Merge pull request #45 from m-jahn/dev

fix: formatting issues and examples for CRAN
showteeth · Jan 24, 2025 · 6cd38ab · 6cd38ab
2 parents 8465fd8 + 6430c5f
commit 6cd38ab
Show file tree

Hide file tree

Showing 19 changed files with 390 additions and 322 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -8,14 +8,13 @@ Authors@R: c(
            comment = c(ORCID = "0000-0002-3913-153X"))
   )
 Maintainer: Yabing Song <[email protected]>
-Description: The goal of 'ggcoverage' is to visualize coverage tracks from
-    genomics, transcriptomics or proteomics data. It contains functions to
-    load data from BAM, BigWig, BedGraph, txt, or xlsx files, create
-    genome/protein coverage plots, and add various annotations including
-    base and amino acid composition, GC content, copy number variation
-    (CNV), genes, transcripts, ideograms, peak highlights, HiC contact
-    maps, contact links and protein features. It is based on and
-    integrates well with 'ggplot2'.
+Description: Visualize coverage tracks from genomics, transcriptomics
+    or proteomics data. The package contains functions to load data from 'BAM',
+    'BigWig', 'BedGraph', 'txt', or 'xlsx' files, create genome/protein coverage
+    plots, and add various annotations including base and amino acid
+    composition, GC content, copy number variation (CNV), genes, transcripts,
+    ideograms, peak highlights, HiC contact maps, contact links and protein
+    features. It is based on and integrates well with 'ggplot2'.
 License: MIT + file LICENSE
 URL: https://showteeth.github.io/ggcoverage/,
     https://github.com/showteeth/ggcoverage
@@ -51,6 +50,7 @@ Suggests:
     HiCBricks,
     htmltools,
     knitr,
+    openxlsx,
     rmarkdown
 VignetteBuilder: 
     knitr

diff --git a/R/ConsensusPeak.R b/R/ConsensusPeak.R
@@ -20,12 +20,21 @@
 #' @export
 #'
 #' @examples
-#' # library(ggcoverage)
-#' # peak.file <- system.file("extdata", "ChIP-seq", "consensus.peak", package = "ggcoverage")
-#' # peak.df <- GetConsensusPeak(peak.file = peak.file)
-GetConsensusPeak <- function(peak.file, peak.folder = NULL, mspc.path = NULL, rep.type = c("bio", "tec"), stringency.threshold = 1e-8,
-                             weak.threshold = 1e-4, gamma = 1e-8, alpha = 0.05, min.overlap.num = 1,
-                             multiple.intersections = c("Lowest", "Highest"), parallelism.degree = 1) {
+#' peak_file <- system.file("extdata", "ChIP-seq", "consensus.peak", package = "ggcoverage")
+#' peak_df <- GetConsensusPeak(peak.file = peak_file)
+#' head(peak_df)
+#'
+GetConsensusPeak <- function(peak.file,
+                             peak.folder = NULL,
+                             mspc.path = NULL,
+                             rep.type = c("bio", "tec"),
+                             stringency.threshold = 1e-8,
+                             weak.threshold = 1e-4,
+                             gamma = 1e-8,
+                             alpha = 0.05,
+                             min.overlap.num = 1,
+                             multiple.intersections = c("Lowest", "Highest"),
+                             parallelism.degree = 1) {
   # check parameters
   rep.type <- match.arg(arg = rep.type)
   multiple.intersections <- match.arg(arg = multiple.intersections)
@@ -39,7 +48,9 @@ GetConsensusPeak <- function(peak.file, peak.folder = NULL, mspc.path = NULL, re
     stop("Peak file number is less than or equal to one!")
   } else if (length(peak.file) == 1) {
     # read file directly, do not get consensus peaks
-    consensus.peak.df <- read.table(file = peak.file, sep = "\t", header = FALSE)
+    consensus.peak.df <- read.table(file = peak.file,
+                                    sep = "\t",
+                                    header = FALSE)
     consensus.peak.df <- consensus.peak.df[, 1:5]
     colnames(consensus.peak.df) <- c("chr", "start", "stop", "name", "score")
   } else {
@@ -62,9 +73,26 @@ GetConsensusPeak <- function(peak.file, peak.folder = NULL, mspc.path = NULL, re
 
     # full command
     mspc.cmd <- paste(
-      mspc.path, input.para, "-r", rep.type, "-s", stringency.threshold,
-      "-w", weak.threshold, "-g", gamma, "-a", alpha, "-c", min.overlap.num, "-m", multiple.intersections,
-      "-d", parallelism.degree, "-o", out.folder
+      mspc.path,
+      input.para,
+      "-r",
+      rep.type,
+      "-s",
+      stringency.threshold,
+      "-w",
+      weak.threshold,
+      "-g",
+      gamma,
+      "-a",
+      alpha,
+      "-c",
+      min.overlap.num,
+      "-m",
+      multiple.intersections,
+      "-d",
+      parallelism.degree,
+      "-o",
+      out.folder
     )
     # change language information
     full.mspc.cmd <- paste0("export LC_ALL=en_US.UTF-8;", mspc.cmd)
@@ -78,11 +106,17 @@ GetConsensusPeak <- function(peak.file, peak.folder = NULL, mspc.path = NULL, re
     # obtain results
     if (!file.exists(file.path(out.folder, "ConsensusPeaks.bed"))) {
       out.base <- basename(out.folder)
-      all.tmp.dirs <- sort(dir(path = dirname(out.folder), pattern = out.base, full.names = TRUE))
+      all.tmp.dirs <- sort(dir(
+        path = dirname(out.folder),
+        pattern = out.base,
+        full.names = TRUE
+      ))
       out.folder <- all.tmp.dirs[length(all.tmp.dirs)]
     }
     consensus.peak.file <- file.path(out.folder, "ConsensusPeaks.bed")
-    consensus.peak.df <- read.table(file = consensus.peak.file, sep = "\t", header = TRUE)
+    consensus.peak.df <- read.table(file = consensus.peak.file,
+                                    sep = "\t",
+                                    header = TRUE)
   }
   return(consensus.peak.df)
 }
diff --git a/R/geom_cnv.R b/R/geom_cnv.R
@@ -22,35 +22,37 @@
 #' @export
 #'
 #' @examples
-#' \dontrun{
-#'   library("BSgenome.Hsapiens.UCSC.hg19")
+#' \donttest{
+#'   if (requireNamespace("BSgenome.Hsapiens.UCSC.hg19", quietly = TRUE)) {
+#'     library("BSgenome.Hsapiens.UCSC.hg19")
 #'
-#'   # load track data
-#'   track_file <-
-#'     system.file("extdata", "DNA-seq", "SRR054616.bw", package = "ggcoverage")
-#'   track_df <- LoadTrackFile(
-#'     track.file = track_file,
-#'     format = "bw",
-#'     region = "4:1-160000000"
-#'   )
-#'   track_df$seqnames <- paste0("chr", track_df$seqnames)
+#'     # load track data
+#'     track_file <-
+#'       system.file("extdata", "DNA-seq", "SRR054616.bw", package = "ggcoverage")
+#'     track_df <- LoadTrackFile(
+#'       track.file = track_file,
+#'       format = "bw",
+#'       region = "4:1-160000000"
+#'     )
+#'     track_df$seqnames <- paste0("chr", track_df$seqnames)
 #'
-#'   # read CNV data
-#'   cnv_file <-
-#'     system.file("extdata", "DNA-seq", "SRR054616_copynumber.txt", package = "ggcoverage")
-#'   cnv_df <- read.table(file = cnv_file, sep = "\t", header = TRUE)
+#'     # read CNV data
+#'     cnv_file <-
+#'       system.file("extdata", "DNA-seq", "SRR054616_copynumber.txt", package = "ggcoverage")
+#'     cnv_df <- read.table(file = cnv_file, sep = "\t", header = TRUE)
 #'
-#'   # plot coverage, GC content, CNV
-#'   basic_coverage <- ggcoverage(
-#'     data = track_df,
-#'     color = "grey",
-#'     mark.region = NULL,
-#'     range.position = "out"
-#'   )
+#'     # plot coverage, GC content, CNV
+#'     basic_coverage <- ggcoverage(
+#'       data = track_df,
+#'       color = "grey",
+#'       mark.region = NULL,
+#'       range.position = "out"
+#'     )
 #'
-#'   basic_coverage +
-#'     geom_gc(bs.fa.seq = BSgenome.Hsapiens.UCSC.hg19) +
-#'     geom_cnv(cnv.df = cnv_df, bin.col = 3, cn.col = 4)
+#'     basic_coverage +
+#'       geom_gc(bs.fa.seq = BSgenome.Hsapiens.UCSC.hg19) +
+#'       geom_cnv(cnv.df = cnv_df, bin.col = 3, cn.col = 4)
+#'   }
 #' }
 geom_cnv <- function(cnv.df, bin.col = 3, cn.col = 4, ref.cn = 2,
                      bin.point.color = "grey", bin.point.alpha = 0.6, cn.line.color = "red",

diff --git a/R/geom_gc.R b/R/geom_gc.R
@@ -20,29 +20,31 @@
 #' @export
 #'
 #' @examples
-#' \dontrun{
-#'   library("BSgenome.Hsapiens.UCSC.hg19")
+#' \donttest{
+#'   if (requireNamespace("BSgenome.Hsapiens.UCSC.hg19", quietly = TRUE)) {
+#'     library("BSgenome.Hsapiens.UCSC.hg19")
 #'
-#'   # load track data
-#'   track_file <-
-#'     system.file("extdata", "DNA-seq", "SRR054616.bw", package = "ggcoverage")
-#'   track_df <- LoadTrackFile(
-#'     track.file = track_file,
-#'     format = "bw",
-#'     region = "4:1-160000000"
-#'   )
-#'   track_df$seqnames <- paste0("chr", track_df$seqnames)
+#'     # load track data
+#'     track_file <-
+#'       system.file("extdata", "DNA-seq", "SRR054616.bw", package = "ggcoverage")
+#'     track_df <- LoadTrackFile(
+#'       track.file = track_file,
+#'       format = "bw",
+#'       region = "4:1-160000000"
+#'     )
+#'     track_df$seqnames <- paste0("chr", track_df$seqnames)
 #'
-#'   # plot coverage and GC content
-#'   basic_coverage <- ggcoverage(
-#'     data = track_df,
-#'     color = "grey",
-#'     mark.region = NULL,
-#'     range.position = "out"
-#'   )
+#'     # plot coverage and GC content
+#'     basic_coverage <- ggcoverage(
+#'       data = track_df,
+#'       color = "grey",
+#'       mark.region = NULL,
+#'       range.position = "out"
+#'     )
 #'
-#'   basic_coverage +
-#'     geom_gc(bs.fa.seq = BSgenome.Hsapiens.UCSC.hg19)
+#'     basic_coverage +
+#'       geom_gc(bs.fa.seq = BSgenome.Hsapiens.UCSC.hg19)
+#'   }
 #' }
 geom_gc <- function(fa.file = NULL, bs.fa.seq = NULL, chr.split = "[[:space:]]", guide.line = NULL,
                     line.color = "black", guide.line.color = "red", guide.line.type = "dashed",

diff --git a/R/geom_ideogram.R b/R/geom_ideogram.R
@@ -35,43 +35,44 @@
 #' @export
 #'
 #' @examples
-#' \dontrun{
-#' # note that you need to have package 'ggbio' installed
-#' library(ggbio)
+#' \donttest{
+#'   if (requireNamespace("ggbio", quietly = TRUE)) {
+#'     library(ggbio)
 #'
-#' # load metadata
-#' meta_file <-
-#'   system.file("extdata", "RNA-seq", "meta_info.csv", package = "ggcoverage")
-#' sample_meta <- read.csv(meta_file)
+#'     # load metadata
+#'     meta_file <-
+#'       system.file("extdata", "RNA-seq", "meta_info.csv", package = "ggcoverage")
+#'     sample_meta <- read.csv(meta_file)
 #'
-#' # track folder
-#' track_folder <-
-#'   system.file("extdata", "RNA-seq", package = "ggcoverage")
-#' # load bigwig file
-#' track_df <- LoadTrackFile(
-#'   track.folder = track_folder,
-#'   format = "bw",
-#'   region = "chr14:21,677,306-21,737,601",
-#'   extend = 2000,
-#'   meta.info = sample_meta
-#' )
+#'     # track folder
+#'     track_folder <-
+#'       system.file("extdata", "RNA-seq", package = "ggcoverage")
+#'     # load bigwig file
+#'     track_df <- LoadTrackFile(
+#'       track.folder = track_folder,
+#'       format = "bw",
+#'       region = "chr14:21,677,306-21,737,601",
+#'       extend = 2000,
+#'       meta.info = sample_meta
+#'     )
 #'
-#' # gene annotation
-#' gtf_file <-
-#'   system.file("extdata", "used_hg19.gtf", package = "ggcoverage")
-#' gtf_gr <- rtracklayer::import.gff(con = gtf_file, format = "gtf")
+#'     # gene annotation
+#'     gtf_file <-
+#'       system.file("extdata", "used_hg19.gtf", package = "ggcoverage")
+#'     gtf_gr <- rtracklayer::import.gff(con = gtf_file, format = "gtf")
 #'
-#' # coverage plot + ideogram
-#' basic_coverage <- ggcoverage(
-#'   data = track_df,
-#'   plot.type = "facet",
-#'   range.position = "in",
-#'   facet.y.scale = "fixed"
-#' )
+#'     # coverage plot + ideogram
+#'     basic_coverage <- ggcoverage(
+#'       data = track_df,
+#'       plot.type = "facet",
+#'       range.position = "in",
+#'       facet.y.scale = "fixed"
+#'     )
 #'
-#' basic_coverage +
-#'   geom_gene(gtf.gr = gtf_gr) +
-#'   geom_ideogram(genome = "hg19", plot.space = 0)
+#'     basic_coverage +
+#'       geom_gene(gtf.gr = gtf_gr) +
+#'       geom_ideogram(genome = "hg19", plot.space = 0)
+#'   }
 #' }
 #'
 geom_ideogram <- function(genome = "hg19", mark.color = "red", mark.alpha = 0.7, mark.line.size = 1,

diff --git a/R/geom_protein.R b/R/geom_protein.R
@@ -33,31 +33,33 @@
 #' @export
 #'
 #' @examples
-#' \dontrun{
-#' library(ggplot2)
-#' library(openxlsx)
+#' \donttest{
+#'   if (requireNamespace("openxlsx", quietly = TRUE)) {
+#'     library(ggplot2)
+#'     library(openxlsx)
 #'
-#' # import coverage dataframe with function from openxlsx
-#' coverage.file <- system.file(
-#'   "extdata", "Proteomics", "MS_BSA_coverage.xlsx",
-#'   package = "ggcoverage"
-#' )
-#' coverage.df <- read.xlsx(coverage.file)
-#' head(coverage.df)
+#'     # import coverage dataframe with function from openxlsx
+#'     coverage.file <- system.file(
+#'       "extdata", "Proteomics", "MS_BSA_coverage.xlsx",
+#'       package = "ggcoverage"
+#'     )
+#'     coverage.df <- read.xlsx(coverage.file)
+#'     head(coverage.df)
 #'
-#' # get fasta file
-#' fasta.file <- system.file(
-#'   "extdata", "Proteomics", "MS_BSA_coverage.fasta",
-#'   package = "ggcoverage"
-#' )
+#'     # get fasta file
+#'     fasta.file <- system.file(
+#'       "extdata", "Proteomics", "MS_BSA_coverage.fasta",
+#'       package = "ggcoverage"
+#'     )
 #'
-#' protein.id <- "sp|P02769|ALBU_BOVIN"
-#' ggplot() +
-#'   geom_protein(
-#'     coverage.df = coverage.df,
-#'     fasta.file = fasta.file,
-#'     protein.id = protein.id
-#'   )
+#'     protein.id <- "sp|P02769|ALBU_BOVIN"
+#'     ggplot() +
+#'       geom_protein(
+#'         coverage.df = coverage.df,
+#'         fasta.file = fasta.file,
+#'         protein.id = protein.id
+#'       )
+#'   }
 #' }
 geom_protein <- function(coverage.df, fasta.file, protein.id, XCorr.threshold = 2,
                          confidence = "High", contaminant = NULL, remove.na = TRUE,