[Bioc-devel] Extending GenomicRanges::`intra-range-methods`

[Bhagwat, Aditya]

Dear bioc-devel,

The ?GenomicRanges::`intra-range-methods` are very useful for range arithmetic<https://genomicsclass.github.io/book/pages/figure/bioc1_igranges-unnamed-chunk-6-1.png>

Feedback request: would it be of general use to add the methods below to the GenomicRanges::`intra-range-methods` palette (after properly S4-ing them)?
Or shall I keep them in multicrispr<https://gitlab.gwdg.de/loosolab/software/multicrispr>?
Additional feedback welcome as well (e.g. re-implementation of already existing functionality).


1)     Left flank

#' Left flank
#' @param gr   \code{\link[GenomicRanges]{GRanges-class}}
#' @param leftstart number: flank start (relative to range start)
#' @param leftend   number: flank end   (relative to range start)
#' @return a \code{\link[GenomicRanges]{GRanges-class}}
#' @export
#' @examples
#' bedfile <- system.file('extdata/SRF.bed', package = 'multicrispr')
#' bsgenome <- BSgenome.Mmusculus.UCSC.mm10::Mmusculus
#' gr <- read_bed(bedfile, bsgenome)
#' left_flank(gr)
left_flank <- function(gr, leftstart = -200, leftend   = -1){

    # Assert
    assert_is_identical_to_true(is(gr, 'GRanges'))
    assert_is_a_number(leftstart)
    assert_is_a_number(leftend)

    # Flank
    newranges <- gr
    end(newranges)   <- start(gr) + leftend
    start(newranges) <- start(gr) + leftstart

    # Return
    newranges
}


2)     Right flank

#' Right flank
#' @param gr    \code{\link[GenomicRanges]{GRanges-class}}
#' @param rightstart number: flank start (relative to range end)
#' @param rightend   number: flank end   (relative to range end)
#' @return     \code{\link[GenomicRanges]{GRanges-class}}
#' @export
#' @examples
#' bedfile <- system.file('extdata/SRF.bed', package = 'multicrispr')
#' bsgenome <- BSgenome.Mmusculus.UCSC.mm10::Mmusculus
#' gr <- read_bed(bedfile, bsgenome)
#' right_flank(gr)
#' @export
right_flank <- function(gr, rightstart = 1, rightend   = 200){

    # Assert
    assert_is_identical_to_true(is(gr, 'GRanges'))
    assert_is_a_number(rightstart)
    assert_is_a_number(rightend)
    assert_is_a_bool(verbose)

    # Flank
    newranges <- gr
    start(newranges) <- end(newranges) + rightstart
    end(newranges)   <- end(newranges) + rightend

    # Plot
    if (plot)  plot_intervals(GRangesList(sites = gr, rightflanks = newranges))

    # Return
    cmessage('\t\t%d right flanks : [end%s%d, end%s%d]',
            length(newranges),
            csign(rightstart),
            abs(rightstart),
            csign(rightend),
            abs(rightend))
    newranges
}


3)     Slop

#' Slop (i.e. extend left/right)
#' @param gr        \code{\link[GenomicRanges]{GRanges-class}}
#' @param leftstart number: flank start (relative to range start)
#' @param rightend  number: flank end   (relative to range end)
#' @return \code{\link[GenomicRanges]{GRanges-class}}
#' @export
#' @examples
#' bedfile <- system.file('extdata/SRF.bed', package = 'multicrispr')
#' bsgenome <- BSgenome.Mmusculus.UCSC.mm10::Mmusculus
#' gr <- read_bed(bedfile, bsgenome)
#' slop(gr)
#' @export
slop <- function(gr, leftstart = -22, rightend  =  22){

    # Assert
    assert_is_identical_to_true(methods::is(gr, 'GRanges'))
    assert_is_a_number(leftstart)
    assert_is_a_number(rightend)
    assert_is_a_bool(verbose)

    # Slop
    newranges <- gr
    start(newranges) <- start(newranges) + leftstart
    end(newranges)   <- end(newranges)   + rightend

    # Return
    newranges
}


4)     Flank fourways

#' Flank fourways
#'
#' Flank left and right, for both strands, and merge overlaps
#' @param gr          \code{\link[GenomicRanges]{GRanges-class}}
#' @param leftstart   number: left flank start  (relative to range start)
#' @param leftend     number: left flank  end   (relative to range start)
#' @param rightstart  number: right flank start (relative to range end)
#' @param rightend    number: right flank end   (relative to range end)
#' @return \code{\link[GenomicRanges]{GRanges-class}}
#' @examples
#' bedfile <- system.file('extdata/SRF.bed', package = 'multicrispr')
#' bsgenome <- BSgenome.Mmusculus.UCSC.mm10::Mmusculus
#' granges <- read_bed(bedfile, bsgenome)
#' flank_fourways(granges)
#' @export
flank_fourways <- function(gr, leftstart  = -200, leftend    =   -1, rightstart =    1, rightend   =  200){

    # Comply
    . <- NULL

    # Flank
    left <-  left_flank( gr, leftstart, leftend)
    right <- right_flank(gr,rightstart, rightend)
    newranges <- c(left, right)

    # Complement
    newranges %<>% c(invertStrand(.))

    # Merge overlaps
    newranges %<>% reduce() # GenomicRanges::reduce

    # Return
    newranges
}



5)     Slop fourways

#' Slop granges for both strands, merging overlaps
#' @param gr   \code{\link[GenomicRanges]{GRanges-class}}
#' @param leftstart number
#' @param rightend  number
#' @return \code{\link[GenomicRanges]{GRanges-class}}
#' @examples
#' bedfile <- system.file('extdata/SRF.bed', package = 'multicrispr')
#' bsgenome <- BSgenome.Mmusculus.UCSC.mm10::Mmusculus
#' gr <- read_bed(bedfile, bsgenome)
#' gr
#' slop_fourways(gr)
#' @export
slop_fourways <- function(gr, leftstart = -22, rightend  =  22){

    # Comply
    . <- NULL

    # Slop
    if (verbose) cmessage('\tSlop fourways')
    newranges <- slop(gr, leftstart, rightend, verbose = verbose)

    # Complement
    newranges %<>% c(invertStrand(.))

    # Merge overlaps
    newranges %<>% reduce()

    # Return
    newranges
}

Thankyou!

Aditya






	[[alternative HTML version deleted]]