fix: most R CMD Check errors/warnings/notes

except documentation problems (in progress)

DESCRIPTION

@@ -25,19 +25,17 @@ Imports:
     edgeR,
     ggplot2,
     ggrepel,
-    gplots,
-    gridExtra,
-    gridGraphics,
-    lattice,
-    limma,
+    methods,
     plotly,
-    RColorBrewer,
-    RCurl,
     reshape2,
+    rlang,
     S7,
-    stringr,
-    tidyr
+    stats,
+    tibble,
+    tidyr,
+    tidyselect
 Suggests:
+    glue,
     knitr,
     readr,
     rmarkdown,
@@ -51,4 +49,4 @@ Config/testthat/edition: 3
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2

NAMESPACE

@@ -4,7 +4,7 @@ export("%>%")
 export(counts_dat_to_matrix)
 export(create_reneeDataSet_from_dataframes)
 export(create_reneeDataSet_from_files)
-export(filter_low_counts)
+export(filter_counts)
 export(meta_tbl_to_dat)
 export(run_deseq2)
 if (getRversion() < "4.3.0") importFrom("S7", "@")

R/0_renee-class.R

@@ -31,25 +31,35 @@ reneeDataSet <- S7::new_class("renee",
 
 #' Construct a reneeDataSet object from tsv files.
 #'
-#' @param gene_counts_filepath path to tsv file of expected gene counts from RSEM.
 #' @param sample_meta_filepath path to tsv file with sample IDs and metadata for differential analysis.
+#' @param gene_counts_filepath path to tsv file of expected gene counts from RSEM.
 #'
 #' @return reneeDataSet object
 #' @export
 #'
 #' @examples
-#' create_reneeDataSet_from_files(
-#'   sample_meta_filepath = system.file("extdata", "sample_metadata.tsv", package = "reneeTools"),
-#'   gene_counts_filepath = system.file("extdata", "RSEM.genes.expected_count.all_samples.txt", package = "reneeTools")
+#' renee_ds <- create_reneeDataSet_from_files(
+#'   sample_meta_filepath = system.file("extdata",
+#'     "sample_metadata.tsv",
+#'     package = "reneeTools"
+#'   ),
+#'   gene_counts_filepath = system.file("extdata",
+#'     "RSEM.genes.expected_count.all_samples.txt",
+#'     package = "reneeTools"
+#'   )
 #' )
+#' renee_ds@counts$raw %>% head()
+#' renee_ds@sample_meta
 create_reneeDataSet_from_files <- function(sample_meta_filepath, gene_counts_filepath,
-                                           count_type = "raw") {
+                                           count_type = "raw",
+                                           sample_id_colname = "sample_id") {
   count_dat <- readr::read_tsv(gene_counts_filepath)
   sample_meta_dat <- readr::read_tsv(sample_meta_filepath)
   return(create_reneeDataSet_from_dataframes(
     sample_meta_dat = sample_meta_dat,
     count_dat = count_dat,
-    count_type = "raw"
+    count_type = "raw",
+    sample_id_colname = sample_id_colname
   ))
 }
 

R/colors.R

@@ -10,15 +10,21 @@
 #' @keywords internal
 #'
 #' @examples
+#' \dontrun{
 #' set.seed(10)
 #' get_random_colors(5)
+#' }
 get_random_colors <- function(num_colors, n = 2e3) {
   if (num_colors < 1) {
     stop("num_colors must be at least 1")
   }
   n <- 2e3
-  ourColorSpace <- colorspace::RGB(runif(n), runif(n), runif(n))
-  ourColorSpace <- as(ourColorSpace, "LAB")
+  ourColorSpace <- colorspace::RGB(
+    stats::runif(n),
+    stats::runif(n),
+    stats::runif(n)
+  )
+  ourColorSpace <- methods::as(ourColorSpace, "LAB")
   currentColorSpace <- ourColorSpace@coords
   # Set iter.max to 20 to avoid convergence warnings.
   km <- stats::kmeans(currentColorSpace, num_colors, iter.max = 20)

R/data.R

@@ -6,3 +6,14 @@
 #' @source Generated by running RENEE v2.5.8 on the
 #' [test dataset](https://github.com/CCBR/RENEE/tree/e08f7db6c6e638cfd330caa182f64665d2ef37fa/.tests)
 "gene_counts"
+
+#' Sample metadata for the NIDAP test dataset
+"nidap_sample_metadata"
+
+#' Clean raw counts for the NIDAP test dataset.
+#' Pairs with `nidap_sample_metadata`.
+"nidap_clean_raw_counts"
+
+#' Filtered counts for the NIDAP test dataset.
+#' The result of running `filter_counts()` on `nidap_clean_raw_counts`.
+"nidap_filtered_counts"

R/filter.R

@@ -10,7 +10,7 @@
 #' renee_ds <- create_reneeDataSet_from_dataframes(
 #'   as.data.frame(nidap_sample_metadata),
 #'   as.data.frame(nidap_clean_raw_counts),
-#'   sample_id_colname = Sample
+#'   sample_id_colname = "Sample"
 #' )
 #' set.seed(10)
 #' renee_ds2 <- filter_counts(renee_ds)
@@ -154,7 +154,9 @@ filter_counts <- function(renee_ds,
   ########################
   histPlot <- plot_histogram(log_counts, sample_metadata,
     gene_names_column = gene_names_column,
+    groups_column = groups_column,
     labels_column = labels_column,
+    color_values = colorval,
     color_histogram_by_group = color_histogram_by_group,
     set_min_max_for_x_axis_for_histogram = set_min_max_for_x_axis_for_histogram,
     minimum_for_x_axis_for_histogram = minimum_for_x_axis_for_histogram,
@@ -171,8 +173,9 @@ filter_counts <- function(renee_ds,
 
   if (plot_correlation_matrix_heatmap == TRUE) {
     if (interactive_plots == TRUE) {
-      pcaPlot1 <- (pcaPlot) %>% ggplotly(tooltip = c("sample", "group"))
-      histPlot2 <- (histPlot + theme(legend.position = "none")) %>% ggplotly(tooltip = c("sample"))
+      pcaPlot1 <- (pcaPlot) %>% plotly::ggplotly(tooltip = c("sample", "group"))
+      histPlot2 <- (histPlot + ggplot2::theme(legend.position = "none")) %>%
+        plotly::ggplotly(tooltip = c("sample"))
 
       grid::grid.newpage()
       # print(pcaPlot1)
@@ -197,8 +200,9 @@ filter_counts <- function(renee_ds,
     }
   } else {
     if (interactive_plots == TRUE) {
-      pcaPlot1 <- (pcaPlot) %>% ggplotly(tooltip = c("sample", "group"))
-      histPlot2 <- (histPlot + theme(legend.position = "none")) %>% ggplotly(tooltip = "sample")
+      pcaPlot1 <- (pcaPlot) %>% plotly::ggplotly(tooltip = c("sample", "group"))
+      histPlot2 <- (histPlot + ggplot2::theme(legend.position = "none")) %>%
+        plotly::ggplotly(tooltip = "sample")
 
       grid::grid.newpage()
       # print(pcaPlot1)
@@ -248,6 +252,7 @@ remove_low_count_genes <- function(counts_matrix, sample_metadata,
                                    Minimum_Count_Value_to_be_Considered_Nonzero = 8,
                                    Minimum_Number_of_Samples_with_Nonzero_Counts_in_Total = 7,
                                    Minimum_Number_of_Samples_with_Nonzero_Counts_in_a_Group = 3) {
+  value <- NULL
   df <- counts_matrix
 
   df <- df[stats::complete.cases(df), ]
@@ -278,7 +283,8 @@ remove_low_count_genes <- function(counts_matrix, sample_metadata,
     tcounts$Row.names <- NULL
     melted <- reshape2::melt(tcounts, id.vars = groups_column)
     tcounts.tot <- dplyr::summarise(dplyr::group_by_at(melted, c(groups_column, "variable")), sum = sum(value))
-    tcounts.tot %>% tidyr::spread(variable, sum) -> tcounts.group
+    tcounts.group <- tcounts.tot %>%
+      tidyr::pivot_wider(names_from = "variable", values_from = "sum")
     colSums(tcounts.group[(1:colnum + 1)] >= Minimum_Number_of_Samples_with_Nonzero_Counts_in_a_Group) >= 1 -> tcounts.keep
     df.filt <- trans.df[tcounts.keep, ]
     df.filt %>% tibble::rownames_to_column(gene_names_column) -> df.filt

R/histogram.R

@@ -1,14 +1,17 @@
 plot_histogram <- function(log_counts,
                            sample_metadata,
                            gene_names_column,
+                           groups_column,
                            labels_column,
+                           color_values,
                            color_histogram_by_group = FALSE,
                            set_min_max_for_x_axis_for_histogram = FALSE,
                            minimum_for_x_axis_for_histogram = -1,
                            maximum_for_x_axis_for_histogram = 1,
                            legend_position_for_histogram = "top",
                            legend_font_size_for_histogram = 10,
                            number_of_histogram_legend_columns = 6) {
+  Var2 <- colgroup <- value <- NULL
   df.m <- reshape2::melt(log_counts, id.vars = c(gene_names_column))
   df.m <- dplyr::rename(df.m, sample = Var2)
 
@@ -21,13 +24,13 @@ plot_histogram <- function(log_counts,
   }
 
   if (color_histogram_by_group == TRUE) {
-    df.m %>% dplyr::mutate(colgroup = sample_metadata[sample, groups_column]) -> df.m
-    df.m <- df.m[complete.cases(df.m[, "colgroup"]), ]
+    df.m <- df.m %>% dplyr::mutate(colgroup = sample_metadata[sample, groups_column])
+    df.m <- df.m[stats::complete.cases(df.m[, "colgroup"]), ]
     df.m$colgroup <- gsub("\\s", "_", df.m$colgroup)
     df.m$colgroup <- factor(df.m$colgroup, levels = unique(df.m$colgroup))
     ## print(unique(df.m$sample))
     n <- length(levels(df.m$colgroup))
-    cols <- colorval[1:n]
+    cols <- color_values[1:n]
 
     # plot Density
     histPlot <- df.m %>%

R/pca.R

@@ -23,10 +23,11 @@ plot_pca <- function(log_counts,
                      label_offset_y_ = 2,
                      label_offset_x_ = 2) {
   # calculate PCA
+  var <- xdata <- ydata <- group <- NULL
   tedf <- t(log_counts)
   tedf <- tedf[, colSums(is.na(tedf)) != nrow(tedf)]
   tedf <- tedf[, apply(tedf, 2, var) != 0]
-  pca <- prcomp(tedf, scale. = T)
+  pca <- stats::prcomp(tedf, scale. = T)
 
   pcx <- paste0("PC", principal_component_on_x_axis)
   pcy <- paste0("PC", principal_component_on_y_axis)