sc-type and Seurat
Ehsan.Rz
2022-05-17
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(Seurat)## Attaching SeuratObjectlibrary(SeuratData)## ── Installed datasets ───────────────────────────────────── SeuratData v0.2.2 ──## ✓ ifnb 3.1.0 ✓ pbmcsca 3.0.0
## ✓ panc8 3.0.2## ────────────────────────────────────── Key ─────────────────────────────────────## ✓ Dataset loaded successfully
## > Dataset built with a newer version of Seurat than installed
## ❓ Unknown version of Seurat installedlibrary(openxlsx)
library(HGNChelper)pbmc <- readRDS("/mnt/nectar_volume/home/eraz0001/pbmc_human/pbmc_tutorial_final.rds")DimPlot(pbmc)
source("https://raw.githubusercontent.com/IanevskiAleksandr/sc-type/master/R/gene_sets_prepare.R")
source("https://raw.githubusercontent.com/IanevskiAleksandr/sc-type/master/R/sctype_score_.R")there are different tissue type here. you can select if you wish
db_ = "https://raw.githubusercontent.com/IanevskiAleksandr/sc-type/master/ScTypeDB_full.xlsx"; tissue = "Muscle"gs_list = gene_sets_prepare(db_, tissue)## Maps last updated on: Thu Oct 24 12:31:05 2019
## Maps last updated on: Thu Oct 24 12:31:05 2019
## Maps last updated on: Thu Oct 24 12:31:05 2019
## Maps last updated on: Thu Oct 24 12:31:05 2019
## Maps last updated on: Thu Oct 24 12:31:05 2019
## Maps last updated on: Thu Oct 24 12:31:05 2019## Warning in checkGeneSymbols(markers_all): x contains non-approved gene symbols## Maps last updated on: Thu Oct 24 12:31:05 2019
## Maps last updated on: Thu Oct 24 12:31:05 2019
## Maps last updated on: Thu Oct 24 12:31:05 2019
## Maps last updated on: Thu Oct 24 12:31:05 2019
## Maps last updated on: Thu Oct 24 12:31:05 2019
## Maps last updated on: Thu Oct 24 12:31:05 2019
## Maps last updated on: Thu Oct 24 12:31:05 2019es.max = sctype_score(scRNAseqData = pbmc[["RNA"]]@scale.data, scaled = TRUE, gs = gs_list$gs_positive, gs2 = gs_list$gs_negative)cL_resutls = do.call("rbind", lapply(unique(pbmc@meta.data$seurat_clusters), function(cl){
es.max.cl = sort(rowSums(es.max[ ,rownames(pbmc@meta.data[pbmc@meta.data$seurat_clusters==cl, ])]), decreasing = !0)
head(data.frame(cluster = cl, type = names(es.max.cl), scores = es.max.cl, ncells = sum(pbmc@meta.data$seurat_clusters==cl)), 10)
}))
sctype_scores = cL_resutls %>% group_by(cluster) %>% top_n(n = 1, wt = scores) sctype_scores$type[as.numeric(as.character(sctype_scores$scores)) < sctype_scores$ncells/4] = "Unknown"print(sctype_scores[,1:3])## # A tibble: 9 × 3
## # Groups: cluster [9]
## cluster type scores
## <fct> <chr> <dbl>
## 1 2 Unknown 83.5
## 2 3 Muscle satellite cell 121.
## 3 1 Unknown 41.6
## 4 6 Smooth muscle cells 50.7
## 5 4 Unknown 31.0
## 6 0 Unknown 93.4
## 7 5 Mesenchymal stem cell 47.9
## 8 7 Myocytes 19.9
## 9 8 Myoepithelial cells 38.0pbmc@meta.data$customclassif = ""
for(j in unique(sctype_scores$cluster)){
cl_type = sctype_scores[sctype_scores$cluster==j,];
pbmc@meta.data$customclassif[pbmc@meta.data$seurat_clusters == j] = as.character(cl_type$type[1])
}
DimPlot(pbmc, reduction = "umap", label = TRUE, repel = TRUE, group.by = 'customclassif') 
lapply(c("ggraph","igraph","tidyverse", "data.tree"), library, character.only = T)## Loading required package: ggplot2##
## Attaching package: 'igraph'## The following objects are masked from 'package:dplyr':
##
## as_data_frame, groups, union## The following objects are masked from 'package:stats':
##
## decompose, spectrum## The following object is masked from 'package:base':
##
## union## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──## ✓ tibble 3.1.6 ✓ purrr 0.3.4
## ✓ tidyr 1.2.0 ✓ stringr 1.4.0
## ✓ readr 2.1.2 ✓ forcats 0.5.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x tibble::as_data_frame() masks igraph::as_data_frame(), dplyr::as_data_frame()
## x purrr::compose() masks igraph::compose()
## x tidyr::crossing() masks igraph::crossing()
## x dplyr::filter() masks stats::filter()
## x igraph::groups() masks dplyr::groups()
## x dplyr::lag() masks stats::lag()
## x purrr::simplify() masks igraph::simplify()## [[1]]
## [1] "ggraph" "ggplot2" "HGNChelper"
## [4] "openxlsx" "pbmcsca.SeuratData" "panc8.SeuratData"
## [7] "ifnb.SeuratData" "SeuratData" "SeuratObject"
## [10] "Seurat" "dplyr" "stats"
## [13] "graphics" "grDevices" "utils"
## [16] "datasets" "methods" "base"
##
## [[2]]
## [1] "igraph" "ggraph" "ggplot2"
## [4] "HGNChelper" "openxlsx" "pbmcsca.SeuratData"
## [7] "panc8.SeuratData" "ifnb.SeuratData" "SeuratData"
## [10] "SeuratObject" "Seurat" "dplyr"
## [13] "stats" "graphics" "grDevices"
## [16] "utils" "datasets" "methods"
## [19] "base"
##
## [[3]]
## [1] "forcats" "stringr" "purrr"
## [4] "readr" "tidyr" "tibble"
## [7] "tidyverse" "igraph" "ggraph"
## [10] "ggplot2" "HGNChelper" "openxlsx"
## [13] "pbmcsca.SeuratData" "panc8.SeuratData" "ifnb.SeuratData"
## [16] "SeuratData" "SeuratObject" "Seurat"
## [19] "dplyr" "stats" "graphics"
## [22] "grDevices" "utils" "datasets"
## [25] "methods" "base"
##
## [[4]]
## [1] "data.tree" "forcats" "stringr"
## [4] "purrr" "readr" "tidyr"
## [7] "tibble" "tidyverse" "igraph"
## [10] "ggraph" "ggplot2" "HGNChelper"
## [13] "openxlsx" "pbmcsca.SeuratData" "panc8.SeuratData"
## [16] "ifnb.SeuratData" "SeuratData" "SeuratObject"
## [19] "Seurat" "dplyr" "stats"
## [22] "graphics" "grDevices" "utils"
## [25] "datasets" "methods" "base"