
 importFrom(HDF5Array,saveHDF5SummarizedExperiment)
 importFrom(HDF5Array,writeHDF5Array)
+importFrom(IRanges,"%over%")
 importFrom(IRanges,IRanges)
+importFrom(IRanges,distance)
 importFrom(IRanges,from)
+importFrom(IRanges,nearest)
 importFrom(IRanges,ranges)
 importFrom(IRanges,subsetByOverlaps)
 importFrom(IRanges,to)
@@ -204,15 +229,18 @@ importFrom(Rsamtools,scanBamHeader)
 importFrom(Rsubread,featureCounts)
 importFrom(S4Vectors,"mcols<-")
 importFrom(S4Vectors,"metadata<-")
+importFrom(S4Vectors,"values<-")
 importFrom(S4Vectors,DataFrame)
 importFrom(S4Vectors,Rle)
 importFrom(S4Vectors,SimpleList)
+importFrom(S4Vectors,elementMetadata)
 importFrom(S4Vectors,end)
 importFrom(S4Vectors,mcols)
 importFrom(S4Vectors,metadata)
 importFrom(S4Vectors,queryHits)
 importFrom(S4Vectors,start)
 importFrom(S4Vectors,subjectHits)
+importFrom(S4Vectors,values)
 importFrom(SummarizedExperiment,"assay<-")
 importFrom(SummarizedExperiment,"assays<-")
 importFrom(SummarizedExperiment,"colData<-")
@@ -236,6 +264,7 @@ importFrom(VGAM,rbetabinom)
 importFrom(VGAM,vglm)
 importFrom(biomaRt,getBM)
 importFrom(biomaRt,useEnsembl)
+importFrom(cowplot,background_grid)
 importFrom(cowplot,theme_cowplot)
 importFrom(extraDistr,dbbinom)
 importFrom(extraDistr,pbbinom)
@@ -245,6 +274,8 @@ importFrom(ggplot2,aes)
 importFrom(ggplot2,annotate)
 importFrom(ggplot2,annotation_logticks)
 importFrom(ggplot2,element_blank)
+importFrom(ggplot2,facet_grid)
+importFrom(ggplot2,facet_wrap)
 importFrom(ggplot2,geom_abline)
 importFrom(ggplot2,geom_histogram)
 importFrom(ggplot2,geom_hline)
@@ -253,10 +284,12 @@ importFrom(ggplot2,geom_point)
 importFrom(ggplot2,geom_ribbon)
 importFrom(ggplot2,geom_segment)
 importFrom(ggplot2,geom_smooth)
+importFrom(ggplot2,geom_text)
 importFrom(ggplot2,geom_vline)
 importFrom(ggplot2,ggplot)
 importFrom(ggplot2,ggtitle)
 importFrom(ggplot2,labs)
+importFrom(ggplot2,quo_name)
 importFrom(ggplot2,scale_color_brewer)
 importFrom(ggplot2,scale_color_discrete)
 importFrom(ggplot2,scale_color_gradientn)
@@ -271,6 +304,7 @@ importFrom(ggplot2,theme_bw)
 importFrom(ggplot2,xlab)
 importFrom(ggplot2,xlim)
 importFrom(ggplot2,ylab)
+importFrom(ggplot2,ylim)
 importFrom(ggrepel,geom_text_repel)
 importFrom(grDevices,colorRampPalette)
 importFrom(matrixStats,colAnys)
@@ -324,9 +358,11 @@ importFrom(stats,rnbinom)
 importFrom(stats,rnorm)
 importFrom(stats,runif)
 importFrom(stats,sd)
+importFrom(tibble,"%>%")
 importFrom(tibble,as_tibble)
 importFrom(tools,file_path_as_absolute)
 importFrom(utils,capture.output)
 importFrom(utils,packageVersion)
+importFrom(utils,tail)
 importMethodsFrom(OUTRIDER,results)
 useDynLib(FRASER)

NEWS

@@ -1,3 +1,24 @@
+CHANGES IN VERSION 2.0.0
+-------------------------
+    o Major update to FRASER2:
+        o Introduction of new & more robust splice metric Intron Jaccard Index
+        o Only Intron Jaccard Index metric used by default    
+        o Improved gene level pvalue calculation and internal storage
+        o Introduction of option to limit FDR correction to user-defined 
+          subsets of genes per sample (e.g. OMIM genes with rare variant)
+        o Updated internal pseudocount parameter and default delta Jaccard 
+          cutoff    
+        o Junction filtering adapted to usage of Intron Jaccard Index metric
+            o Require min expression of N >= 10 in 25% of the samples
+        o Results table:
+            o Functionality to flag outliers in blacklist regions of the genome
+            o Functionality to annotate the predicted type of aberrantSplicing 
+              (e.g. exon skipping, intron retention etc.)
+        o Several updates in the plotting functions    
+            o introduction of manhattan plot functionality
+            o possibility to create sashimi plots to visualize read coverage in 
+              the bam files for outliers
+
 CHANGES IN VERSION 1.8.1
 -------------------------
     o Bugfix in merging splicing counts (#41)

R/AllGenerics-definitions.R

@@ -146,3 +146,14 @@ setGeneric("nonSplicedReads",
 #' @export
 setGeneric("nonSplicedReads<-", signature = "object", 
         function(object, value) standardGeneric("nonSplicedReads<-"))
+
+#' @rdname plotFunctions
+#' @export
+setGeneric("plotManhattan", function(object, ...) 
+    standardGeneric("plotManhattan"))
+
+#' @rdname filtering
+#' @export
+setGeneric("filterVariability", function(object, ...)
+    standardGeneric("filterVariability"))
+