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

 # Generated by roxygen2: do not edit by hand

-export("")

 export(CoGAPS)

 export(CoGapsFromCheckpoint)

 export(GWCoGAPS)

@@ -9,12 +8,14 @@ export(binaryA)

 export(calcCoGAPSStat)

 export(calcGeneGSStat)

 export(calcZ)

+export(cellMatchR)

 export(computeGeneGSProb)

 export(createGWCoGAPSSets)

 export(createscCoGAPSSets)

 export(displayBuildReport)

 export(gapsMapRun)

 export(gapsRun)

+export(patternMarkers)

 export(patternMatch4Parallel)

 export(patternMatch4singleCell)

 export(plotAtoms)

new file mode 100644

@@ -0,0 +1,91 @@

+

+#' patternMatch4Parallel

+#'

+#' @param Atot a matrix containing the total by set estimates of Pmean 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 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{Atot}

+#' @param R2mean 

+#' @param

+#' @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.

+#' @export

+#' @seealso \code{\link{fastcluster}}

+#'

+#'

+

+cellMatchR <- function(Atot,nSets, cnt, minNS=NULL, maxNS=NULL, ignore.NA=FALSE, bySet=FALSE, plotDen=FALSE,...){

+

+  if(is.null(minNS)){minNS=nSets/2}

+  if(is.null(maxNS)){maxNS=nSets+minNS}

+

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

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

+  }}

+  if(ignore.NA==TRUE){Atot<-Atot[complete.cases(Atot),]}

+

+

+corcut<-function(Atot,minNS,cnt,cluster.method){

+  corr.dist=cor(Atot)

+  corr.dist=1-corr.dist

+

+  clust=agnes(x=corr.dist,diss=TRUE,cluster.method)

+  #clust=fastcluster::hclust(dist(corr.dist))

+  cut=cutree(as.hclust(clust),k=cnt)

+

+  cls=sort(unique(cut))

+  cMNs=matrix(ncol=cnt,nrow=dim(Atot)[1])

+  colnames(cMNs)=cls

+  rownames(cMNs)=rownames(Atot)

+

+  RtoMeanPattern <- list()

+  AByClust <- list()

+    for(i in cls){

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

+          next

+        } else if(dim(Atot[,cut == i])[2] < minNS){

+            next

+        } else{

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

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

+            nIN=sum(cut==i)

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

+        }

+      }

+    PByClust[sapply(PByClust,is.null)]<-NULL

+    RtoMeanPattern[sapply(RtoMeanPattern,is.null)]<-NULL

+    return(list("RtoMeanPattern"=RtoMeanPattern,"AByClust"=AByClust))

+  }   

+

+  cc<-corcut(Atot,minNS,cnt,cluster.method)

+

+    ### split by maxNS

+    indx<-which(unlist(lapply(cc$PByClust,function(x) dim(x)[1]>maxNS)))

+    while(length(indx)>0){

+          icc<-corcut(cc$AByClust[[indx[1]]],minNS,2,cluster.method)

+          cc$AByClust[[indx[1]]]<-icc[[2]][[2]]

+          cc$RtoMeanPattern[[indx[1]]]<-icc[[1]][[2]]

+          if(length(icc[[2]])>1){

+                cc$AByClust<-append(cc$AByClust,icc[[2]][1])

+                cc$RtoMeanPattern<-append(cc$RtoMeanPattern,icc[[1]][1])

+          }

+      indx<-which(unlist(lapply(cc$PByClust,function(x) dim(x)[1]>maxNS)))

+    }

+

+#weighted.mean(AByClustDrop[[1]],RtoMPDrop[[1]])

+AByCDSWavg<- t(sapply(1:length(cc$AByClust),function(z) apply(cc$AByClust[[z]],1,function(x) weighted.mean(x,(cc$RtoMeanPattern[[z]])^3))))

+rownames(AByCDSWavg) <- lapply(1:length(cc$AByClust),function(x) paste("Pattern",x))

+

+#scale As

+Amax <- apply(AByCDSWavg,1,max)

+AByCDSWavgScaled <- t(sapply(1:dim(AByCDSWavg)[1],function(x) AByCDSWavg[x,]/Amax[x]))

+rownames(AByCDSWavgScaled) <- rownames(AByCDSWavg)

+

+  if(bySet){  

+    return(list("consenusAs"=t(AByCDSWavgScaled),"ABySet"=cc))

+  } else {return(AByCDSWavgScaled)}

+

+}

@@ -14,7 +14,7 @@

 #' data(SimpSim)

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

 #' @export

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

+createscCoGAPSSets <- function(D, nSets, simulationName,samplingRatio=NULL,path="",annotionObj=NULL)

 {

     # check gene names

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

@@ -16,8 +16,8 @@

 patternMatch4Parallel <- function(Ptot, nSets, cnt, minNS=NULL, maxNS=NULL, 

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

-    if (!is.null(minNS)){minNS=nSets/2}

-    if (!is.null(maxNS)){maxNS=nSets+minNS}

+    if (is.null(minNS)){minNS=ceiling(nSets/2)}

+    if (is.null(maxNS)){maxNS=nSets+minNS}

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

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

@@ -53,6 +53,8 @@ patternMatch4Parallel <- function(Ptot, nSets, cnt, minNS=NULL, maxNS=NULL,

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

         }

     }

+    PByClust[sapply(PByClust,is.null)]<-NULL

+    RtoMeanPattern[sapply(RtoMeanPattern,is.null)]<-NULL

     return(list("RtoMeanPattern"=RtoMeanPattern,"PByClust"=PByClust))

     }    

@@ -64,14 +66,11 @@ patternMatch4Parallel <- function(Ptot, nSets, cnt, minNS=NULL, maxNS=NULL,

             icc<-corcut(cc$PByClust[[indx[1]]],minNS,2,cluster.method)

             cc$PByClust[[indx[1]]]<-icc[[2]][[1]]

             cc$RtoMeanPattern[[indx[1]]]<-icc[[1]][[1]]

-            if(is.null(icc[[2]][[2]])){ 

-                indx<-which(unlist(lapply(cc$PByClust,function(x) dim(x)[1]>maxNS)))

-                next

-            } else {

+            if(length(icc[[2]])>1){

                 cc$PByClust<-append(cc$PByClust,icc[[2]][2])

-                cc$RtoMeanPattern<-append(cc$PByClust,icc[[1]][[2]])

-                indx<-which(unlist(lapply(cc$PByClust,function(x) dim(x)[1]>maxNS)))

-            }

+                cc$RtoMeanPattern<-append(cc$RtoMeanPattern,icc[[1]][2])

+            } 

+            indx<-which(unlist(lapply(cc$PByClust,function(x) dim(x)[1]>maxNS)))

     }

     #weighted.mean

new file mode 100644

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

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/cellMatchR.R

+\name{cellMatchR}

+\alias{cellMatchR}

+\title{patternMatch4Parallel}

+\usage{

+cellMatchR(Atot, nSets, cnt, minNS = NULL, maxNS = NULL,

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

+}

+\arguments{

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

+

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

+

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

+

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

+

+\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{Atot}}

+

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

+

+\item{R2mean}{}

+}

+\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{

+patternMatch4Parallel

+}

+\seealso{

+\code{\link{fastcluster}}

+}

@@ -4,14 +4,15 @@

 \alias{createGWCoGAPSSets}

 \title{createGWCoGAPSSets}

 \usage{

-createGWCoGAPSSets(data = D, nSets = nSets,

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

+createGWCoGAPSSets(D, S, nSets, simulationName, path = "")

 }

 \arguments{

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

-

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

+\item{path}{character string indicating were to save resulting data objects}

+

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

+

 \item{outRDA}{name of output file}

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

@@ -4,19 +4,22 @@

 \alias{createscCoGAPSSets}

 \title{Create Gene Sets for scCoGAPS}

 \usage{

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

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

+  path = "")

 }

 \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{path}{character string indicating were to save resulting data objects. default is current working dir}

+

+\item{S}{uncertainty matrix}

+

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

 }

 \value{

@@ -4,8 +4,8 @@

 \alias{patternMatch4Parallel}

 \title{patternMatch4Parallel}

 \usage{

-patternMatch4Parallel(Ptot, nSets, cnt, minNS, cluster.method = "complete",

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

+patternMatch4Parallel(Ptot, nSets, cnt, minNS = NULL, maxNS = NULL,

+  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}}

@@ -16,6 +16,8 @@ patternMatch4Parallel(Ptot, nSets, cnt, minNS, cluster.method = "complete",

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

+\item{maxNS}{max of individual set contributions a cluster must contain. default is nSets+minNS}

+

 \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.}

@@ -4,13 +4,13 @@

 \alias{patternMatch4singleCell}

 \title{patternMatch4singleCell}

 \usage{

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

+patternMatch4singleCell(Atot, 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{Atot}{a matrix containing the total by set estimates of Amean output from \code{reOrderBySet}}

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

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

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

@@ -20,7 +20,7 @@ patternMatch4singleCell(Ptot, nSets, cnt, minNS, cluster.method = "complete",

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

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

 }

new file mode 100644

@@ -0,0 +1,21 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/postFixed4SC.R

+\name{postFixed4SC}

+\alias{postFixed4SC}

+\title{Post Processing of Parallel Output}

+\usage{

+postFixed4SC(AP.fixed, setAs)

+}

+\arguments{

+\item{AP.fixed}{output of parallel gapsMapRun calls with same FP}

+

+\item{setPs}{data.frame with rows giving fixed patterns for P used as input

+for gapsMapRun}

+}

+\value{

+list of two data.frames containing the A matrix estimates or their

+corresponding standard deviations from output of parallel CoGAPS

+}

+\description{

+Post Processing of Parallel Output

+}