Step2:L1 projection of ReferenceCD4Tcells

1. load libraries

2. Read object with all samples

All_samples_Merged <- readRDS("../../0-Seurat_RDS_OBJECT_FINAL/All_samples_Merged_with_STCAT_and_renamed_FINAL.rds")

3. Read object with all Reference_CD4Tcells

 reference_integrated <- readRDS("Step1_sezary_cell_lines_mapped_to_cd4_reference_integrated_before_Query_Projection_03-09-2025.rds")

Trajectory and Pseudotime with Monocle3

reference_integrated$pseudotime[!is.finite(reference_integrated$pseudotime)] <- NA


max_finite <- max(reference_integrated$pseudotime, na.rm = TRUE)
reference_integrated$pseudotime[!is.finite(reference_integrated$pseudotime)] <- max_finite

summary(reference_integrated$pseudotime)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
0.00000 0.01969 0.19290 0.93865 0.90736 5.63665 

table(is.finite(reference_integrated$pseudotime))

TRUE 
8610 

FeaturePlot(
  reference_integrated,
  features = "pseudotime",
  reduction = "umap",
  cols = c("lightblue", "red"),
  label = TRUE
) + ggtitle("UMAP of Integrated CD4⁺ T Cells by Pseudotime") +
  theme(plot.title = element_text(hjust = 0.5))

NA
NA

Trajectory and Pseudotime with Monocle3

# Visualize UMAP colored by original donor (cell_line)
DimPlot(reference_integrated, group.by = "Prediction", reduction = "umap") +
  ggtitle("UMAP of Integrated CD4⁺ T Cells")

# Visualize UMAP colored by original donor (cell_line)
DimPlot(reference_integrated, group.by = "predicted.celltype.l2", reduction = "umap") +
  ggtitle("UMAP of Integrated CD4⁺ T Cells")

3. Subset L1 cells

# Convert numeric pseudotime vector into a 1-row matrix with rowname
pseudo_mat <- matrix(reference_integrated$pseudotime, nrow = 1)
colnames(pseudo_mat) <- colnames(reference_integrated)  # cells
rownames(pseudo_mat) <- "pseudotime"                     # feature name

# Transfer numeric pseudotime
pseudotime_transfer <- TransferData(
  anchorset = anchors,
  refdata = pseudo_mat,
  weight.reduction = L1[["pca"]],
  dims = 1:18
)

0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|

# Extract the data from the assay
pseudotime_vector <- GetAssayData(pseudotime_transfer, slot = "data")["pseudotime", ]

# Add to metadata
mapped_L1$pseudotime <- pseudotime_vector

#  Visualize pseudotime
FeaturePlot(mapped_L1,
            features = "pseudotime",
            reduction = "ref.umap",
            cols = c("lightblue","red"),
            label = TRUE) +
  ggtitle("Pseudotime Mapping of L1 onto Reference") +
  theme(plot.title = element_text(hjust = 0.5))

#  Visualize transferred cell type annotations
DimPlot(mapped_L1, group.by = "Prediction", reduction = "ref.umap") +
  ggtitle("Mapped L1: Prediction Annotations") +
  theme(plot.title = element_text(hjust = 0.5))

DimPlot(mapped_L1, group.by = "predicted.celltype.l2", reduction = "ref.umap") +
  ggtitle("Mapped L1: predicted.celltype.l2 Annotations") +
  theme(plot.title = element_text(hjust = 0.5))

Mapping of L1 on Reference

library(ggplot2)

# Prepare reference data
ref_df <- data.frame(Embeddings(reference_integrated, "umap"))
ref_df$dataset <- "Reference"

# Prepare L1 query data
query_df <- data.frame(Embeddings(mapped_L1, "ref.umap"))
query_df$dataset <- "L1"
query_df$pseudotime <- mapped_L1$pseudotime  # if pseudotime exists

# Plot reference in grey, L1 cells colored by pseudotime
ggplot() +
  geom_point(data = ref_df, aes(x = umap_1, y = umap_2),
             color = "grey80", size = 0.5) +
  geom_point(data = query_df, aes(x = refUMAP_1, y = refUMAP_2, color = pseudotime),
             size = 1) +
  scale_color_gradient(low = "lightblue", high = "red") +
  theme_classic() +
  ggtitle("L1 cells projected onto reference UMAP") +
  theme(plot.title = element_text(hjust = 0.5))

NA
NA

Mapping of L1 on Reference (Azimuth)

library(ggplot2)

# Reference coordinates (grey background)
ref_df <- data.frame(Embeddings(reference_integrated, "umap"))
ref_df$dataset <- "Reference"

# Query (L1) coordinates
query_df <- data.frame(Embeddings(mapped_L1, "ref.umap"))
query_df$dataset <- "L1"

# Make sure annotations exist in mapped_L1
query_df$celltype <- mapped_L1$predicted.celltype.l2  # or "Prediction"

# Plot reference in grey and L1 cells colored by annotation
ggplot() +
  geom_point(data = ref_df, aes(x = umap_1, y = umap_2),
             color = "grey80", size = 0.5) +
  geom_point(data = query_df, aes(x = refUMAP_1, y = refUMAP_2, color = celltype),
             size = 1) +
  scale_color_brewer(palette = "Set1") +
  theme_classic() +
  ggtitle("L1 cells projected onto reference UMAP with annotations") +
  theme(plot.title = element_text(hjust = 0.5))

Mapping of L1 on Reference (STCAT)

library(ggplot2)

# Reference coordinates (grey background)
ref_df <- data.frame(Embeddings(reference_integrated, "umap"))
ref_df$dataset <- "Reference"

# Query (L1) coordinates
query_df <- data.frame(Embeddings(mapped_L1, "ref.umap"))
query_df$dataset <- "L1"

# Make sure annotations exist in mapped_L1
query_df$celltype <- mapped_L1$Prediction  # or "Prediction"

# Plot reference in grey and L1 cells colored by annotation
ggplot() +
  geom_point(data = ref_df, aes(x = umap_1, y = umap_2),
             color = "grey80", size = 0.5) +
  geom_point(data = query_df, aes(x = refUMAP_1, y = refUMAP_2, color = celltype),
             size = 1) +
  scale_color_brewer(palette = "Set1") +
  theme_classic() +
  ggtitle("L1 cells projected onto reference UMAP with annotations") +
  theme(plot.title = element_text(hjust = 0.5))

4. Subset L1 Projection

save(mapped_L1, file = file.path(out_dir, "L1_mapped_on_reference_with_pseudotime-3-8-2025.Robj"))