Add to documentation.

DESCRIPTION

@@ -1,31 +1,31 @@
 Package: MotifStats
 Title: Uncover the relationship between peaks and motifs
 Version: 0.0.0.9000
-Authors@R: 
-  person(given = "Thomas", family = "Roberts", 
-	email = "[email protected]", 
+Authors@R:
+  person(given = "Thomas", family = "Roberts",
+	email = "[email protected]",
 	role = c("aut", "cre"),
 	comment = c(ORCID = "0009-0006-6244-8670"))
-Description: This package calculates metrics to quantify the relationship 
+Description: This package calculates metrics to quantify the relationship
   between peaks and motifs.
 URL: https://github.com/Tomrrr1/MotifStats
 License: GPL (>= 3)
 Encoding: UTF-8
 LazyData: true
-Depends: 
+Depends:
   R (>= 4.2.0)
 Imports:
   Biostrings,
   BSgenome,
-  BSgenome.Hsapiens.UCSC.hg19,
-  BSgenome.Hsapiens.UCSC.hg38,
   GenomicRanges,
   ggplot2,
   memes,
   rGADEM,
   rtracklayer,
   universalmotif
-Suggests: 
+Suggests:
+  BSgenome.Hsapiens.UCSC.hg19,
+  BSgenome.Hsapiens.UCSC.hg38,
   knitr,
   rmarkdown,
   rworkflows,

R/creb_motif.R

@@ -0,0 +1,8 @@
+#' CREB Motif
+#'
+#' This dataset contains the MA0018.5 CREB1 motif from JASPAR2024.
+#'
+#' @format A universalmotif object produced by the \code{read_motif_file}
+#' function.
+#' @source JASPAR2024 \link{https://jaspar.elixir.no/matrix/MA0018.5/}
+"creb_motif"

R/creb_peaks.R

@@ -0,0 +1,8 @@
+#' CREB Peaks
+#'
+#' This dataset contains a set of CREB1 TIP-seq peaks (narrowPeak) produced by
+#' MACS3.
+#'
+#' @format A GRanges peak object outputted by \code{read_peak_file}
+#' function.
+"creb_peaks"

R/de_novo_motif.R

@@ -1,7 +1,7 @@
 #' Perform de novo motif discovery
 #'
 #' \code{de_novo_motif()} is a wrapper of several de novo motif discovery
-#' methods, including Streme (meme suite), meme and rGADEM.
+#' methods, including Streme, meme and rGADEM.
 #'
 #' Streme is preferable over Meme, except when you have a small number of
 #' input sequences (< 50).
@@ -16,6 +16,8 @@
 #' q-value) and the remaining 0.9 peaks as the background. If you wish to
 #' supply your own control sequences, these must be passed as a DNAStringSet
 #' object.
+#' @param genome_build The genome build to use. The peak sequences will be
+#' extracted from this genome.
 #' @param ... Additional parameters to be passed to Streme, Meme or rGADEM. See
 #' the respective documentation for more details.
 #'
@@ -65,9 +67,9 @@ de_novo_motif <- function(peak_input,
 
   if (control == "weak_peaks") {
     top_index <- round(length(peaks) * 0.1)
-    ordered_peaks <- peaks[order(peaks$qValue, decreasing = TRUE), ]
-    top_peaks <- ordered_peaks[seq_len(top_index), ]
-    bottom_peaks <- ordered_peaks[!seq_len(top_index), ]
+    ordered_peaks <- peaks[order(peaks$qValue, decreasing = TRUE),]
+    top_peaks <- ordered_peaks[seq_len(top_index),]
+    bottom_peaks <- ordered_peaks[!seq_len(top_index),]
 
     input_peak_sequences <-
       BSgenome::getSeq(genome_build,
@@ -114,31 +116,3 @@ de_novo_motif <- function(peak_input,
 
   return(motifs)
 }
-
-# de_novo_motif(peak_file = peak_file)
-#
-# peak_file <- "./rep1_peaks.narrowPeak"
-# peaks <- read_peak_file(peak_file)
-# peak_sequences <-
-#    BSgenome::getSeq(BSgenome.Hsapiens.UCSC.hg38::BSgenome.Hsapiens.UCSC.hg38,
-#                     peaks)
-# #
-# #
-# # fa <- system.file("extdata/fasta_ex/fa1.fa", package = "memes")
-# # dreme_out <- memes::runDreme(fa, "shuffle", evalue = 39, outdir = tempdir())
-# # ?memes::runStreme()
-# #
-# # BiocManager::install("rGADEM")
-# # library(rGADEM)
-# # peak_file <- "./rep1_peaks.narrowPeak"
-# # peaks <- read_peak_file(peak_file)
-# # peak_sequences <-
-# #   BSgenome::getSeq(BSgenome.Hsapiens.UCSC.hg38::BSgenome.Hsapiens.UCSC.hg38,
-# #                    peaks)
-# # gad <- rGADEM::GADEM(Sequences = peak_sequences)
-# # rGADEM::getPWM(gad
-# # )
-#
-# ?memes::runStreme()
-
-

R/density_plot.R

@@ -5,6 +5,14 @@
 #'
 #' @import ggplot2
 #'
+#' @param distance_vec A vector of summit-to-motif distances. This is an
+#' output of the \code{summit_to_motif} function.
+#' @param plot_title Title for the density plot.
+#' @param x_label X-axis label.
+#' @param y_label Y-axis label.
+#' @param limits A vector of length 2 denoting the lower and upper bounds of the
+#' x-axis. The default is \code{c(-400, 400)}.
+#'
 #' @returns NULL
 #' @export
 density_plot <- function(distance_vec,
@@ -13,9 +21,9 @@ density_plot <- function(distance_vec,
                          y_label = NULL,
                          limits = c(-400, 400)){
   df <- as.data.frame(distance_vec)
-  colnames(df) <- "dist"
+  colnames(df) <- "distance"
 
-  ggplot(df, aes(x = dist)) +
+  ggplot(df, aes(x = distance)) +
     geom_line(stat = "density", linetype = "solid", linewidth = 1) +
     labs(x = x_label,
          y = y_label,

tests/testthat/test-density_plot.R

@@ -11,7 +11,8 @@ test_that("the density_plot function outputs a ggplot", {
     out_dir = temp_dir,
     genome_build = BSgenome.Hsapiens.UCSC.hg38::BSgenome.Hsapiens.UCSC.hg38
   )
-  res <- density_plot(summit_to_motif_out$distance_to_summit)
+  res <- density_plot(
+    distance_vec = summit_to_motif_out$distance_to_summit)
 
   expect_true(is.ggplot(res))
 })