-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathS5a_Create_Loom_From_Seurat_Object.Rmd
executable file
·169 lines (129 loc) · 6.31 KB
/
S5a_Create_Loom_From_Seurat_Object.Rmd
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
---
title: "Creating ASAP/SCENIC-compatible Loom file from Seurat object"
author: "Vincent Gardeux"
date: "2024/03/05"
updated: "2025/02/12"
output:
html_document:
df_print: paged
---
```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
knitr::opts_knit$set(root.dir = "/data/gardeux/Neuro_Droso_ND75KD/")
```
## Libraries & functions
First, I'm loading the required libraries & functions
```{r}
suppressPackageStartupMessages(library(Seurat, lib.loc = "/software/Seuratv4/lib/")) # Seurat v4.4.0, library for single-cell analysis
suppressPackageStartupMessages(library(SeuratObject, lib.loc = "/software/Seuratv4/lib/")) # For compatibility purpose
suppressPackageStartupMessages(library(data.table)) # For writing DE gene file
suppressPackageStartupMessages(library(loomR)) # For building a file for ASAP
suppressPackageStartupMessages(library(Matrix)) # For building a file for ASAP
suppressPackageStartupMessages(library(crayon)) # Just for bolding the console output :D
cat(bold("Seurat"), "version", as.character(packageVersion("Seurat")), "\n")
cat(bold("SeuratObject"), "version", as.character(packageVersion("SeuratObject")), "\n")
cat(bold("data.table"), "version", as.character(packageVersion("data.table")), "\n")
cat(bold("loomR"), "version", as.character(packageVersion("loomR")), "\n")
cat(bold("Matrix"), "version", as.character(packageVersion("Matrix")), "\n")
```
## Parameters
```{r}
# Parameters
seurat_input <- "./data/Pan_neuro_integrated_FINAL.rds"
loom_output <- "./data/Pan_neuro_integrated_FINAL.loom"
gene_ensembl_mapping_path <- "./data/features.tsv"
# Random seed
set.seed(42)
```
## I.1 Reading Seurat object
First step is to read the Seurat object, previously created
```{r}
message("Loading Seurat object...")
data.seurat <- readRDS(seurat_input)
message(ncol(data.seurat), " cells were loaded")
message(nrow(data.seurat), " genes were loaded")
```
## I.2 Loading gene mapping from CellRanger output (I did not perform the CellRanger alignment)
```{r}
gene.mapping = fread(gene_ensembl_mapping_path, header = F, data.table = F)
colnames(gene.mapping) <- c("Ensembl", "Name", "Biotype")
gene.mapping$Name <- gsub(x = gene.mapping$Name, pattern = "_", replacement = "-")
rownames(gene.mapping) <- gene.mapping$Name
# To solve issue with ASAP DB
gene.mapping$Ensembl <- gsub(x = gene.mapping$Ensembl, pattern = "-", replacement = "_")
gene.mapping
```
## II. ASAP
If you want to use ASAP, you need to package the Seurat object into a Loom file, to upload on ASAP.
NOTE: I could use SeuratDisk SaveDisk option, but it does not do what I want. And there are many missing fields. So I'll create the Loom from scratch.
# Prepare Cell attributes to put in Loom
```{r}
attributes_cells <- list(CellID=data.seurat@assays$RNA@counts@Dimnames[[2]])
for(m in names(data.seurat@meta.data)){
attributes_cells[[m]] <- data.seurat@meta.data[m]
}
```
# Main /matrix (I remove colnames and rownames)
```{r}
count_matrix <- data.seurat@assays$RNA@counts
colnames(count_matrix) <- NULL
rownames(count_matrix) <- NULL
```
# Create Loom file
```{r}
data.loom <- create(filename = loom_output, data = count_matrix, gene.attrs = list(Accession=gene.mapping[data.seurat@assays$RNA@counts@Dimnames[[1]],"Ensembl"], Gene=data.seurat@assays$RNA@counts@Dimnames[[1]]), cell.attrs = attributes_cells, overwrite = T)
```
# Adding Integrated NN graph
Generate b vector, from p
```{r}
b_vec <- rep(0, length(data.seurat@graphs$RNA_nn_harmony@i))
val <- 0
ind <- 0
for(i in 2:length(data.seurat@graphs$RNA_nn_harmony@p)){
b_vec[(ind + 1):data.seurat@graphs$RNA_nn_harmony@p[i]] <- val
val <- val + 1
ind <- data.seurat@graphs$RNA_nn_harmony@p[i]
}
data.loom$add.graph(name = "RNA_nn_harmony", a = data.seurat@graphs$RNA_nn_harmony@i, b = b_vec, w = data.seurat@graphs$RNA_nn_harmony@x)
```
# Adding Integrated SNN graph
Generate b vector, from p
```{r}
b_vec <- rep(0, length(data.seurat@graphs$RNA_snn_harmony@i))
val <- 0
ind <- 0
for(i in 2:length(data.seurat@graphs$RNA_snn_harmony@p)){
b_vec[(ind + 1):data.seurat@graphs$RNA_snn_harmony@p[i]] <- val
val <- val + 1
ind <- data.seurat@graphs$RNA_snn_harmony@p[i]
}
data.loom$add.graph(name = "RNA_snn_harmony", a = data.seurat@graphs$RNA_snn_harmony@i, b = b_vec, w = data.seurat@graphs$RNA_snn_harmony@x)
```
# Adding Layers
Saving also the normalized data in a layer
```{r}
data.loom$add.layer(layers = list(normalized=data.seurat@assays$RNA@data))
```
# Add Embeddings
Saving the PCA, UMAP and t-SNE coordinates
```{r}
data.loom$add.col.attribute(list(PCA=data.seurat@reductions$pca@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(t_SNE_uncorrected=data.seurat@reductions$tsne_uncorrected@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(UMAP_uncorrected=data.seurat@reductions$umap_uncorrected@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(Harmony=data.seurat@reductions$harmony@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(t_SNE_harmony=data.seurat@reductions$tsne_harmony@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(UMAP_harmony=data.seurat@reductions$umap_harmony@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(Harmony_overcorrected=data.seurat@reductions$harmony_overcorrected@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(t_SNE_harmony_overcorrected=data.seurat@reductions$tsne_harmony_overcorrected@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(UMAP_harmony_overcorrected=data.seurat@reductions$umap_harmony_overcorrected@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(SCENIC=data.seurat@reductions$SCENIC@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(t_SNE_SCENIC=data.seurat@reductions$SCENICtsne@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(UMAP_SCENIC=data.seurat@reductions$SCENICumap@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(SCENIC_binarized=data.seurat@reductions$SCENICbinarized@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(t_SNE_SCENIC_binarized=data.seurat@reductions$SCENICbinarizedtsne@cell.embeddings), overwrite = TRUE)
data.loom$add.col.attribute(list(UMAP_SCENIC_binarized=data.seurat@reductions$SCENICbinarizedumap@cell.embeddings), overwrite = TRUE)
```
# Close the Loom file
```{r}
data.loom$close_all()
```