Add files via upload

01.RNA-seq/DEseqForKallisto.R

@@ -0,0 +1,144 @@
+#!/usr/bin/Rscript
+suppressPackageStartupMessages({
+  library("data.table")
+  library(DESeq2)
+  library(ggplot2)
+  library(stringr)
+  library(dplyr)
+  library(ggpubr)
+  library(ggthemes)
+  library(tximport)
+  library(ggrepel)
+  library("tibble")
+  library("optparse")
+  library("BiocParallel")
+
+})
+
+option_list <- list(
+  make_option(c("-i", "--inputfile"), dest = "Rinput", default = "", 
+              help="[opt] inputdir"),
+  make_option(c("-n", "--namefle"), dest = "namefile", default = "",
+              help="[opt] namefile"),
+  make_option(c("-c","--t2g"),dest = "t2gfile",default = "",
+              help = "[opt] t2g config file"),
+  make_option(c("-t","--contrast"),dest = "contrastfile",default = "",
+              help = "[opt] contrast config file"),
+  make_option(c("-p", "--padj"), dest = "p", default = "",
+              help="[opt] padj cutoff "),
+  make_option(c("-f", "--foldchange"), dest = "f", default = "0",
+              help="[opt] log2foldchange defalut 0"),
+  make_option(c("-x", "--threads"), dest = "x", default = "4",
+              help="[opt] threads defalut 4"),
+  make_option(c("-o", "--outprefix"), dest = "outfile", default = "",
+              help="[opt] DEseq2 out file")
+) 
+
+parser <- OptionParser(usage = "%prog [options] file",
+     option_list=option_list, description = " 2019-3-24 \
+Description: \
+  Wrapper for DEseq2.\
+Example: \
+  DEseqForKallisto.R -i 01.kallisto   -n design.conf -c t2g -t contrast.conf -x 1  -o out "
+)
+#
+
+
+
+arguments <- parse_args(parser)
+opt <- arguments$options
+test <- arguments$Rinput
+files = file.path(test ,list.files(test),"abundance.h5")
+
+names(files) = list.files(test)
+
+register(MulticoreParam(arguments$x))
+
+if(test == "") {
+  print_help(parser)
+  stop(sprintf("input file is not specified"))
+  test = file("stdin")  
+}
+
+designfile <- arguments$namefile
+
+designfile =  read.table(designfile,header=T,stringsAsFactors = F)
+
+t2gfile <- arguments$t2gfile
+
+tx2gene <- read.table(t2gfile,header=T)
+
+
+
+contrastfile <- arguments$contrastfile
+
+contrastfile = read.csv(contrastfile,sep="\t",header = FALSE,stringsAsFactors = F)
+
+
+
+P <- as.numeric(arguments$p)
+F <- as.numeric(arguments$f)
+o <- arguments$outfile
+
+
+
+txi = tximport(files, type = "kallisto", tx2gene = tx2gene, 
+               txIn = TRUE, txOut = FALSE, countsFromAbundance = "no")
+
+
+if(  unique(colnames(txi$abundance) == designfile$sample) ) {
+  print("all  samples matched")
+} else {
+  print( "rename file from :" )
+  colnames(txi$abundance)
+  print("to :")
+  designfile$sample
+  }
+
+dds <- DESeqDataSetFromTximport(txi,colData = designfile,design= ~ condition)
+
+dds2 <- DESeq(dds,parallel = TRUE)
+
+mergetable <- data.frame(row.names =row.names(dds2))
+
+for (i in 1:nrow(contrastfile)) {
+    contrast_name <- paste0(as.character(unlist(contrastfile[i,]))[2:3],collapse = "vs")
+    contrast_vector <- as.vector(unlist(contrastfile[i,]))
+    results <- results(dds2, contrast = contrast_vector,parallel = T)
+    results <- lfcShrink(dds2, contrast = contrast_vector, res=results,parallel = T)
+    if( arguments$p  == "") {
+        diff <- subset(results,(log2FoldChange > F|log2FoldChange < -F)) %>% as.data.frame()
+    }else {
+    diff <- subset(results, padj<P & (log2FoldChange > F|log2FoldChange < -F)) %>% as.data.frame()
+    }
+    diff2 <- subset(results) %>% as.data.frame()
+    diff2$logQ <- -log10(diff2$padj)
+    diff2$Group <- "Not-changed"
+    diff2$Label <- ""
+    diff2 <- diff2[order(diff2$padj),] 
+    diff2$Group[which( (diff2$padj<0.05) & (diff2$log2FoldChange > F))] = "Up-regulated"
+    diff2$Group[which( (diff2$padj<0.05) & (diff2$log2FoldChange < -F) )] = "Down-regulated"
+    upgenes <- head(rownames(diff2[which(diff2$Group =="Up-regulated"),]),10)
+    downgenes <- head(rownames(diff2[which(diff2$Group =="Down-regulated"),]),10)
+    top10genes <- c(as.character(upgenes),as.character(downgenes))
+    diff2$Label[match(top10genes,rownames(diff2)) ] <- top10genes
+    Vplot <- ggscatter(diff2,x = "log2FoldChange",y = "logQ", color = "Group" , palette=c("#2f5688","#BBBBBB","#CC0000"),size=1,label =diff2$Label,font.label = 8,repel = T,xlab = "Log2FC",ylab="-Log10(padj)") + theme_base() +
+      geom_hline(yintercept = -log10(P), linetype="dashed")+
+      geom_vline(xintercept = -c(-F, F), linetype="dashed")
+    ggsave(paste0("./",contrast_name,"vp.pdf"),plot = Vplot)
+    colnames(diff) <-  paste(contrast_name,colnames(diff),sep = "_")
+    mergetable <- merge(mergetable,diff[,c(2,6)],by="row.names",sort=FALSE,all=TRUE)
+    rownames(mergetable) <- mergetable$Row.names
+    mergetable$Row.names <- NULL
+    final <- merge(diff,as.data.frame(counts(dds2,normalize=TRUE)),by="row.names",sort=FALSE)
+    outfile <- paste(o,contrast_name,sep = ".")
+    write.table(final,file = outfile,row.names = FALSE,sep = "\t",quote = FALSE)
+}
+
+
+mergetable <- merge(mergetable,counts(dds2,normalize=TRUE),by="row.names",sort=FALSE,all=TRUE)
+
+
+
+write.table(mergetable,file = paste0(o,"all"),row.names = FALSE,sep = "\t",quote = FALSE)
+

01.RNA-seq/contrast.conf

@@ -0,0 +1,3 @@
+condition	KO_0h	WT_0h
+condition	KO_3h	WT_3h
+condition	KO_6h	WT_6h

01.RNA-seq/design.conf

@@ -0,0 +1,19 @@
+sample	condition	reps
+KO-0h-rep1	KO_0h	1
+KO-0h-rep2	KO_0h	2
+KO-0h-rep3	KO_0h	3
+KO-3h-rep1	KO_3h	1
+KO-3h-rep2	KO_3h	2
+KO-3h-rep3	KO_3h	3
+KO-6h-rep1	KO_6h	1
+KO-6h-rep2	KO_6h	2
+KO-6h-rep3	KO_6h	3
+WT-0h-rep1	WT_0h	1
+WT-0h-rep2	WT_0h	2
+WT-0h-rep3	WT_0h	3
+WT-3h-rep1	WT_3h	1
+WT-3h-rep2	WT_3h	2
+WT-3h-rep3	WT_3h	3
+WT-6h-rep1	WT_6h	1
+WT-6h-rep2	WT_6h	2
+WT-6h-rep3	WT_6h	3

01.RNA-seq/kallisto_strand.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+
+pwd; hostname; mydate
+
+mkdir -p 00.clean
+mkdir -p 01.kallisto
+
+for i in `echo ${1}`
+    do 
+        (R1=`echo ${i} | awk -F "|" '{print$1}'`
+        R2=`echo ${i} | awk -F "|" '{print$2}'`
+        name=`echo ${i} | awk -F "|" '{print$1}' | cut -d '_' -f1`
+        echo "R1 fastq file:" ${R1}
+        echo "R2 fastq file:" ${R2}
+        echo "   out prefix:" ${name}
+        echo "------fastp START-----"
+        fastp -i ./${R1} -I ./${R2} \
+            -o ./00.clean/${name}_R1_clean.fq.gz \
+            -O ./00.clean/${name}_R2_clean.fq.gz \
+            -3 -5 -W 6 -l 30 -c -h ./00.clean/${name}.html -z 6 -w 10
+        wait
+        echo `mydate` "------fastp END-----"
+        echo "------quant START-----"
+        kallisto quant \
+            -i ~/genome/index/IWGSC_v1_part/IWGSC_part_v1.1_HC_LC_kallisto  \
+            -o ./01.kallisto/${name}  \
+      		--bias -t 1 \
+      		-b 2 \
+      		--single-overhang \
+            --rf-stranded \
+            --genomebam \
+            -g  ~/genome/index/IWGSC_v1_part/IWGSC_part_v1.1_HC_LC.gtf \
+            -c  ~/genome/index/IWGSC_v1_part/chrlength.tab \
+            ./00.clean/${name}_R1_clean.fq.gz ./00.clean/${name}_R2_clean.fq.gz ) &
+done
+wait
+mydate
+echo '------ALL FINISH-----'

01.RNA-seq/mapping.conf

@@ -0,0 +1,9 @@
+WT-0h-rep1_R1.fastq.gz|WT-0h-rep1_R2.fastq.gz
+WT-0h-rep2_R1.fastq.gz|WT-0h-rep2_R2.fastq.gz
+WT-0h-rep3_R1.fastq.gz|WT-0h-rep3_R2.fastq.gz
+WT-3h-rep1_R1.fastq.gz|WT-3h-rep1_R2.fastq.gz
+WT-3h-rep2_R1.fastq.gz|WT-3h-rep2_R2.fastq.gz
+WT-3h-rep3_R1.fastq.gz|WT-3h-rep3_R2.fastq.gz
+WT-6h-rep1_R1.fastq.gz|WT-6h-rep1_R2.fastq.gz
+WT-6h-rep2_R1.fastq.gz|WT-6h-rep2_R2.fastq.gz
+WT-6h-rep3_R1.fastq.gz|WT-6h-rep3_R2.fastq.gz