#Efrain Gonzalez
#January 23, 2018
#R code for DESeq2 Analysis Dr. Hooi

##Choose directory with files in it
##set directory before this step
mydirectory <- getwd()

##Grab Treated files
myFiles <- grep("Count",list.files(mydirectory),value=TRUE)

##chop up file name to obtain condition status
#mycondition <- sub("(.*R4).*","\\1",myFiles)
mycondition <- c(rep("R4",4),rep("R5",4))
myTable <- data.frame(sampleName = myFiles, fileName = myFiles, condition = mycondition)

##Build DESeqDataSet
ddsHTSeq <- DESeqDataSetFromHTSeqCount(sampleTable = myTable, directory = mydirectory, design = ~ condition)

ddsHTSeq


##Collapse technical replicates

ddsHTSeq$sample <- factor(c("R1","R1","R1","R1","R4","R4","R4","R4","R5","R5","R5","R5"))

ddsHTSeq$run <- paste0("run",1:12)

DDSHTSEQ <- collapseReplicates(ddsHTSeq,ddsHTSeq$sample,ddsHTSeq$run)
matchFirstLevel <-ddsHTSeq$sample == levels(ddsHTSeq$sample)[1]

stopifnot(all(rowSums(counts(ddsHTSeq[,matchFirstLevel])) == counts(DDSHTSEQ[,1])))



##Analysis of Differential Expression
DDS <- DESeq(DDSHTSEQ)
#R4 VS R5
RES1 <- results(DDS,contrast = c("condition","R4","R5"))
RES1ordered <- RES1[order(RES1$pvalue),]
#R1 VS R5
RES2 <- results(DDS,contrast = c("condition","R1","R5"))
RES2ordered <- RES2[order(RES2$pvalue),]
#R1 VS R4
RES3 <- results(DDS,contrast = c("condition","R1","R4"))
RES3ordered <- RES3[order(RES3$pvalue),]

##PLOT LOG2 FOLD CHANGES
plotMA(RES1,ylim = c(-2,2))



##Write to tab delimeted txt file
write.table(as.data.frame(RES1ordered),sep="\t",col.names = TRUE, row.names= FALSE,file="R4_R5_results.txt")

write.table(as.data.frame(RES2ordered),sep="\t",col.names = TRUE, row.names= FALSE,file="R1_R5_results.txt")

write.table(as.data.frame(RES3ordered),sep="\t",col.names = TRUE, row.names= FALSE,file="R1_R4_results.txt")