first commit

.Rbuildignore

@@ -0,0 +1,6 @@
+^LICENSE\.md$
+^README\.Rmd$
+^\.github$
+^_pkgdown\.yml$
+^docs$
+^pkgdown$

.github/.gitignore

@@ -0,0 +1 @@
+*.html

.github/CODE_OF_CONDUCT.md

@@ -0,0 +1,17 @@
+The Bioconductor community values
+
+* an open approach to science that promotes the sharing of ideas, code, and expertise
+* collaboration
+* diversity and inclusivity
+* a kind and welcoming environment
+* community contributions
+
+In line with these values, Bioconductor is dedicated to providing a welcoming, supportive, collegial, experience free of harassment, intimidation, and bullying regardless of:
+
+* identity: gender, gender identity and expression, sexual orientation, disability, physical appearance, ethnicity, body size, race, age, religion, etc.
+* intellectual position: approaches to data analysis, software preferences, coding style, scientific perspective, etc.
+* stage of career
+
+In order to uphold these values, members of the Bioconductor community are required to follow the Code of Conduct.The latest version of Bioconductor project Code of Conduct is available at http://bioconductor.org/about/code-of-conduct/. Please read the Code of Conduct before contributing to this project.
+
+Thank you!

.github/workflows/rworkflows.yml

@@ -0,0 +1,57 @@
+name: rworkflows
+'on':
+  push:
+    branches:
+    - master
+    - main
+    - devel
+    - RELEASE_**
+  pull_request:
+    branches:
+    - master
+    - main
+    - devel
+    - RELEASE_**
+jobs:
+  rworkflows:
+    permissions: write-all
+    runs-on: ${{ matrix.config.os }}
+    name: ${{ matrix.config.os }} (${{ matrix.config.r }})
+    container: ${{ matrix.config.cont }}
+    strategy:
+      fail-fast: ${{ false }}
+      matrix:
+        config:
+        - os: ubuntu-latest
+          bioc: devel
+          r: auto
+          cont: ghcr.io/bioconductor/bioconductor_docker:devel
+          rspm: ~
+        - os: macOS-latest
+          bioc: release
+          r: auto
+          cont: ~
+          rspm: ~
+        - os: windows-latest
+          bioc: release
+          r: auto
+          cont: ~
+          rspm: ~
+    steps:
+    - uses: neurogenomics/rworkflows@master
+      with:
+        run_bioccheck: ${{ false }}
+        run_rcmdcheck: ${{ true }}
+        as_cran: ${{ true }}
+        run_vignettes: ${{ true }}
+        has_testthat: ${{ true }}
+        run_covr: ${{ true }}
+        run_pkgdown: ${{ true }}
+        has_runit: ${{ false }}
+        has_latex: ${{ false }}
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run_docker: ${{ false }}
+        DOCKER_TOKEN: ${{ secrets.DOCKER_TOKEN }}
+        runner_os: ${{ runner.os }}
+        cache_version: cache-v1
+        docker_registry: ghcr.io

.gitignore

@@ -0,0 +1,2 @@
+inst/doc
+docs

DESCRIPTION

@@ -0,0 +1,35 @@
+Package: AggregatedCoverage
+Title: Coverage metrics over aligned genomic features of interest 
+Version: 0.99.0
+Date: 2023-11-09
+Authors@R: 
+    person("First", "Last", , "[email protected]", role = c("aut", "cre"),
+           comment = c(ORCID = "YOUR-ORCID-ID"))
+Description: What the package does (one paragraph).
+License: MIT + file LICENSE
+URL: 
+BugReports: https://support.bioconductor.org/tag/AggregatedCoverage
+biocViews: Software
+Encoding: UTF-8
+Roxygen: list(markdown = TRUE)
+RoxygenNote: 7.2.3
+Imports: 
+    SummarizedExperiment,
+    dplyr,
+    GenomicRanges,
+    GenomeInfoDb, 
+    methods,
+    BiocParallel
+Suggests: 
+    plyranges,
+    rtracklayer,
+    ggplot2,
+    TxDb.Hsapiens.UCSC.hg19.knownGene,
+    GenomicFeatures, 
+    BiocStyle,
+    knitr,
+    rmarkdown,
+    sessioninfo,
+    testthat (>= 3.0.0)
+Config/testthat/edition: 3
+VignetteBuilder: knitr

LICENSE

@@ -0,0 +1,2 @@
+YEAR: 2023
+COPYRIGHT HOLDER: AggregatedCoverage authors

LICENSE.md

@@ -0,0 +1,21 @@
+# MIT License
+
+Copyright (c) 2023 AggregatedCoverage authors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

NAMESPACE

@@ -0,0 +1,22 @@
+# Generated by roxygen2: do not edit by hand
+
+S3method(as_tibble,AggregatedCoverage)
+export(AggregatedCoverage)
+import(GenomeInfoDb)
+import(GenomicRanges)
+import(SummarizedExperiment)
+import(methods)
+importFrom(BiocParallel,bplapply)
+importFrom(BiocParallel,bpparam)
+importFrom(SummarizedExperiment,SummarizedExperiment)
+importFrom(SummarizedExperiment,assay)
+importFrom(SummarizedExperiment,assays)
+importFrom(SummarizedExperiment,colData)
+importFrom(SummarizedExperiment,rowData)
+importFrom(SummarizedExperiment,rowRanges)
+importFrom(dplyr,as_tibble)
+importFrom(dplyr,bind_cols)
+importFrom(dplyr,bind_rows)
+importFrom(dplyr,filter)
+importFrom(dplyr,mutate)
+importFrom(dplyr,relocate)

R/AggregatedCoverage.R

@@ -0,0 +1,107 @@
+#' AggregatedCoverage
+#'
+#' This function initiates a `AggregatedCoverage` object. 
+#'
+#' @param tracks Named list of genomic tracks (RleList)
+#' @param features Named GRangesList
+#' @param width Width at which each feature will be rescaled
+#' @param BPPARAM Passed to BiocParallel
+#' @return A `AggregatedCoverage` object
+#'
+#' @import GenomicRanges
+#' @import GenomeInfoDb
+#' @import SummarizedExperiment
+#' @importFrom dplyr filter
+#' @importFrom dplyr bind_rows
+#' @importFrom dplyr bind_cols
+#' @importFrom dplyr mutate
+#' @importFrom dplyr relocate
+#' @import methods
+#' @importFrom SummarizedExperiment SummarizedExperiment
+#' @importFrom SummarizedExperiment colData
+#' @importFrom SummarizedExperiment rowData
+#' @importFrom SummarizedExperiment rowRanges
+#' @importFrom SummarizedExperiment assay
+#' @importFrom SummarizedExperiment assays
+#' @importFrom BiocParallel bpparam
+#' @importFrom BiocParallel bplapply
+#' @export
+#'
+#' @examples
+#' library(plyranges)
+#' library(rtracklayer)
+#' scc1_peaks <- system.file("extdata", "Scc1-peaks.narrowPeak", package = "AggregatedCoverage") |> 
+#'     import()
+#' conv_loci <- system.file("extdata", "conv_transcription_loci.bed", package = "AggregatedCoverage") |> 
+#'     import()
+#' features <- GRangesList(Scc1 = scc1_peaks, Conv_transcription = conv_loci)
+#' tracks <- list(
+#'     Scc1 = system.file("extdata", "Scc1-vs-input.bw", package = "AggregatedCoverage") |> import(as = 'Rle'), 
+#'     RNA_fwd = system.file("extdata", "SRR2045244.fwd.CPM.bw", package = "AggregatedCoverage") |> import(as = 'Rle'), 
+#'     RNA_rev = system.file("extdata", "SRR2045244.rev.CPM.bw", package = "AggregatedCoverage") |> import(as = 'Rle')
+#' )
+#' AC <- AggregatedCoverage(tracks, features, 3000)
+#' AC
+
+AggregatedCoverage <- function(tracks, features, width, BPPARAM = BiocParallel::bpparam()) {
+
+    ## Check that input lists are named
+    stopifnot(length(unique(names(tracks))) == length(tracks))
+    stopifnot(length(unique(names(features))) == length(features))
+
+    ## Extend and filter features
+    tracks <- .set_seqinfo(tracks)
+    si <- seqinfo(tracks[[1]])[[1]]
+    features <- lapply(features, .resize_granges, width = width, seqinfo = si) 
+
+    ## Prepare cData and rData
+    cData <- data.frame(
+        track = names(tracks)
+    )
+    rData <- GRangesList(features)
+    mcols(rData) <- data.frame(
+        features = names(features)
+    )
+
+    ## Aggregate scores
+    dfs <- BiocParallel::bplapply(names(tracks), function(t) {
+        lapply(names(features), function(f) {
+            df <- .compute_cov(tracks[[t]], features[[f]])
+            df$track <- t
+            df$features <- f
+            return(df)
+        }) |> dplyr::bind_rows()
+    }, BPPARAM = BPPARAM) |> dplyr::bind_rows()
+
+    ## Fill out different assay matrices
+    m0 <- matrix(
+        list(), 
+        nrow = length(features), ncol = length(tracks)
+    )
+    colnames(m0) <- names(tracks)
+    rownames(m0) <- names(features)
+    assays <- c("mean", "median", "min", "max", "sd", "se", "ci_low", "ci_high")
+    l_assays <- vector("list", length = length(assays))
+    names(l_assays) <- assays
+    for (assay in assays) {
+        m <- m0
+        for (t in names(tracks)) {
+            df <- dplyr::filter(dfs, track == t)
+            for (f in names(features)) {
+                m[f, t][[1]] <- dplyr::filter(df, features == f)[[assay]]
+            }
+        }
+        l_assays[[assay]] <- m
+    }
+
+    AC <- methods::new(
+        "AggregatedCoverage",
+        SummarizedExperiment::SummarizedExperiment(
+            rowRanges = rData,
+            colData = cData,
+            assays = l_assays
+        )
+    )
+
+    return(AC)
+}

R/AllClasses.R

@@ -0,0 +1,4 @@
+methods::setClass(
+    "AggregatedCoverage", 
+    contains = c("RangedSummarizedExperiment")
+)

R/AllMethods.R

@@ -0,0 +1,23 @@
+#' @importFrom dplyr as_tibble
+#' @export
+
+as_tibble.AggregatedCoverage <- function(x, ...) {
+    tracks <- colData(x)$track
+    features <- rowData(x)$features
+    assays <- names(assays(x))
+    w <- width(rowRanges(x)[[1]])[[1]]
+    lapply(tracks, function(t) {
+        lapply(features, function(f) {
+            lapply(assays(x), `[[`, f, t) |> 
+                stats::setNames(assays) |> 
+                dplyr::bind_cols() |> 
+                dplyr::mutate(
+                    coord = seq(-w/2, w/2-1, 1), 
+                    track = t, features = f
+                ) |> 
+                dplyr::relocate(coord) |> 
+                dplyr::relocate(features) |> 
+                dplyr::relocate(track)
+        }) |> dplyr::bind_rows()
+    }) |> dplyr::bind_rows()
+}

R/utils.R

@@ -0,0 +1,55 @@
+.set_seqinfo <- function(tracks) {
+    n <- names(tracks)
+    sls <- lapply(tracks, lengths)
+    has_seqlengths <- any(!is.na(lapply(sls, sum)))
+    if (!has_seqlengths) {
+        sis <- lapply(tracks, function(rle) {
+            Seqinfo(
+                names(lengths(rle)), 
+                lengths(rle)
+            )
+        }) |> unique()
+        if (length(unique(sis)) > 1) 
+            stop("More than 1 seqinfo inferred from the tracks.")
+        si <- sis[[1]]
+    } 
+    else {
+        sl <- sls[[which(!is.na(lapply(sls, sum)))[[1]]]]
+        si <- list(Seqinfo(
+            names(sl), 
+            sl
+        ))
+    }
+    tracks <- lapply(tracks, function(rle) {
+        GenomeInfoDb::seqinfo(rle) <- si
+        return(rle)
+    })
+    names(tracks) <- n
+    return(tracks)
+}
+
+.resize_granges <- function(gr, width, seqinfo) {
+    GenomeInfoDb::seqlevels(gr, pruning.mode = "coarse") <- GenomeInfoDb::seqlevels(seqinfo)
+    GenomeInfoDb::seqinfo(gr) <- seqinfo
+    gr <- suppressWarnings(resize(gr, fix = 'center', width = width))
+    w <- width
+    gr <- trim(gr)
+    gr <- gr[width(gr) == w]
+}
+
+.compute_cov <- function(rle, gr) {
+    scores <- NumericList(rle[gr]) |> as.matrix()
+    mean <- colMeans(scores, na.rm = TRUE)
+    median <- apply(scores, 2, median, na.rm = TRUE)
+    min <- apply(scores, 2, min, na.rm = TRUE)
+    max <- apply(scores, 2, max, na.rm = TRUE)
+    sd <- apply(scores, 2, sd, na.rm = TRUE)
+    se <- sd/sqrt(nrow(scores))
+    ci_low <- mean - qt(1 - (0.05 / 2), nrow(scores) - 1) * se
+    ci_high <- mean + qt(1 - (0.05 / 2), nrow(scores) - 1) * se
+    data.frame(
+        coord = seq(-ncol(scores)/2, ncol(scores)/2-1, 1), 
+        mean = mean, median = median, min = min, max = max, 
+        sd = sd, se = se, ci_low = ci_low, ci_high = ci_high
+    )
+}

README.md

@@ -0,0 +1,5 @@
+# AggregatedCoverage
+
+<!-- badges: start -->
+<!-- badges: end -->
+

_pkgdown.yml

@@ -0,0 +1,4 @@
+url: ~
+template:
+  bootstrap: 5
+