Add 'colors' Parameter to pathway_heatmap and pathway_pca Functions

This update introduces a significant enhancement to the `pathway_heatmap` and `pathway_pca` functions by adding a new `colors` parameter. This parameter allows users to customize the color schemes of their heatmaps and PCA plots, providing a more tailored and visually appealing representation of their data.

#### Key Changes:
1. **`pathway_heatmap` Function:**
   - Added `colors` parameter to allow custom color choices for facet label backgrounds.
   - The parameter influences the background of the facet strips generated by `ggh4x::facet_nested`.
   - Default color set is used if `colors` is not specified or NULL.

2. **`pathway_pca` Function:**
   - Introduced `colors` parameter to customize the color scheme of PCA scatter and density plots.
   - Ensured compatibility with existing color mechanisms and added error checks for color vector length.
   - Default color palette applied if `colors` is NULL.

#### Enhanced Examples:
- Updated examples to demonstrate the use of the new `colors` parameter in both functions.
- Provided examples with both default and custom color sets for real and simulated datasets.

This update aims to provide users with greater control over the aesthetics of their plots, thereby enhancing the interpretability and presentation quality of their data analyses.

R/pathway_heatmap.R

@@ -6,6 +6,11 @@
 #' @param abundance A matrix or data frame of pathway abundance data, where columns correspond to samples and rows correspond to pathways.
 #' @param metadata A data frame of metadata, where each row corresponds to a sample and each column corresponds to a metadata variable.
 #' @param group A character string specifying the column name in the metadata data frame that contains the group variable.
+#' @param colors A vector of colors used for the background of the facet labels in the
+#' heatmap. These colors are applied to the background of the facet strips generated by
+#' the 'ggh4x::facet_nested' function, allowing customization of the facet label appearance.
+#' Each color in the vector corresponds to a group level defined in the 'group' parameter.
+#' If NULL or not provided, a default color set is used for the facet strips.
 #'
 #' @return A ggplot heatmap object. The output is a ggplot object representing the heatmap of the predicted functional pathway abundance data. The heatmap visualizes the z score of pathways in different samples.
 #' @export
@@ -32,26 +37,34 @@
 #' metadata_example <- data.frame(sample_name = colnames(kegg_abundance_example),
 #'                                group = factor(rep(c("Control", "Treatment"), each = 5)))
 #'
-#' # Create a heatmap
-#' pathway_heatmap(kegg_abundance_example, metadata_example, "group")
+#' # Custom colors for facet strips
+#' custom_colors <- c("skyblue", "salmon")
+#'
+#' # Create a heatmap using custom colors for facet strips
+#' pathway_heatmap(kegg_abundance_example, metadata_example, "group", colors = custom_colors)
+#'
 #' # Use real dataset
 #' data("metacyc_abundance")
 #' data("metadata")
 #' metacyc_daa_results_df <- pathway_daa(abundance = metacyc_abundance %>%
-#' column_to_rownames("pathway"),
-#' metadata = metadata, group = "Environment", daa_method = "LinDA")
+#'                                       column_to_rownames("pathway"),
+#'                                       metadata = metadata, group = "Environment", daa_method = "LinDA")
 #' annotated_metacyc_daa_results_df <- pathway_annotation(pathway = "MetaCyc",
-#' daa_results_df = metacyc_daa_results_df, ko_to_kegg = FALSE)
+#'                                                        daa_results_df = metacyc_daa_results_df, ko_to_kegg = FALSE)
 #' feature_with_p_0.05 <- metacyc_daa_results_df %>% filter(p_adjust < 0.05)
 #' pathway_heatmap(abundance = metacyc_abundance %>%
-#' right_join(annotated_metacyc_daa_results_df %>%
-#' select(all_of(c("feature","description"))), by = c("pathway" = "feature")) %>%
-#' filter(pathway %in% feature_with_p_0.05$feature) %>%
-#' select(-"pathway") %>%
-#' column_to_rownames("description"), metadata = metadata, group = "Environment")
+#'                 right_join(annotated_metacyc_daa_results_df %>%
+#'                            select(all_of(c("feature","description"))), by = c("pathway" = "feature")) %>%
+#'                 filter(pathway %in% feature_with_p_0.05$feature) %>%
+#'                 select(-"pathway") %>%
+#'                 column_to_rownames("description"),
+#'                 metadata = metadata, group = "Environment", colors = custom_colors)
 #' }
 utils::globalVariables(c("rowname","Sample","Value","quantile","facet_nested","strip_nested","elem_list_rect"))
-pathway_heatmap <- function(abundance, metadata, group) {
+pathway_heatmap <- function(abundance,
+                            metadata,
+                            group,
+                            colors) {
    # Heatmaps use color changes to visualize changes in values. However, if the
    # data for plotting the heat map are too different, for example, if the heat
    # map is plotted using gene expression data, gene1 is expressed above 1000 in
@@ -110,7 +123,9 @@ pathway_heatmap <- function(abundance, metadata, group) {
   # Compute breaks from the data
   breaks <- range(long_df$Value, na.rm = TRUE)
 
-  colors <- c("#d93c3e", "#3685bc", "#6faa3e", "#e8a825", "#c973e6", "#ee6b3d", "#2db0a7", "#f25292")
+  if (is.null(colors)) {
+    colors <- c("#d93c3e", "#3685bc", "#6faa3e", "#e8a825", "#c973e6", "#ee6b3d", "#2db0a7", "#f25292")
+  }
 
   # Create the heatmap using ggplot
   p <-

R/pathway_pca.R

@@ -20,15 +20,26 @@
 #' metadata_example <- data.frame(sample_name = colnames(kegg_abundance_example),
 #'                                group = factor(rep(c("Control", "Treatment"), each = 5)))
 #'
-#' pca_plot <- pathway_pca(kegg_abundance_example, metadata_example, "group")
+#' # Define custom colors for PCA plot
+#' custom_colors <- c("blue", "red")
+#'
+#' # Generate PCA plot with custom colors
+#' pca_plot <- pathway_pca(kegg_abundance_example, metadata_example, "group", colors = custom_colors)
+#'
+#' pca_plot <- pathway_pca(kegg_abundance_example, metadata_example, "group", colors = NULL)
+#'
 #' print(pca_plot)
 #'
 #' \donttest{
 #' data("metacyc_abundance")
 #' data("metadata")
-#' pathway_pca(metacyc_abundance %>% column_to_rownames("pathway"), metadata, "Environment")
+#' # Generate PCA plot for real dataset with custom colors
+#' pathway_pca(metacyc_abundance %>% column_to_rownames("pathway"), metadata, "Environment", colors = c("green", "purple"))
 #' }
-pathway_pca <- function(abundance, metadata, group){
+pathway_pca <- function(abundance,
+                        metadata,
+                        group,
+                        colors = NULL){
   # due to NSE notes in R CMD check
   PC1 = PC2 = Group = NULL
   # Perform PCA on the abundance data, keeping the first two principal components
@@ -43,18 +54,24 @@ pathway_pca <- function(abundance, metadata, group){
 
   levels <- length(levels(factor(pca$Group)))
 
+  # Set default colors if colors are not provided
+  if (is.null(colors)) {
+    colors <- c("#d93c3e", "#3685bc","#208A42","#89288F","#F47D2B",
+                "#FEE500","#8A9FD1","#C06CAB","#E6C2DC","#90D5E4",
+                "#89C75F","#F37B7D","#9983BD","#D24B27","#3BBCA8",
+                "#6E4B9E","#0C727C", "#7E1416","#D8A767","#3D3D3D")[1:levels]
+  }
 
-
-  colors_choices <- c("#d93c3e", "#3685bc","#208A42","#89288F","#F47D2B",
-             "#FEE500","#8A9FD1","#C06CAB","#E6C2DC","#90D5E4",
-             "#89C75F","#F37B7D","#9983BD","#D24B27","#3BBCA8",
-             "#6E4B9E","#0C727C", "#7E1416","#D8A767","#3D3D3D")[1:levels]
+  # Ensure the number of colors matches the number of levels in Group
+  if (length(colors) != levels) {
+    stop("The length of colors vector must match the number of levels in Group")
+  }
 
 
   # Create a ggplot object for the PCA scatter plot
   Fig1a.taxa.pca <- ggplot2::ggplot(pca,ggplot2::aes(PC1,PC2))+
     ggplot2::geom_point(size=2,ggplot2::aes(color=Group),show.legend = T)+
-    ggplot2::scale_color_manual(values=colors_choices)+
+    ggplot2::scale_color_manual(values=colors)+
     ggplot2::stat_ellipse(ggplot2::aes(color = Group),fill="white",geom = "polygon",
                  level=0.95,alpha = 0.01,show.legend = F)+
     ggplot2::labs(x=paste0("PC1(",round(pca_proportion[1],1),"%)"),y=paste0("PC2(",round(pca_proportion[2],1),"%)"),color = group)+
@@ -76,7 +93,7 @@ pathway_pca <- function(abundance, metadata, group){
     ggplot2::ggplot(pca) +
     ggplot2::geom_density(ggplot2::aes(x=PC1, group=Group, fill=Group), # Plot the density of PC1
                  color="black", alpha=1, position = 'identity',show.legend = F) +
-    ggplot2::scale_fill_manual(values=colors_choices) + # Manually set the fill color for each group
+    ggplot2::scale_fill_manual(values=colors) + # Manually set the fill color for each group
     ggplot2::theme_classic() + # Set the classic theme
     ggplot2::scale_y_discrete(expand = c(0,0.001)) + # Scale the y-axis with a small expansion to improve appearance
     ggplot2::labs(x=NULL, y=NULL) + # Remove x and y labels
@@ -88,7 +105,7 @@ pathway_pca <- function(abundance, metadata, group){
     ggplot2::ggplot(pca) +
     ggplot2::geom_density(ggplot2::aes(x=PC2, group=Group, fill=Group), # Plot the density of PC2
                  color="black", alpha=1, position = 'identity',show.legend = F) +
-    ggplot2::scale_fill_manual(values=colors_choices) + # Manually set the fill color for each group
+    ggplot2::scale_fill_manual(values=colors) + # Manually set the fill color for each group
     ggplot2::theme_classic() + # Set the classic theme
     ggplot2::scale_y_discrete(expand = c(0,0.001)) + # Scale the y-axis with a small expansion to improve appearance
     ggplot2::labs(x=NULL, y=NULL) + # Remove x and y labels