Visualization Guide

Introduction

MOFSR provides comprehensive visualization functions for multi-omics clustering analysis. All visualizations work with both base R graphics and ggplot2 when available.

Setup

library(MOFSR)
set.seed(42)

# Generate simulated data with 3 subtypes
n_samples <- 60
true_clusters <- rep(1:3, each = 20)

generate_omics <- function(n, p, clusters) {
  n_clusters <- length(unique(clusters))
  centers <- matrix(rnorm(n_clusters * p, sd = 2), n_clusters, p)
  data <- t(sapply(clusters, function(k) {
    centers[k, ] + rnorm(p, sd = 1)
  }))
  colnames(data) <- paste0("Feature_", seq_len(p))
  rownames(data) <- paste0("Sample_", seq_len(n))
  return(t(data))
}

data_list <- list(
  mRNA = generate_omics(n_samples, 500, true_clusters),
  miRNA = generate_omics(n_samples, 200, true_clusters),
  methylation = generate_omics(n_samples, 100, true_clusters)
)

# Run clustering
result_snf <- run_snf(data_list, n_clusters = 3)

UMAP Visualization

MOFSR includes an internal UMAP implementation that requires no external dependencies.

Basic UMAP Plot

# Compute UMAP coordinates
umap_coords <- compute_umap(data_list, n_neighbors = 15, n_epochs = 100, seed = 42)

# Basic plot
plot_umap(umap_coords, result_snf, title = "Multi-Omics UMAP")

Customized UMAP

# Custom color palette
my_colors <- c("#E64B35", "#4DBBD5", "#00A087")

plot_umap(umap_coords, result_snf, 
          title = "SNF Clustering Results",
          point_size = 3,
          colors = my_colors,
          show_legend = TRUE)

UMAP Parameters

Parameter	Default	Description
`n_neighbors`	15	Number of neighbors for local structure
`min_dist`	0.1	Minimum distance between points
`n_epochs`	200	Number of optimization iterations
`seed`	NULL	Random seed for reproducibility

# Tight clustering (small min_dist)
umap_tight <- compute_umap(data_list, min_dist = 0.01, n_epochs = 100, seed = 42)
plot_umap(umap_tight, result_snf, title = "min_dist = 0.01 (Tight)")

Consensus Matrix Heatmap

Consensus matrices show clustering stability across bootstrap resamples.

Generate Consensus Matrix

# Run consensus clustering
cc_result <- consensus_cluster(data_list$mRNA, maxK = 5, reps = 50, seed = 42)

Basic Heatmap

plot_consensus_heatmap(cc_result[[3]]$consensusMatrix,
                       title = "Consensus Matrix (K=3)")

Ordered by Clusters

plot_consensus_heatmap(cc_result[[3]]$consensusMatrix,
                       clusters = cc_result[[3]]$consensusClass,
                       title = "Consensus Matrix (Ordered)")

Custom Colors

# Purple-green palette
custom_colors <- grDevices::colorRampPalette(c("white", "#7570B3", "#1B9E77"))(100)

plot_consensus_heatmap(cc_result[[3]]$consensusMatrix,
                       colors = custom_colors,
                       title = "Custom Color Palette")

Cluster Quality Metrics

PAC (Proportion of Ambiguous Clustering)

Lower PAC indicates more stable clustering.

# Calculate PAC for each K
pac_values <- calc_pac(cc_result)
print(pac_values)

plot_cluster_quality(pac_values, title = "PAC Scores (Lower is Better)")

Combined Metrics

# Calculate CHI (Calinski-Harabasz Index)
# Higher CHI indicates better separation
chi_values <- sapply(2:5, function(k) {
  CalCHI(t(data_list$mRNA), cc_result[[k]]$consensusClass)
})
names(chi_values) <- 2:5
print(chi_values)

Silhouette Analysis

Silhouette width measures how similar samples are to their own cluster compared to other clusters.

# Compute distance matrix
dist_mat <- dist(t(data_list$mRNA))

# Plot silhouette
plot_silhouette(result_snf$Cluster, dist_mat,
                title = "Silhouette Analysis")

Interpretation

Silhouette > 0.7: Strong cluster structure
Silhouette 0.5-0.7: Reasonable structure
Silhouette 0.25-0.5: Weak structure
Silhouette < 0.25: No substantial structure

Algorithm Comparison

Compare clustering results across multiple algorithms.

# Run multiple algorithms
algorithms <- c("SNF", "RGCCA", "CPCA")

results <- lapply(algorithms, function(alg) {
  run_integration(data_list, algorithm = alg, n_clusters = 3)
})
names(results) <- algorithms

plot_algorithm_comparison(results, title = "Algorithm Agreement")

ARI Matrix

ari_matrix <- compare_clusterings(results)
print(round(ari_matrix, 3))

Survival Analysis (Optional)

If you have survival data, MOFSR can generate Kaplan-Meier curves.

# Example with simulated survival data
time <- rexp(60, rate = 0.1)
event <- sample(0:1, 60, replace = TRUE, prob = c(0.3, 0.7))

# Plot survival curves
plot_survival(time, event, result_snf,
              title = "Survival by Cluster",
              conf_int = TRUE)

Base R vs ggplot2

MOFSR automatically uses ggplot2 when available, falling back to base R graphics otherwise.

Check ggplot2 Availability

has_ggplot <- requireNamespace("ggplot2", quietly = TRUE)
cat("ggplot2 available:", has_ggplot, "\n")

Consistent API

All plot functions have the same API regardless of the backend:

# These work identically with or without ggplot2
plot_umap(umap_coords, clusters)
plot_consensus_heatmap(matrix)
plot_silhouette(clusters, dist_matrix)
plot_cluster_quality(pac_values)

Saving Plots

With ggplot2

library(ggplot2)

# Create plot
p <- plot_umap(umap_coords, result_snf, title = "My Plot")

# Save to file
ggsave("umap_plot.png", p, width = 8, height = 6, dpi = 300)
ggsave("umap_plot.pdf", p, width = 8, height = 6)

With Base R

# PNG
png("umap_plot.png", width = 800, height = 600, res = 150)
plot_umap(umap_coords, result_snf)
dev.off()

# PDF
pdf("umap_plot.pdf", width = 8, height = 6)
plot_umap(umap_coords, result_snf)
dev.off()

Color Palettes

Default Palette

default_colors <- c("#E41A1C", "#377EB8", "#4DAF4A", "#984EA3", "#FF7F00",
                    "#FFFF33", "#A65628", "#F781BF", "#999999", "#66C2A5")
cat("Default 10-color palette:\n")
print(default_colors)

Nature-Style Palettes

# Nature Publishing Group colors
npg_colors <- c("#E64B35", "#4DBBD5", "#00A087", "#3C5488", "#F39B7F",
                "#8491B4", "#91D1C2", "#DC0000", "#7E6148", "#B09C85")

# Lancet colors
lancet_colors <- c("#00468B", "#ED0000", "#42B540", "#0099B4", "#925E9F",
                   "#FDAF91", "#AD002A", "#ADB6B6", "#1B1919")

Summary

MOFSR provides a complete visualization toolkit for multi-omics analysis:

Function	Purpose
`plot_umap()`	Dimensionality reduction visualization
`plot_consensus_heatmap()`	Clustering stability
`plot_cluster_quality()`	Optimal K selection
`plot_silhouette()`	Cluster validation
`plot_algorithm_comparison()`	Method comparison
`plot_survival()`	Clinical outcome analysis

Session Info

sessionInfo()

Zaoqu Liu

2026-01-29