-
Notifications
You must be signed in to change notification settings - Fork 0
/
PYF-100G数据.txt
177 lines (132 loc) · 6.58 KB
/
PYF-100G数据.txt
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
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
library(tidyverse)
library(Seurat)
library(ggplot2)
outdir = "E:/薛琪/1020"
sample = "PYF"
matrix_file = "E:/薛琪/1020/PYF-wta_filtered_feature_bc_matrix"
matrix= Seurat::Read10X(matrix_file, gene.column = 2) #dgCMatrix
rds = CreateSeuratObject(matrix, project=sample,min.cells = 5,min.features = 50)
all_genes = rownames(rds@assays$RNA@data)
mito.genes <- grep(pattern = "^MT-", x = all_genes, value = TRUE, ignore.case=TRUE)
percent.mito <- Matrix::colSums(rds@assays$RNA@counts[mito.genes,,drop=FALSE])/Matrix::colSums(rds@assays$RNA@counts)
rds <- AddMetaData(object = rds, metadata = percent.mito, col.name = "percent.mito")
rds = subset(rds, percent.mito<0.2)
VlnPlot(object = rds, features = c("nFeature_RNA", "nCount_RNA", "percent.mito"), ncol = 3, pt.size = 0.1)
rds <- NormalizeData(rds, normalization.method = "LogNormalize",scale.factor = 10000)
nfeatures = 2000
rds <- FindVariableFeatures(rds, selection.method = "vst", nfeatures = nfeatures, mean.cutoff = c(0.1, 8), dispersion.cutoff = c(1, Inf),
mean.function = ExpMean, dispersion.function = LogVMR)
use.genes <- rds@assays$RNA@var.features
rds <- ScaleData(rds, vars.to.regress = c("nCount_RNA", "percent.mito"), features = use.genes)
rds <- RunPCA(object = rds, features = use.genes, do.print = FALSE)
rds <- FindNeighbors(rds, dims = 1:20, force.recalc = TRUE, reduction = "pca")
rds <- FindClusters(rds, resolution = 2)
DimPlot(rds,reduction = "pca")->p
p
rds = RunUMAP(rds, dims=1:20)
DimPlot(rds,reduction = "umap",label = TRUE)->p
p
p_file <- paste0(outdir,"/",sample,".umap.eps")
ggsave(p_file,p,width = 8, height = 6)
VlnPlot(rds, features = c("Cd20","Ptprc","Cd19"))
VlnPlot(rds, features = c("Ly6c","Gsr","Cd14","Gsr","Itgam","S100a8"))
data.frame(cluster = c('0','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'),
celltype = c("MՓ", "MՓ","MՓ","Mono","Tmem","Mono","DC","Tmem","MՓ",
"DC","CD4T","TEX Int","TEX Int","NK","TEX Term","TEX Term","MՓ","undetermined",
"TEX Int","DC","Mono","MՓ","DC","TEX Term","MՓ",
"undetermined","NK"))->celltype_df
celltype_df$cluster = factor(celltype_df$cluster)
data.frame(cell_ident = Cells(rds),cluster = rds$RNA_snn_res.2 )%>%
left_join(celltype_df)->celltype_df
rownames(celltype_df) <- celltype_df$cell_ident
AddMetaData(rds,celltype_df%>%dplyr::select(-cluster,-cell_ident))->rds
tag_file = "E:/薛琪/1020/PYF-TAG_umi_tag.tsv"
tag_df = read.table(tag_file,header = TRUE)
head(tag_df)
rds <- AddMetaData(rds,tag_df)
subset(rds, tag %in% c("tag1","tag3","tag4","tag5"))->rds_tag
tag_df$cell_ident = rownames(tag_df)
data.frame(cell_ident = Cells(rds_tag), celltype = rds_tag$celltype)%>%
left_join(tag_df)-> tag_df
rownames(tag_df) <- tag_df$cell_ident
tag_df$tag <- factor(tag_df$tag,levels = c("Multiplet","tag1","tag3","tag4","tag5","Undetermined"))
table(tag_df$tag)
ggplot(tag_df%>%filter(!is.na(tag)),aes(x = tag, fill = celltype))+
geom_bar(position = "fill",width = 0.5)+
#scale_fill_manual(values = c("SlateBlue3","DarkOrange","GreenYellow","Purple"))+
theme_bw()
ggsave("PYF tag_df1023.jpg", width = 15, height = 10)
ggsave("PYF tag_df1023.jpg.eps", width = 15, height = 10)
tag_df %>%
group_by(celltype)%>%
summarise(n_celltype = n())-> count_celltype_df
tag_df %>%
group_by(celltype,tag)%>%
summarise(n_celltype_tag = n()) %>%
left_join(count_celltype_df) %>%
mutate(ratio=round(n_celltype_tag/n_celltype, 4)) -> gdf
head(gdf)
write.csv(gdf,file="pyf-gdf")
ann_umap <- DimPlot(rds_tag, reduction = "umap", label = T, group.by = "celltype",split.by = "tag")
ggsave("ann_umap1011.eps", plot = ann_umap, width = 16, height = 6)
ggsave("ann_umap1011.jpg", plot = ann_umap, width = 20, height = 6)
rds_T = subset(rds_tag, celltype %in% c("CD4T","TEX Int","TEX Term","Tmem"))
rds_CD8 = subset(rds_tag, celltype %in% c("TEX Int","TEX Term","Tmem"))
rds_CD4 = subset(rds_tag, celltype %in% c("CD4T"))
rds_NK = subset(rds_tag, celltype %in% c("NK"))
rds_T <- RunPCA(object = rds_T, features = use.genes, do.print = FALSE)
rds_T <- FindNeighbors(rds_T, dims = 1:20, force.recalc = TRUE, reduction = "pca")
rds_T <- FindClusters(rds_T, resolution = 0.5)
DimPlot(rds_T,reduction = "pca")->p
p
rds_T = RunUMAP(rds_T, dims=1:20)
DimPlot(rds_T,reduction = "umap",label = TRUE)->p
p
ann_umap <- DimPlot(rds_T, reduction = "umap", label = T, split.by = "tag")
ggsave("ann_umap1023-T.eps", plot = ann_umap, width = 16, height = 6)
ggsave("ann_umap1023-T.jpg", plot = ann_umap, width = 20, height = 6)
VlnPlot(rds_T1, features = c("Il7r","Lef1","Sell","Cd44",""))
VlnPlot(rds_T1, features = c("Cxcr3","S1pr1","Klf2"," Itgb1","Cd44","Ly6c2"))
VlnPlot(rds_T1, features = c("Cxcr3","S1pr1","Klf2"," Itgb1","Cd44","Ly6c2"))
VlnPlot(rds_T1, features = c("Gzma","Gzmb","Gzmc","Gzmf","Ifng","Klrg1","Cx3cr1"))
VlnPlot(rds_T1, features = c("Havcr2","Lag3","Entpd1","Cd38","Tox","Ctla4","Ctla4"))
VlnPlot(rds_T1, features = c("Mki67","Top2a"))
VlnPlot(rds_T1, features = c("Tcf1","Tcf7","Cxcr5"))
gene = "Nkg7"
FeaturePlot(rds_NK, features = gene, split.by = "tag")
gene = "Btla"
FeaturePlot(rds_tag, features = gene, split.by = "tag")
gene = "Eomes"
FeaturePlot(rds_tag, features = gene, split.by = "tag")
library(readr)
library(dplyr)
library(cowplot)
library(ggplot2)
library('RColorBrewer')
library(Seurat)
library(readxl)
library(pheatmap)
features <- read_excel("Migration.xlsx")
feature <- features$GENE
AverageExpression(rds_CD4,features=feature,group.by = "tag") -> Tgene
as.data.frame(Tgene) -> Tgene
head(Tgene)
pheatmap(Tgene,scale = "row", cluster_cols = F,color = colorRampPalette(c("navy", "white", "firebrick3"))(50))
features <- read_excel("differentiation.xlsx")
feature <- features$GENE
AverageExpression(rds_NK,features=feature,group.by = "tag") -> Tgene
as.data.frame(Tgene) -> Tgene
head(Tgene)
pheatmap(Tgene,scale = "row", cluster_cols = F,color = colorRampPalette(c("navy", "white", "firebrick3"))(50))
rds = readRDS("PYF.rds")
subset(rds, tag %in% c("tag1","tag3","tag4","tag5"))->rds_tag
rds_T = subset(rds_tag, celltype %in% c("CD4T","TEX Int","TEX Term","Tmem"))
rds_CD8 = subset(rds_tag, celltype %in% c("TEX Int","TEX Term","Tmem"))
rds_CD4 = subset(rds_tag, celltype %in% c("CD4T"))
rds_NK = subset(rds_tag, celltype %in% c("NK"))
features <- read_excel("Transcription factors_nk.xlsx")
feature <- features$GENE
AverageExpression(rds_NK,features=feature,group.by = "tag") -> Tgene
as.data.frame(Tgene) -> Tgene
head(Tgene)
pheatmap(Tgene,scale = "row", cluster_cols = F,color = colorRampPalette(c("navy", "white", "firebrick3"))(50))