\section{Convert data from plate order to SGI-arrary}

Convert data from primary plate readout to an multi-dimensional SGI-array.

\subsection{Preliminaries}

Load HD2013SGI library.

<<convertData1>>=
library(HD2013SGI)
@

Load screening data.

<<convertData1>>=
data("featuresPerWell", package="HD2013SGI")
@

Create output directories.

<<convertData1>>=
dir.create(file.path("result","data"),recursive=TRUE,showWarnings=FALSE)
@

\subsection{Parse plate barcodes to annotate the plates}
<<convertData2,echo=FALSE,results=hide>>=
NROW = 15
NCOL = 23
NFIELD = 4
@

Plate barcodes and plate numbers are extracted from the annotation. 

The plates have \Sexpr{NROW} rows and \Sexpr{NCOL} columns. \Sexpr{NFIELD} fields are imaged per well. 

The plate annotation is summarized in a data frame.
<<convertData3>>=
plates = featuresPerWell$Anno[seq(1,nrow(featuresPerWell$Anno),
                                  by=NFIELD*NCOL*NROW),"plate"]
PlateAnnotation = HD2013SGI:::parsePlateBarcodes(plates)
head(PlateAnnotation)
@

The names of all query genes are extracted.

<<convertData4>>=
S = which(PlateAnnotation$queryGroup=="sample")
tdnames = unique(PlateAnnotation$targetDesign[S])
qnames = unique(PlateAnnotation$queryGene[S])
qdnames = unique(PlateAnnotation$queryDesign[S])
repnames = unique(PlateAnnotation$replicate[S])
@

\subsection{Reorder data}
The data is reordered and saved as an array. The mean of the measurements in the four fields per well is taken.
<<convertData9>>=
D = array(0.0, dim=c(field=NFIELD,col=NCOL,row=NROW,
                     features=dim(featuresPerWell$data)[2],
                     targetDesign=length(tdnames),
                     query=length(qnames),queryDesign=length(qdnames),
                     replicate=length(repnames)))
dimnames(D) = list(field=seq_len(NFIELD),
                   col=seq_len(NCOL),row=LETTERS[seq_len(NROW)+1],
                   features=dimnames(featuresPerWell$data)[[2]],
                   targetDesign=tdnames,
                   queryGene=qnames,queryDesign=qdnames,replicate=repnames)
z=0
for (td in tdnames) {
  for (q in qnames) {
    for (qd in qdnames) {
      for (r in repnames) {
        plate = PlateAnnotation$plate[
                      which((PlateAnnotation$targetDesign == td) &
          (PlateAnnotation$queryGene == q) &
          (PlateAnnotation$queryDesign == qd) &
          (PlateAnnotation$replicate == r) ) ]
        z=z+1
        I = which(featuresPerWell$Anno$plate == plate)
        D[,,,,td,q,qd,r] = as.vector(featuresPerWell$data[I,])
      }
    }
  }
}
D[is.na(D)] = 0.0
D = (D[1,,,,,,,] + D[2,,,,,,,] + D[3,,,,,,,] + D[4,,,,,,,])/4
# D = apply(D,2:8,mean,na.rm=TRUE)

D = aperm(D,c(1,2,4,5,6,3,7))
dn = dimnames(D)
dim(D) = c(prod(dim(D)[1:2]),dim(D)[3:7])
dimnames(D) = c(list(targetGene = 
                       sprintf("%s%d",rep(LETTERS[seq_len(NROW)+1],each=NCOL),
                                      rep(seq_len(NCOL),times=NROW))),
                   dn[3:7])

datamatrixfull = list(D = D)

save(datamatrixfull, file=file.path("result","data","datamatrixfull.rda"))
@

The raw data is represented as a 6-dimensional array with dimensions\\
\begin{center}
\begin{tabular}{lrrl}
& \Sexpr{dim(datamatrixfull$D)[1]} & target genes \\
$\times$ & \Sexpr{dim(datamatrixfull$D)[2]} & siRNA target designs \\
$\times$ & \Sexpr{dim(datamatrixfull$D)[3]} & query genes \\
$\times$ & \Sexpr{dim(datamatrixfull$D)[4]} & siRNA query designs \\
$\times$ & \Sexpr{dim(datamatrixfull$D)[5]} & phenotypic features\\
$\times$ & \Sexpr{dim(datamatrixfull$D)[6]} & biological replicates
\end{tabular}
\end{center}