@@ -1,5 +1,6 @@

 # Generated by roxygen2: do not edit by hand

+export("")

 export(CoGAPS)

 export(CoGapsFromCheckpoint)

 export(GWCoGAPS)

@@ -10,10 +11,12 @@ export(calcGeneGSStat)

 export(calcZ)

 export(computeGeneGSProb)

 export(createGWCoGAPSSets)

+export(createscCoGAPSSets)

 export(displayBuildReport)

 export(gapsMapRun)

 export(gapsRun)

 export(patternMatch4Parallel)

+export(patternMatch4singleCell)

 export(plotAtoms)

 export(plotDiag)

 export(plotGAPS)

@@ -13,22 +13,29 @@

 #'}

 #'

-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)

-}

-

+createGWCoGAPSSets <- function(D, S, nSets, simulationName)

+{

+    # check gene names

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

+    {

+        warning("Cell identifiers not unique!")

+    }

+    # partition data by sampling random sets of cells

+    genes <- 1:nrow(D)

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

+    for (set in 1:nSets)

+    {

+        

+        # sample genes

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

+            geneset <- sample(genes, sampleSize, replace=FALSE)

+            genes <- genes[!(genes %in% geneset)]

+        # partition data

+        sampleD <- D[geneset,]

+        sampleS <- S[geneset,]

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

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

+    }

+    return(simulationName)

+}

@@ -1,12 +1,12 @@

 #' 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}

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

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

 #' @param cnt  number of branches at which to cut dendrogram

 #' @param minNS minimum of individual set contributions a cluster must contain

 #' @param cluster.method the agglomeration method to be used for clustering

 #' @param ignore.NA logical indicating whether or not to ignore NAs from potential over dimensionalization. Default is FALSE.

-#' @param bySet logical indicating whether to return list of matched set solutions from \code{Ptot}

+#' @param bySet logical indicating whether to return list of matched set solutions from \code{Atot}

 #' @param ... additional parameters for \code{agnes}

 #' @return a matrix of concensus patterns by samples. If \code{bySet=TRUE} then a list of the set contributions to each

 #' concensus pattern is also returned.

@@ -15,19 +15,19 @@

 #' 

 #' 

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

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

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

 {

     if (!is.null(minNS))

         minNS=nSets/2

-    if (ignore.NA==FALSE & anyNA(Ptot))

+    if (ignore.NA==FALSE & anyNA(Atot))

         warning('Non-sparse matrixes produced. Reducing the number of patterns asked for and rerun.')

     if (ignore.NA==TRUE)

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

+        Atot <- Atot[complete.cases(Atot),]

     # corr dist

-    corr.dist=cor(Ptot)

+    corr.dist=cor(Atot)

     corr.dist=1-corr.dist

     # cluster

     #library(cluster)

@@ -37,26 +37,26 @@ cluster.method="complete", ignore.NA=FALSE, bySet=FALSE, ...)

     #drop n<4 and get weighted Avg

     cls=sort(unique(cut))

-    cMNs=matrix(nrow=cnt,ncol=dim(Ptot)[2])

+    cMNs=matrix(nrow=cnt,ncol=dim(Atot)[2])

     rownames(cMNs)=cls

-    colnames(cMNs)=colnames(Ptot)

+    colnames(cMNs)=colnames(Atot)

     RtoMeanPattern <- list()

     PByClust <- list()

     for(i in cls)

     {

-        if (is.null(dim(Ptot[cut == i, ]))==TRUE)

+        if (is.null(dim(Atot[cut == i, ]))==TRUE)

         {

-            cMNs[i,] <- Ptot[cut == i, ]

-            RtoMeanPattern[[i]] <- rep(1,length(Ptot[cut == i, ]))

-            PByClust[[i]] <- t(as.matrix(Ptot[cut == i, ]))

+            cMNs[i,] <- Atot[cut == i, ]

+            RtoMeanPattern[[i]] <- rep(1,length(Atot[cut == i, ]))

+            PByClust[[i]] <- t(as.matrix(Atot[cut == i, ]))

         }

         else

         {

-            cMNs[i,]=colMeans(Ptot[cut==i,])

-            PByClust[[i]] <- Ptot[cut==i,]

+            cMNs[i,]=colMeans(Atot[cut==i,])

+            PByClust[[i]] <- Atot[cut==i,]

             nIN=sum(cut==i)

-            RtoMeanPattern[[i]] <- sapply(1:nIN,function(j) {round(cor(x=Ptot[cut==i,][j,],y=cMNs[i,]),3)})

+            RtoMeanPattern[[i]] <- sapply(1:nIN,function(j) {round(cor(x=Atot[cut==i,][j,],y=cMNs[i,]),3)})

         }

     }

@@ -124,7 +124,7 @@ cluster.method="complete", ignore.NA=FALSE, bySet=FALSE, ...)

     {

         # return by set and final

         PBySet<-PByCDS

-        return(list("consenusPatterns"=PByCDSWavgScaled,"PBySet"=PBySet,"RtoMPDS"=RtoMPDS))

+        return(list("consenusAs"=PByCDSWavgScaled,"ABySet"=PBySet,"RtoMPDS"=RtoMPDS))

     }

     else

     {

@@ -66,11 +66,11 @@ GWCoGapsFromCheckpoint <- function(simulationName, nCores=NA, cut=NA, minNS=NA,

             cptFileName <- paste(simulationName, "_final_cpt_", i, ".out", sep="")

             CoGapsFromCheckpoint(sampleD, sampleS, cptFileName)

         }

-        load(paste(simulationName, "_matched_ps.RData", sep=""))

+        load(paste(simulationName, "_matched_As.RData", sep=""))

     }

-    else if (file_test("-f", paste(simulationName, "_matched_ps.RData", sep="")))

+    else if (file_test("-f", paste(simulationName, "_matched_As.RData", sep="")))

     {

-        load(paste(simulationName, "_matched_ps.RData", sep=""))

+        load(paste(simulationName, "_matched_As.RData", sep=""))

         consensusAs<-matchedAmplitudes[[1]]

         finalResult <- runFinalPhase(simulationName, allDataSets, consensusAs, ...)

     }

@@ -88,7 +88,7 @@ GWCoGapsFromCheckpoint <- function(simulationName, nCores=NA, cut=NA, minNS=NA,

             CoGapsFromCheckpoint(sampleD, sampleS, cptFileName)

         }

         matchedAmplitudes <- postInitialPhase(initialResult, length(allDataSets), cut, minNS)

-        save(matchedAmplitudes, file=paste(simulationName, "_matched_ps.RData", sep=""))

+        save(matchedAmplitudes, file=paste(simulationName, "_matched_As.RData", sep=""))

         consensusAs<-matchedAmplitudes[[1]]

         finalResult <- runFinalPhase(simulationName, allDataSets, consensusAs, ...)

     }

@@ -182,7 +182,7 @@ runFinalPhase <- function(simulationName, allDataSets, consensusAs, nCores, ...)

 postFinalPhase <- function(finalResult, consensusAs)

 {

     Aresult <- postFixed4Parallel(finalResult, consensusAs)

-    finalResult <- list("Amean"=Aresult$A, "Asd"=Aresult$Asd,"Pmean"=consensusAs)

+    finalResult <- list("Pmean"=Aresult$P, "Psd"=Aresult$Psd,"Amean"=consensusAs)

     class(finalResult) <- append(class(finalResult), "CoGAPS")

     return(finalResult)

 }

@@ -2,29 +2,29 @@

 % Please edit documentation in R/createGWCoGAPSSets.R

 \name{createGWCoGAPSSets}

 \alias{createGWCoGAPSSets}

-\title{Create Gene Sets for GWCoGAPS}

+\title{createGWCoGAPSSets}

 \usage{

-createGWCoGAPSSets(D, S, nSets, simulationName)

+createGWCoGAPSSets(data = D, nSets = nSets,

+  outRDA = "GenesInCoGAPSSets.Rda", keep = TRUE)

 }

 \arguments{

-\item{D}{data matrix}

+\item{data}{data matrix with unique rownames}

-\item{S}{uncertainty matrix}

+\item{nSets}{number of sets for parallelization}

-\item{nSets}{number of sets to partition the data into}

+\item{outRDA}{name of output file}

-\item{simulationName}{name used to identify files created by this simulation}

+\item{keep}{logical indicating whether or not to save gene set list. Default is TRUE.}

 }

 \value{

-simulationName used to identify saved files

+list with randomly generated sets of genes from whole genome data

 }

 \description{

-Create Gene Sets for GWCoGAPS

-}

-\details{

-factors whole genome data into randomly generated sets for indexing

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

 }

 \examples{

-data(SimpSim)

-createGWCoGAPSSets(SimpSim.D, SimpSim.S, nSets=2, "example")

+\dontrun{

+createGWCoGAPSSet(D,nSets=nSets)

+}

+

 }

new file mode 100644

@@ -0,0 +1,34 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/createscCoGAPSSets.R

+\name{createscCoGAPSSets}

+\alias{createscCoGAPSSets}

+\title{Create Gene Sets for scCoGAPS}

+\usage{

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

+}

+\arguments{

+\item{D}{data matrix}

+

+\item{S}{uncertainty matrix}

+

+\item{nSets}{number of sets to partition the data into}

+

+\item{simulationName}{name used to identify files created by this simulation}

+

+\item{samplingRatio}{vector of relative quantities to use for sampling celltypes}

+

+\item{annotionObj}{vector of same length as number of columns of D}

+}

+\value{

+simulationName used to identify saved files

+}

+\description{

+Create Gene Sets for scCoGAPS

+}

+\details{

+factors whole genome data into randomly generated sets for indexing

+}

+\examples{

+data(SimpSim)

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

+}

new file mode 100644

@@ -0,0 +1,36 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/patternMatch4singleCell.R

+\name{patternMatch4singleCell}

+\alias{patternMatch4singleCell}

+\title{patternMatch4singleCell}

+\usage{

+patternMatch4singleCell(Ptot, nSets, cnt, minNS, cluster.method = "complete",

+  ignore.NA = FALSE, bySet = FALSE, ...)

+}

+\arguments{

+\item{Ptot}{a matrix containing the total by set estimates of Pmean output from \code{reOrderBySet}}

+

+\item{nSets}{number of parallel sets used to generate \code{Ptot}}

+

+\item{cnt}{number of branches at which to cut dendrogram}

+

+\item{minNS}{minimum of individual set contributions a cluster must contain}

+

+\item{cluster.method}{the agglomeration method to be used for clustering}

+

+\item{ignore.NA}{logical indicating whether or not to ignore NAs from potential over dimensionalization. Default is FALSE.}

+

+\item{bySet}{logical indicating whether to return list of matched set solutions from \code{Ptot}}

+

+\item{...}{additional parameters for \code{agnes}}

+}

+\value{

+a matrix of concensus patterns by samples. If \code{bySet=TRUE} then a list of the set contributions to each

+concensus pattern is also returned.

+}

+\description{

+patternMatch4singleCell

+}

+\seealso{

+\code{\link{agnes}}

+}

@@ -15,7 +15,7 @@ greater than or equal to the number of rows of FP}

 \item{nCores}{number of cores for parallelization. If left to the default NA, nCores = nSets.}

-\item{cut}{number of branches at which to cut dendrogram used in patternMatch4Parallel}

+\item{cut}{number of branches at which to cut dendrogram used in patternMatch4singleCell}

 \item{minNS}{minimum of individual set contributions a cluster must contain}

@@ -40,8 +40,8 @@ the data matrix for whole genome data;

 data(SimpSim)

 sim_name <- "example"

 createscCoGAPSSets(SimpSim.D, SimpSim.S, nSets=2, sim_name)

-result <- GWCoGAPS(sim_name, nFactor=3, nEquil=1000, nSample=1000)

+result <- scCoGAPS(sim_name, nFactor=3, nEquil=1000, nSample=1000)

 }

 \seealso{

-\code{\link{gapsRun}}, \code{\link{patternMatch4Parallel}}, and \code{\link{gapsMapRun}}

+\code{\link{gapsRun}}, \code{\link{patternMatch4singleCell}}, and \code{\link{gapsMapRun}}

 }