v4 Miltenyi annotation
Kimberly Olney, PhD
02/09/2024
Pipseq chemistry kit comparison Sample NPID control female NA05-055
Libraries & paths
library(dplyr)
library(Seurat)
library(patchwork)
library(knitr)
library(dittoSeq)
library(reshape2)
Sys.setenv(RSTUDIO_PANDOC="/usr/local/biotools/pandoc/3.1.2/bin")
sampleID <- c("v4_Miltenyi")
sample_color.panel <- c("gold")
color.panel <- dittoColors()Read in object
# read object
dataObject <- readRDS(file = paste0("../../../rObjects/", sampleID, ".filtered.rds"))
markers.strict <- readRDS(file = paste0("../../../rObjects/",
sampleID, "_FindAllMarkers_strict_logFC1_FDR0.05.rds"))Unannotated
UMAP
ditto_umap <- dittoDimPlot(object = dataObject,
var = "seurat_clusters",
reduction.use = "umap",
do.label = TRUE,
labels.highlight = TRUE)
ditto_umap
Nuclei count per cluster
count_per_cluster <- FetchData(dataObject,
vars = c("ident", "orig.ident")) %>%
dplyr::count(ident, orig.ident) %>%
tidyr::spread(ident, n)
count_per_cluster## orig.ident 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14
## 1 v4Miltenyi 2057 1953 1775 1334 1277 1205 872 827 522 464 432 378 354 223 193
## 15 16 17
## 1 168 129 123count_melt <- reshape2::melt(count_per_cluster)
colnames(count_melt) <- c("ident", "cluster", "number of nuclei")
count_max <- count_melt[which.max(count_melt$`number of nuclei`), ]
count_max_value <- count_max$`number of nuclei`
cellmax <- count_max_value + 200 # so that the figure doesn't cut off the text
count_bar <- ggplot(count_melt, aes(x = factor(cluster), y = `number of nuclei`, fill = `ident`)) +
geom_bar(
stat = "identity",
colour = "black",
width = 1,
position = position_dodge(width = 0.8)
) +
geom_text(
aes(label = `number of nuclei`),
position = position_dodge(width = 0.9),
vjust = -0.25,
angle = 45,
hjust = -.01
) +
theme_classic() + scale_fill_manual(values = sample_color.panel) +
ggtitle("Number of nuclei per cluster") + xlab("cluster") +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
scale_y_continuous(limits = c(0, cellmax))
count_bar
Cluster tree
dataObject <- BuildClusterTree(
object = dataObject,
dims = 1:30,
reorder = FALSE,
reorder.numeric = FALSE
)
tree <- dataObject@tools$BuildClusterTree
tree$tip.label <- paste0("Cluster ", tree$tip.label)
nClusters <- length(tree$tip.label)
tree_graph <- ggtree::ggtree(tree, aes(x, y)) +
scale_y_reverse() +
ggtree::geom_tree() +
ggtree::theme_tree() +
ggtree::geom_tiplab(offset = 1) +
ggtree::geom_tippoint(color = color.panel[1:nClusters],
shape = 16,
size = 5) +
coord_cartesian(clip = 'off') +
theme(plot.margin = unit(c(0, 2.5, 0, 0), 'cm'))
tree_graph
Violins - Canonical cell-type markers
Markers obtained from dropviz
# Astrocytes
VlnPlot(dataObject,
features = c("AQP4", "GJA1", "CLU", "GFAP"))
# Endothelial
VlnPlot(dataObject,
features = c("CLDN5", "ADGRF5", "FLT1"))
# Fibroblast-Like_Dcn
VlnPlot(dataObject,
features = c("COL1A1", "COL1A2", "DCN"))
# Microglia / Marchophage
VlnPlot(dataObject,
features = c("C1QA", "C1QC", "C1QB"))
# Microglia / Marchophage
VlnPlot(dataObject,
features = c( "HEXB", "TMEM119", "ITGAM", "TYROBP","P2RY12", "AIF1"))
# Neurons
VlnPlot(dataObject,
features = c("RBFOX3", "SNAP25","SYT1", "GAD1", "GAD2"))
# Oligodendrocyte
VlnPlot(dataObject,
features = c("PLP1","MBP", "MOG"))
# OPC
VlnPlot(dataObject,
features = c("OLIG1","PDGFRA", "VCAN", "TNR"))
# Smooth muscle
VlnPlot(dataObject,
features = c("ACTA2","RGS5", "VTN", "MYL5"))
Percent cell type - Canonical cell-type markers
# astrocyte
dataObject[["percent.astrocyte"]] <- PercentageFeatureSet(dataObject,
features = c("CLU", "GFAP", "AQP4", "GJA1"))
# endothelial
dataObject[["percent.endothelial"]] <- PercentageFeatureSet(dataObject,
features = c("CLDN5", "ADGRF5", "FLT1"))
# fibroblast
dataObject[["percent.fibroblast"]] <- PercentageFeatureSet(dataObject,
features = c("COL1A1", "COL1A2", "DCN"))
# microglia
dataObject[["percent.microglia"]] <- PercentageFeatureSet(dataObject,
features = c("HEXB", "C1QA", "C1QC", "C1QB",
"TMEM119", "ITGAM", "TYROBP","P2RY12", "AIF1"))
# neuron
dataObject[["percent.neurons"]] <- PercentageFeatureSet(dataObject,
features = c("RBFOX3", "SNAP25","SYT1", "GAD1", "GAD2"))
# oligodendrocyte
dataObject[["percent.oligodendrocyte"]] <- PercentageFeatureSet(dataObject,
features = c("PLP1","MBP", "MOG"))
# oligodendrocyte precursor cells
dataObject[["percent.opc"]] <- PercentageFeatureSet(dataObject,
features = c("OLIG1","PDGFRA", "VCAN", "TNR"))
# smooth muscle
dataObject[["percent.smooth"]] <- PercentageFeatureSet(dataObject,
features = c("ACTA2","RGS5", "VTN", "MYL5"))Feature plot percent cell type - Canonical cell-type markers
# astrocyte
FeaturePlot(dataObject, features = "percent.astrocyte", label = TRUE) 
# endothelial
FeaturePlot(dataObject, features = "percent.endothelial", label = TRUE) 
# fibroblast
FeaturePlot(dataObject, features = "percent.fibroblast", label = TRUE) 
# microglia
FeaturePlot(dataObject, features = "percent.microglia", label = TRUE) 
# neuron
FeaturePlot(dataObject, features = "percent.neurons", label = TRUE) 
# oligodendrocyte
FeaturePlot(dataObject, features = "percent.oligodendrocyte", label = TRUE) 
# oligodendrocyte precursor cells
FeaturePlot(dataObject, features = "percent.opc", label = TRUE) 
# smooth
FeaturePlot(dataObject, features = "percent.smooth", label = TRUE) 
Markers per cluster
Get markers for each cluster
# unique clusters variable
unique_clusters <- unique(markers.strict$cluster)
# empty list to store individual cluster data frames
cluster_list <- list()
# loop through each cluster and create a data frame
for (i in unique_clusters) {
cluster_name <- paste0("cluster", i)
cluster_data <- markers.strict[markers.strict$cluster == i, ]
assign(cluster_name, cluster_data)
cluster_list[[cluster_name]] <- cluster_data
}Feature plot
# UMAP showing the expression of select features
umap_feature <-
FeaturePlot(dataObject,
features = c("TYROBP", "MOG", "AQP4", "RBFOX3"))
umap_feature
Cluster Annotation
Cluster 0 - oligodendrocyte
# Number of cells per condition
count_per_cluster[,c(1,2)]## orig.ident 0
## 1 v4Miltenyi 2057# UMAP with only cluster 0
DimPlot(object = subset(dataObject, seurat_clusters == "0"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[1])
VlnPlot(dataObject,
features = cluster0$gene[1:10],
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster0$gene[1:10]## [1] "CNP" "LINC00844" "APOD" "LINC01608" "SUN2" "AMER2"
## [7] "FTH1" "VWA1" "MBP" "PLP1"Cluster 1 - noise
count_per_cluster[,c(1,3)]## orig.ident 1
## 1 v4Miltenyi 1953DimPlot(object = subset(dataObject, seurat_clusters == "1"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[2])
VlnPlot(dataObject,
features = cluster1$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster1$gene[1:10]## [1] "LINC01608" "DYSF" "LAMA2" "LINC01170" "KIF19"
## [6] "SVEP1" "CR1" "RP4-537K23.4" "LINC02073" "RP11-50D16.4"Cluster 2 - oligodendrocyte
count_per_cluster[,c(1,4)]## orig.ident 2
## 1 v4Miltenyi 1775DimPlot(object = subset(dataObject, seurat_clusters == "2"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[3])
VlnPlot(dataObject,
features = cluster2$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster2$gene[1:10]## [1] "SLC5A11" "ANKRD18A" "LRRC63" "SAMD12" "LINC00609"
## [6] "RASGRF1" "RP11-141F7.1" "RP1-223B1.1" "SEC14L5" "LDB3"Cluster 3 - noise
count_per_cluster[,c(1,4)]## orig.ident 2
## 1 v4Miltenyi 1775DimPlot(object = subset(dataObject, seurat_clusters == "3"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[4])
VlnPlot(dataObject,
features = cluster3$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster3$gene[1:10]## [1] "FGFR1" "SH3RF1" "GADD45B" "ITPKB" "UHRF2" "FNIP2"
## [7] "SH3PXD2B" "GTF2H2B" "PLA2G4C" "CAMK2D"Cluster 4 - noise
count_per_cluster[,c(1,5)]## orig.ident 3
## 1 v4Miltenyi 1334DimPlot(object = subset(dataObject, seurat_clusters == "4"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[5])
VlnPlot(dataObject,
features = cluster4$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster4$gene[1:10]## [1] "SLC5A11" "MARCKSL1" "SPP1" "TUBA1A" "S100B" "CNP"
## [7] "STMN1" "RASGRF1" "TF" "PLP1"Cluster 5 - noise
count_per_cluster[,c(1,6)]## orig.ident 4
## 1 v4Miltenyi 1277DimPlot(object = subset(dataObject, seurat_clusters == "5"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[6])
VlnPlot(dataObject,
features = cluster5$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster5$gene[1:10]## [1] "CCDC200" "LINC00685" "CERS4" "SLCO5A1" "SAMHD1" "ATAD3C"
## [7] "LINC00463" "PRDM1" "MMP17" "COL19A1"Cluster 6 - oligodendrocyte
count_per_cluster[,c(1,7)]## orig.ident 5
## 1 v4Miltenyi 1205DimPlot(object = subset(dataObject, seurat_clusters == "6"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = "#CC79A7")
VlnPlot(dataObject,
features = cluster6$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster6$gene[1:10]## [1] "QDPR" "CD9" "AMD1" "TMTC4" "SUN2"
## [6] "H3-3B" "SFRP1" "SYT11" "RP4-613B23.1" "PSAP"Cluster 7 - noise
count_per_cluster[,c(1,8)]## orig.ident 6
## 1 v4Miltenyi 872DimPlot(object = subset(dataObject, seurat_clusters == "7"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[7])
VlnPlot(dataObject,
features = cluster7$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster7$gene[1:10]## [1] "CNDP1" "PLA2G4C" "MIDN" "IL6R" "IRAK2"
## [6] "ARRB1" "AC005609.16" "LINC02197" "MAP2K3" "SPRED3"Cluster 8 - astrocyte
count_per_cluster[,c(1,9)]## orig.ident 7
## 1 v4Miltenyi 827DimPlot(object = subset(dataObject, seurat_clusters == "8"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[8])
VlnPlot(dataObject,
features = cluster8$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster8$gene[1:10]## [1] "GLIS3" "CD44" "FAM189A2" "GFAP" "ADCY2"
## [6] "RFX4" "RP11-6L16.1" "WWC1" "ABLIM1" "AQP4"Cluster 9 - microglia
count_per_cluster[,c(1,10)]## orig.ident 8
## 1 v4Miltenyi 522DimPlot(object = subset(dataObject, seurat_clusters == "9"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[9])
VlnPlot(dataObject,
features = cluster9$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster9$gene[1:10]## [1] "ADAM28" "SLC11A1" "DOCK8" "LRMDA" "ARHGAP24" "DENND3"
## [7] "APBB1IP" "PTPRC" "MEF2C" "ST6GAL1"Cluster 10 - neuron
count_per_cluster[,c(1,11)]## orig.ident 9
## 1 v4Miltenyi 464DimPlot(object = subset(dataObject, seurat_clusters == "10"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[10])
VlnPlot(dataObject,
features = cluster10$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster10$gene[1:10]## [1] "DDIT3" "FOS" "EGR1" "GADD45B"
## [5] "HSP90B1" "RP11-181L23.10" "NAMPT" "FGFR1"
## [9] "ATF3" "CREB5"Cluster 11 - polydendrocyte
count_per_cluster[,c(1,12)]## orig.ident 10
## 1 v4Miltenyi 432DimPlot(object = subset(dataObject, seurat_clusters == "11"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[11])
VlnPlot(dataObject,
features = cluster11$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster11$gene[1:10]## [1] "TNR" "VCAN" "MMP16" "PTPRZ1" "CA10" "LHFPL3" "MEGF11" "FGF14"
## [9] "DSCAM" "LUZP2"Cluster 12 - astrocyte
count_per_cluster[,c(1,13)]## orig.ident 11
## 1 v4Miltenyi 378DimPlot(object = subset(dataObject, seurat_clusters == "12"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[12])
VlnPlot(dataObject,
features = cluster12$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster12$gene[1:10]## [1] "IRAG1" "SLC1A2" "BMPR1B" "FAM189A2" "AQP4" "RFX4"
## [7] "ADGRV1" "RYR3" "SLC14A1" "ADCY2"Cluster 13 - neuron
count_per_cluster[,c(1,14)]## orig.ident 12
## 1 v4Miltenyi 354DimPlot(object = subset(dataObject, seurat_clusters == "13"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[13])
VlnPlot(dataObject,
features = cluster13$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster13$gene[1:10]## [1] "RP11-909M7.3" "PAK3" "MEG3" "MYT1L" "CELF4"
## [6] "GRIP1" "GRIN2B" "KCNC2" "GRIA1" "CACNA1B"Cluster 14 - neuron
count_per_cluster[,c(1,15)]## orig.ident 13
## 1 v4Miltenyi 223DimPlot(object = subset(dataObject, seurat_clusters == "14"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[14])
VlnPlot(dataObject,
features = cluster14$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster14$gene[1:10]## [1] "RALYL" "RP11-909M7.3" "NELL2" "MEG3" "SNAP25"
## [6] "LRFN5" "SCN2A" "UNC80" "GRM5" "SLC4A10"Cluster 15 - neuron
count_per_cluster[,c(1,16)]## orig.ident 14
## 1 v4Miltenyi 193DimPlot(object = subset(dataObject, seurat_clusters == "15"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[15])
VlnPlot(dataObject,
features = cluster15$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster15$gene[1:10]## [1] "HS3ST4" "CELF4" "CTD-2337L2.1" "GABRB2" "MYT1L"
## [6] "GABRG3" "SCN2A" "PAK3" "MIR137HG" "MIAT"Cluster 16 - fibroblast-like
count_per_cluster[,c(1,17)]## orig.ident 15
## 1 v4Miltenyi 168DimPlot(object = subset(dataObject, seurat_clusters == "16"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[16])
VlnPlot(dataObject,
features = cluster16$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster16$gene[1:10]## [1] "EBF1" "NID1" "CFH" "LEF1" "DCN" "COL1A2" "IFITM1" "NR2F2"
## [9] "PDLIM1" "FMO2"Cluster 17 - noise
count_per_cluster[,c(1,18)]## orig.ident 16
## 1 v4Miltenyi 129DimPlot(object = subset(dataObject, seurat_clusters == "17"),
reduction = "umap",
label = TRUE,
label.box = TRUE,
label.size = 3,
repel = TRUE,
cols = color.panel[17])
VlnPlot(dataObject,
features = cluster17$gene[1:10],
cols = color.panel,
stack = TRUE,
flip = TRUE,
split.by = "seurat_clusters")
cluster17$gene[1:10]## [1] "ZSCAN31" "SLC5A11" "RP11-141F7.1" "LRRC63" "SAMD12"
## [6] "LINC00609" "RP1-223B1.1" "PLEKHG1" "LINC01877" "GPX6"Assign identities
Individual
dataObject.annotated <- RenameIdents(object = dataObject,
"0" = "oligodendrocyte 1",
"1" = "noise 1",
"2" = "oligodendrocyte 2",
"3" = "noise 2",
"4" = "noise 3",
"5" = "noise 4",
"6" = "oligodendrocyte/polydendrocyte",
"7" = "noise 5",
"8" = "astrocyte 1",
"9" = "microglia",
"10" = "neuron 1",
"11" = "polydendrocyte",
"12" = "astrocyte 2",
"13" = "neuron 2",
"14" = "neuron 3",
"15" = "neuron 4",
"16" = "fibroblast-like",
"17" = "noise 6")
dataObject.annotated$individual_clusters <- factor(Idents(dataObject.annotated))
UMAP_ind <- dittoDimPlot(object = dataObject.annotated,
var = "individual_clusters",
reduction.use = "umap",
do.label = TRUE,
labels.highlight = TRUE)
UMAP_ind
## png
## 2Nuclei count per cluster
count_per_cluster <- FetchData(dataObject.annotated,
vars = c("ident", "orig.ident")) %>%
dplyr::count(ident, orig.ident) %>%
tidyr::spread(ident, n)
count_per_cluster## orig.ident oligodendrocyte 1 noise 1 oligodendrocyte 2 noise 2 noise 3
## 1 v4Miltenyi 2057 1953 1775 1334 1277
## noise 4 oligodendrocyte/polydendrocyte noise 5 astrocyte 1 microglia neuron 1
## 1 1205 872 827 522 464 432
## polydendrocyte astrocyte 2 neuron 2 neuron 3 neuron 4 fibroblast-like noise 6
## 1 378 354 223 193 168 129 123count_melt <- reshape2::melt(count_per_cluster)
colnames(count_melt) <- c("ident", "cluster", "number of nuclei")
count_max <- count_melt[which.max(count_melt$`number of nuclei`), ]
count_max_value <- count_max$`number of nuclei`
cellmax <- count_max_value + 500 # so that the figure doesn't cut off the text
count_bar <- ggplot(count_melt, aes(x = factor(cluster), y = `number of nuclei`, fill = `cluster`)) +
geom_bar(
stat = "identity",
colour = "black",
width = 1,
position = position_dodge(width = 0.8)
) +
geom_text(
aes(label = `number of nuclei`),
position = position_dodge(width = 0.9),
vjust = -0.25,
angle = 45,
hjust = -.01
) +
theme_classic() + scale_fill_manual(values = color.panel) +
ggtitle("Number of nuclei per cluster") + xlab("cluster") +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
scale_y_continuous(limits = c(0, cellmax))
count_bar
## png
## 2DotPlot
markers.to.plot <-
c(
"CLU",
"GFAP",
"AQP4",
"GJA1",
"CLDN5",
"ADGRF5",
"FLT1",
"COL1A1",
"COL1A2",
"DCN",
"HEXB",
"C1QA",
"C1QC",
"C1QB",
"TMEM119",
"ITGAM",
"TYROBP",
"P2RY12",
"AIF1",
"RBFOX3",
"SNAP25",
"SYT1",
"GAD1",
"GAD2",
"PLP1",
"MBP",
"MOG",
"OLIG1",
"PDGFRA",
"VCAN",
"TNR",
"ACTA2",
"RGS5",
"VTN",
"MYL5"
)
dot_ind <- DotPlot(dataObject,
features = markers.to.plot,
cluster.idents = TRUE,
dot.scale = 8) + RotatedAxis()
dot_ind
## png
## 2Merged
dataObject.annotated <- RenameIdents(object = dataObject,
"0" = "oligodendrocyte",
"1" = "noise",
"2" = "oligodendrocyte",
"3" = "noise",
"4" = "noise",
"5" = "noise",
"6" = "oligodendrocyte",
"7" = "noise",
"8" = "astrocyte",
"9" = "microglia",
"10" = "neuron",
"11" = "polydendrocyte",
"12" = "astrocyte",
"13" = "neuron",
"14" = "neuron",
"15" = "neuron",
"16" = "fibroblast-like",
"17" = "noise")
dataObject.annotated$annotated_clusters <- factor(Idents(dataObject.annotated))
Idents(dataObject.annotated) <- "annotated_clusters"
UMAP_merge <- dittoDimPlot(object = dataObject.annotated,
var = "annotated_clusters",
reduction.use = "umap",
do.label = TRUE,
labels.highlight = TRUE)
UMAP_merge
## png
## 2Nuclei count per cluster
count_per_cluster <- FetchData(dataObject.annotated,
vars = c("ident", "orig.ident")) %>%
dplyr::count(ident, orig.ident) %>%
tidyr::spread(ident, n)
count_per_cluster## orig.ident oligodendrocyte noise astrocyte microglia neuron polydendrocyte
## 1 v4Miltenyi 4704 6719 876 464 1016 378
## fibroblast-like
## 1 129count_melt <- reshape2::melt(count_per_cluster)
colnames(count_melt) <- c("ident", "cluster", "number of nuclei")
count_max <- count_melt[which.max(count_melt$`number of nuclei`), ]
count_max_value <- count_max$`number of nuclei`
cellmax <- count_max_value + 500 # so that the figure doesn't cut off the text
count_bar <- ggplot(count_melt, aes(x = factor(cluster), y = `number of nuclei`, fill = `cluster`)) +
geom_bar(
stat = "identity",
colour = "black",
width = 1,
position = position_dodge(width = 0.8)
) +
geom_text(
aes(label = `number of nuclei`),
position = position_dodge(width = 0.9),
vjust = -0.25,
angle = 45,
hjust = -.01
) +
theme_classic() + scale_fill_manual(values = color.panel) +
ggtitle("Number of nuclei per cluster") + xlab("cluster") +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
scale_y_continuous(limits = c(0, cellmax))
count_bar
## png
## 2Relative abundance
relative_abundance <- dataObject.annotated@meta.data %>%
group_by(annotated_clusters, orig.ident) %>%
dplyr::count() %>%
group_by(orig.ident) %>%
dplyr::mutate(percent = 100 * n / sum(n)) %>%
ungroup()
rel_abun <- ggplot(relative_abundance, aes(x = orig.ident, y = percent, fill = annotated_clusters)) +
geom_col() +
geom_text(aes(label = paste0(round(percent), "%")),
position = position_stack(vjust = 0.5), size = 3, color = "white") +
scale_fill_manual(values = color.panel) +
ggtitle("Percentage of cell type") +
theme_bw() +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1))
rel_abun
DotPlot
markers.to.plot <-
c(
"CLU",
"GFAP",
"AQP4",
"GJA1",
"CLDN5",
"ADGRF5",
"FLT1",
"COL1A1",
"COL1A2",
"DCN",
"HEXB",
"C1QA",
"C1QC",
"C1QB",
"TMEM119",
"ITGAM",
"TYROBP",
"P2RY12",
"AIF1",
"RBFOX3",
"SNAP25",
"SYT1",
"GAD1",
"GAD2",
"PLP1",
"MBP",
"MOG",
"OLIG1",
"PDGFRA",
"VCAN",
"TNR",
"ACTA2",
"RGS5",
"VTN",
"MYL5"
)
dot_merge <- DotPlot(dataObject.annotated,
features = markers.to.plot,
cluster.idents = TRUE,
dot.scale = 8) + RotatedAxis()
dot_merge
## png
## 2Save RDS
saveRDS(dataObject.annotated, paste0("../../../rObjects/", sampleID, ".annotated.rds"))