Commit 8713aaa9 authored by Gervaise Henry's avatar Gervaise Henry 🤠
Browse files

Merge branch 'develop' into 'master'

Merge ds_D17 from develop into master

See merge request sc-TissueMapper_Pr!4
parents 25690b09 68fdeb80
#!/bin/bash
#SBATCH --job-name R_FullAnalysis
#SBATCH -p 256GB,256GBv1
#SBATCH -N 1
#SBATCH -t 7-0:0:0
#SBATCH -o job_%j.out
#SBATCH -e job_%j.out
#SBATCH --mail-type ALL
#SBATCH --mail-user gervaise.henry@utsouthwestern.edu
module load R/3.4.1-gccmkl
Rscript ../r.scripts/sc-TissueMapper_RUN.DS_D17.R
......@@ -103,14 +103,17 @@ scCellCycle <- function(sc10x,sub=FALSE){
sc10x <- ScaleData(object=sc10x,display.progress=FALSE,do.par=TRUE,num.cores=45)
sc10x <- CellCycleScoring(object=sc10x,s.genes=genes.s,g2m.genes=genes.g2m,set.ident=TRUE)
postscript(paste0(folder,"Ridge_cc.Raw.eps"))
plot <- RidgePlot(object=sc10x,features.plot=c("PCNA","TOP2A","MCM6","MKI67"),y.log=TRUE,nCol=2,do.return=TRUE)
plot(plot)
dev.off()
postscript(paste0(folder,"Violin_cc.Raw.eps"))
plot <- VlnPlot(object=sc10x,features.plot=c("PCNA","TOP2A","MCM6","MKI67"),nCol=2,point.size.use=1,size.title.use=20,x.lab.rot=TRUE)
plot(plot)
dev.off()
tryCatch({
postscript(paste0(folder,"Ridge_cc.Raw.eps"))
plot <- RidgePlot(object=sc10x,features.plot=c("PCNA","TOP2A","MCM6","MKI67"),y.log=TRUE,nCol=2,do.return=TRUE)
plot(plot)
dev.off()
postscript(paste0(folder,"Violin_cc.Raw.eps"))
plot <- VlnPlot(object=sc10x,features.plot=c("PCNA","TOP2A","MCM6","MKI67"),nCol=2,point.size.use=1,size.title.use=20,x.lab.rot=TRUE)
plot(plot)
dev.off()
},error=function(e){cat("ERROR : ",conditionMessage(e),"/\n")})
sc10x <- RunPCA(object=sc10x,pc.genes=c(genes.s,genes.g2m),do.print=FALSE,pcs.store=2)
postscript(paste0(folder,"PCA_cc.Raw.eps"))
plot <- PCAPlot(object=sc10x,do.return=TRUE)
......@@ -401,7 +404,7 @@ scStress <- function(sc10x,stg="go",res.use=1,pc.use=10,cut=0.95){
dev.off()
#Subsample all cells (+Stress) to better visualize their clustering
if (ncol(sc10x@data)<2500){
if (ncol(sc10x@data)>2500){
rnd <- sample(1:ncol(sc10x@data),2500)
} else {
rnd <- 1:ncol(sc10x@data)
......@@ -898,7 +901,7 @@ scNE <- function(sc10x,neg="EurUro",cut=0.95){
dev.off()
#Subsample all cells (+NE) to better visualize their clustering
if (ncol(sc10x@data)<2500){
if (ncol(sc10x@data)>2500){
rnd <- sample(1:ncol(sc10x@data),2500)
} else {
rnd <- 1:ncol(sc10x@data)
......
gc()
library(methods)
library(optparse)
library(Seurat)
library(readr)
library(fBasics)
library(pastecs)
library(qusage)
library(RColorBrewer)
library(monocle)
library(dplyr)
library(viridis)
library(reshape2)
library(NMI)
source("../r.scripts/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/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")
}
if (!dir.exists("./analysis/deg")){
dir.create("./analysis/deg")
}
if (!dir.exists("./analysis/cca")){
dir.create("./analysis/cca")
}
if (!dir.exists("./analysis/diy")){
dir.create("./analysis/diy")
}
if (!dir.exists("./analysis/pseudotime")){
dir.create("./analysis/pseudotime")
}
#Retrieve command-line options
option_list=list(
make_option("--p",action="store",default="DPrF",type='character',help="Project Name"),
make_option("--g",action="store",default="ALL",type='character',help="Group To analyze"),
make_option("--lg",action="store",default=0,type='integer',help="Threshold for cells with minimum genes"),
make_option("--hg",action="store",default=3000,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=0.2,type='numeric',help="x low threshold for hvg selection"),
make_option("--hx",action="store",default=5,type='numeric',help="x high threshold for hvg selection"),
make_option("--ly",action="store",default=1,type='numeric',help="y low threshold for hvg selection"),
make_option("--cc",action="store",default=TRUE,type='logical',help="Scale cell cycle?"),
make_option("--cca",action="store",default=50,type='integer',help="Number of CCAs to cacluate"),
make_option("--acca",action="store",default=30,type='integer',help="Number of CCAs to align"),
make_option("--pc",action="store",default=50,type='integer',help="Number of PCs to cacluate"),
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="dws",type='character',help="Geneset to use for stress ID"),
make_option("--cut.stress",action="store",default=0.9,type='numeric',help="Cutoff for stress score"),
make_option("--res.poststress",action="store",default=1,type='numeric',help="Resolution to cluster, post-stress"),
make_option("--cut.ne",action="store",default=0.999,type='numeric',help="Cutoff for NE score")
)
opt=parse_args(OptionParser(option_list=option_list))
rm(option_list)
if (opt$lg==0){opt$lg=-Inf}
if (opt$lm==0){opt$lm=-Inf}
sc10x.data <- Read10X(data.dir="./analysis/DATA/10x/filtered_gene_bc_matrices/GRCh38/")
sc10x <- new("seurat",raw.data=sc10x.data)
cell.codes <- as.data.frame(sc10x@raw.data@Dimnames[[2]])
colnames(cell.codes) <- "barcodes"
rownames(cell.codes) <- cell.codes$barcodes
cell.codes$samples <- "All"
sc10x <- CreateSeuratObject(raw.data=sc10x.data,meta.data=cell.codes["samples"],min.cells=3,min.genes=-Inf,project="DS.D17")
rm(cell.codes)
rm(sc10x.data)
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$hm)
sc10x <- results[[1]]
counts.cell.raw <- results[[2]]
counts.gene.raw <- results[[3]]
counts.cell.filtered <- results[[4]]
counts.gene.filtered <- results[[5]]
rm(results)
gc()
if (opt$cc==TRUE){
sc10x <- ScaleData(object=sc10x,vars.to.regress=c("nUMI","percent.mito","S.Score","G2M.Score"),display.progress=FALSE,do.par=TRUE,num.cores=45)
} else {
sc10x <- ScaleData(object=sc10x,vars.to.regress=c("nUMI","percent.mito"),display.progress=FALSE,do.par=TRUE,num.cores=45)
}
gc()
results <- scPC(sc10x,lx=opt$lx,hx=opt$hx,ly=opt$ly,cc=opt$cc,pc=50,hpc=0.85,file="pre.stress",cca=FALSE)
sc10x <- results[[1]]
genes.hvg.prestress <- results[[2]]
pc.use.prestress <- results[[3]]
rm(results)
sc10x <- scCluster(sc10x,pc.use=pc.use.prestress,res.use=opt$res.prestress,folder="pre.stress",red="pca")
if (opt$st==TRUE){
results <- scStress(sc10x,stg=opt$stg,res.use=opt$res.prestress,cut=opt$cut.stress)
sc10x <- results[[1]]
counts.cell.filtered.stress <- results[[2]]
sc10x.Stress <- results[[3]]
rm(results)
results <- scPC(sc10x,lx=opt$lx,hx=opt$hx,ly=opt$ly,cc=opt$cc,pc=50,hpc=0.85,file="post.stress",cca=FALSE)
sc10x <- results[[1]]
genes.hvg.poststress <- results[[2]]
pc.use.poststress <- results[[3]]
rm(results)
sc10x <- scCluster(sc10x,pc.use=pc.use.poststress,res.use=opt$res.poststress,folder="post.stress",red="pca")
}
gene.set1 <- read_delim("./genesets/genes.deg.Epi.csv",",",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
gene.set1 <- gene.set1[1]
gene.set1 <- as.list(gene.set1)
names(gene.set1) <- "Epi"
gene.set <- c(gene.set1)
gene.set1 <- read_delim("./genesets/genes.deg.St.csv",",",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
gene.set1 <- gene.set1[1]
gene.set1 <- as.list(gene.set1)
names(gene.set1) <- "St"
gene.set <- c(gene.set,gene.set1)
rm(gene.set1)
gc()
min.all <- min(table(sc10x@meta.data[,paste0("res",opt$res.poststress)]))
results <- scQuSAGE(sc10x,gs=gene.set,res.use=opt$res.poststress,ds=min.all,nm="Lin",folder="lin")
sc10x <- results[[1]]
results.cor.Lin <- results[[2]]
results.clust.Lin.id <- results[[3]]
rm(results)
rm(gene.set)
sc10x <- SetAllIdent(object=sc10x,id="Lin")
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")
}
sc10x.Epi <- SetAllIdent(object=sc10x.Epi,id=paste0("res",opt$res.poststress))
sc10x.Epi <- BuildClusterTree(sc10x.Epi,do.reorder=TRUE,reorder.numeric=TRUE,do.plot=FALSE)
sc10x.Epi <- StashIdent(object=sc10x.Epi,save.name=paste0("res",opt$res.poststress))
sc10x.St <- SetAllIdent(object=sc10x.St,id=paste0("res",opt$res.poststress))
sc10x.St <- BuildClusterTree(sc10x.St,do.reorder=TRUE,reorder.numeric=TRUE,do.plot=FALSE)
sc10x.St <- StashIdent(object=sc10x.St,save.name=paste0("res",opt$res.poststress))
sc10x.Epi <- RunTSNE(object=sc10x.Epi,reduction.use="pca",dims.use=1:pc.use.poststress,do.fast=TRUE)
postscript(paste0("./analysis/tSNE/epi/tSNE_Sample.eps"))
plot <- TSNEPlot(object=sc10x.Epi,group.by="samples",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()
postscript(paste0("./analysis/tSNE/epi/tSNE_res",opt$res.poststress,".eps"))
plot <- TSNEPlot(object=sc10x.Epi,pt.size=5,do.label=TRUE,label.size=10,do.return=TRUE,vector.friendly=FALSE)
plot <- plot+theme(axis.text.x=element_text(size=20),axis.text.y=element_text(size=20),axis.title.x=element_text(size=20),axis.title.y=element_text(size=20),legend.text=element_text(size=20))
plot <- plot+guides(colour=guide_legend(override.aes=list(size=10)))
plot(plot)
dev.off()
rm(plot)
sc10x.St <- RunTSNE(object=sc10x.St,reduction.use="pca",dims.use=1:pc.use.poststress,do.fast=TRUE)
postscript(paste0("./analysis/tSNE/st/tSNE_Sample.eps"))
plot <- TSNEPlot(object=sc10x.St,group.by="samples",pt.size=2.5,do.return=TRUE,vector.friendly=FALSE)
plot <- plot+theme(axis.text.x=element_text(size=20),axis.text.y=element_text(size=20),axis.title.x=element_text(size=20),axis.title.y=element_text(size=20),legend.text=element_text(size=20))
plot <- plot+guides(colour=guide_legend(override.aes=list(size=10)))
plot(plot)
dev.off()
postscript(paste0("./analysis/tSNE/st/tSNE_res",opt$res.poststress,".eps"))
plot <- TSNEPlot(object=sc10x.St,pt.size=5,do.label=TRUE,label.size=10,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()
rm(plot)
gene.set1 <- read_delim("./genesets/genes.deg.BE.csv",",",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
gene.set1 <- gene.set1[1]
gene.set1 <- as.list(gene.set1)
names(gene.set1) <- "BE"
gene.set <- c(gene.set1)
gene.set1 <- read_delim("./genesets/genes.deg.LE.csv",",",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
gene.set1 <- gene.set1[1]
gene.set1 <- as.list(gene.set1)
names(gene.set1) <- "LE"
gene.set <- c(gene.set,gene.set1)
gene.set1 <- read_delim("./genesets/genes.deg.OE1.csv",",",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
gene.set1 <- gene.set1[1]
gene.set1 <- as.list(gene.set1)
names(gene.set1) <- "OE_SCGB"
gene.set <- c(gene.set,gene.set1)
gene.set1 <- read_delim("./genesets/genes.deg.OE2.csv",",",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
gene.set1 <- gene.set1[1]
gene.set1 <- as.list(gene.set1)
names(gene.set1) <- "OE_KRT13"
gene.set <- c(gene.set,gene.set1)
rm(gene.set1)
gc()
min.epi <- min(table(sc10x.Epi@meta.data[,paste0("res",opt$res.poststress)]))
results <- scQuSAGE(sc10x.Epi,gs=gene.set,res.use=opt$res.poststress,ds=min.epi,nm="Epi.dws.sc",folder="epi")
sc10x.Epi <- results[[1]]
results.cor.Epi.dws <- results[[2]]
results.clust.Epi.dws.id <- results[[3]]
rm(results)
rm(gene.set)
gene.set1 <- read_delim("./genesets/genes.deg.Endo.csv",",",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
gene.set1 <- gene.set1[1]
gene.set1 <- as.list(gene.set1)
names(gene.set1) <- "Endo"
gene.set <- c(gene.set1)
gene.set1 <- read_delim("./genesets/genes.deg.SM.csv",",",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
gene.set1 <- gene.set1[1]
gene.set1 <- as.list(gene.set1)
names(gene.set1) <- "SM"
gene.set <- c(gene.set,gene.set1)
gene.set1 <- read_delim("./genesets/genes.deg.Fib.csv",",",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
gene.set1 <- gene.set1[1]
gene.set1 <- as.list(gene.set1)
names(gene.set1) <- "Fib"
gene.set <- c(gene.set,gene.set1)
gene.set1 <- read_delim("./genesets/genes.deg.Leu.csv",",",escape_double=FALSE,trim_ws=TRUE,col_names=TRUE)
gene.set1 <- gene.set1[1]
gene.set1 <- as.list(gene.set1)
names(gene.set1) <- "Leu"
gene.set <- c(gene.set,gene.set1)
rm(gene.set1)
gc()
min.st <- min(table(sc10x.St@meta.data[,paste0("res",opt$res.poststress)]))
results <- scQuSAGE(sc10x.St,gs=gene.set,res.use=opt$res.poststress,ds=min.st,nm="St.dws.sc",folder="st")
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="dws",cut=opt$cut.ne)
sc10x <- scMerge(sc10x,sc10x.Epi,sc10x.St,i.1="Epi.dws.sc",i.2="St.dws.sc",nm="Merge_Epi.dws.sc_St.dws.sc")
sc10x <- SetAllIdent(object=sc10x,id="Merge_Epi.dws.sc_St.dws.sc")
sc10x <- SetAllIdent(object=sc10x,id="Merge_Epi.dws.sc_St.dws.sc")
sc10x@ident <- factor(sc10x@ident,levels=c("BE","LE","OE_SCGB","OE_KRT13","Fib","SM","Endo","Leu"))
postscript("./analysis/tSNE/FINAL/tSNE_FINAL.eps")
plot <- TSNEPlot(object=sc10x,pt.size=2.5,do.return=TRUE,vector.friendly=FALSE)
plot <- plot+theme(axis.text.x=element_text(size=20),axis.text.y=element_text(size=20),axis.title.x=element_text(size=20),axis.title.y=element_text(size=20),legend.text=element_text(size=20))
plot <- plot+guides(colour=guide_legend(override.aes=list(size=10)))
plot(plot)
dev.off()
scTables(sc10x,i.1="samples",i.2="Merge_Epi.dws.sc_St.dws.sc")
sctSNECustCol(sc10x,i="Lin",bl="Epi",rd="St",file="D17")
sctSNECustCol(sc10x,i="Merge_Epi.dws.sc_St.dws.sc",bl=c("BE","LE","OE_SCGB","OE_KRT13"),rd=c("Fib","SM","Endo","Leu"),file="D17")
sctSNECustCol(sc10x.Epi,i="Epi.dws.sc",bl=c("BE","LE","OE_SCGB","OE_KRT13"),rd="",file="D17")
sctSNECustCol(sc10x.St,i="St.dws.sc",bl="",rd=c("Fib","SM","Endo","Leu"),file="D17")
sctSNEbwCol(sc10x,i=paste0("res",opt$res.poststress),file="ALL",files="D17")
sctSNEbwCol(sc10x.Epi,i=paste0("res",opt$res.poststress),file="Epi",files="D17")
sctSNEbwCol(sc10x.St,i=paste0("res",opt$res.poststress),file="St",files="D17")
sctSNEbwCol(sc10x,i="Merge_Epi.dws.sc_St.dws.sc",file="ALL",files="D17")
sctSNEbwCol(sc10x.Epi,i="Epi.dws.sc",file="Epi",files="D17")
sctSNEbwCol(sc10x.St,i="St.dws.sc",file="St",files="D17")
for (g in c("Epi","St","Unknown")){
sctSNEHighlight(sc10x,i="Lin",g=g,file="D17")
}
for (g in c("BE","LE","OE_SCGB","OE_KRT13")){
sctSNEHighlight(sc10x,i="Merge_Epi.dws.sc_St.dws.sc",g=g,file="D17")
sctSNEHighlight(sc10x.Epi,i="Epi.dws.c",g=g,file="D17")
}
for (g in c("Fib","SM","Endo","Leu")){
sctSNEHighlight(sc10x,i="Merge_Epi.dws.sc_St.dws.sc",g=g,file="D17")
sctSNEHighlight(sc10x.St,i="St.dws.sc",g=g,file="D17")
}
rm(i)
rm(g)
save(list=ls(pattern="sc10x.Stress"),file="./analysis/sc10x.Stress.Rda")
rm(list=ls(pattern="sc10x.Stress"))
save(list=ls(pattern="sc10x.Epi"),file="./analysis/sc10x.Epi.Rda")
rm(list=ls(pattern="^sc10x.Epi"))
save(list=ls(pattern="sc10x.St"),file="./analysis/sc10x.St.Rda")
rm(list=ls(pattern="sc10x.St"))
save(list=ls(pattern="^sc10x"),file="./analysis/sc10x.Rda")
rm(list=ls(pattern="^sc10x"))
save.image(file="./analysis/Data.RData")
gc()
library(methods)
library(optparse)
library(Seurat)
library(readr)
library(fBasics)
library(pastecs)
library(qusage)
library(RColorBrewer)
library(monocle)
library(dplyr)
library(viridis)
library(reshape2)
library(NMI)
source("../r.scripts/sc-TissueMapper.R")
setwd("../")
load("./analysis/sc10x.Rda")
sc10x.All <-sc10x
rm(sc10x)
downsample <- c("All","350","300","250","200","150","100","075","050","037","025","012","007","005","002")
for (i in downsample[-1]){
load(paste0("../../",i,"/sc-TissueMapper_Pr/analysis/sc10x.Rda"))
assign(paste0("sc10x.",i),sc10x)
rm(sc10x)
}
all.cells <- NULL
for (i in downsample){
all.cells <- c(all.cells,get(paste0("sc10x.",i))@data@Dimnames[[2]])
}
all.cells <- unique(all.cells)
shared.cells <- all.cells
shared.cells.no002<- all.cells
for (i in downsample){
shared.cells <- intersect(shared.cells,get(paste0("sc10x.",i))@data@Dimnames[[2]])
if (i != "002"){shared.cells <- intersect(shared.cells.no002,get(paste0("sc10x.",i))@data@Dimnames[[2]])}
}
for (i in downsample){
assign(paste0("sc10x.",i),SetAllIdent(get(paste0("sc10x.",i)),id="Merge_Epi.dws.sc_St.dws.sc"))
assign(paste0("cluster.",i),data.frame(Barcodes=names(get(paste0("sc10x.",i))@ident),Cluster=get(paste0("sc10x.",i))@ident))
assign(paste0("cluster.",i,".filter"),get(paste0("cluster.",i))[get(paste0("cluster.",i))$Barcodes %in% sc10x.All@data@Dimnames[[2]],])
}
nmi <- data.frame(Sample=character(),value=double())
for (i in downsample[-1]){
nmi <- rbind(nmi,data.frame(Sample=i,value=NMI(cluster.All.filter,get(paste0("cluster.",i,".filter")))))
}
nmi$Sample <- as.numeric(levels(nmi$Sample))
png(paste0("./analysis/NMI.png"),width=1000,height=500,type="cairo")
plot.nmi <- ggplot(nmi,aes(x=Sample,y=value))+geom_point()+geom_smooth(method='loess',formula=y~log(x))+labs(x="Sample (Million Reads)",y="NMI")
model.nmi <- loess(value~log(Sample),data=nmi)
fit.nmi.y <- 0.9
fit.nmi.x <- approx(x=predict(model.nmi),y=nmi$Sample,xout=fit.nmi.y)$y
plot.nmi <- plot.nmi+geom_vline(xintercept=fit.nmi.x)+geom_hline(yintercept=fit.nmi.y)
plot(plot.nmi)
dev.off()
for (i in downsample[-1]){
assign(paste0("rpc.",i),read_csv(paste0("../../../../count/",i,"M_D17PrTzF_Via/outs/metrics_summary.csv"))[,2])
}
rpc <- data.frame(Sample=character(),value=double())
for (i in downsample[-1]){
rpc <- rbind(rpc,data.frame(Sample=i,value=get(paste0("rpc.",i))))
}
colnames(rpc)[2] <- "value"
rpc$Sample <- as.numeric(levels(rpc$Sample))
png(paste0("./analysis/RPC.png"),width=1000,height=500,type="cairo")
plot.rpc <- ggplot(rpc,aes(x=Sample,y=value))+geom_point()+geom_smooth(method='lm',formula=y~x)+labs(x="Sample (Million Reads)",y="Mean Reads Per Cell")
model.rpc <- lm(value~Sample,data=rpc)
fit.rpc.y <- approx(x=rpc$Sample,y=predict(model.rpc),xout=fit.nmi.x)$y
plot.rpc <- plot.rpc+geom_vline(xintercept=fit.nmi.x)+geom_hline(yintercept=fit.rpc.y)
plot(plot.rpc)
dev.off()
comb <- cbind(nmi,rpc[,2])
colnames(comb) <- c("Sample","NMI","RPC")
nmi.rpc <- merge(nmi,rpc,by="Sample")
nmi.rpc <- nmi.rpc[,-1]
colnames(nmi.rpc) <- c("NMI","RPC")
nmi.rpc$NMI <- round(as.numeric(nmi.rpc$NMI),2)
postscript("./analysis/RPC+NMI.eps")
plot.comb <- ggplot(nmi.rpc,aes(x=RPC,y=NMI))+geom_point(colour="blue",size=4)
plot.comb <- plot.comb+geom_smooth(method='loess',formula=y~log(x),size=2)
model <- loess(NMI~RPC,data=nmi.rpc)
fit.y <- 0.9
fit.x <- approx(y=nmi.rpc$RPC,x=predict(model),xout=fit.y)$y
plot.comb <- plot.comb+geom_vline(xintercept=fit.x,linetype=2,size=1.5)+geom_hline(yintercept=fit.y,linetype=2,size=1.5)
plot.comb <- plot.comb+labs(x="Mean Reads Per Cell",y="NMI")
plot.comb <- plot.comb+scale_x_continuous(expand=c(0,0),limits=c(0,80000),breaks=c(seq(0,100000,25000),round(fit.x,0)))+scale_y_continuous(expand=c(0,0),limits=c(0,1),breaks=c(seq(0,1,0.2),fit.y))
plot(plot.comb)
dev.off()
save.image(file="./analysis/NMI.RData")
......@@ -312,7 +312,7 @@ names(gene.set1) <- "Leu"
gene.set <- c(gene.set,gene.set1)
rm(gene.set1)
gc()
min.st <- min(table(sc10x.Epi@meta.data[,paste0("res",opt$res.poststress)]))
min.st <- min(table(sc10x.St@meta.data[,paste0("res",opt$res.poststress)]))
results <- scQuSAGE(sc10x.St,gs=gene.set,res.use=0.2,ds=min.st,nm="St.go",folder="st")
sc10x.St <- results[[1]]
results.cor.St.go <- results[[2]]
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment