Skip to contents

Create an Alluvial Plot Comparing Original and Predicted Classifications

make_alluvial.Rd

This function generates a detailed alluvial plot to visualize the concordance and discordance between original (e.g., Lymphgen) and predicted (e.g., DLBCLone) class assignments for samples. It supports annotation of concordance rates, per-group accuracy, unclassified rates, and flexible labeling and coloring options.

Usage

make_alluvial(
  optimized,
  count_excluded_as_other = FALSE,
  title = "",
  group_order = NULL,
  add_accuracy_to_title = TRUE,
  accuracy_per_group = TRUE,
  accuracy_type = "sensitivity",
  truth_column = "lymphgen",
  pred_name = "DLBCLone",
  truth_name = "Lymphgen",
  pred_column = "predicted_label_optimized",
  nudge = 0.03,
  box_nudge = 0.15,
  min_flip_n = 10,
  add_percent = TRUE,
  add_unclass_rate = TRUE,
  denom = 20,
  label_size = 3,
  label_lock_y = TRUE,
  label_line_flip_colour = TRUE,
  label_box_flip_colour = TRUE,
  concordant_label_relative_pos = 0.5,
  verbose = FALSE,
  custom_colours = NULL,
  hide_legend = TRUE,
  rotate = FALSE
)

Arguments

optimized

List containing prediction results and metadata, typically output from a DLBCLone optimization function.

count_excluded_as_other

Logical; if TRUE, samples excluded due to missing features are counted as "Other" in the plot.

title

Plot title (default: empty string).

group_order

Character vector specifying the order of groups/classes for axes and coloring.

add_accuracy_to_title

Logical; if TRUE, adds accuracy/concordance rate to the plot title.

accuracy_per_group

Logical; if TRUE, computes and displays per-group accuracy.

accuracy_type

Type of accuracy to report (default: "sensitivity").

nudge

Amount to nudge labels horizontally (default: 0.03).

box_nudge

Amount to nudge label boxes (default: 0.15).

min_flip_n

Minimum number of samples for a flow to be labeled (default: 10).

add_percent

Logical; if TRUE, adds percent concordance to labels.

add_unclass_rate

Logical; if TRUE, adds unclassified rate annotation to the plot.

denom

Denominator for stratum/flow width scaling (default: 20).

label_size

Size of label text (default: 3).

label_lock_y

Logical; if TRUE, locks label movement to the x-axis only.

label_line_flip_colour

Logical; controls color assignment for label lines.

label_box_flip_colour

Logical; controls color assignment for label boxes.

concordant_label_relative_pos

Position for concordant labels: 0 (left), 0.5 (middle), or 1 (right).

rotate
pred

Name of the column in predictions to use for the predicted class (default: "predicted_label_optimized").

original_name

Name for the original class column (default: "Lymphgen").

new_name

Name for the predicted class column (default: "DLBCLone").

Value

A ggplot2 object representing the alluvial plot.

Details

  • Visualizes flows between original and predicted classes, highlighting concordant and discordant assignments.

  • Annotates concordance rate, per-group accuracy, and unclassified rate as specified.

  • Supports flexible labeling, coloring, and axis ordering for publication-quality plots.

Examples

if (FALSE) { # \dontrun{
  make_alluvial(optimized_result)
} # }