CytypeR Annotation using AI-Finalized

1. load libraries

2. Load Seurat Object

All_samples_Merged <- readRDS("../../../../0-Seurat_RDS_OBJECT_FINAL/Seurat_object_Final_changes/All_samples_Merged_with_STCAT_Annotation_final-5-09-2025.rds")

DefaultAssay(All_samples_Merged) <- "RNA"

# If RNA has not been normalized yet, run NormalizeData (safe to run again)
All_samples_Merged <- NormalizeData(All_samples_Merged,
                                    normalization.method = "LogNormalize",
                                    scale.factor = 1e4,
                                    verbose = TRUE)

3. Run CytypeR for cluster annotation

Idents(All_samples_Merged) <- "seurat_clusters"

# ---------------------------------------------------------
# 2️⃣ Find marker genes per cluster
SS_markers <- FindAllMarkers(
  All_samples_Merged,
  only.pos = TRUE,
  min.pct = 0.25,
  logfc.threshold = 0.25,
  min.pct.diff = 0.2
  
)

library(dplyr)

# Precise blacklist for uninformative genes
blacklist_patterns <- c(
  "^TRAV", "^TRBV", "^TRGV", "^TRDV", "^TRBC", "^TRAC", "^TRDC", "^TRGC", # TCR
  "^IGH", "^IGK", "^IGL", "^IGJ",                                         # Ig genes
  "^RPL", "^RPS",                                                         # ribosomal
  "^MT-",                                                                 # mitochondria
  "^HBA", "^HBB", "^HB[ABZ]",                                             # hemoglobins
  "^NEAT1$", "^MALAT1$",                                                  # optional lncRNAs
  "^XIST$"                              )

blacklist_regex <- paste(blacklist_patterns, collapse = "|")

# Preview which markers will be removed
to_remove <- SS_markers %>%
  filter(grepl(blacklist_regex, gene, ignore.case = TRUE))
message("Rows to remove: ", nrow(to_remove))
head(to_remove$gene)

# Filter markers (keep important metabolic/proliferation genes)
SS_markers_filtered <- SS_markers %>%
  filter(!grepl(blacklist_regex, gene, ignore.case = TRUE))

3. Run CytypeR for cluster annotation