| 1 | # Set the wd:
|
|---|
| 2 | setwd("C:/BASE/Illumina imports/BeadStudio output")
|
|---|
| 3 |
|
|---|
| 4 | # Choose the file:
|
|---|
| 5 | filename <- "gene_profile.csv"
|
|---|
| 6 |
|
|---|
| 7 | #Set the number of arrays per chip:
|
|---|
| 8 | arraysPerChip = 8; # 6
|
|---|
| 9 | columnsPerArray = 8;
|
|---|
| 10 |
|
|---|
| 11 | # assign the column headers:
|
|---|
| 12 | headerColumnNames <-c("MIN_Signal","AVG_Signal","MAX_Signal","NARRAYS","ARRAY_STDEV","BEAD_STDEV","Avg_NBEADS","Detection"
|
|---|
| 13 |
|
|---|
| 14 | illumina <- read.csv(file=paste(getwd(),"/",filename,sep=""),skip=7,header=TRUE,row.name=1)
|
|---|
| 15 |
|
|---|
| 16 | ncol(illumina)
|
|---|
| 17 | nrow(illumina)
|
|---|
| 18 |
|
|---|
| 19 | numData = ncol(illumina) -
|
|---|
| 20 | numArrays = numData / columnsPerArray # 8 data columns per array
|
|---|
| 21 | numChips = numArrays/arraysPerChip #
|
|---|
| 22 |
|
|---|
| 23 | numChips
|
|---|
| 24 |
|
|---|
| 25 | if numChips%%1 ~= 0
|
|---|
| 26 | "ERROR: an incomplete chip is in this file!"
|
|---|
| 27 |
|
|---|
| 28 | colnames(illumina) -> myCols
|
|---|
| 29 |
|
|---|
| 30 | # Derive the Chip names from the colnames:
|
|---|
| 31 | # Format of first entry: "MIN_Signal.XXXXXXXXXX_A" ( 10 Xs: maybe different?)
|
|---|
| 32 |
|
|---|
| 33 | lenFirstData <-nchar(headerColumnNames[1])
|
|---|
| 34 |
|
|---|
| 35 | chipNums = NULL
|
|---|
| 36 | arrayNames = NULL
|
|---|
| 37 |
|
|---|
| 38 | # Derive names of arrays:
|
|---|
| 39 | for (k in 1:numChips){
|
|---|
| 40 |
|
|---|
| 41 | # Get the numbers of the chips:
|
|---|
| 42 | colNum = 1 + (k-1)* (arraysPerChip *columnsPerArray)
|
|---|
| 43 | chipNums = c(chipNums, substr(myCols [colNum],lenFirstData+2,nchar(myCols[colNum])-2))
|
|---|
| 44 |
|
|---|
| 45 | # Get names of all the arrays
|
|---|
| 46 | labels = c("A","B","C","D","E","F","G","H")
|
|---|
| 47 | labels = labels[1: arraysPerChip]
|
|---|
| 48 | arrayNames = c(arrayNames, paste(chipNums[k],labels,sep="_"))
|
|---|
| 49 | }
|
|---|
| 50 | chipNums
|
|---|
| 51 | arrayNames
|
|---|
| 52 |
|
|---|
| 53 |
|
|---|
| 54 | # output arrays (groups of columnsPerArray columns, plus gene names)
|
|---|
| 55 | for (k in 1:length(arrayNames))
|
|---|
| 56 | {
|
|---|
| 57 | outputCols <- c(1: columnsPerArray) + columnsPerArray * (k-1)
|
|---|
| 58 | outputData <- illumina[,outputCols]
|
|---|
| 59 | outputData <- cbind(rownames(illumina),outputData)
|
|---|
| 60 |
|
|---|
| 61 | colnames(outputData) <- as.character(c("TargetID",headerColumnNames))
|
|---|
| 62 |
|
|---|
| 63 | write.table(outputData,file = paste(arrayNames[k],".txt",sep=""),sep = "\t",row.names=FALSE,na="")
|
|---|
| 64 | }
|
|---|
