data-raw/pbmc_meta.R

In rnabioco/clustifyrdata: External data sets for clustifyr

library(Seurat)
library(tidyverse)
library(usethis)
library(clustifyr)

# follow seurat tutorial from https://satijalab.org/seurat/v3.0/pbmc3k_tutorial.html
download.file("https://s3-us-west-2.amazonaws.com/10x.files/samples/cell/pbmc3k/pbmc3k_filtered_gene_bc_matrices.tar.gz", 
              destfile = "pbmc3k_filtered_gene_bc_matrices.tar.gz")
untar("pbmc3k_filtered_gene_bc_matrices.tar.gz")
pbmc.data <- Read10X(data.dir = "filtered_gene_bc_matrices/hg19")
pbmc <- CreateSeuratObject(counts = pbmc.data, project = "pbmc3k", min.cells = 3, min.features = 200)
pbmc[["percent.mt"]] <- PercentageFeatureSet(pbmc, pattern = "^MT-")
pbmc <- subset(pbmc, subset = nFeature_RNA > 200 & nFeature_RNA < 2500 & percent.mt < 5)
pbmc <- NormalizeData(pbmc, normalization.method = "LogNormalize", scale.factor = 10000)
pbmc <- FindVariableFeatures(pbmc, selection.method = "vst", nfeatures = 2000)
all.genes <- rownames(pbmc)
pbmc <- ScaleData(pbmc, features = all.genes)
pbmc <- RunPCA(pbmc, features = VariableFeatures(object = pbmc))
pbmc <- FindNeighbors(pbmc, dims = 1:10)
pbmc <- FindClusters(pbmc, resolution = 0.5)
pbmc <- RunUMAP(pbmc, dims = 1:10)
new.cluster.ids <- c("Naive CD4 T", "Memory CD4 T", "CD14+ Mono", "B", "CD8 T", "FCGR3A+ Mono", 
                     "NK", "DC", "Platelet")
names(new.cluster.ids) <- levels(pbmc)
pbmc <- RenameIdents(pbmc, new.cluster.ids)
pbmc <- StashIdent(pbmc, "classified")

pbmc_meta <- use_seurat_meta(pbmc, dr = "umap")

usethis::use_data(pbmc_meta, compress = "xz", overwrite = TRUE)