Summarize peak distribution over exon, intron, enhancer, proximal promoter, 5 prime UTR and 3 prime UTR

Description

Summarize peak distribution over exon, intron, enhancer, proximal promoter, 5 prime UTR and 3 prime UTR

Usage

assignChromosomeRegion(peaks.RD, exon, TSS, utr5, utr3, 
         proximal.promoter.cutoff=1000L, immediate.downstream.cutoff=1000L, 
         nucleotideLevel=FALSE, precedence=NULL, TxDb=NULL)

Arguments

Value

A list of two named vectors: percentage and jacard (Jacard Index). The information in the vectors:

Author(s)

Jianhong Ou, Lihua Julie Zhu

References

1. Zhu L.J. et al. (2010) ChIPpeakAnno: a Bioconductor package to annotate ChIP-seq and ChIP-chip data. BMC Bioinformatics 2010, 11:237doi:10.1186/1471-2105-11-237

2. Zhu L.J. (2013) Integrative analysis of ChIP-chip and ChIP-seq dataset. Methods Mol Biol. 2013;1067:105-24. doi: 10.1007/978-1-62703-607-8_8.

See Also

annotatePeakInBatch, findOverlapsOfPeaks,getEnriched, makeVennDiagram,addGeneIDs, peaksNearBDP,summarizePatternInPeaks

Examples

if (interactive()){
    ##Display the list of genomes available at UCSC:
    #library(rtracklayer)
    #ucscGenomes()[, "db"]
    ## Display the list of Tracks supported by makeTxDbFromUCSC()
    #supportedUCSCtables()
    ##Retrieving a full transcript dataset for Human from UCSC
    ##TranscriptDb <- 
    ##     makeTxDbFromUCSC(genome="hg19", tablename="ensGene")
    if(require(TxDb.Hsapiens.UCSC.hg19.knownGene)){
        TxDb <- TxDb.Hsapiens.UCSC.hg19.knownGene
        exons <- exons(TxDb, columns=NULL)
        fiveUTRs <- unique(unlist(fiveUTRsByTranscript(TxDb)))
        Feature.distribution <- 
            assignChromosomeRegion(exons, nucleotideLevel=TRUE, TxDb=TxDb)
        barplot(Feature.distribution$percentage)
        assignChromosomeRegion(fiveUTRs, nucleotideLevel=FALSE, TxDb=TxDb)
        data(myPeakList)
        assignChromosomeRegion(myPeakList, nucleotideLevel=TRUE, 
                               precedence=c("Promoters", "immediateDownstream", 
                                            "fiveUTRs", "threeUTRs", 
                                            "Exons", "Introns"), 
                               TxDb=TxDb)
    }
}

Results

R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> library(ChIPpeakAnno)
Loading required package: grid
Loading required package: IRanges
Loading required package: BiocGenerics
Loading required package: parallel

Attaching package: 'BiocGenerics'

The following objects are masked from 'package:parallel':

    clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
    clusterExport, clusterMap, parApply, parCapply, parLapply,
    parLapplyLB, parRapply, parSapply, parSapplyLB

The following objects are masked from 'package:stats':

    IQR, mad, xtabs

The following objects are masked from 'package:base':

    Filter, Find, Map, Position, Reduce, anyDuplicated, append,
    as.data.frame, cbind, colnames, do.call, duplicated, eval, evalq,
    get, grep, grepl, intersect, is.unsorted, lapply, lengths, mapply,
    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int, rank,
    rbind, rownames, sapply, setdiff, sort, table, tapply, union,
    unique, unsplit

Loading required package: S4Vectors
Loading required package: stats4

Attaching package: 'S4Vectors'

The following objects are masked from 'package:base':

    colMeans, colSums, expand.grid, rowMeans, rowSums

Loading required package: Biostrings
Loading required package: XVector
Loading required package: GenomicRanges
Loading required package: GenomeInfoDb
Loading required package: VennDiagram
Loading required package: futile.logger

> png(filename="/home/ddbj/snapshot/RGM3/R_BC/result/ChIPpeakAnno/assignChromosomeRegion.Rd_%03d_medium.png", width=480, height=480)
> ### Name: assignChromosomeRegion
> ### Title: Summarize peak distribution over exon, intron, enhancer,
> ###   proximal promoter, 5 prime UTR and 3 prime UTR
> ### Aliases: assignChromosomeRegion
> ### Keywords: misc
> 
> ### ** Examples
> 
> #if (interactive()){
>     ##Display the list of genomes available at UCSC:
>     #library(rtracklayer)
>     #ucscGenomes()[, "db"]
>     ## Display the list of Tracks supported by makeTxDbFromUCSC()
>     #supportedUCSCtables()
>     ##Retrieving a full transcript dataset for Human from UCSC
>     ##TranscriptDb <- 
>     ##     makeTxDbFromUCSC(genome="hg19", tablename="ensGene")
>     if(require(TxDb.Hsapiens.UCSC.hg19.knownGene)){
+         TxDb <- TxDb.Hsapiens.UCSC.hg19.knownGene
+         exons <- exons(TxDb, columns=NULL)
+         fiveUTRs <- unique(unlist(fiveUTRsByTranscript(TxDb)))
+         Feature.distribution <- 
+             assignChromosomeRegion(exons, nucleotideLevel=TRUE, TxDb=TxDb)
+         barplot(Feature.distribution$percentage)
+         assignChromosomeRegion(fiveUTRs, nucleotideLevel=FALSE, TxDb=TxDb)
+         data(myPeakList)
+         assignChromosomeRegion(myPeakList, nucleotideLevel=TRUE, 
+                                precedence=c("Promoters", "immediateDownstream", 
+                                             "fiveUTRs", "threeUTRs", 
+                                             "Exons", "Introns"), 
+                                TxDb=TxDb)
+     }
Loading required package: TxDb.Hsapiens.UCSC.hg19.knownGene
Loading required package: GenomicFeatures
Loading required package: AnnotationDbi
Loading required package: Biobase
Welcome to Bioconductor

    Vignettes contain introductory material; view with
    'browseVignettes()'. To cite Bioconductor, see
    'citation("Biobase")', and for packages 'citation("pkgname")'.

$percentage
          Promoters immediateDownstream            fiveUTRs           threeUTRs 
         0.12420582          0.12556664          0.03018612          0.20546008 
              Exons             Introns           microRNAs               tRNAs 
         0.37187685         98.48957484          0.00000000          0.00000000 
  Intergenic.Region 
         0.43333172 

$jaccard
          Promoters immediateDownstream            fiveUTRs           threeUTRs 
        0.002950441         0.003303413         0.001391700         0.003238811 
              Exons             Introns           microRNAs               tRNAs 
        0.001881843         0.018346983         0.000000000         0.000000000 
  Intergenic.Region 
        0.584224691 

Warning messages:
1: In valid.GenomicRanges.seqinfo(x, suggest.trim = TRUE) :
  GRanges object contains 2386 out-of-bound ranges located on sequences
  chr12, chr16, chr17, chr18, chr19, chr20, chr21, and chr22. Note that
  only ranges located on a non-circular sequence whose length is not NA
  can be considered out-of-bound (use seqlengths() and isCircular() to
  get the lengths and circularity flags of the underlying sequences). You
  can use trim() to trim these ranges. See ?`trim,GenomicRanges-method`
  for more information.
2: In valid.GenomicRanges.seqinfo(x, suggest.trim = TRUE) :
  GRanges object contains 2386 out-of-bound ranges located on sequences
  chr12, chr16, chr17, chr18, chr19, chr20, chr21, and chr22. Note that
  only ranges located on a non-circular sequence whose length is not NA
  can be considered out-of-bound (use seqlengths() and isCircular() to
  get the lengths and circularity flags of the underlying sequences). You
  can use trim() to trim these ranges. See ?`trim,GenomicRanges-method`
  for more information.
> #}
> 
> 
> 
> 
> 
> dev.off()
null device 
          1 
>