Benchmark cell Prediction Methods-5-012-2025 on Clusters

load libraries————————————

1. Load and Subset Normal CD4 T Cells

All_samples_Merged <- readRDS("../All_samples_Merged_Benchmarked_05-11-2025.rds")

Idents(All_samples_Merged) <- "seurat_clusters"
table(All_samples_Merged@active.ident)

   0    1    2    3    4    5    6    7    8    9   10   11   12   13 
6789 5275 4663 4661 4086 3634 3536 3409 3338 3273 3212 1675 1063  691 

2. Create the annotation summary table

library(dplyr)
library(tidyr)
library(purrr)

methods <- c(
  "predicted.id",             #scPred
  "predicted.celltype.l2",    # Azimuth (l2 prediction)
  "singler.immune",           # Example of other annotation methods like SingleR
  "Prediction",               #STCAT
  "scATOMIC_annotation"      #scATOMIC
  )

annotation_summary <- map_dfr(methods, function(m) {
  df <- All_samples_Merged@meta.data
  df %>%
    group_by(seurat_clusters, label = .data[[m]]) %>%
    summarise(n = n(), .groups = "drop") %>%
    group_by(seurat_clusters) %>%
    slice_max(n, n = 1, with_ties = FALSE) %>%
    mutate(method = m)
})



# Set the order of methods
annotation_summary$method <- factor(annotation_summary$method, levels = methods)

head(annotation_summary)

# Should show columns: seurat_clusters | label | n | method

3. Convert to matrix format for plotting

library(tidyr)
library(ggplot2)

annotation_matrix <- annotation_summary %>%
  select(method, seurat_clusters, label) %>%
  pivot_wider(names_from = seurat_clusters, values_from = label)

# Rename methods for the plot
annotation_summary <- annotation_summary %>%
  mutate(method = recode(method,
                         "predicted.id" = "scPred",
                         "predicted.celltype.l2" = "Azimuth.l2",
                         "singler.immune" = "SingleR(Immune)",
                         "Prediction" = "STCAT",
                         "scATOMIC_annotation" = "scATOMIC"))

# Save the annotation summary table to a CSV file for further analysis

write.csv(annotation_summary, "annotation_summary_table.csv", row.names = FALSE)