I'm trying to create a umap for single cell data from human samples and ptx samples. I can get the umap to where it shows the umap with the different clusters but I want to show where the ptx samples are and where the human samples are.
My code is as follows:
#create the Seurat object
OD_10K_HUMAN <- CreateSeuratObject(counts = HUMAN_OD_10K.data, min.cells = 0, project = "human")
SD_5K_HUMAN <- CreateSeuratObject(counts = HUMAN_SD_5K.data, min.cells = 0, project = "human")
BNL.5K <- CreateSeuratObject(counts = SD_BNL_5K.data, min.cells = 0, project = "ptx")
BNL.10K <- CreateSeuratObject(counts = OD_BNL_10K.data, min.cells = 0, project = "ptx")
BNM.10K <- CreateSeuratObject(counts = OD_BNM_10K.data, min.cells = 0, project = "ptx")
BNM.5K <- CreateSeuratObject(counts = SD_BNM_5K.data, min.cells = 0, project = "ptx")
#merge data
scData <- merge(BNL.10K, y = c(BNL.5K, BNM.10K, BNM.5K, SD_5K_HUMAN, OD_10K_HUMAN), add.cell.ids = c("A", "B", "C", "D", "E", "F"), project = "HTB2876")
mark the mito genes
mito.genes <- grep(pattern = "^MT-", x = rownames(x = scData), value = TRUE)
length(mito.genes)
scData[["percent.mt"]] <- PercentageFeatureSet(scData, pattern = "^MT-")
scData[["log_nCount_RNA"]] <- log2(scData[["nCount_RNA"]]+1)
# remove cells with <200 RNA molecules, or >6000 molecules, or >30% mito
scData <- subset(scData, subset = nFeature_RNA > 200 & nFeature_RNA < 6000 & percent.mt < 30)
scData <- NormalizeData(scData, normalization.method = "LogNormalize", scale.factor = 10000)
scData <- FindVariableFeatures(scData, selection.method = "vst", nfeatures = 2000)
all.genes <- rownames(scData)
scData <- ScaleData(scData, features = VariableFeatures(object = scData), vars.to.regress = c("nCount_RNA"))
scData <- RunPCA(scData, features = VariableFeatures(object = scData))
#DimPlot(scData, reduction = "pca")
numPC = 20
scData <- FindNeighbors(scData, dims = 1:numPC)
scData <- FindClusters(scData, resolution = 0.4)
scData <- RunUMAP(scData, dims = 1:numPC)
DimPlot(scData, reduction = "umap", label = TRUE)