spRandom-seq/01_Preprocessing_Downsampling.R at main · WangycLab/spRandom-seq · GitHub

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
source("./Helper_functions.R")

######### Process Downsampled Data ##########
SPA_hFB48_downsampled <- CreateSeuratObject(
  counts = Read10X("./Data/SPA_hFB48_downsampled_57_raw/"), min.cells = 1
)
SPA_hFB48_downsampled[['RNA']] <- as(object = SPA_hFB48_downsampled[['RNA']], Class = "Assay")

UT_FB48 <- readxl::read_xlsx("../Sept_DDL/Under_Tissue/SPA_hFB48_2.xlsx") %>%
  pivot_longer(., colnames(.)[-1], names_to = "X", values_to = "under_tissue") %>%
  mutate(Y = as.numeric(Y),
         X = as.numeric(X)) %>%
  dplyr::select(X, Y, under_tissue)

SPA_hFB48_downsampled@meta.data <- SPA_hFB48_downsampled@meta.data %>%
  rownames_to_column(var = "SPOT_ID") %>%
  left_join(., SPA_hFB48_add@meta.data %>%
              rownames_to_column(var = "SPOT_ID") %>%
              dplyr::select(SPOT_ID, X, Y)
            , by = c("SPOT_ID")) %>%
  left_join(., UT_FB48, by = c("X", "Y")) %>%
  column_to_rownames(var = "SPOT_ID")
SPA_hFB48_downsampled@meta.data[is.na(SPA_hFB48_downsampled@meta.data)] <- 0
SPA_hFB48_downsampled <- subset(SPA_hFB48_downsampled, subset = (under_tissue == "1"))

SPA_hFB48_downsampled@meta.data <- SPA_hFB48_downsampled@meta.data %>%
  rownames_to_column(var = "SPOT_ID") %>%
  left_join(., SPA_hFB48_add@meta.data %>%
              rownames_to_column(var = "SPOT_ID") %>%
              dplyr::select(SPOT_ID, seurat_clusters)
            , by = "SPOT_ID") %>%
  column_to_rownames(var = "SPOT_ID")

median(SPA_hFB48_downsampled$nCount_RNA)
median(SPA_hFB48_downsampled$nFeature_RNA)

######### Process miRNA matrix for comparison ##########
walk(list.files("./Data/SPA_hFB48_downsampled_57_miRNA_raw/", full.names = T), function(x) gzip(x))
miRNA_hFB48 <- CreateSeuratObject(
  counts = Read10X("./Data/SPA_hFB48_downsampled_57_miRNA_raw/")
)
miRNA_hFB48[['RNA']] <- as(object = miRNA_hFB48[['RNA']], Class = "Assay")
miRNA_hFB48 <- subset(miRNA_hFB48, cells = intersect(colnames(SPA_hFB48_add),
                                                     colnames(miRNA_hFB48)))
miRNA_hFB48 <- CreateSeuratObject(
  counts = miRNA_hFB48@assays$RNA@counts,
  min.cells = 1
)
miRNA_hFB48[['RNA']] <- as(object = miRNA_hFB48[['RNA']], Class = "Assay")
miRNA_hFB48@meta.data <- miRNA_hFB48@meta.data %>%
  rownames_to_column(var = "SPOT_ID") %>%
  left_join(., SPA_hFB48_add@meta.data %>%
              rownames_to_column(var = "SPOT_ID") %>%
              dplyr::select(SPOT_ID, X,Y),
            by = "SPOT_ID") %>%
  column_to_rownames(var = "SPOT_ID")

UT_FB48 <- readxl::read_xlsx("./Under_Tissue/SPA_hFB48_2.xlsx") %>%
  pivot_longer(., colnames(.)[-1], names_to = "X", values_to = "under_tissue") %>%
  mutate(Y = as.numeric(Y),
         X = as.numeric(X)) %>%
  dplyr::select(X, Y, under_tissue)

miRNA_hFB48@meta.data <- miRNA_hFB48@meta.data %>%
  rownames_to_column(var = "SPOT_ID") %>%
  left_join(., UT_FB48, by = c("X", "Y")) %>%
  column_to_rownames(var = "SPOT_ID")
miRNA_hFB48 <- subset(miRNA_hFB48, subset = under_tissue == "1")