Add code to create and analize Continual Integreation test data

bash.scripts/sc_CIAnalysis-Pr.sh

+#!/bin/bash
+#
+# CREATED USING THE BIOHPC PORTAL on Thu Nov 30 2017 16:16:26 GMT-0600 (Central Standard Time)
+#
+# This file is batch script used to run commands on the BioHPC cluster.
+# The script is submitted to the cluster using the SLURM `sbatch` command.
+# Lines starting with # are comments, and will not be run.
+# Lines starting with #SBATCH specify options for the scheduler.
+# Lines that do not start with # or #SBATCH are commands that will run.
+
+# Name for the job that will be visible in the job queue and accounting tools.
+#SBATCH --job-name R_CIAnalysis
+
+# Name of the SLURM partition that this job should run on.
+#SBATCH -p super       # partition (queue)
+# Number of nodes required to run this job
+#SBATCH -N 1
+
+# Time limit for the job in the format Days-H:M:S
+# A job that reaches its time limit will be cancelled.
+# Specify an accurate time limit for efficient scheduling so your job runs promptly.
+#SBATCH -t 7-0:0:0
+
+# The standard output and errors from commands will be written to these files.
+# %j in the filename will be replace with the job number when it is submitted.
+#SBATCH -o job_%j.out
+#SBATCH -e job_%j.err
+
+# Send an email when the job status changes, to the specfied address.
+#SBATCH --mail-type ALL
+#SBATCH --mail-user gervaise.henry@utsouthwestern.edu
+
+module load R/3.3.2-gccmkl
+
+# COMMAND GROUP 1
+Rscript ../r.scripts/sc_Demultiplex.R
+Rscript ../r.scritps/sc_D-SampleReorder.R
+Rscript ../r.scripts/sc_Seurat.Score.CellCycle.R
+Rscript ../r.scripts/sc_QC.R
+Rscript ../r.scripts/sc_Cluster.R
+Rscript ../r.scripts/sc_PC.Score.Stress.R --sv=NA
+Rscript ../r.scripts/sc_QuSAGE.Lineage.R --s=NA
+Rscript ../r.scripts/sc_LineageSubClust.R
+Rscript ../r.scripts/sc_QuSAGE_EpiSubClust.R --s=NA --r=0.2
+Rscript ../r.scripts/sc_QuSAGE_StSubClust.R --s=NA --r=0.2
+Rscript ../r.scripts/sc_MergeSubClust.R --r=0.2
+Rscript ../r.scripts/sc_PC.Score.NE.R --sv=NA
+Rscript ../r.scripts/sc_DEG.R
+Rscript ../r.scripts/sc_Tables.R
+# END OF SCRIPT

bash.scripts/sc_LinkData-CI.TestData.Create.sh

+#!/bin/bash
+mkdir ../analysis
+mkdir ../analysis/DATA
+ln -s /work/urology/ghenry/RNA-Seq/SingleCell/PIPELINE/DATA/"$1"/10x/filtered_gene_bc_matrices_mex/GRCh38/* ../analysis/DATA/
+ln -s /work/urology/ghenry/RNA-Seq/SingleCell/PIPELINE/DATA/ANALYSIS/"$1"/sc10x.Pr.ALL.cluster.NOStress.IDepi+st+ne.Merge.Rda ../analysis/DATA/sc10x.data.Rda
+
+mkdir ../analysis/CI.TestData.downsample
+mkdir ../analysis/CI.TestData.downsample/10x
+mkdir ../analysis/CI.TestData.downsample/10x/filtered_gene_bc_matrices_mex
+mkdir ../analysis/CI.TestData.downsample/10x/filtered_gene_bc_matrices_mex/GRCh38
+cp /work/urology/ghenry/RNA-Seq/SingleCell/PIPELINE/DATA/"$1"/"$1"-demultiplex.csv ../analysis/CI.TestData.downsample/"$1"-demultiplex.csv
+cp /work/urology/ghenry/RNA-Seq/SingleCell/PIPELINE/DATA/"$1"/10x/"$1"-aggr.csv ../analysis/CI.TestData.downsample/10x/"$1"-aggr.csv
\ No newline at end of file

r.scripts/sc_CI.TestData.Create.R

+gc()
+.libPaths("/home2/ghenry/R/x86_64-pc-linux-gnu-library/3.3")
+library(readr)
+library(Matrix)
+library(Seurat)
+
+setwd("../")
+genes <- read_delim("./analysis/DATA/genes.tsv","\t",escape_double=FALSE,col_names=FALSE,trim_ws=TRUE)
+barcodes <- read_delim("./analysis/DATA/barcodes.tsv","\t",escape_double=FALSE,col_names=FALSE,trim_ws=TRUE)
+matrix <- readMM("./analysis/DATA/matrix.mtx")
+load("./analysis/DATA/sc10x.data.Rda")
+
+sc10x.Group <- SetAllIdent(object=sc10x.Group,id="SubClust.ID+NE")
+barcodes.NE <- names(sc10x.Group@ident[sc10x.Group@ident=="NE"])
+
+genes.rnd <- 1:nrow(genes)
+#genes.rnd <- sample(genes.rnd,2500)
+
+barcodes.rnd <- 1:nrow(barcodes)
+barcodes.NE.index <- c()
+for (i in 1:length(barcodes.NE)){
+  barcodes.NE.index <- c(barcodes.NE.index,which(barcodes==barcodes.NE[i]))
+}
+barcodes.rnd <- barcodes.rnd[!barcodes.rnd %in% barcodes.NE.index]
+barcodes.rnd <- sample(barcodes.rnd,(2500-length(barcodes.NE)))
+barcodes.rnd <- c(barcodes.rnd,barcodes.NE.index)
+
+genes.sample <- genes[genes.rnd,]
+barcodes.sample <- barcodes[barcodes.rnd,]
+matrix.sample <- matrix[genes.rnd,barcodes.rnd]
+
+if (!dir.exists("./analysis/CI.TestData.downsample")){
+  dir.create("./analysis/CI.TestData.downsample")
+}
+if (!dir.exists("./analysis/CI.TestData.downsample/10x")){
+  dir.create("./analysis/CI.TestData.downsample/10x")
+}
+if (!dir.exists("./analysis/CI.TestData.downsample/10x/filtered_gene_bc_matrices_mex")){
+  dir.create("./analysis/CI.TestData.downsample/10x/filtered_gene_bc_matrices_mex")
+}
+if (!dir.exists("./analysis/CI.TestData.downsample/10x/filtered_gene_bc_matrices_mex/GRCh38")){
+  dir.create("./analysis/CI.TestData.downsample/10x/filtered_gene_bc_matrices_mex/GRCh38")
+}
+
+write.table(genes.sample,file="./analysis/CI.TestData.downsample/10x/filtered_gene_bc_matrices_mex/GRCh38/genes.tsv",row.names=FALSE,col.names=FALSE,append=FALSE,sep="\t",quote=FALSE)
+write.table(barcodes.sample,file="./analysis/CI.TestData.downsample/10x/filtered_gene_bc_matrices_mex/GRCh38/barcodes.tsv",row.names=FALSE,col.names=FALSE,append=FALSE,sep="\t",quote=FALSE)
+writeMM(matrix.sample,file="./analysis/CI.TestData.downsample/10x/filtered_gene_bc_matrices_mex/GRCh38/matrix.mtx")
\ No newline at end of file