mapping transferdata FindTransferAnchors TransferData

这里是引用

library(Seurat)
library(SeuratData)

#InstallData("panc8")

data("panc8")
pancreas.list <- SplitObject(panc8, split.by = "tech")
pancreas.list
pancreas.list <- pancreas.list[c("celseq", "celseq2", "fluidigmc1", "smartseq2")]

for (i in 1:length(pancreas.list)) {
    
  pancreas.list[[i]] <- NormalizeData(pancreas.list[[i]], verbose = FALSE)
  pancreas.list[[i]] <- FindVariableFeatures(pancreas.list[[i]], selection.method = "vst", nfeatures = 2000,
                                             verbose = FALSE)
}


reference.list <- pancreas.list[c("celseq", "celseq2", "smartseq2")]
pancreas.anchors <- FindIntegrationAnchors(object.list = reference.list, dims = 1:30)
pancreas.integrated <- IntegrateData(anchorset = pancreas.anchors, dims = 1:30)
DefaultAssay(pancreas.integrated)


library(ggplot2)
library(cowplot)
library(patchwork)
# switch to integrated assay. The variable features of this assay are automatically set during
# IntegrateData
DefaultAssay(pancreas.integrated) <- "integrated"
# Run the standard workflow for visualization and clustering
pancreas.integrated <- ScaleData(pancreas.integrated, verbose = FALSE)
pancreas.integrated <- RunPCA(pancreas.integrated, npcs = 30, verbose = FALSE)
pancreas.integrated <- RunUMAP(pancreas.integrated, reduction = "pca", dims = 1:30, verbose = FALSE)
p1 <- DimPlot(pancreas.integrated, reduction = "umap", group.by = "tech")
p2 <- DimPlot(pancreas.integrated, reduction = "umap", group.by = "celltype", label = TRUE, repel = TRUE) +
  NoLegend()
p1 + p2


##
pancreas.query <- pancreas.list[["fluidigmc1"]]
pancreas.anchors <- FindTransferAnchors(reference = pancreas.integrated, query = pancreas.query,
                                        dims = 1:30, reference.reduction = "pca")
predictions <- TransferData(anchorset = pancreas.anchors, refdata = pancreas.integrated$celltype,
                            dims = 1:30)
pancreas.query <- AddMetaData(pancreas.query, metadata = predictions)


pancreas.query$prediction.match <- pancreas.query$predicted.id == pancreas.query$celltype
table(pancreas.query$prediction.match)

table(pancreas.query$predicted.id)

VlnPlot(pancreas.query, c("REG1A", "PPY", "SST", "GHRL", "VWF", "SOX10"), group.by = "predicted.id")

https://satijalab.org/seurat/articles/integration_mapping.html