R_loaddata

rm(list=ls())
source('scRNA_scripts/lib.R')
#设置工作路径setwd()
getwd()
####单个txt/csv/tsv数据读取###
# 一般下载下来的都是tar结尾的压缩文件
untar("GSE221575/GSE221575_RAW.tar",exdir = "GSE221575/GSE221575_RAW")
#对压缩文件进行解压 函数untar
dir='GSE221575/GSE221575_RAW' 
fs=list.files('GSE221575/GSE221575_RAW/','^GSM')
#按照正则表达式进行文件的列出
?list.files
fs
library(tidyverse)
samples=str_split(fs,'_',simplify = T)[,1]
按照_进行字符分割，并保存为矩阵的形式
samples
##处理数据，将原始文件分别整理为barcodes.tsv.gz，features.tsv.gz和matrix.mtx.gz到各自的文件夹
#批量将文件名改为 Read10X()函数能够识别的名字
if(T){
  lapply(unique(samples),function(x){
    # x = unique(samples)[1]
    y=fs[grepl(x,fs)]
    folder=paste0("GSE221575/GSE221575_RAW/", paste(str_split(y[1],'_',simplify = T)[,1:2], collapse = "_"))
    dir.create(folder,recursive = T)
    #为每个样本创建子文件夹
    file.rename(paste0("GSE221575/GSE221575_RAW/",y[1]),file.path(folder,"barcodes.tsv.gz"))
    #重命名文件，并移动到相应的子文件夹里
    file.rename(paste0("GSE221575/GSE221575_RAW/",y[2]),file.path(folder,"features.tsv.gz"))
    file.rename(paste0("GSE221575/GSE221575_RAW/",y[3]),file.path(folder,"matrix.mtx.gz"))
  })
}
#循环函数，并对文件进行清洗、重命名，以符合可以创建seruat对象的源文件格式
samples=list.files( dir )
samples 
sceList = lapply(samples,function(pro){ 
  # pro=samples[1] 
  print(pro)  
  tmp = Read10X(file.path(dir,pro )) 
  if(length(tmp)==2){
    ct = tmp[[1]] 
  }else{ct = tmp}
  sce =CreateSeuratObject(counts =  ct ,
                          project =  pro  ,
                          min.cells = 5,
                          min.features = 300 )
  return(sce)
}) 
#读取数据，并创建为seruat对象。
do.call(rbind,lapply(sceList, dim)) 
##       [,1] [,2]
## [1,] 18506 3760
## [2,] 20137 2959
## [3,] 19179 4793
## [4,] 19766 4994
## [5,] 20505 5290
sce.all=merge(x=sceList[[1]],
              y=sceList[ -1 ],   add.cell.ids = samples ) 
names(sce.all@assays$RNA@layers)
sce.all[["RNA"]]$counts[1:5,1:5]
LayerData(sce.all,assay = "RNA", layer = "counts")
sce.all <- JoinLayers(sce.all)
dim(sce.all[["RNA"]]$counts )

as.data.frame(sce.all@assays$RNA$counts[1:10, 1:2])
head(sce.all@meta.data, 10)
table(sce.all$orig.ident)