@@ -3,8 +3,7 @@ Version: 2.7.0

 Date: 2014-08-23

 Title: Coordinated Gene Activity in Pattern Sets

 Author: Thomas Sherman, Wai-shing Lee, Conor Kelton, Ondrej Maxian, Jacob Carey,

-    Genevieve Stein-O'Brien, Michael Considine, John Stansfield, Shawn Sivy, Carlo

-    Colantuoni, Alexander Favorov, Mike Ochs, Elana Fertig

+    Genevieve Stein-O'Brien, Michael Considine, Maggie Wodicka, John Stansfield, Shawn Sivy, Carlo Colantuoni, Alexander Favorov, Mike Ochs, Elana Fertig

 Description: Coordinated Gene Activity in Pattern Sets (CoGAPS)

     implements a Bayesian MCMC matrix factorization algorithm,

     GAPS, and links it to gene set statistic methods to infer biological

@@ -24,6 +24,8 @@

 #' @param fixedPatterns matrix of fixed values in either A or P matrix

 #' @param checkpointInterval time (in seconds) between creating a checkpoint

 #' @param checkpointFile name of the checkpoint file

+#' @param pumpThreshold type of threshold for pump statistic

+#' @param nPumpSamples number of samples used in pump statistic

 #' @param ... keeps backwards compatibility with arguments from older versions

 #' @return list with A and P matrix estimates

 #' @importFrom methods new

@@ -36,7 +38,7 @@ nSnapshots=0, alphaA=0.01, alphaP=0.01, maxGibbmassA=100, maxGibbmassP=100,

 seed=-1, messages=TRUE, singleCellRNASeq=FALSE, whichMatrixFixed='N',

 fixedPatterns=matrix(0), checkpointInterval=0, 

 checkpointFile="gaps_checkpoint.out", pumpThreshold="unique",

-nPumpSamples=100, ...)

+nPumpSamples=0, ...)

 {

     # get v2 arguments

     oldArgs <- list(...)

@@ -94,6 +96,7 @@ nPumpSamples=100, ...)

 #' @param D data matrix

 #' @param S uncertainty matrix

 #' @param path path to checkpoint file

+#' @param checkpointFile name for future checkpooints made

 #' @return list with A and P matrix estimates

 #' @export

 CoGapsFromCheckpoint <- function(D, S, path, checkpointFile=NA)

@@ -166,7 +169,7 @@ alphaP=0.01, nMaxP=100000, max_gibbmass_paraP=100.0, seed=-1, messages=TRUE)

 #' @examples

 #' data(SimpSim)

 #' nC <- ncol(SimpSim.D)

-#' patterns <- matrix(runif(nC, 0, 1), nrow=1, ncol=nC)

+#' patterns <- matrix(1:nC/nC, nrow=1, ncol=nC)

 #' result <- gapsMapRun(SimpSim.D, SimpSim.S, FP=patterns, nFactor=3)

 #' @export

 gapsMapRun <- function(D, S, FP, ABins=data.frame(), PBins=data.frame(),

@@ -3,6 +3,7 @@

 #' @details calls the C++ MCMC code and performs Bayesian

 #' matrix factorization returning the two matrices that reconstruct

 #' the data matrix for whole genome data;

+#' @param simulationName name of this simulation

 #' @param nFactor number of patterns (basis vectors, metagenes), which must be

 #' greater than or equal to the number of rows of FP

 #' @param nCores number of cores for parallelization. If left to the default NA, nCores = nSets.

@@ -12,10 +13,10 @@

 #' @return list of A and P estimates

 #' @seealso \code{\link{gapsRun}}, \code{\link{patternMatch4Parallel}}, and \code{\link{gapsMapRun}}

 #' @examples

-#' # Load the sample data from CoGAPS

 #' data(SimpSim)

-#' # Run GWCoGAPS

-#' GWCoGAPS(SimpSim.D, SimpSim.S, nFactor=3, nSets=2)

+#' sim_name <- "example"

+#' createGWCoGAPSSets(SimpSim.D, SimpSim.S, nSets=2, sim_name)

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

 #' @export

 GWCoGAPS <- function(simulationName, nFactor, nCores=NA, cut=NA, minNS=NA, ...)

 {

@@ -31,6 +32,9 @@ GWCoGAPS <- function(simulationName, nFactor, nCores=NA, cut=NA, minNS=NA, ...)

 #' Restart a GWCoGaps Run from Checkpoint

 #'

+#' @inheritParams GWCoGAPS

+#' @return list of A and P estimates

+#' @importFrom utils file_test

 #' @export

 GWCoGapsFromCheckpoint <- function(simulationName, nCores=NA, cut=NA, minNS=NA, ...)

 {

@@ -9,9 +9,7 @@

 #' that an element of Amean must be to get a value of 1

 #' @return plots a heatmap of the A Matrix

 #' @examples

-#' # Load the sample data from CoGAPS

 #' data(SimpSim)

-#' # Run binaryA with the correct arguments from 'results'

 #' binaryA(SimpSim.result$Amean, SimpSim.result$Asd, threshold=3)

 #' @export

 binaryA <-function(Amean, Asd, threshold=3)

@@ -6,9 +6,7 @@

 #' @param sdMat matrix of standard deviation values

 #' @return matrix of z-scores

 #' @examples

-#' # Load the sample data from CoGAPS

 #' data(SimpSim)

-#' # Run calcZ

 #' calcZ(SimpSim.result$Amean, SimpSim.result$Asd)

 #' @export

 calcZ <- function(meanMat, sdMat)

@@ -5,10 +5,10 @@

 #' @param D data matrix

 #' @param S uncertainty matrix

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

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

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

 #' @return simulationName used to identify saved files

 #' @examples

-#' data(SimpSim) # Load the sample data from CoGAPS

+#' data(SimpSim)

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

 #' @export

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

@@ -8,9 +8,7 @@

 #' atom numbers

 #' @return plot

 #' @examples

-#' # Load the sample data from CoGAPS

 #' data(SimpSim)

-#' # Run plotAtoms

 #' plotAtoms(SimpSim.result, type="sampA")

 #' @export

 plotAtoms<-function(gapsRes, type='sampA')

@@ -4,9 +4,7 @@

 #' @param gapsRes list returned by CoGAPS

 #' @return plot

 #' @examples

-#' # Load the sample data from CoGAPS

 #' data(SimpSim)

-#' # Run plotDiag

 #' plotDiag(SimpSim.result)

 #' @export

 plotDiag <-function(gapsRes)

@@ -8,9 +8,7 @@

 #' not specified, output goes to screen

 #' @return plot

 #' @examples

-#' # Load the sample data from CoGAPS

 #' data(SimpSim)

-#' # Run plotGAPS with arguments from CoGAPS results list

 #' plotGAPS(SimpSim.result$Amean, SimpSim.result$Pmean)

 #' @export

 plotGAPS <- function(A, P, outputPDF="")

@@ -5,9 +5,7 @@

 #' @param Psd matrix of standard deviation values of P

 #' @return plot

 #' @examples

-#' # Load the sample data from CoGAPS

 #' data(SimpSim)

-#' # Run plotP with arguments from CoGAPS results list

 #' plotP(SimpSim.result$Pmean, SimpSim.result$Psd)

 #' @export

 plotP <- function(Pmean, Psd)

@@ -5,9 +5,7 @@

 #' @param genes an index of the gene or genes of interest

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

 #' @examples

-#' # Load the sample data from CoGAPS

 #' data(SimpSim)

-#' # Run reconstructGene

 #' reconstructGene(SimpSim.result$Amean, SimpSim.result$Pmean)

 #' @export

 reconstructGene<-function(A, P, genes=NA)

@@ -7,9 +7,7 @@

 #' @param S original standard deviation matrix run through GAPS

 #' @return creates a residual plot

 #' @examples

-#' # Load the sample data from CoGAPS

 #' data(SimpSim)

-#' # Run residuals with the correct arguments

 #' residuals(SimpSim.result$Amean, SimpSim.result$Pmean, SimpSim.D, SimpSim.S)

 #' @export

 residuals <- function(AMean_Mat, PMean_Mat, D, S)

@@ -10,7 +10,7 @@ CoGAPS(D, S, nFactor = 7, nEquil = 1000, nSample = 1000,

   singleCellRNASeq = FALSE, whichMatrixFixed = "N",

   fixedPatterns = matrix(0), checkpointInterval = 0,

   checkpointFile = "gaps_checkpoint.out", pumpThreshold = "unique",

-  nPumpSamples = 100, ...)

+  nPumpSamples = 0, ...)

 }

 \arguments{

 \item{D}{data matrix}

@@ -52,6 +52,10 @@ the fixed patterns}

 \item{checkpointFile}{name of the checkpoint file}

+\item{pumpThreshold}{type of threshold for pump statistic}

+

+\item{nPumpSamples}{number of samples used in pump statistic}

+

 \item{...}{keeps backwards compatibility with arguments from older versions}

 }

 \value{

@@ -12,6 +12,8 @@ CoGapsFromCheckpoint(D, S, path, checkpointFile = NA)

 \item{S}{uncertainty matrix}

 \item{path}{path to checkpoint file}

+

+\item{checkpointFile}{name for future checkpooints made}

 }

 \value{

 list with A and P matrix estimates

@@ -7,6 +7,8 @@

 GWCoGAPS(simulationName, nFactor, nCores = NA, cut = NA, minNS = NA, ...)

 }

 \arguments{

+\item{simulationName}{name of this simulation}

+

 \item{nFactor}{number of patterns (basis vectors, metagenes), which must be

 greater than or equal to the number of rows of FP}

@@ -30,10 +32,10 @@ matrix factorization returning the two matrices that reconstruct

 the data matrix for whole genome data;

 }

 \examples{

-# Load the sample data from CoGAPS

 data(SimpSim)

-# Run GWCoGAPS

-GWCoGAPS(SimpSim.D, SimpSim.S, nFactor=3, nSets=2)

+sim_name <- "example"

+createGWCoGAPSSets(SimpSim.D, SimpSim.S, nSets=2, sim_name)

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

 }

 \seealso{

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

@@ -7,6 +7,20 @@

 GWCoGapsFromCheckpoint(simulationName, nCores = NA, cut = NA, minNS = NA,

   ...)

 }

+\arguments{

+\item{simulationName}{name of this simulation}

+

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

+

+\item{...}{additional parameters to be fed into \code{gapsRun} and \code{gapsMapRun}}

+}

+\value{

+list of A and P estimates

+}

 \description{

 Restart a GWCoGaps Run from Checkpoint

 }

@@ -26,9 +26,7 @@ in which the value is 1 if the value in Amean is greater than

 threshold * Asd and 0 otherwise

 }

 \examples{

-# Load the sample data from CoGAPS

 data(SimpSim)

-# Run binaryA with the correct arguments from 'results'

 binaryA(SimpSim.result$Amean, SimpSim.result$Asd, threshold=3)

 }

@@ -22,9 +22,7 @@ calculates the Z-score for each element based on input mean

 and standard deviation matrices

 }

 \examples{

-# Load the sample data from CoGAPS

 data(SimpSim)

-# Run calcZ

 calcZ(SimpSim.result$Amean, SimpSim.result$Asd)

 }

@@ -13,7 +13,7 @@ createGWCoGAPSSets(D, S, nSets, simulationName)

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

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

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

 }

 \value{

 simulationName used to identify saved files

@@ -25,7 +25,7 @@ Create Gene Sets for GWCoGAPS

 factors whole genome data into randomly generated sets for indexing

 }

 \examples{

-data(SimpSim) # Load the sample data from CoGAPS

+data(SimpSim)

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

 }

@@ -74,7 +74,7 @@ Backwards Compatibility with v2

 \examples{

 data(SimpSim)

 nC <- ncol(SimpSim.D)

-patterns <- matrix(runif(nC, 0, 1), nrow=1, ncol=nC)

+patterns <- matrix(1:nC/nC, nrow=1, ncol=nC)

 result <- gapsMapRun(SimpSim.D, SimpSim.S, FP=patterns, nFactor=3)

 }

@@ -24,9 +24,7 @@ a simple plot of the number of atoms

 from one of the vectors returned with atom numbers

 }

 \examples{

-# Load the sample data from CoGAPS

 data(SimpSim)

-# Run plotAtoms

 plotAtoms(SimpSim.result, type="sampA")

 }

@@ -19,9 +19,7 @@ Diagnostic Plots

 plots a series of diagnostic plots

 }

 \examples{

-# Load the sample data from CoGAPS

 data(SimpSim)

-# Run plotDiag

 plotDiag(SimpSim.result)

 }

@@ -25,9 +25,7 @@ plots the output A and P matrices as a

 heatmap and line plot respectively

 }

 \examples{

-# Load the sample data from CoGAPS

 data(SimpSim)

-# Run plotGAPS with arguments from CoGAPS results list

 plotGAPS(SimpSim.result$Amean, SimpSim.result$Pmean)

 }

@@ -21,9 +21,7 @@ Plot the P Matrix

 plots the P matrix in a line plot with error bars

 }

 \examples{

-# Load the sample data from CoGAPS

 data(SimpSim)

-# Run plotP with arguments from CoGAPS results list

 plotP(SimpSim.result$Pmean, SimpSim.result$Psd)

 }

@@ -20,9 +20,7 @@ the D' estimate of a gene or set of genes

 Reconstruct Gene

 }

 \examples{

-# Load the sample data from CoGAPS

 data(SimpSim)

-# Run reconstructGene

 reconstructGene(SimpSim.result$Amean, SimpSim.result$Pmean)

 }

@@ -25,9 +25,7 @@ Plot of Residuals

 calculate residuals and produce heatmap

 }

 \examples{

-# Load the sample data from CoGAPS

 data(SimpSim)

-# Run residuals with the correct arguments

 residuals(SimpSim.result$Amean, SimpSim.result$Pmean, SimpSim.D, SimpSim.S)

 }

@@ -151,12 +151,12 @@ TEST_CASE("Test Archive.h")

     SECTION("GibbsSampler Serialization")

     {

-

+        //TODO

     }

     SECTION("GapsInternalState Serialization")

     {

-

+        //TODO

     }

     SECTION("Random Generator Serialization")