-
Notifications
You must be signed in to change notification settings - Fork 3
/
03_seurat_integration.R
135 lines (117 loc) · 7.17 KB
/
03_seurat_integration.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
suppressMessages(library(tidyverse))
suppressMessages(library(pacman))
suppressMessages(library(data.table))
suppressMessages(library(Seurat))
suppressMessages(library(SeuratData))
suppressMessages(library(SeuratWrappers))
suppressMessages(library(patchwork))
options(stringsAsFactors = F)
rm(list = ls())
# 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)
# 整合
immune.anchors <- FindIntegrationAnchors(object.list = ifnb.list, anchor.features = features)
# this command creates an 'integrated' data assay
immune.combined <- IntegrateData(anchorset = immune.anchors)
# 综合分析
# 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
set.seed(457865)
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
DimPlot(immune.combined, reduction = "umap", split.by = "stim")
# 确定保守的细胞类型标记--------------
# For performing differential expression after integration, we switch back to the original data
DefaultAssay(immune.combined) <- "RNA"
nk.markers <- FindConservedMarkers(immune.combined, ident.1 = 6, grouping.var = "stim", verbose = FALSE)
head(nk.markers)
FeaturePlot(immune.combined, features = c("CD3D", "SELL", "CREM", "CD8A", "GNLY", "CD79A", "FCGR3A",
"CCL2", "PPBP"), min.cutoff = "q9")
immune.combined <- RenameIdents(immune.combined, `0` = "CD14 Mono", `1` = "CD4 Naive T", `2` = "CD4 Memory T",
`3` = "CD16 Mono", `4` = "B", `5` = "CD8 T", `6` = "NK", `7` = "T activated", `8` = "DC", `9` = "B Activated",
`10` = "Mk", `11` = "pDC", `12` = "Eryth", `13` = "Mono/Mk Doublets", `14` = "HSPC")
DimPlot(immune.combined, label = TRUE)
Idents(immune.combined) <- factor(Idents(immune.combined), levels = c("HSPC", "Mono/Mk Doublets",
"pDC", "Eryth", "Mk", "DC", "CD14 Mono", "CD16 Mono", "B Activated", "B", "CD8 T", "NK", "T activated",
"CD4 Naive T", "CD4 Memory T"))
markers.to.plot <- c("CD3D", "CREM", "HSPH1", "SELL", "GIMAP5", "CACYBP", "GNLY", "NKG7", "CCL5",
"CD8A", "MS4A1", "CD79A", "MIR155HG", "NME1", "FCGR3A", "VMO1", "CCL2", "S100A9", "HLA-DQA1",
"GPR183", "PPBP", "GNG11", "HBA2", "HBB", "TSPAN13", "IL3RA", "IGJ", "PRSS57")
DotPlot(immune.combined, features = markers.to.plot, cols = c("blue", "red"), dot.scale = 8, split.by = "stim") +
RotatedAxis()
# 识别不同条件下的差异表达基因------------------
library(ggplot2)
library(cowplot)
theme_set(theme_cowplot())
t.cells <- subset(immune.combined, idents = "CD4 Naive T")
Idents(t.cells) <- "stim"
avg.t.cells <- as.data.frame(log1p(AverageExpression(t.cells, verbose = FALSE)$RNA))
avg.t.cells$gene <- rownames(avg.t.cells)
cd14.mono <- subset(immune.combined, idents = "CD14 Mono")
Idents(cd14.mono) <- "stim"
avg.cd14.mono <- as.data.frame(log1p(AverageExpression(cd14.mono, verbose = FALSE)$RNA))
avg.cd14.mono$gene <- rownames(avg.cd14.mono)
genes.to.label = c("ISG15", "LY6E", "IFI6", "ISG20", "MX1", "IFIT2", "IFIT1", "CXCL10", "CCL8")
p1 <- ggplot(avg.t.cells, aes(CTRL, STIM)) + geom_point() + ggtitle("CD4 Naive T Cells")
p1 <- LabelPoints(plot = p1, points = genes.to.label, repel = TRUE)
p2 <- ggplot(avg.cd14.mono, aes(CTRL, STIM)) + geom_point() + ggtitle("CD14 Monocytes")
p2 <- LabelPoints(plot = p2, points = genes.to.label, repel = TRUE)
p1 + p2
immune.combined$celltype.stim <- paste(Idents(immune.combined), immune.combined$stim, sep = "_")
immune.combined$celltype <- Idents(immune.combined)
Idents(immune.combined) <- "celltype.stim"
b.interferon.response <- FindMarkers(immune.combined, ident.1 = "B_STIM", ident.2 = "B_CTRL", verbose = FALSE)
head(b.interferon.response, n = 15)
FeaturePlot(immune.combined, features = c("CD3D", "GNLY", "IFI6"),
split.by = "stim", max.cutoff = 3,cols = c("grey", "red"))
plots <- VlnPlot(immune.combined, features = c("LYZ", "ISG15", "CXCL10"), split.by = "stim", group.by = "celltype",
pt.size = 0, combine = FALSE)
wrap_plots(plots = plots, ncol = 1)
# 使用 SCTransform 对数据集进行规范化集成--------
LoadData("ifnb")
ifnb.list <- SplitObject(ifnb, split.by = "stim")
ifnb.list <- lapply(X = ifnb.list, FUN = SCTransform)
features <- SelectIntegrationFeatures(object.list = ifnb.list, nfeatures = 3000)
ifnb.list <- PrepSCTIntegration(object.list = ifnb.list, anchor.features = features)
immune.anchors <- FindIntegrationAnchors(object.list = ifnb.list, normalization.method = "SCT",
anchor.features = features)
immune.combined.sct <- IntegrateData(anchorset = immune.anchors, normalization.method = "SCT")
set.seed(123)
immune.combined.sct <- RunPCA(immune.combined.sct, verbose = FALSE)
immune.combined.sct <- RunUMAP(immune.combined.sct, reduction = "pca", dims = 1:30)
p1 <- DimPlot(immune.combined.sct, reduction = "umap", group.by = "stim")
p2 <- DimPlot(immune.combined.sct, reduction = "umap", group.by = "seurat_annotations", label = TRUE,
repel = TRUE)
p1 + p2
immune.combined.sct <- FindNeighbors(immune.combined.sct, reduction = "pca", dims = 1:30)
immune.combined.sct <- FindClusters(immune.combined.sct, resolution = 0.5)
# Visualization
p1 <- DimPlot(immune.combined.sct, reduction = "umap", group.by = "stim")
p2 <- DimPlot(immune.combined.sct, reduction = "seurat_annotations", label = TRUE, repel = TRUE)
p1 + p2
DefaultAssay(immune.combined.sct) <- "RNA"
nk.markers <- FindConservedMarkers(immune.combined.sct, ident.1 = 6, grouping.var = "stim", verbose = FALSE)
head(nk.markers)
FeaturePlot(immune.combined.sct, features = c('FCGR3A', 'LST1'), min.cutoff = "q9")
immune.combined.sct <- RenameIdents(immune.combined.sct, `0` = "CD14 Mono", `1` = "CD4 Naive T", `2` = "CD4 Memory T",
`3` = "CD16 Mono", `4` = "B", `5` = "CD8 T", `6` = "NK", `7` = "T activated", `8` = "DC", `9` = "B Activated",
`10` = "Mk", `11` = "pDC", `12` = "Eryth", `13` = "Mono/Mk Doublets", `14` = "HSPC")
DimPlot(immune.combined.sct, label = TRUE)