@@ -1,48 +1,34 @@

-#' Create Gene Sets for scCoGAPS

+#' createGWCoGAPSSets

 #'

-#' @details factors whole genome data into randomly generated sets for indexing

+#'\code{createGWCoGAPSSets} factors whole genome data into randomly generated sets for indexing;

+#'

+#'@param data data matrix with unique rownames

+#'@param nSets number of sets for parallelization

+#'@param outRDA name of output file

+#'@param keep logical indicating whether or not to save gene set list. Default is TRUE.

+#'@export

+#'@return list with randomly generated sets of genes from whole genome data

+#'@examples \dontrun{

+#'createGWCoGAPSSet(D,nSets=nSets)

+#'}

 #'

-#' @param D data matrix

-#' @param S uncertainty matrix

-#' @param nSets number of sets to partition the data into

-#' @param simulationName name used to identify files created by this simulation

-#' @param samplingRatio vector of relative quantities to use for sampling celltypes

-#' @param annotionObj vector of same length as number of columns of D 

-#' @return simulationName used to identify saved files

-#' @examples

-#' data(SimpSim)

-#' createscCoGAPSSets(SimpSim.D, SimpSim.S, nSets=2, "example")

-#' @export

-createscCoGAPSSets <- function(D, S, nSets, simulationName,samplingRatio=NULL)

-{

-    # check gene names

-    if (length(unique(colnames(D))) != length(colnames(D)))

-    {

-        warning("Cell identifiers not unique!")

-    }

-

-    # partition data by sampling random sets of cells

-    cells <- 1:ncol(D)

-    setSize <- floor(length(cells) / nSets)

-    for (set in 1:nSets)

-    {

-        

-        if(is.null(samplingRatio)){

-        # sample cell names

-            sampleSize <- ifelse(set == nSets, length(cells), setSize)

-            cellset <- sample(cells, sampleSize, replace=FALSE)

-            cells <- cells[!(cells %in% cellset)]

-        } else {

-        if(length(unique(annotionObj))!=length(samplingRatio)){warning("Not all celltypes will be sampled from.")}

-        ct.indx<-lapply(unique(annotionObj),function(x) which(annotionObj == x))

-        cellset<-sample(colnames(D)[ct.indx[[x]]], samplingRatio[x],replace=TRUE)

-        }

-        # partition data

-        sampleD <- D[,cellset]

-        sampleS <- S[,cellset]

-        save(sampleD, sampleS, file=paste(simulationName, "_partition_", set,

-            ".RData", sep=""));

-    }

-    return(simulationName)

+createGWCoGAPSSets<-function(data=D, #data matrix with unique rownames

+	nSets=nSets, #number of sets for parallelization

+	outRDA="GenesInCoGAPSSets.Rda", #name of output file

+	keep=TRUE #logical indicating whether or not to save gene set list. Default is TRUE.

+	){

+genes=rownames(data)

+setSize=floor(length(genes)/nSets)

+genesInSets <- list()

+for (set in 1:nSets) {

+  if(set!=nSets){genesInSets[[set]] <- sample(genes,setSize)}

+  if(set==nSets){genesInSets[[set]] <- genes}

+  genes=genes[!genes%in%genesInSets[[set]]]

+}

+if(!identical(sort(unlist(genesInSets)),sort(rownames(data)))){print("Gene identifiers not unique!")}

+if(keep==TRUE){save(list=c('genesInSets'),file=outRDA)}

+return(genesInSets)

 }

+

+

new file mode 100644

@@ -0,0 +1,48 @@

+#' Create Gene Sets for scCoGAPS

+#'

+#' @details factors whole genome data into randomly generated sets for indexing

+#'

+#' @param D data matrix

+#' @param S uncertainty matrix

+#' @param nSets number of sets to partition the data into

+#' @param simulationName name used to identify files created by this simulation

+#' @param samplingRatio vector of relative quantities to use for sampling celltypes

+#' @param annotionObj vector of same length as number of columns of D 

+#' @return simulationName used to identify saved files

+#' @examples

+#' data(SimpSim)

+#' createscCoGAPSSets(SimpSim.D, SimpSim.S, nSets=2, "example")

+#' @export

+createscCoGAPSSets <- function(D, S, nSets, simulationName,samplingRatio=NULL)

+{

+    # check gene names

+    if (length(unique(colnames(D))) != length(colnames(D)))

+    {

+        warning("Cell identifiers not unique!")

+    }

+

+    # partition data by sampling random sets of cells

+    cells <- 1:ncol(D)

+    setSize <- floor(length(cells) / nSets)

+    for (set in 1:nSets)

+    {

+        

+        if(is.null(samplingRatio)){

+        # sample cell names

+            sampleSize <- ifelse(set == nSets, length(cells), setSize)

+            cellset <- sample(cells, sampleSize, replace=FALSE)

+            cells <- cells[!(cells %in% cellset)]

+        } else {

+        if(length(unique(annotionObj))!=length(samplingRatio)){warning("Not all celltypes will be sampled from.")}

+        ct.indx<-lapply(unique(annotionObj),function(x) which(annotionObj == x))

+        cellset<-sample(colnames(D)[ct.indx[[x]]], samplingRatio[x],replace=TRUE)

+        }

+

+        # partition data

+        sampleD <- D[,cellset]

+        sampleS <- S[,cellset]

+        save(sampleD, sampleS, file=paste(simulationName, "_partition_", set,

+            ".RData", sep=""));

+    }

+    return(simulationName)

+}

@@ -1,4 +1,4 @@

-#' patternMatch4Parallel

+#' patternMatch4singleCell

 #'

 #' @param Ptot a matrix containing the total by set estimates of Pmean output from \code{reOrderBySet}

 #' @param nSets number of parallel sets used to generate \code{Ptot}

@@ -12,7 +12,10 @@

 #' concensus pattern is also returned.

 #' @seealso \code{\link{agnes}}

 #' @export

-patternMatch4Parallel <- function(Ptot, nSets, cnt, minNS, 

+#' 

+#' 

+

+patternMatch4singleCell <- function(Ptot, nSets, cnt, minNS, 

 cluster.method="complete", ignore.NA=FALSE, bySet=FALSE, ...)

 {

     if (!is.null(minNS))

@@ -24,7 +27,7 @@ cluster.method="complete", ignore.NA=FALSE, bySet=FALSE, ...)

         Ptot <- Ptot[complete.cases(Ptot),]

     # corr dist

-    corr.dist=cor(t(Ptot))

+    corr.dist=cor(Ptot)

     corr.dist=1-corr.dist

     # cluster

     #library(cluster)