Add files via upload

Author: sebastian-gregoricchio

R/data.R

@@ -0,0 +1,41 @@
+#' @title RNA-seq example
+#' @description Extract of a DESeq2 result for differential expression analysis on RNA-seq data
+#' @format A data frame with 300 rows and 7 variables:
+#' \describe{
+#'   \item{\code{geneName}}{genes symbols}
+#'   \item{\code{baseMean}}{The average of the normalized count values, dividing by size factors, taken over all samples}
+#'   \item{\code{log2FC}}{the log2 value of the Fold Change expression between two conditions}
+#'   \item{\code{lfcSE}}{log2 Fold Change standard error (SE)}
+#'   \item{\code{stat}}{Wald statistic}
+#'   \item{\code{pvalue}}{Wald test p-value}
+#'   \item{\code{padj}}{BH adjusted p-values}
+#'}
+#' @source \url{http://path.to.paper/}
+"RNAseq"
+#'
+#'
+#'
+#'
+#' @title RNA-seq example
+#' @description List result of the function \code{read.computeMatrix.file} used to read a matrix.gz file generated by deepTools computeMatrix function.
+#' @format A named list of 3 variables:
+#' \describe{
+#'   \item{\code{metadata}}{data.frame with the information gotten from the matrix_file.gz}
+#'   \item{\code{matrix.data}}{data.frame with the scores gotten from}
+#'   \item{\code{original.file.path}}{with full path to the original matrix_file.gz}
+#'}
+#' @source \url{http://path.to.paper/}
+"deeptools.matrix"
+#'
+#'
+#'
+#'
+#' @title CNV data results example
+#' @description Simulation of Copy Number Variation (CNV) analysis on a cohort of patients.
+#' @format A data frame with 25 rows and 9 variables:
+#' \describe{
+#'   \item{\code{geneName}}{hypothetical gene symbols}
+#'   \item{\code{patient_1 ... patient_N}}{hypothetical patients ID}
+#'}
+#' @source Simulated data
+"CNV.data"

R/density.matrix.R

@@ -1,8 +1,8 @@
 #' @title Plot of NGS density signal at specific regions from deepTools matrices.
 #'
-#' @description Plots the density profile of NGS data signals, using as input a score matrix computed by deeptools's computeMatrix function or by \link{computeMatrix.deeptools} from this package.
+#' @description Plots the density profile of NGS data signals, using as input a score matrix computed by deeptools's computeMatrix function or by \link{computeMatrix.deeptools} and \link{density.matrix} functions from this package.
 #'
-#' @param matrix.file A single string indicating a full path to a matrix.gz file generated by \code{deepTools/computeMatrix} or by \link{computeMatrix.deeptools}, or a list generated by the function \link{read.computeMatrix.file}.
+#' @param matrix.file A single string indicating a full path to a matrix.gz file generated by \code{deepTools/computeMatrix} or by \link{computeMatrix.deeptools}, or a list generated by the function \link{read.computeMatrix.file} or \link{density.matrix}.
 #' @param plot.by.group Logical value to define whether plot by group of regions or by sample. By default \code{TRUE}.
 #' @param missing.data.as.zero Logical value to define whether treat missing data as 0. If set as \code{FALSE} missing data will be converted to \code{NA} and will be excluded from the computations of the signal. By default \code{TRUE}.
 #' @param sample.names Samples names could be defined by a string vector. If set as \code{NULL} sample names will be get automatically by the matrix file. By default \code{NULL}. \cr Example: \code{c("sample1", "sample2", "sample3")}
@@ -34,7 +34,7 @@
 #' @param by.row Logical value to define whether the plots should be arranged by row. By default \code{TRUE}.
 #' @param print.multiplot Logical value to define whether to print the multiplot once created. By default \code{FALSE}.
 #'
-#' @return The functions returns a list containing:
+#' @return The function returns a list containing:
 #' \itemize{
 #'   \item \code{data.table} with the computed values used for the plot;
 #'   \item \code{metadata} table with the information gotten from the matrix_file.gz;
@@ -294,7 +294,10 @@ plot.density.profile = function(
 
 
   # Merge of all the tables in a single one
-  full.stat.table = purrr::reduce(.x = sample.stat.table.list, .f = rbind)
+  full.stat.table =
+    purrr::reduce(.x = sample.stat.table.list, .f = rbind) %>%
+    dplyr::mutate(sample = factor(sample, levels = sample_names),
+                  group = factor(group, levels = group_names))
 
 
   ##############################################################################
@@ -480,6 +483,10 @@ plot.density.profile = function(
           print_plot = F,
           line_width = line.width,
           variance_opacity = error.transparency) +
+        labs(color = "regions group",
+             fill = "regions group",
+             linetype = "regions group",
+             group = "regions group") +
         theme(legend.position = legend.position,
               legend.background = element_blank(),
               axis.line = element_line(size = axis.line.width),

R/plot.density.differences.R

@@ -1,8 +1,8 @@
 #' @title Plot the distribution of overall NGS density at specific regions from deepTools matrices.
 #'
-#' @description Computes the score of each element in a list of regions and generates violins plots with percentiles and the mean (optional) for each sample/region. It uses as input a score matrix computed by deeptools's computeMatrix function or by \link{computeMatrix.deeptools} from this package.
+#' @description Computes the score of each element in a list of regions and generates violins plots with percentiles and the mean (optional) for each sample/region. It uses as input a score matrix computed by deeptools's computeMatrix function or by \link{computeMatrix.deeptools} and \link{density.matrix} functions from this package.
 #'
-#' @param matrix.file A single string indicating a full path to a matrix.gz file generated by \code{deepTools/computeMatrix} or by \link{computeMatrix.deeptools}, or a list generated by the function \link{read.computeMatrix.file}.
+#' @param matrix.file A single string indicating a full path to a matrix.gz file generated by \code{deepTools/computeMatrix} or by \link{computeMatrix.deeptools}, or a list generated by the function \link{read.computeMatrix.file} or \link{density.matrix}.
 #' @param plot.by.group Logical value to define whether plot by group of regions or by sample. By default \code{TRUE}.
 #' @param missing.data.as.zero Logical value to define whether treat missing data as 0. If set as \code{FALSE} missing data will be converted to \code{NA} and will be excluded from the computations of the signal. By default \code{TRUE}.
 #' @param sample.names Samples names could be defined by a string vector. If set as \code{NULL} sample names will be get automatically by the matrix file. By default \code{NULL}. \cr Example: \code{c("sample1", "sample2", "sample3")}
@@ -52,7 +52,7 @@
 #' @param by.row Logical value to define whether the plots should be arranged by row. By default \code{TRUE}.
 #' @param print.multiplot Logical value to define whether to print the multiplot once generated. By default \code{FALSE}.
 #'
-#' @return The functions returns a list containing:
+#' @return The function returns a list containing:
 #' \itemize{
 #'   \item \code{data.table} with the computed values used for the plot;
 #'   \item \code{metadata} table with the information obtained from the matrix_file.gz;
@@ -334,7 +334,10 @@ plot.density.summary = function(
 
   # Merge of all the tables in a single one
   full.stat.table = purrr::reduce(.x = sample.stat.table.list, .f = rbind)
-  full.stat.table = Rseb::move.df.col(data.frame = full.stat.table, move.command = "sample first")
+  full.stat.table =
+    Rseb::move.df.col(data.frame = full.stat.table, move.command = "sample first") %>%
+    dplyr::mutate(sample = factor(sample, levels = sample_names),
+                  group = factor(group, levels = group_names))
 
 
   #############################################################################
@@ -967,7 +970,7 @@ plot.density.summary = function(
   ## generate the table with regions (from the matrix, equivalent to the bed used) to add then to the full.stat.table
 
   # Bed files from original matrix
-  regions.position = m$matrix.data[, 1:6]
+  regions.position = matrix.data[, 1:6]
   names(regions.position) = c("chr", "start", "end", "name", "score", "strand")
 
   # Repeating the regions n times as the number of samples

R/plot.density.profile.R

@@ -8,9 +8,9 @@
 #'
 #' @return The functions returns a named list containing:
 #' \itemize{
-#'   \item \code{metadata} data.frame with the information gotten from the matrix_file.gz;
-#'   \item \code{matrix.data} data.frame with the scores gotten from;
-#'   \item \code{original.file.path} with full path to the original matrix_file.gz.
+#'   \item{\code{metadata}}{data.frame with the information gotten from the matrix_file.gz}
+#'   \item{\code{matrix.data}}{data.frame with the scores gotten from}
+#'   \item{\code{original.file.path}}{with full path to the original matrix_file.gz.}
 #'  }
 #'  This list can be passed as it is to the function \link{plot.density.profile}.
 #'