Make function based pipeline

r.scripts/sc-TissueMapper_RUN.R

+gc()
+library(methods)
+library(optparse)
+library(Seurat)
+library(readr)
+library(fBasics)
+library(pastecs)
+library(qusage)
+
+source("sc-TissueMapper.R")
+
+#Create folder structure
+setwd("../")
+if (!dir.exists("./analysis")){
+  dir.create("./analysis")
+}
+if (!dir.exists("./analysis/qc")){
+  dir.create("./analysis/qc")
+}
+if (!dir.exists("./analysis/qc/cc")){
+  dir.create("./analysis/qc/cc")
+}
+if (!dir.exists("./analysis/tSNE")){
+  dir.create("./analysis/tSNE")
+}
+if (!dir.exists("./analysis/tSNE/pre.stress")){
+  dir.create("./analysis/tSNE/pre.stress")
+}
+if (!dir.exists("./analysis/pca")){
+  dir.create("./analysis/pca")
+}
+if (!dir.exists("./analysis/pca/stress")){
+  dir.create("./analysis/pca/stress")
+}
+if (!dir.exists("./analysis/tSNE/stress")){
+  dir.create("./analysis/tSNE/stress")
+}
+if (!dir.exists("./analysis/violin")){
+  dir.create("./analysis/violin")
+}
+if (!dir.exists("./analysis/violin/stress")){
+  dir.create("./analysis/violin/stress")
+}
+if (!dir.exists("./analysis/table")){
+  dir.create("./analysis/table")
+}
+if (!dir.exists("./analysis/tSNE/post.stress")){
+  dir.create("./analysis/tSNE/post.stress")
+}
+if (!dir.exists("./analysis/cor")){
+  dir.create("./analysis/cor")
+}
+if (!dir.exists("./analysis/tSNE/lin")){
+  dir.create("./analysis/tSNE/lin")
+}
+if (!dir.exists("./analysis/tSNE/epi")){
+  dir.create("./analysis/tSNE/epi")
+}
+if (!dir.exists("./analysis/tSNE/st")){
+  dir.create("./analysis/tSNE/st")
+}
+if (!dir.exists("./analysis/tSNE/merge")){
+  dir.create("./analysis/tSNE/merge")
+}
+if (!dir.exists("./analysis/pca/ne")){
+  dir.create("./analysis/pca/ne")
+}
+if (!dir.exists("./analysis/tSNE/ne")){
+  dir.create("./analysis/tSNE/ne")
+}
+if (!dir.exists("./analysis/violin/ne")){
+  dir.create("./analysis/violin/ne")
+}
+if (!dir.exists("./analysis/tSNE/FINAL")){
+  dir.create("./analysis/tSNE/FINAL")
+}
+
+#Retrieve command-line options
+option_list=list(
+  make_option("--p",action="store",default="Pr",type='character',help="Project Name"),
+  make_option("--g",action="store",default="ALL",type='character',help="Group To analyze"),
+  make_option("--lg",action="store",default=500,type='integer',help="Threshold for cells with minimum genes"),
+  make_option("--hg",action="store",default=2500,type='integer',help="Threshold for cells with maximum genes"),
+  make_option("--lm",action="store",default=0,type='numeric',help="Threshold for cells with minimum %mito genes"),
+  make_option("--hm",action="store",default=0.1,type='numeric',help="Threshold for cells with maximum %mito genes"),
+  make_option("--lx",action="store",default=0.15,type='numeric',help="x low threshold for hvg selection"),
+  make_option("--hx",action="store",default=3.5,type='numeric',help="x high threshold for hvg selection"),
+  make_option("--ly",action="store",default=0.75,type='numeric',help="y low threshold for hvg selection"),
+  make_option("--cc",action="store",default=TRUE,type='logical',help="Scale cell cycle?"),
+  make_option("--pc",action="store",default=50,type='integer',help="Number of PCs to cacluate"),
+  make_option("--hpc",action="store",default=0.75,type='numeric',help="Max variance cutoff for PCs to use, pre-stress"),
+  make_option("--res.prestress",action="store",default=1,type='numeric',help="Resolution to cluster, pre-stress"),
+  make_option("--st",action="store",default="TRUE",type='logical',help="Remove stressed cells?"),
+  make_option("--stg",action="store",default="go",type='character',help="Geneset to use for stress ID"),
+  make_option("--hpc.poststress",action="store",default=0.75,type='numeric',help="Max variance cutoff for PCs to use, post-stress"),
+  make_option("--res.poststress",action="store",default=0.1,type='numeric',help="Resolution to cluster, post-stress"),
+  make_option("--ds",action="store",default=25000,type='integer',help="Number of cells to downsample"),
+  make_option("--hpc.epi",action="store",default=0.75,type='numeric',help="Max variance cutoff for PCs to use, Epi"),
+  make_option("--res.epi",action="store",default=0.1,type='numeric',help="Resolution to cluster, Epi"),
+  make_option("--hpc.st",action="store",default=0.75,type='numeric',help="Max variance cutoff for PCs to use, St"),
+  make_option("--res.st",action="store",default=0.1,type='numeric',help="Resolution to cluster, St")
+  )
+opt=parse_args(OptionParser(option_list=option_list))
+rm(option_list)
+if (opt$lm==0){opt$lm=-Inf}
+
+sc10x <- scLoad(opt$p)
+
+sc10x <- scSubset(sc10x,"ALL",opt$g)
+
+if (opt$cc==TRUE){
+  results <- scCellCycle(sc10x)
+  sc10x <- results[[1]]
+  genes.s <- results[[2]]
+  genes.g2m <- results[[3]]
+  rm(results)
+} else {
+  genes.s=""
+  genes.g2m=""
+}
+
+results <- scQC(sc10x,lg=opt$lg,hg=opt$hg,lm=opt$lm,hm=opt$hm)
+sc10x <- results[[1]]
+counts.cell.raw <- results[[2]]
+counts.gene.raw <- results[[3]]
+counts.cell.filtered <- results[[4]]
+counts.gene.filtered <- results[[5]]
+rm(results)
+
+results <- scPC(sc10x,lx=opt$lx,hx=opt$hx,ly=opt$ly,cc=opt$cc,genes.s=genes.s,genes.g2m=genes.g2m,pc=opt$pc,hpc=opt$hpc)
+sc10x <- results[[1]]
+genes.hvg <- results[[2]]
+pc.use <- results[[3]]
+rm(results)
+
+sc10x <- scCluster(sc10x,pc.use=pc.use,res=opt$res.prestress,folder="pre.stress")
+
+if (opt$st==TRUE){
+  results <- scStress(sc10x,stg=opt$stg,res.use=opt$res.prestress,pc.use=pc.use)
+  sc10x <- results[[1]]
+  counts.cell.filtered.stress <- results[[2]]
+  rm(results)
+
+  results <- scPC(sc10x,lx=opt$lx,hx=opt$hx,ly=opt$ly,cc=opt$cc,genes.s=genes.s,genes.g2m=genes.g2m,pc=opt$pc,hpc=opt$hpc.poststress)
+  sc10x <- results[[1]]
+  genes.hvg.poststress <- results[[2]]
+  pc.use.poststress <- results[[3]]
+  rm(results)
+  
+  sc10x <- scCluster(sc10x,pc.use=pc.use.poststress,res=opt$res.poststress,folder="post.stress")
+}
+
+gene.set1 <- read_delim("./genesets/DEG_FMSt_5FC.txt","\t",escape_double=FALSE,trim_ws=TRUE,col_names=FALSE)
+gene.set1 <- as.list(gene.set1)
+names(gene.set1) <- "St"
+gene.set <- c(gene.set1)
+gene.set1 <- read_delim("./genesets/DEG_Epi_5FC.txt","\t",escape_double=FALSE,trim_ws=TRUE,col_names=FALSE)
+gene.set1 <- as.list(gene.set1)
+names(gene.set1) <- "Epi"
+gene.set <- c(gene.set,gene.set1)
+rm(gene.set1)
+results <- scQuSAGE(sc10x,gs=gene.set,res.use=opt$res.poststress,ds=opt$ds,nm="Lin")
+sc10x <- results[[1]]
+results.cor.Lin <- results[[2]]
+results.clust.Lin.id <- results[[3]]
+rm(results)
+rm(gene.set)
+
+sc10x.Epi <- scSubset(sc10x,i="Lin",g="Epi")
+if (any(levels(sc10x@ident)=="Unknown")){
+  sc10x.St <- scSubset(sc10x,i="Lin",g=c("St","Unknown"))
+} else {
+  sc10x.St <- scSubset(sc10x,i="Lin",g="St")
+}
+
+results <- scPC(sc10x.Epi,lx=opt$lx,hx=opt$hx,ly=opt$ly,cc=opt$cc,genes.s=genes.s,genes.g2m=genes.g2m,pc=opt$pc,hpc=opt$hpc.epi)
+sc10x.Epi <- results[[1]]
+genes.hvg.epi <- results[[2]]
+pc.use.epi <- results[[3]]
+rm(results)
+
+sc10x.Epi <- scCluster(sc10x.Epi,pc.use=pc.use.epi,res=opt$res.epi,folder="epi")
+
+gene.set1 <- read_delim("./genesets/DEG_BE_5FC.txt","\t",escape_double=FALSE,trim_ws=TRUE,col_names=FALSE)
+gene.set1 <- as.list(gene.set1)
+names(gene.set1) <- "BE"
+gene.set <- c(gene.set1)
+gene.set1 <- read_delim("./genesets/DEG_LE_5FC.txt","\t",escape_double=FALSE,trim_ws=TRUE,col_names=FALSE)
+gene.set1 <- as.list(gene.set1)
+names(gene.set1) <- "LE"
+gene.set <- c(gene.set,gene.set1)
+gene.set1 <- read_delim("./genesets/DEG_OE_5FC.txt","\t",escape_double=FALSE,trim_ws=TRUE,col_names=FALSE)
+gene.set1 <- as.list(gene.set1)
+names(gene.set1) <- "OE"
+gene.set <- c(gene.set,gene.set1)
+rm(gene.set1)
+results <- scQuSAGE(sc10x.Epi,gs=gene.set,res.use=opt$res.epi,ds=opt$ds,nm="Epi.dws")
+sc10x.Epi <- results[[1]]
+results.cor.Epi.dws <- results[[2]]
+results.clust.Epi.dws.id <- results[[3]]
+rm(results)
+rm(gene.set)
+
+results <- scPC(sc10x.St,lx=opt$lx,hx=opt$hx,ly=opt$ly,cc=opt$cc,genes.s=genes.s,genes.g2m=genes.g2m,pc=opt$pc,hpc=opt$hpc.st)
+sc10x.St <- results[[1]]
+genes.hvg.st <- results[[2]]
+pc.use.st <- results[[3]]
+rm(results)
+
+sc10x.St <- scCluster(sc10x.St,pc.use=pc.use.st,res=opt$res.st,folder="st")
+
+gene.set1 <- read_delim("./genesets/DEG_C5.BP.M11704.txt","\t",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
+gene.set1 <- as.list(gene.set1[-1,])
+names(gene.set1) <- "Endo"
+gene.set <- c(gene.set1)
+gene.set1 <- read_delim("./genesets/DEG_C5.BP.M10794.txt","\t",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
+gene.set1 <- as.list(gene.set1[-1,])
+names(gene.set1) <- "SM"
+gene.set <- c(gene.set,gene.set1)
+gene.set1 <- read_delim("./genesets/DEG_C5.BP.M13024.txt","\t",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
+gene.set1 <- as.list(gene.set1[-1,])
+names(gene.set1) <- "Fib"
+gene.set <- c(gene.set,gene.set1)
+gene.set1 <- read_delim("./genesets/DEG_C5.BP.M10124.txt","\t",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
+gene.set1 <- as.list(gene.set1[-1,])
+names(gene.set1) <- "Leu"
+gene.set <- c(gene.set,gene.set1)
+rm(gene.set1)
+results <- scQuSAGE(sc10x.St,gs=gene.set,res.use=opt$res.st,ds=opt$ds,nm="St.go")
+sc10x.St <- results[[1]]
+results.cor.St.go <- results[[2]]
+results.clust.St.go.id <- results[[3]]
+rm(results)
+rm(gene.set)
+
+sc10x.Epi.NE <- scNE(sc10x.Epi,neg="EurUro")
+
+sc10x.Epi <- scMergeSubClust(sc10x.Epi,i="Epi.dws",g=c("BE","LE"),nm="Merge")
+
+sc10x.St <- scMergeSubClust(sc10x.St,i="St.go",g=c("Endo","SM","Fib","Leu"),nm="Merge")
+
+sc10x <- scMerge(sc10x,sc10x.Epi,sc10x.St,i.1="Merge",i.2="Merge",nm="Merge_Epi.dws_St.go")
+
+sc10x <- scMerge(sc10x,sc10x,sc10x.Epi.NE,i.1="Merge_Epi.dws_St.go",i.2="NE",nm="Merge_Epi.dws_St.go_NE")
+
+sc10x <- SetAllIdent(object=sc10x,id="Merge_Epi.dws_St.go")
+sc10x@ident <- factor(sc10x@ident,levels=c("BE","LE","OE","NE","Fib","SM","Endo","Leu"))
+postscript("./analysis/tSNE/FINAL/tSNE_FINAL.eps")
+plot <- TSNEPlot(object=sc10x,pt.size=2.5,do.return=TRUE,vector.friendly=FALSE)
+plot <- plot+theme(axis.text.x=element_text(size=20),axis.text.y=element_text(size=20),axis.title.x=element_text(size=20),axis.title.y=element_text(size=20),legend.text=element_text(size=20))
+plot <- plot+guides(colour=guide_legend(override.aes=list(size=10)))
+plot(plot)
+dev.off()
+
+scTables(sc10x,i.1="samples",i.2="Merge_Epi.dws_St.go")
+scTables(sc10x,i.1="Merge_Epi.dws_St.go_NE",i.2="Merge_Epi.dws_St.go")