-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathyueling13-monocle3.R
287 lines (201 loc) · 9.83 KB
/
yueling13-monocle3.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
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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
### https://zenodo.org/records/5461803
### https://www.science.org/doi/10.1126/science.abe6474
### https://github.com/ma-jq/B/blob/main/Fig1/fig1.R
##系统报错改为英文
Sys.setenv(LANGUAGE = "en")
##禁止转化为因子
options(stringsAsFactors = FALSE)
##清空环境
rm(list=ls())
library(dplyr)
library(Seurat)
library(tidyverse)
library(patchwork)
library(monocle3)
BiocManager::install(c('BiocGenerics', 'DelayedArray', 'DelayedMatrixStats',
'limma', 'lme4', 'S4Vectors', 'SingleCellExperiment',
'SummarizedExperiment', 'batchelor', 'HDF5Array',
'terra', 'ggrastr'))
install.packages("devtools")
devtools::install_github('cole-trapnell-lab/leidenbase')
devtools::install_github('cole-trapnell-lab/monocle3')
setwd("F:/shangke/lession17/")
load("scRNA_harmony.Rdata")
library(SingleR)
load("F:/ref.data/ref_Human_all.RData")
refdata <- ref_Human_all
load("scRNA_harmony.Rdata")
testdata <- GetAssayData(scRNA_harmony, slot="data")
###把scRNA数据中的seurat_clusters提取出来，注意这里是因子类型的
clusters <- [email protected]$seurat_clusters
###开始用singler分析
cellpred <- SingleR(test = testdata, ref = refdata, labels = refdata$label.main,
method = "cluster", clusters = clusters,
assay.type.test = "logcounts", assay.type.ref = "logcounts")
celltype = data.frame(ClusterID=rownames(cellpred), celltype=cellpred$labels, stringsAsFactors = FALSE)
[email protected]$celltype = "NA"
for(i in 1:nrow(celltype)){
[email protected][which([email protected]$seurat_clusters == celltype$ClusterID[i]),'celltype'] <- celltype$celltype[i]}
table([email protected]$celltype)
table([email protected]$seurat_clusters)
sc.t=scRNA_harmony[,rownames(subset([email protected],celltype=="T_cells"))]
data <- GetAssayData(scRNA_harmony, assay = 'RNA', slot = 'counts')
cell_metadata <- [email protected]
gene_annotation <- data.frame(gene_short_name = rownames(data))
rownames(gene_annotation) <- rownames(data)
cds <- new_cell_data_set(data,
cell_metadata = cell_metadata,
gene_metadata = gene_annotation)
cds <- preprocess_cds(cds, num_dim = 100)
plot_pc_variance_explained(cds)
cds <- reduce_dimension(cds)
plot_cells(cds)
plot_cells(cds, color_cells_by="seurat_clusters")
plot_cells(cds, color_cells_by="celltype")
plot_cells(cds, genes=c("GAPDH"))
?reduce_dimension
cds <- reduce_dimension(cds,umap.fast_sgd=T,cores = 3,reduction_method="tSNE")
plot_cells(cds, reduction_method="tSNE")
plot_cells(cds, reduction_method="tSNE", color_cells_by="celltype")
#########查看有没有批次效应 肯定是有的 因为此时还没有去批次
plot_cells(cds, color_cells_by="orig.ident", label_cell_groups=FALSE,reduction_method="tSNE")
#############
cds = align_cds(cds, num_dim = 100, alignment_group ="orig.ident")####其批次
cds = reduce_dimension(cds,reduction_method="tSNE")
plot_cells(cds, color_cells_by="orig.ident", label_cell_groups=FALSE,,reduction_method="tSNE")
cds = reduce_dimension(cds,reduction_method="UMAP")####这里也做了一个umap 的降维 因为我们的单细胞数据是umap降维
#####做完去批次 降维 然就是monocle3聚类了##########
cds = cluster_cells(cds, resolution=1e-5)
plot_cells(cds)
#########################
####97-139代码都是monocle3细胞注释的内容，因为我们在seurat已经完成了注释 所以可以跳过
table(cds@clusters$UMAP$clusters)
cds@clusters$UMAP$partitions
plot_cells(cds, color_cells_by="partition", group_cells_by="partition")
plot_cells(cds, color_cells_by="celltype")
marker_test_res <- top_markers(cds, group_cells_by="partition",
reference_cells=1000, cores=8)
top_specific_markers <- marker_test_res %>%
filter(fraction_expressing >= 0.10) %>%
group_by(cell_group) %>%
top_n(1, pseudo_R2)
top_specific_marker_ids <- unique(top_specific_markers %>% pull(gene_id))
plot_genes_by_group(cds,
top_specific_marker_ids,
group_cells_by="celltype",
ordering_type="maximal_on_diag",
max.size=3)
top_specific_markers = marker_test_res %>%
filter(fraction_expressing >= 0.10) %>%
group_by(cell_group) %>%
top_n(3, pseudo_R2)
top_specific_marker_ids = unique(top_specific_markers %>% pull(gene_id))
plot_genes_by_group(cds,
top_specific_marker_ids,
group_cells_by="celltype",
ordering_type="cluster_row_col",
max.size=3)
# 先将partitions的分组由因子型转为字符型
colData(cds)$assigned_cell_type <- as.character(partitions(cds))
cds_subset <- choose_cells(cds)
#################################################################
cds <- learn_graph(cds)
plot_cells(cds,
color_cells_by = "celltype",
label_groups_by_cluster=FALSE,
label_leaves=FALSE,
label_branch_points=FALSE,
group_label_size=4,cell_size=0.5)
cds = order_cells(cds)
plot_cells(cds,
color_cells_by = "pseudotime",
label_cell_groups=FALSE,
label_leaves=TRUE,
label_branch_points=TRUE,
graph_label_size=1.5,
group_label_size=4,cell_size=1.5)
table([email protected]$celltype)
# a helper function to identify the root principal points:
get_earliest_principal_node <- function(cds, time_bin="T_cells"){
cell_ids <- which(colData(cds)[, "celltype"] == time_bin)
closest_vertex <-cds@principal_graph_aux[["UMAP"]]$pr_graph_cell_proj_closest_vertex
closest_vertex <- as.matrix(closest_vertex[colnames(cds), ])
root_pr_nodes <-
igraph::V(principal_graph(cds)[["UMAP"]])$name[as.numeric(names(which.max(table(closest_vertex[cell_ids,]))))]
root_pr_nodes
}
cds = order_cells(cds, root_pr_nodes=get_earliest_principal_node(cds))
plot_cells(cds,
color_cells_by = "pseudotime",
label_cell_groups=FALSE,
label_leaves=FALSE,
label_branch_points=FALSE,
graph_label_size=1.5,
group_label_size=4,cell_size=1.5)
cds_sub <- choose_graph_segments(cds)
#Working with 3D trajectories
cds_3d = reduce_dimension(cds, max_components = 3)
cds_3d = cluster_cells(cds_3d)
cds_3d = learn_graph(cds_3d)
cds_3d = order_cells(cds_3d, root_pr_nodes=get_earliest_principal_node(cds))
cds_3d_plot_obj = plot_cells_3d(cds_3d, color_cells_by="celltype")
cds_3d_plot_obj
ciliated_genes = top_specific_markers$gene_id[5:10]
cds_subset = cds[rowData(cds)$gene_short_name %in% ciliated_genes,]
gene_fits = fit_models(cds_subset, model_formula_str = "~seurat_clusters")
fit_coefs
fit_coefs = coefficient_table(gene_fits)
# 挑出时间相关的组分
emb_time_terms = fit_coefs %>% filter(term == "seurat_clusters1")
emb_time_terms
emb_time_terms = fit_coefs %>% filter(term == "seurat_clusters1")
emb_time_terms %>% filter (q_value < 0.05) %>%
select(gene_short_name, term, q_value, estimate)
plot_genes_violin(cds_subset[,], group_cells_by="celltype", ncol=2) +
theme(axis.text.x=element_text(angle=45, hjust=1))
neurons_cds <- cds[,grepl("Macrophage", colData(cds)$celltype, ignore.case=TRUE)]
plot_cells(neurons_cds, color_cells_by="partition")
pr_graph_test_res <- graph_test(neurons_cds, neighbor_graph="knn", cores=3)
pr_deg_ids <- row.names(subset(pr_graph_test_res, q_value < 0.05))
gene_module_df = find_gene_modules(neurons_cds[pr_deg_ids,], resolution=1e-2)
cell_group_df = tibble::tibble(cell=row.names(colData(neurons_cds)), cell_group=neurons_cds@colData@listData[["seurat_clusters"]])
agg_mat = aggregate_gene_expression(neurons_cds, gene_module_df, cell_group_df)
row.names(agg_mat) = stringr::str_c("Module ", row.names(agg_mat))
colnames(agg_mat) = stringr::str_c("Partition ", colnames(agg_mat))
pheatmap::pheatmap(agg_mat, cluster_rows=TRUE, cluster_cols=TRUE,
scale="column", clustering_method="ward.D2",
fontsize=6)
plot_cells(neurons_cds,
genes=gene_module_df %>% filter(module %in% c(16,38,33,42)),
group_cells_by="cluster",
color_cells_by="cluster",
show_trajectory_graph=FALSE)
plot_cells(cds,
color_cells_by = "celltype",
label_groups_by_cluster=FALSE,
label_leaves=FALSE,
label_branch_points=FALSE)
##找到影响发育轨迹的基因
trace('calculateLW', edit = T, where = asNamespace("monocle3"))
## change Matrix::rBind to rbind on line 93
# 使用neighbor_graph="principal_graph"来检验轨迹相邻的细胞的表达是否相关
ciliated_cds_pr_test_res <- graph_test(cds, neighbor_graph="principal_graph", cores=4)
pr_deg_ids <- row.names(subset(ciliated_cds_pr_test_res, q_value < 0.05))
AFD_genes <-pr_deg_ids[20:22]
AFD_lineage_cds <- cds[rowData(cds)$gene_short_name %in% AFD_genes,
]
plot_genes_in_pseudotime(AFD_lineage_cds,
color_cells_by="celltype",
min_expr=0.5)
cds_subset <- choose_cells(cds)
subset_pr_test_res <- graph_test(cds_subset, neighbor_graph="principal_graph", cores=4)
pr_deg_ids <- row.names(subset(subset_pr_test_res, q_value < 0.05))
gene_module_df <- find_gene_modules(cds_subset[pr_deg_ids,], resolution=0.001)
agg_mat <- aggregate_gene_expression(cds_subset, gene_module_df)
module_dendro <- hclust(dist(agg_mat))
gene_module_df$module <- factor(gene_module_df$module,
levels = row.names(agg_mat)[module_dendro$order])
plot_cells(cds_subset,
genes=gene_module_df,
label_cell_groups=FALSE,
show_trajectory_graph=FALSE)