Seurat重要命令汇总

参考：https://satijalab.org/seurat/articles/essential_commands.html

⚠️⚠️

1. Seurat 标准工作流程

读入数据 -> 构建Seurat对象 -> 归一化 -> 寻找特征基因 -> 标准化 -> PCA降维 -> 计算KNN最近邻 -> 分群 -> 非线性降维UMAP和TSNE -> 可视化降维结果

pbmc.counts <- Read10X(data.dir = "~/Downloads/pbmc3k/filtered_gene_bc_matrices/hg19/")
pbmc <- CreateSeuratObject(counts = pbmc.counts)
pbmc <- NormalizeData(object = pbmc)
pbmc <- FindVariableFeatures(object = pbmc)
pbmc <- ScaleData(object = pbmc)
pbmc <- RunPCA(object = pbmc)
pbmc <- FindNeighbors(object = pbmc)
pbmc <- FindClusters(object = pbmc)
pbmc <- RunTSNE(object = pbmc)
DimPlot(object = pbmc, reduction = "tsne")

2. Seurat对象交互

获取细胞和基因名，并计数

colnames(x = pbmc)
rownames(x = pbmc)
ncol(x = pbmc)
nrow(x = pbmc)

设置identity classes（active.ident）

# 查看目前所用的identity（也就是查看目前用于细胞分类的metadata）并计数
Idents(object = pbmc)
levels(x = pbmc)

# 存放细胞identity classes
pbmc[["old.ident"]] <- Idents(object = pbmc) #将"old.ident"存放在pbmc的metadata中

# 设置identity classes
Idents(object = pbmc) <- "CD4 T cells"  #将"CD4 T cells"设置为pbmc的 "active.ident"
Idents(object = pbmc, cells = 1:10) <- "CD4 T cells" #将前10个细胞的ident设置为"CD4 T cells"

# 将meta data中已有的分类设置为identity classes
Idents(object = pbmc, cells = 1:10) <- "orig.ident" #将前10个细胞的ident设置为"orig.ident"
Idents(object = pbmc) <- "orig.ident" #将"orig.ident"设置为pbmc的 "active.ident"

# 重命名 identity classes
pbmc <- RenameIdents(object = pbmc, `CD4 T cells` = "T Helper cells")

从seurat对象中取子集⚠️

# 根据identity class取子集（also see ?SubsetData）
subset(x = pbmc, idents = "B cells")
subset(x = pbmc, idents = c("CD4 T cells", "CD8 T cells"), invert = TRUE)

# 根据某个基因/特征的表达水平取子集
subset(x = pbmc, subset = MS4A1 > 3)

# 根据组合的标准取子集
subset(x = pbmc, subset = MS4A1 > 3 & PC1 > 5)
subset(x = pbmc, subset = MS4A1 > 3, idents = "B cells")

# 根据某个meta data中的某一分组来取子集
subset(x = pbmc, subset = orig.ident == "Replicate1")

# Downsample the number of cells per identity class
subset(x = pbmc, downsample = 100)

多个Seurat对象的合并

# Merge两个Seurat对象
merge(x = pbmc1, y = pbmc2)
# Merge多个Seurat对象
merge(x = pbmc1, y = list(pbmc2, pbmc3))

3. 数据访问

#查看metadata数据库框, metadata存储在object@meta.data
pbmc[[]]

# 检索metadata中的特定指标
pbmc$nCount_RNA
pbmc[[c("percent.mito", "nFeature_RNA")]]

# 添加metadata, （见?AddMetaData）
random_group_labels <- sample(x = c("g1", "g2"), size = ncol(x = pbmc), replace = TRUE)
pbmc$groups <- random_group_labels

# 检索或设置表达矩阵数据，包括原始表达矩阵、标准化的矩阵和降维后的矩阵 ('counts', 'data', and 'scale.data')
GetAssayData(object = pbmc, slot = "counts")[1:5,1:5]
count.data <- GetAssayData(object = pbmc[["RNA"]], slot = "counts")
count.data <- as.matrix(x = count.data + 1)
new.seurat.object <- SetAssayData(object = pbmc, slot = "counts", new.data = count.data, assay = "RNA"）
#⚠️ 使用GetAssayData函数可以从Seurat对象访问数据。
#⚠️ 可以使用SetAssayData将数据添加到counts，data或scale.data插槽中。新数据必须具有与当前数据相同顺序的相同细胞。添加到counts'或data`中的数据必须具有与当前数据相同的features。

# Get cell embeddings and feature loadings
Embeddings(object = pbmc, reduction = "pca") #检索每个细胞的PC矩阵
Loadings(object = pbmc, reduction = "pca") #检索每个基因的PC矩阵
Loadings(object = pbmc, reduction = "pca", projected = TRUE)

# ⚠️FetchData函数可以从expression matrices, cell embeddings或metadata中取出任何值
head(FetchData(object = pbmc, vars = c("PC_1", "percent.mt", "MS4A1")))
#                        PC_1 percent.mt    MS4A1
# AAACATACAACCAC-1 -4.7296855  3.0177759 0.000000
# AAACATTGAGCTAC-1 -0.5174029  3.7935958 2.583047
# AAACATTGATCAGC-1 -3.1891063  0.8897363 0.000000
# AAACCGTGCTTCCG-1 12.7933021  1.7430845 0.000000
# AAACCGTGTATGCG-1 -3.1288078  1.2244898 0.000000
# AAACGCACTGGTAC-1 -3.1088963  1.6643551 0.000000

4. 可视化

Seurat的绘图基于ggplot2
详见Seurat绘图函数总结

# Dimensional reduction plot for PCA or tSNE
DimPlot(object = pbmc, reduction = "tsne")
DimPlot(object = pbmc, reduction = "pca")

# Dimensional reduction plot, with cells colored by a quantitative feature
FeaturePlot(object = pbmc, features = "MS4A1")

# Scatter plot across single cells, replaces GenePlot
FeatureScatter(object = pbmc, feature1 = "MS4A1", feature2 = "PC_1")
FeatureScatter(object = pbmc, feature1 = "MS4A1", feature2 = "CD3D")

# Scatter plot across individual features, repleaces CellPlot
CellScatter(object = pbmc, cell1 = "AGTCTACTAGGGTG", cell2 = "CACAGATGGTTTCT")

VariableFeaturePlot(object = pbmc)

# Violin and Ridge plots
VlnPlot(object = pbmc, features = c("LYZ", "CCL5", "IL32"))
RidgePlot(object = pbmc, feature = c("LYZ", "CCL5", "IL32"))

# Heatmaps
DoHeatmap(object = pbmc, features = heatmap_markers)
DimHeatmap(object = pbmc, reduction = "pca", cells = 200)

# New things to try!  Note that plotting functions now return ggplot2 objects, so you can add themes, titles, and options
# onto them
VlnPlot(object = pbmc, features = "MS4A1", split.by = "groups")
DotPlot(object = pbmc, features = c("LYZ", "CCL5", "IL32"), split.by = "groups")
FeaturePlot(object = pbmc, features = c("MS4A1", "CD79A"), blend = TRUE)
DimPlot(object = pbmc) + DarkTheme()
DimPlot(object = pbmc) + labs(title = "2,700 PBMCs clustered using Seurat and viewed\non a two-dimensional tSNE")

Seurat还提供了很多可以添加到ggplot2图中的预制个性化主题

主题	功能
DarkTheme	Set a black background with white text
FontSize	Set font sizes for various elements of a plot
NoAxes	Remove axes and axis text
NoLegend	Remove all legend elements
RestoreLegend	Restores a legend after removal
RotatedAxis	Rotates x-axis labels

# Plotting helper functions work with ggplot2-based scatter plots, such as DimPlot, FeaturePlot, CellScatter, and
# FeatureScatter
plot <- DimPlot(object = pbmc) + NoLegend()

# HoverLocator replaces the former `do.hover` argument It can also show extra data throught the `information` argument,
# designed to work smoothly with FetchData
HoverLocator(plot = plot, information = FetchData(object = pbmc, vars = c("ident", "PC_1", "nFeature_RNA")))

# FeatureLocator replaces the former `do.identify`
select.cells <- FeatureLocator(plot = plot)

# Label points on a ggplot object
LabelPoints(plot = plot, points = TopCells(object = pbmc[["pca"]]), repel = TRUE)

5. Multi-Assay Features

With Seurat, you can easily switch between different assays at the single cell level (such as ADT counts from CITE-seq, or integrated/batch-corrected data). Most functions now take an assay parameter, but you can set a Default Assay to avoid repetitive statements.

cbmc <- CreateSeuratObject(counts = cbmc.rna)
# Add ADT data
cbmc[["ADT"]] <- CreateAssayObject(counts = cbmc.adt)
# Run analyses by specifying the assay to use
NormalizeData(object = cbmc, assay = "RNA")
NormalizeData(object = cbmc, assay = "ADT", method = "CLR")

# Retrieve and set the default assay
DefaultAssay(object = cbmc)
DefaultAssay(object = cbmc) <- "ADT"
DefaultAssay(object = cbmc)

# Pull feature expression from both assays by using keys
FetchData(object = cbmc, vars = c("rna_CD3E", "adt_CD3"))

# Plot data from multiple assays using keys
FeatureScatter(object = cbmc, feature1 = "rna_CD3E", feature2 = "adt_CD3")

6. 其他好用的函数

HVFInfo函数从Assay对象中提取特征均值和离散度。可变特征向量可以通过VariableFeatures函数提取。VariableFeatures也可以设置可变特征向量。

# HVFInfo pulls mean, dispersion, and dispersion scaled
# Useful for viewing the results of FindVariableFeatures
> head(x = HVFInfo(object = pbmc))
#                      mean    variance variance.standardized
# AL627309.1    0.003411676 0.003401325             0.9330441
# AP006222.2    0.001137225 0.001136363             0.9924937
# RP11-206L10.2 0.001895375 0.001892500             0.9627290
# RP11-206L10.9 0.001137225 0.001136363             0.9924937
# LINC00115     0.006823351 0.006779363             0.9062135
# NOC2L         0.107278241 0.159514698             0.7849309

# VariableFeatures both accesses and sets the vector of variable features
> head(x = VariableFeatures(object = pbmc))
# [1] "PPBP"   "LYZ"    "S100A9" "IGLL5"  "GNLY"   "FTL" 
# Set variable features example

可以通过Stdev找到Seurat对象中存储的DimReduc的标准差向量。

Stdev(object = pbmc, reduction.use = 'pca')
# Warning: The following arguments are not used: reduction.use
#  [1] 7.098420 4.495493 3.872592 3.748859 3.171755 2.545292 2.068137 1.945133
#  [9] 1.847375 1.834689 1.820439 1.788429 1.779215 1.757395 1.751558 1.746384
# [17] 1.732116 1.729550 1.722981 1.720541 1.717668 1.715182 1.710343 1.705735
# [25] 1.705204 1.702498 1.700713 1.695816 1.694965 1.690976 1.688388 1.681423
# [33] 1.679596 1.678656 1.674677 1.674487 1.670084 1.667662 1.666598 1.664131
# [41] 1.660317 1.657907 1.656963 1.654456 1.654188 1.649514 1.647186 1.645571
# [49] 1.642952 1.641145

可以通过以下方法找到Seurat类：

library(Seurat)
utils::methods(class = 'Seurat')