Seurat integration
https://satijalab.org/seurat/articles/integration_introduction.html
这些方法首先识别处于匹配生物状态（“锚定”）的跨数据集细胞对，既可用于校正数据集之间的技术差异（即批效应校正），也可用于对跨实验条件进行比较性scRNA序列分析。
library(Seurat)
library(SeuratData)
# InstallData("ifnb")
LoadData("ifnb")
# load dataset
LoadData("ifnb")
# split the dataset into a list of two seurat objects (stim and CTRL)
ifnb.list <- SplitObject(ifnb, split.by = "stim")
# normalize and identify variable features for each dataset independently
ifnb.list <- lapply(X = ifnb.list, FUN = function(x) {
x <- NormalizeData(x)
x <- FindVariableFeatures(x, selection.method = "vst", nfeatures = 2000)
})
# select features that are repeatedly variable across datasets for integration
features <- SelectIntegrationFeatures(object.list = ifnb.list)
length(features)
immune.anchors <- FindIntegrationAnchors(object.list = ifnb.list, anchor.features = features)
# this command creates an 'integrated' data assay
immune.combined <- IntegrateData(anchorset = immune.anchors)
# specify that we will perform downstream analysis on the corrected data note that the
# original unmodified data still resides in the 'RNA' assay
DefaultAssay(immune.combined) <- "integrated"
Run the standard workflow for visualization and clustering
immune.combined <- ScaleData(immune.combined, verbose = FALSE)
immune.combined <- RunPCA(immune.combined, npcs = 30, verbose = FALSE)
immune.combined <- RunUMAP(immune.combined, reduction = "pca", dims = 1:30)
immune.combined <- FindNeighbors(immune.combined, reduction = "pca", dims = 1:30)
immune.combined <- FindClusters(immune.combined, resolution = 0.5)
# Visualization
p1 <- DimPlot(immune.combined, reduction = "umap", group.by = "stim")
p2 <- DimPlot(immune.combined, reduction = "umap", label = TRUE, repel = TRUE)
p1 + p2
图片alt