@@ -26,6 +26,7 @@

 ^src/file_parser/TsvParser.o

 ^src/file_parser/MtxParser.o

 ^src/math/Algorithms.o

+^src/math/Math.o

 ^src/math/Random.o

 ^src/cpp_tests/testAlgorithms.o

 ^src/cpp_tests/testAtomicDomain.o

@@ -22,10 +22,12 @@ Imports:

     methods,

     gplots,

     graphics,

+    RColorBrewer,

     Rcpp,

     S4Vectors,

     SingleCellExperiment,

-    SummarizedExperiment

+    SummarizedExperiment,

+    utils

 Suggests:

     testthat,

     knitr,

@@ -25,6 +25,7 @@ importClassesFrom(S4Vectors,character_OR_NULL)

 importClassesFrom(SingleCellExperiment,LinearEmbeddingMatrix)

 importFrom(BiocParallel,MulticoreParam)

 importFrom(BiocParallel,bplapply)

+importFrom(RColorBrewer,brewer.pal)

 importFrom(Rcpp,evalCpp)

 importFrom(SummarizedExperiment,assay)

 importFrom(cluster,agnes)

@@ -53,4 +54,5 @@ importFrom(stats,hclust)

 importFrom(stats,runif)

 importFrom(stats,weighted.mean)

 importFrom(tools,file_ext)

+importFrom(utils,packageVersion)

 useDynLib(CoGAPS)

@@ -36,27 +36,29 @@ supported <- function(file)

 #' @param transposeData T/F for transposing data while reading it in - useful

 #' for data that is stored as samples x genes since CoGAPS requires data to be

 #' genes x samples

+#' @param BPPARAM BiocParallel backend 

 #' @param ... allows for overwriting parameters in params

 #' @return CogapsResult object

 #' @examples

 #' # Running from R object

 #' data(GIST)

-#' resultA <- CoGAPS(GIST.D)

+#' resultA <- CoGAPS(GIST.data_frame)

 #'

 #' # Running from file name

 #' gist_path <- system.file("extdata/GIST.mtx", package="CoGAPS")

 #' resultB <- CoGAPS(gist_path)

 #'

-#' Setting Parameters

+#' # Setting Parameters

 #' params <- new("CogapsParams")

 #' params <- setParam(params, "nPatterns", 5)

-#' resultC <- CoGAPS(GIST.D, params)

+#' resultC <- CoGAPS(GIST.data_frame, params)

 #' @importFrom methods new is

 #' @importFrom SummarizedExperiment assay

+#' @importFrom utils packageVersion

 CoGAPS <- function(data, params=new("CogapsParams"), nThreads=1,

 messages=TRUE, outputFrequency=500, uncertainty=NULL,

 checkpointOutFile="gaps_checkpoint.out", checkpointInterval=1000,

-checkpointInFile=NULL, transposeData=FALSE, ...)

+checkpointInFile=NULL, transposeData=FALSE, BPPARAM=NULL, ...)

 {

     # store all parameters in a list and parse parameters from ...

     allParams <- list("gaps"=params,

@@ -67,10 +69,14 @@ checkpointInFile=NULL, transposeData=FALSE, ...)

         "checkpointInterval"=checkpointInterval,

         "checkpointInFile"=checkpointInFile,

         "transposeData"=transposeData,

+        "bpBackend"=BPPARAM,

         "whichMatrixFixed"=NULL # internal parameter

     )

     allParams <- parseExtraParams(allParams, list(...))

+    # display start up message for the user

+    startupMessage(data, allParams$transposeData, allParams$gaps@distributed)

+

     # check file extension

     if (is(data, "character") & !supported(data))

         stop("unsupported file extension for data")

@@ -90,6 +96,9 @@ checkpointInFile=NULL, transposeData=FALSE, ...)

         if (allParams$gaps@distributed == "single-cell" & !allParams$gaps@singleCell)

             warning("running single-cell CoGAPS with singleCell=FALSE")

+    if (!is.null(allParams$gaps@distributed) & allParams$nThreads > 1)

+        stop("can't run multi-threaded and distributed CoGAPS at the same time")

+

     # convert data to matrix

     if (is(data, "data.frame"))

         data <- data.matrix(data)

@@ -126,7 +135,10 @@ checkpointInFile=NULL, transposeData=FALSE, ...)

         Psd         = gapsReturnList$Psd,

         seed        = gapsReturnList$seed,

         meanChiSq   = gapsReturnList$meanChiSq,

-        diagnostics = list("diag"=gapsReturnList$diagnostics, "params"=params)

+        geneNames   = getGeneNames(data, allParams),

+        sampleNames = getSampleNames(data, allParams),

+        diagnostics = list("diag"=gapsReturnList$diagnostics, "params"=params,

+                            "version"=utils::packageVersion("CoGAPS"))

     ))

 }

@@ -140,13 +152,13 @@ checkpointInFile=NULL, transposeData=FALSE, ...)

 scCoGAPS <- function(data, params=new("CogapsParams"), nThreads=1,

 messages=TRUE, outputFrequency=500, uncertainty=NULL,

 checkpointOutFile="gaps_checkpoint.out", checkpointInterval=1000,

-checkpointInFile=NULL, transposeData=FALSE, ...)

+checkpointInFile=NULL, transposeData=FALSE, BPPARAM=NULL, ...)

 {

     params@distributed <- "single-cell"

     params@singleCell <- TRUE

     CoGAPS(data, params, nThreads, messages, outputFrequency, uncertainty,

         checkpointOutFile, checkpointInterval, checkpointInFile, transposeData,

-        ...)

+        BPPARAM, ...)

 }

 #' Genome Wide CoGAPS

@@ -159,14 +171,58 @@ checkpointInFile=NULL, transposeData=FALSE, ...)

 GWCoGAPS <- function(data, params=new("CogapsParams"), nThreads=1,

 messages=TRUE, outputFrequency=500, uncertainty=NULL,

 checkpointOutFile="gaps_checkpoint.out", checkpointInterval=1000,

-checkpointInFile=NULL, transposeData=FALSE, ...)

+checkpointInFile=NULL, transposeData=FALSE, BPPARAM=NULL, ...)

 {

     params@distributed <- "genome-wide"

     CoGAPS(data, params, nThreads, messages, outputFrequency, uncertainty,

         checkpointOutFile, checkpointInterval, checkpointInFile, transposeData,

-        ...)

+        BPPARAM, ...)

 }   

+#' write start up message

+#'

+#' @param data data set

+#' @param transpose if we are transposing the data set

+#' @param distributed if we are running distributed CoGAPS

+#' @return message displayed to screen

+startupMessage <- function(data, transpose, distributed)

+{

+    nGenes <- ifelse(transpose, ncol_helper(data), nrow_helper(data))

+    nSamples <- ifelse(transpose, nrow_helper(data), ncol_helper(data))

+

+    dist_message <- "Standard"

+    if (!is.null(distributed))

+        dist_message <- distributed

+    message(paste("Running", dist_message, "CoGAPS on", nGenes, "genes and",

+        nSamples, "samples"))

+}

+

+#' find the gene names in the data

+#'

+#' @param data data set

+#' @param allParams list of all cogaps parameters

+#' @return vector of gene names

+getGeneNames <- function(data, allParams)

+{

+    if (is(data, "matrix") & !allParams$transposeData)

+        return(rownames(data))

+    if (is(data, "matrix") & allParams$transposeData)

+        return(colnames(data))

+}

+

+#' find the sample names in the data

+#'

+#' @param data data set

+#' @param allParams list of all cogaps parameters

+#' @return vector of sample names

+getSampleNames <- function(data, allParams)

+{

+    if (is(data, "matrix") & !allParams$transposeData)

+        return(colnames(data))

+    if (is(data, "matrix") & allParams$transposeData)

+        return(rownames(data))

+}

+

 #' parse parameters passed through the ... variable

 #'

 #' @param allParams list of all parameters

@@ -8,27 +8,32 @@

 #' @param uncertainty uncertainty matrix (same supported types as data)

 #' @return list

 #' @importFrom BiocParallel bplapply MulticoreParam

-distributedCogaps <- function(data, allParams, uncertainty, BPPARAM=NULL)

+distributedCogaps <- function(data, allParams, uncertainty)

 {

-    FUN <- function(set, data, allParams, uncertainty, fixedMatrix=NULL)

+    FUN <- function(index, sets, data, allParams, uncertainty, fixedMatrix=NULL)

     {

         internal <- ifelse(is(data, "character"), cogaps_cpp_from_file, cogaps_cpp)

-        raw <- internal(data, allParams, uncertainty, set, fixedMatrix)

+        raw <- internal(data, allParams, uncertainty, sets[[index]],

+            fixedMatrix, index == 1)

         new("CogapsResult", Amean=raw$Amean, Asd=raw$Asd, Pmean=raw$Pmean,

-            Psd=raw$Psd, seed=raw$seed, meanChiSq=raw$meanChiSq)    

+            Psd=raw$Psd, seed=raw$seed, meanChiSq=raw$meanChiSq)

     }

     # randomly sample either rows or columns into subsets to break the data up

     set.seed(allParams$gaps@seed)

     sets <- createSets(data, allParams)

-    if (is.null(BPPARAM))

-        BPPARAM <- BiocParallel::MulticoreParam(workers=length(sets))

+    if (is.null(allParams$bpBackend))

+        allParams$bpBackend <- BiocParallel::MulticoreParam(workers=length(sets))

     # run Cogaps normally on each subset of the data

-    initialResult <- bplapply(sets, FUN, BPPARAM=BPPARAM, data=data,

-        allParams=allParams, uncertainty=uncertainty)

+    if (allParams$messages)

+        message("Running Across Subsets...")

+    initialResult <- bplapply(1:length(sets), FUN, BPPARAM=allParams$bpBackend,

+        sets=sets, data=data, allParams=allParams, uncertainty=uncertainty)

     # match patterns in either A or P matrix

+    if (allParams$messages)

+        message("Matching Patterns Across Subsets...")

     consensusMatrix <- findConsensusMatrix(initialResult, allParams)

     allParams$gaps@nPatterns <- ncol(consensusMatrix)

@@ -36,9 +41,12 @@ distributedCogaps <- function(data, allParams, uncertainty, BPPARAM=NULL)

     allParams$whichMatrixFixed <- ifelse(allParams$gaps@distributed

         == "genome-wide", "P", "A")

-    # ru final phase with fixed matrix

-    finalResult <- bplapply(sets, FUN, BPPARAM=BPPARAM, data=data, 

-        allParams=allParams, uncertainty=uncertainty, fixedMatrix=consensusMatrix)

+    # run final phase with fixed matrix

+    if (allParams$messages)

+        message("Running Final Stage...")

+    finalResult <- bplapply(1:length(sets), FUN, BPPARAM=allParams$bpBackend,

+        sets=sets, data=data, allParams=allParams, uncertainty=uncertainty,

+        fixedMatrix=consensusMatrix)

     # get result 

     return(stitchTogether(finalResult, allParams))

@@ -121,16 +129,9 @@ findConsensusMatrix <- function(result, allParams)

 }

 #' Match Patterns Across Multiple Runs

-#' @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 maxNS maximum 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 ... additional parameters for \code{agnes}

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

-#' consensus pattern is also returned.

+#' @param allPatterns matrix of patterns stored in the columns

+#' @param allParams list of all CoGAPS parameters

+#' @return a matrix of consensus patterns

 #' @importFrom stats weighted.mean

 patternMatch <- function(allPatterns, allParams)

 {

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

 # Generated by using Rcpp::compileAttributes() -> do not edit by hand

 # Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393

-cogaps_cpp_from_file <- function(data, allParams, uncertainty = NULL, indices = NULL, fixedMatrix = NULL) {

-    .Call('_CoGAPS_cogaps_cpp_from_file', PACKAGE = 'CoGAPS', data, allParams, uncertainty, indices, fixedMatrix)

+cogaps_cpp_from_file <- function(data, allParams, uncertainty = NULL, indices = NULL, fixedMatrix = NULL, isMaster = TRUE) {

+    .Call('_CoGAPS_cogaps_cpp_from_file', PACKAGE = 'CoGAPS', data, allParams, uncertainty, indices, fixedMatrix, isMaster)

 }

-cogaps_cpp <- function(data, allParams, uncertainty = NULL, indices = NULL, fixedMatrix = NULL) {

-    .Call('_CoGAPS_cogaps_cpp', PACKAGE = 'CoGAPS', data, allParams, uncertainty, indices, fixedMatrix)

+cogaps_cpp <- function(data, allParams, uncertainty = NULL, indices = NULL, fixedMatrix = NULL, isMaster = TRUE) {

+    .Call('_CoGAPS_cogaps_cpp', PACKAGE = 'CoGAPS', data, allParams, uncertainty, indices, fixedMatrix, isMaster)

 }

 getBuildReport_cpp <- function() {

@@ -38,6 +38,9 @@ setClass("CogapsParams", slots = c(

 ))

 #' constructor for CogapsParams

+#' @param .Object CogapsParams object

+#' @param ... initial values for slots

+#' @return initialized CogapsParams object

 #' @importFrom methods callNextMethod

 setMethod("initialize", "CogapsParams",

     function(.Object, ...)

@@ -114,7 +117,7 @@ setGeneric("setParam", function(object, whichParam, value)

 #' @return the modified params object

 #' @examples

 #'  params <- new("CogapsParams")

-#'  params <- setDistributedParams(3, 2, 4)

+#'  params <- setDistributedParams(params, 5)

 setGeneric("setDistributedParams", function(object, nSets, cut=NULL,

 minNS=NULL, maxNS=NULL)

     {standardGeneric("setDistributedParams")})

@@ -1,6 +1,8 @@

 #' CogapsResult

 #' @export

 #'

+#' @slot sampleStdDev std dev of the sampled P matrices

+#' @slot featureStdDev std dev of the sampled A matrices

 #' @description Contains all output from Cogaps run

 #' @importClassesFrom S4Vectors Annotated

 #' @importClassesFrom SingleCellExperiment LinearEmbeddingMatrix

@@ -10,20 +12,30 @@ setClass("CogapsResult", contains="LinearEmbeddingMatrix", slots=c(

 ))

 #' Constructor for CogapsResult

+#' @param .Object CogapsResult object

+#' @param Amean mean of sampled A matrices

+#' @param Pmean mean of sampled P matrices

+#' @param Asd std dev of sampled A matrices

+#' @param Psd std dev of sampled P matrices

+#' @param seed random seed used for the run

+#' @param meanChiSq mean value of ChiSq statistic

+#' @param geneNames names of genes in original data set

+#' @param sampleNames names of samples in original data set

+#' @param diagnostics assorted diagnostic reports from the run

+#' @param ... initial values for slots

 #' @return initialized CogapsResult object

 #' @importFrom methods callNextMethod

 setMethod("initialize", "CogapsResult",

-function(.Object, Amean, Pmean, Asd, Psd, seed, meanChiSq, diagnostics=list(),

-...)

+function(.Object, Amean, Pmean, Asd, Psd, seed, meanChiSq, geneNames=NULL,

+sampleNames=NULL, diagnostics=NULL, ...)

 {

     .Object@featureLoadings <- Amean

     .Object@sampleFactors <- Pmean

+    .Object@featureStdDev <- Asd

+    .Object@sampleStdDev <- Psd

-    if (!is.null(Asd))

-        .Object@featureStdDev <- Asd

-    if (!is.null(Psd))

-        .Object@sampleStdDev <- Psd

-

+    .Object@metadata[["geneNames"]] <- geneNames

+    .Object@metadata[["sampleNames"]] <- sampleNames

     .Object@metadata[["seed"]] <- seed

     .Object@metadata[["meanChiSq"]] <- meanChiSq

     .Object@metadata[["diagnostics"]] <- diagnostics

@@ -52,7 +64,7 @@ setValidity("CogapsResult",

 #' @param object an object of type CogapsResult

 #' @return chi-sq error

 #' data(SimpSim)

-#' result <- CoGAPS(SimpSim.D)

+#' result <- CoGAPS(SimpSim.data)

 #' meanChiSq(result)

 setGeneric("getMeanChiSq", function(object)

     {standardGeneric("getMeanChiSq")})

@@ -70,7 +82,7 @@ setGeneric("getMeanChiSq", function(object)

 #' @return matrix of z-scores

 #' @examples

 #' data(SimpSim)

-#' result <- CoGAPS(SimpSim.D)

+#' result <- CoGAPS(SimpSim.data)

 #' feature_zscore <- calcZ(result)

 setGeneric("calcZ", function(object, which="feature")

     {standardGeneric("calcZ")})

@@ -85,7 +97,7 @@ setGeneric("calcZ", function(object, which="feature")

 #' @return the D' estimate of a gene or set of genes

 #' @examples

 #' data(SimpSim)

-#' result <- CoGAPS(SimpSim.D)

+#' result <- CoGAPS(SimpSim.data)

 #' D_estimate <- reconstructGene(result)

 setGeneric("reconstructGene", function(object, genes=NULL)

     {standardGeneric("reconstructGene")})

@@ -104,7 +116,7 @@ setGeneric("reconstructGene", function(object, genes=NULL)

 #' @return plots a heatmap of the A Matrix

 #' @examples

 #' data(SimpSim)

-#' result <- CoGAPS(SimpSim.D)

+#' result <- CoGAPS(SimpSim.data)

 #' binMatrix <- binaryA(result, threshold=3)

 setGeneric("binaryA", function(object, threshold=3)

     {standardGeneric("binaryA")})

@@ -121,8 +133,8 @@ setGeneric("binaryA", function(object, threshold=3)

 #' @return creates a residual plot

 #' @examples

 #' data(SimpSim)

-#' result <- CoGAPS(SimpSim.D)

-#' plotResiduals(result, SimpSim.D)

+#' result <- CoGAPS(SimpSim.data)

+#' plotResiduals(result, SimpSim.data)

 setGeneric("plotResiduals", function(object, data, uncertainty=NULL)

     {standardGeneric("plotResiduals")})

@@ -138,10 +150,6 @@ setGeneric("plotResiduals", function(object, data, uncertainty=NULL)

 #' @param GStoGenes data.frame or list with gene sets

 #' @param numPerm number of permutations for null

 #' @return gene set statistics for each column of A

-#' @examples

-#' data('SimpSim')

-#' result <- CoGAPS(SimpSim.D)

-#' calcCoGAPSStat(result, GStoGenes=GSets, numPerm=500)

 setGeneric("calcCoGAPSStat", function(object, GStoGenes, numPerm=500)

     {standardGeneric("calcCoGAPSStat")})

@@ -159,10 +167,6 @@ setGeneric("calcCoGAPSStat", function(object, GStoGenes, numPerm=500)

 #' @param Pw weight on genes

 #' @param nullGenes logical indicating gene adjustment

 #' @return gene similiarity statistic

-#' @examples

-#' data(SimpSim)

-#' result <- CoGAPS(SimpSim.D)

-#' calcGeneGSStat(result, GSGenes=GSets[[1]], numPerm=500)

 setGeneric("calcGeneGSStat", function(object, GStoGenes, numPerm,

 Pw=rep(1,ncol(object@featureLoadings)), nullGenes=FALSE)

     {standardGeneric("calcGeneGSStat")})

@@ -184,10 +188,6 @@ Pw=rep(1,ncol(object@featureLoadings)), nullGenes=FALSE)

 #' @param PwNull - logical indicating gene adjustment

 #' @return A vector of length GSGenes containing the p-values of set membership

 #' for each gene containined in the set specified in GSGenes.

-#' @examples

-#' data(SimpSim)

-#' result <- CoGAPS(SimpSim.D)

-#' computeGeneGSProb(result, GSGenes=GSets[[1]], numPerm=500)

 setGeneric("computeGeneGSProb", function(object, GStoGenes, numPerm=500,

 Pw=rep(1,ncol(object@featureLoadings)), PwNull=FALSE)

     {standardGeneric("computeGeneGSProb")})

@@ -207,6 +207,6 @@ Pw=rep(1,ncol(object@featureLoadings)), PwNull=FALSE)

 #' @return By default a non-overlapping list of genes associated with each

 #' \code{lp}. If \code{full=TRUE} a data.frame of genes rankings with a column

 #' for each \code{lp} will also be returned.

-setGeneric("patternMarkers", function(object, threshold="all", lp=NA, full=FALSE)

+setGeneric("patternMarkers", function(object, threshold="all", lp=NA)

     {standardGeneric("patternMarkers")})

@@ -21,7 +21,8 @@ plot.CogapsResult <- function(x, ...)

     xlimits <- c(0, nSamples + 1)

     ylimits <- c(0, max(x@sampleFactors) * 1.1)

-    plot(NULL, xlim=xlimits, ylim=ylimits, ylab="Relative Amplitude")

+    plot(NULL, xlim=xlimits, ylim=ylimits, ylab="Relative Amplitude",

+        xlab="Samples")

     for (i in 1:nFactors)

     {

@@ -77,6 +78,7 @@ function(object, genes)

 #' @aliases binaryA

 #' @importFrom gplots heatmap.2

 #' @importFrom graphics mtext

+#' @importFrom RColorBrewer brewer.pal

 setMethod("binaryA", signature(object="CogapsResult"),

 function(object, threshold)

 {

@@ -95,6 +97,7 @@ function(object, threshold)

 #' @aliases plotResiduals

 #' @importFrom gplots heatmap.2

 #' @importFrom grDevices colorRampPalette

+#' @importFrom RColorBrewer brewer.pal

 setMethod("plotResiduals", signature(object="CogapsResult"),

 function(object, data, uncertainty)

 {

@@ -142,9 +145,9 @@ function(object, threshold, lp)

         ssranks <- matrix(NA, nrow=nGenes, ncol=nPatterns,

             dimnames=dimnames(object@featureLoadings))

         ssgenes <- matrix(NA, nrow=nGenes, ncol=nPatterns, dimnames=NULL)

-        for (i in 1:nP)

+        for (i in 1:nPatterns)

         {

-            lp <- rep(0,dim(Amatrix)[2])

+            lp <- rep(0,nPatterns)

             lp[i] <- 1

             sstat[,i] <- unlist(apply(Arowmax, 1, function(x) sqrt(t(x-lp)%*%(x-lp))))

             ssranks[,i]<-rank(sstat[,i])

@@ -152,8 +155,8 @@ function(object, threshold, lp)

         }

         if (threshold=="cut")

         {

-            geneThresh <- sapply(1:nP,function(x) min(which(ssranks[ssgenes[,x],x] > apply(ssranks[ssgenes[,x],],1,min))))

-            ssgenes.th <- sapply(1:nP,function(x) ssgenes[1:geneThresh[x],x])

+            geneThresh <- sapply(1:nPatterns,function(x) min(which(ssranks[ssgenes[,x],x] > apply(ssranks[ssgenes[,x],],1,min))))

+            ssgenes.th <- sapply(1:nPatterns,function(x) ssgenes[1:geneThresh[x],x])

         }

         else if (threshold=="all")

         {

@@ -451,7 +451,7 @@ configure:6353: gcc -o conftest -UNDEBUG -Wall -pedantic -g -O0   conftest.c  >&

 configure:6353: $? = 0

 configure:6353: ./conftest

 configure:6353: $? = 0

-configure:6363: result: 806ea:7100800:7ffafbff:bfebfbff

+configure:6363: result: 806ea:6100800:7ffafbff:bfebfbff

 configure:6390: checking for x86 cpuid 0x00000007 output

 configure:6420: gcc -o conftest -UNDEBUG -Wall -pedantic -g -O0   conftest.c  >&5

 configure:6420: $? = 0

@@ -757,7 +757,7 @@ ax_cv_cxx_openmp=-fopenmp

 ax_cv_gcc_x86_avx_xgetbv_0x00000000=1f:0

 ax_cv_gcc_x86_avx_xgetbv_=unknown

 ax_cv_gcc_x86_cpuid_0x00000000=16:756e6547:6c65746e:49656e69

-ax_cv_gcc_x86_cpuid_0x00000001=806ea:7100800:7ffafbff:bfebfbff

+ax_cv_gcc_x86_cpuid_0x00000001=806ea:6100800:7ffafbff:bfebfbff

 ax_cv_gcc_x86_cpuid_0x00000007=0:29c6fbf:0:0

 ax_cv_gcc_x86_cpuid_0x80000000=80000008:0:0:0

 ax_cv_gcc_x86_cpuid_0x80000001=0:0:121:2c100800

@@ -7,7 +7,8 @@

 CoGAPS(data, params = new("CogapsParams"), nThreads = 1,

   messages = TRUE, outputFrequency = 500, uncertainty = NULL,

   checkpointOutFile = "gaps_checkpoint.out", checkpointInterval = 1000,

-  checkpointInFile = NULL, transposeData = FALSE, ...)

+  checkpointInFile = NULL, transposeData = FALSE, BPPARAM = NULL,

+  ...)

 }

 \arguments{

 \item{data}{File name or R object (see details for supported types)}

@@ -36,6 +37,8 @@ contained in this file}

 for data that is stored as samples x genes since CoGAPS requires data to be

 genes x samples}

+\item{BPPARAM}{BiocParallel backend}

+

 \item{...}{allows for overwriting parameters in params}

 }

 \value{

@@ -53,14 +56,14 @@ SingleCellExperiment. The supported file types are csv, tsv, and mtx.

 \examples{

 # Running from R object

 data(GIST)

-resultA <- CoGAPS(GIST.D)

+resultA <- CoGAPS(GIST.data_frame)

 # Running from file name

 gist_path <- system.file("extdata/GIST.mtx", package="CoGAPS")

 resultB <- CoGAPS(gist_path)

-Setting Parameters

+# Setting Parameters

 params <- new("CogapsParams")

 params <- setParam(params, "nPatterns", 5)

-resultC <- CoGAPS(GIST.D, params)

+resultC <- CoGAPS(GIST.data_frame, params)

 }

@@ -7,3 +7,11 @@

 \description{

 Contains all output from Cogaps run

 }

+\section{Slots}{

+

+\describe{

+\item{\code{sampleStdDev}}{std dev of the sampled P matrices}

+

+\item{\code{featureStdDev}}{std dev of the sampled A matrices}

+}}

+

@@ -4,10 +4,11 @@

 \alias{GWCoGAPS}

 \title{Genome Wide CoGAPS}

 \usage{

-GWCoGAPS(data, params = new("CogapsParams"), nThreads = NULL,

+GWCoGAPS(data, params = new("CogapsParams"), nThreads = 1,

   messages = TRUE, outputFrequency = 500, uncertainty = NULL,

   checkpointOutFile = "gaps_checkpoint.out", checkpointInterval = 1000,

-  checkpointInFile = NULL, transposeData = FALSE, ...)

+  checkpointInFile = NULL, transposeData = FALSE, BPPARAM = NULL,

+  ...)

 }

 \arguments{

 \item{data}{File name or R object (see details for supported types)}

@@ -36,6 +37,8 @@ contained in this file}

 for data that is stored as samples x genes since CoGAPS requires data to be

 genes x samples}

+\item{BPPARAM}{BiocParallel backend}

+

 \item{...}{allows for overwriting parameters in params}

 }

 \value{

@@ -26,6 +26,6 @@ threshold * Asd and 0 otherwise

 }

 \examples{

 data(SimpSim)

-result <- CoGAPS(SimpSim.D)

+result <- CoGAPS(SimpSim.data)

 binMatrix <- binaryA(result, threshold=3)

 }

@@ -25,8 +25,3 @@ calculates the gene set statistics for each

 column of A using a Z-score from the elements of the A matrix,

 the input gene set, and permutation tests

 }

-\examples{

-data('SimpSim')

-result <- CoGAPS(SimpSim.D)

-calcCoGAPSStat(result, GStoGenes=GSets, numPerm=500)

-}

@@ -31,8 +31,3 @@ calculates the probability that a gene

 listed in a gene set behaves like other genes in the set within

 the given data set

 }

-\examples{

-data(SimpSim)

-result <- CoGAPS(SimpSim.D)

-calcGeneGSStat(result, GSGenes=GSets[[1]], numPerm=500)

-}

@@ -25,6 +25,6 @@ and standard deviation matrices

 }

 \examples{

 data(SimpSim)

-result <- CoGAPS(SimpSim.D)

+result <- CoGAPS(SimpSim.data)

 feature_zscore <- calcZ(result)

 }

@@ -35,8 +35,3 @@ membership for each candidate gene in a set specified in \code{GSGenes} by

 comparing the inferred activity of that gene to the average activity of the

 set.

 }

-\examples{

-data(SimpSim)

-result <- CoGAPS(SimpSim.D)

-computeGeneGSProb(result, GSGenes=GSets[[1]], numPerm=500)

-}

@@ -4,7 +4,7 @@

 \alias{distributedCogaps}

 \title{CoGAPS Distributed Matrix Factorization Algorithm}

 \usage{

-distributedCogaps(data, allParams, uncertainty, BPPARAM = NULL)

+distributedCogaps(data, allParams, uncertainty)

 }

 \arguments{

 \item{data}{File name or R object (see details for supported types)}

new file mode 100644

@@ -0,0 +1,19 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/CoGAPS.R

+\name{getGeneNames}

+\alias{getGeneNames}

+\title{find the gene names in the data}

+\usage{

+getGeneNames(data, allParams)

+}

+\arguments{

+\item{data}{data set}

+

+\item{allParams}{list of all cogaps parameters}

+}

+\value{

+vector of gene names

+}

+\description{

+find the gene names in the data

+}

@@ -16,7 +16,7 @@ getMeanChiSq(object)

 \value{

 chi-sq error

 data(SimpSim)

-result <- CoGAPS(SimpSim.D)

+result <- CoGAPS(SimpSim.data)

 meanChiSq(result)

 }

 \description{

new file mode 100644

@@ -0,0 +1,19 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/CoGAPS.R

+\name{getSampleNames}

+\alias{getSampleNames}

+\title{find the sample names in the data}

+\usage{

+getSampleNames(data, allParams)

+}

+\arguments{

+\item{data}{data set}

+

+\item{allParams}{list of all cogaps parameters}

+}

+\value{

+vector of sample names

+}

+\description{

+find the sample names in the data

+}

@@ -7,6 +7,14 @@

 \usage{

 \S4method{initialize}{CogapsParams}(.Object, ...)

 }

+\arguments{

+\item{.Object}{CogapsParams object}

+

+\item{...}{initial values for slots}

+}

+\value{

+initialized CogapsParams object

+}

 \description{

 constructor for CogapsParams

 }

@@ -6,7 +6,31 @@

 \title{Constructor for CogapsResult}

 \usage{

 \S4method{initialize}{CogapsResult}(.Object, Amean, Pmean, Asd, Psd, seed,

-  meanChiSq, diagnostics = list(), ...)

+  meanChiSq, geneNames = NULL, sampleNames = NULL,

+  diagnostics = NULL, ...)

+}

+\arguments{

+\item{.Object}{CogapsResult object}

+

+\item{Amean}{mean of sampled A matrices}

+

+\item{Pmean}{mean of sampled P matrices}

+

+\item{Asd}{std dev of sampled A matrices}

+

+\item{Psd}{std dev of sampled P matrices}

+

+\item{seed}{random seed used for the run}

+

+\item{meanChiSq}{mean value of ChiSq statistic}

+

+\item{geneNames}{names of genes in original data set}

+

+\item{sampleNames}{names of samples in original data set}

+

+\item{diagnostics}{assorted diagnostic reports from the run}

+

+\item{...}{initial values for slots}

 }

 \value{

 initialized CogapsResult object

@@ -6,9 +6,10 @@

 \alias{patternMarkers,CogapsResult-method}

 \title{compute pattern markers statistic}

 \usage{

-patternMarkers(object, threshold = "all", lp = NA, full = FALSE)

+patternMarkers(object, threshold = "all", lp = NA)

-\S4method{patternMarkers}{CogapsResult}(object, threshold, lp)

+\S4method{patternMarkers}{CogapsResult}(object, threshold = "all",

+  lp = NA)

 }

 \arguments{

 \item{object}{an object of type CogapsResult}

@@ -7,25 +7,12 @@

 patternMatch(allPatterns, allParams)

 }

 \arguments{

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

+\item{allPatterns}{matrix of patterns stored in the columns}

-\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{maxNS}{maximum 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{allParams}{list of all CoGAPS parameters}

 }

 \value{

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

-consensus pattern is also returned.

+a matrix of consensus patterns

 }

 \description{

 Match Patterns Across Multiple Runs

@@ -25,6 +25,6 @@ calculate residuals and produce heatmap

 }

 \examples{

 data(SimpSim)

-result <- CoGAPS(SimpSim.D)

-plotResiduals(result, SimpSim.D)

+result <- CoGAPS(SimpSim.data)

+plotResiduals(result, SimpSim.data)

 }

@@ -23,6 +23,6 @@ reconstruct gene

 }

 \examples{

 data(SimpSim)

-result <- CoGAPS(SimpSim.D)

+result <- CoGAPS(SimpSim.data)

 D_estimate <- reconstructGene(result)

 }

@@ -4,10 +4,11 @@

 \alias{scCoGAPS}

 \title{Single Cell CoGAPS}

 \usage{

-scCoGAPS(data, params = new("CogapsParams"), nThreads = NULL,

+scCoGAPS(data, params = new("CogapsParams"), nThreads = 1,

   messages = TRUE, outputFrequency = 500, uncertainty = NULL,

   checkpointOutFile = "gaps_checkpoint.out", checkpointInterval = 1000,

-  checkpointInFile = NULL, transposeData = FALSE, ...)

+  checkpointInFile = NULL, transposeData = FALSE, BPPARAM = NULL,

+  ...)

 }

 \arguments{

 \item{data}{File name or R object (see details for supported types)}

@@ -36,6 +37,8 @@ contained in this file}

 for data that is stored as samples x genes since CoGAPS requires data to be

 genes x samples}

+\item{BPPARAM}{BiocParallel backend}

+

 \item{...}{allows for overwriting parameters in params}

 }

 \value{

@@ -32,5 +32,5 @@ these parameters  are interrelated so they must be set together

 }

 \examples{

  params <- new("CogapsParams")

- params <- setDistributedParams(3, 2, 4)

+ params <- setDistributedParams(params, 5)

 }

new file mode 100644

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

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/CoGAPS.R

+\name{startupMessage}

+\alias{startupMessage}

+\title{write start up message}

+\usage{

+startupMessage(data, transpose, distributed)

+}

+\arguments{

+\item{data}{data set}

+

+\item{transpose}{if we are transposing the data set}

+

+\item{distributed}{if we are running distributed CoGAPS}

+}

+\value{

+message displayed to screen

+}

+\description{

+write start up message

+}

@@ -76,16 +76,17 @@ std::vector<unsigned> getSubsetIndices(const Rcpp::Nullable<Rcpp::IntegerVector>

     return std::vector<unsigned>(1); // interpreted as null, i.e. will be ignored

 }

-bool processDistributedParameters(const Rcpp::List &allParams)

+// return if running distributed, and if so, are we partitioning rows/cols

+std::pair<bool, bool> processDistributedParameters(const Rcpp::List &allParams)

 {

     const Rcpp::S4 &gapsParams(allParams["gaps"]);

     if (!Rf_isNull(gapsParams.slot("distributed")))

     {

         std::string d = Rcpp::as<std::string>(gapsParams.slot("distributed"));

         GAPS_ASSERT(d == "genome-wide" || d == "single-cell");

-        return d == "genome-wide";