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

 Package: GSVA

-Version: 1.25.3

+Version: 1.25.4

 Title: Gene Set Variation Analysis for microarray and RNA-seq data

 Authors@R: c(person("Justin", "Guinney", role=c("aut", "cre"), email="justin.guinney@sagebase.org"),

              person("Robert", "Castelo", role="aut", email="robert.castelo@upf.edu"),

@@ -8,6 +8,7 @@ setGeneric("gsva", function(expr, gset.idx.list, ...) standardGeneric("gsva"))

 setMethod("gsva", signature(expr="ExpressionSet", gset.idx.list="list"),

           function(expr, gset.idx.list, annotation,

   method=c("gsva", "ssgsea", "zscore", "plage"),

+  kcdf=c("Gaussian", "Poisson", "none"),

   rnaseq=FALSE,

   abs.ranking=FALSE,

   min.sz=1,

@@ -23,6 +24,13 @@ setMethod("gsva", signature(expr="ExpressionSet", gset.idx.list="list"),

   verbose=TRUE)

 {

   method <- match.arg(method)

+  kcdf <- match.arg(kcdf)

+

+  if (!missing(rnaseq))

+    warning("The argument 'rnaseq' is deprecated and will be removed in the next release of GSVA. Please use the 'kcdf' argument instead.")

+

+  if (!missing(kernel))

+    warning("The argument 'kernel' is deprecated and will be removed in the next release of GSVA. Please use the 'kcdf' argument instead.")

   ## filter out genes with constant expression values

   sdGenes <- Biobase::esApply(expr, 1, sd)

@@ -52,7 +60,18 @@ setMethod("gsva", signature(expr="ExpressionSet", gset.idx.list="list"),

                                          min.sz=max(1, min.sz),

                                          max.sz=max.sz)

-  eSco <- .gsva(exprs(expr), mapped.gset.idx.list, method, rnaseq, abs.ranking,

+  if (!missing(kcdf)) {

+    if (kcdf == "Gaussian") {

+      rnaseq <- FALSE

+      kernel <- TRUE

+    } else if (kcdf == "Poisson") {

+      rnaseq <- TRUE

+      kernel <- TRUE

+    } else

+      kernel <- FALSE

+  }

+

+  eSco <- .gsva(exprs(expr), mapped.gset.idx.list, method, kcdf, rnaseq, abs.ranking,

                 no.bootstraps, bootstrap.percent, parallel.sz, parallel.type,

                 mx.diff, tau, kernel, ssgsea.norm, verbose)

@@ -70,6 +89,7 @@ setMethod("gsva", signature(expr="ExpressionSet", gset.idx.list="list"),

 setMethod("gsva", signature(expr="ExpressionSet", gset.idx.list="GeneSetCollection"),

           function(expr, gset.idx.list, annotation,

   method=c("gsva", "ssgsea", "zscore", "plage"),

+  kcdf=c("Gaussian", "Poisson", "none"),

   rnaseq=FALSE,

   abs.ranking=FALSE,

   min.sz=1,

@@ -85,6 +105,13 @@ setMethod("gsva", signature(expr="ExpressionSet", gset.idx.list="GeneSetCollecti

   verbose=TRUE)

 {

   method <- match.arg(method)

+  kcdf <- match.arg(kcdf)

+

+  if (!missing(rnaseq))

+    warning("The argument 'rnaseq' is deprecated and will be removed in the next release of GSVA. Please use the 'kcdf' argument instead.")

+

+  if (!missing(kernel))

+    warning("The argument 'kernel' is deprecated and will be removed in the next release of GSVA. Please use the 'kcdf' argument instead.")

   ## filter out genes with constant expression values

   sdGenes <- Biobase::esApply(expr, 1, sd)

@@ -118,7 +145,18 @@ setMethod("gsva", signature(expr="ExpressionSet", gset.idx.list="GeneSetCollecti

                                          min.sz=max(1, min.sz),

                                          max.sz=max.sz)

-  eSco <- .gsva(exprs(expr), mapped.gset.idx.list, method, rnaseq, abs.ranking,

+  if (!missing(kcdf)) {

+    if (kcdf == "Gaussian") {

+      rnaseq <- FALSE

+      kernel <- TRUE

+    } else if (kcdf == "Poisson") {

+      rnaseq <- TRUE

+      kernel <- TRUE

+    } else

+      kernel <- FALSE

+  }

+

+  eSco <- .gsva(exprs(expr), mapped.gset.idx.list, method, kcdf, rnaseq, abs.ranking,

                 no.bootstraps, bootstrap.percent, parallel.sz, parallel.type,

                 mx.diff, tau, kernel, ssgsea.norm, verbose)

@@ -136,6 +174,7 @@ setMethod("gsva", signature(expr="ExpressionSet", gset.idx.list="GeneSetCollecti

 setMethod("gsva", signature(expr="matrix", gset.idx.list="GeneSetCollection"),

           function(expr, gset.idx.list, annotation,

   method=c("gsva", "ssgsea", "zscore", "plage"),

+  kcdf=c("Gaussian", "Poisson", "none"),

   rnaseq=FALSE,

   abs.ranking=FALSE,

   min.sz=1,

@@ -151,6 +190,13 @@ setMethod("gsva", signature(expr="matrix", gset.idx.list="GeneSetCollection"),

   verbose=TRUE)

 {

   method <- match.arg(method)

+  kcdf <- match.arg(kcdf)

+

+  if (!missing(rnaseq))

+    warning("The argument 'rnaseq' is deprecated and will be removed in the next release of GSVA. Please use the 'kcdf' argument instead.")

+

+  if (!missing(kernel))

+    warning("The argument 'kernel' is deprecated and will be removed in the next release of GSVA. Please use the 'kcdf' argument instead.")

   ## filter out genes with constant expression values

   sdGenes <- apply(expr, 1, sd)

@@ -191,7 +237,18 @@ setMethod("gsva", signature(expr="matrix", gset.idx.list="GeneSetCollection"),

                                          min.sz=max(1, min.sz),

                                          max.sz=max.sz)

-  .gsva(expr, mapped.gset.idx.list, method, rnaseq, abs.ranking,

+  if (!missing(kcdf)) {

+    if (kcdf == "Gaussian") {

+      rnaseq <- FALSE

+      kernel <- TRUE

+    } else if (kcdf == "Poisson") {

+      rnaseq <- TRUE

+      kernel <- TRUE

+    } else

+      kernel <- FALSE

+  }

+

+  .gsva(expr, mapped.gset.idx.list, method, kcdf, rnaseq, abs.ranking,

         no.bootstraps, bootstrap.percent, parallel.sz, parallel.type,

         mx.diff, tau, kernel, ssgsea.norm, verbose)

 })

@@ -199,6 +256,7 @@ setMethod("gsva", signature(expr="matrix", gset.idx.list="GeneSetCollection"),

 setMethod("gsva", signature(expr="matrix", gset.idx.list="list"),

           function(expr, gset.idx.list, annotation,

   method=c("gsva", "ssgsea", "zscore", "plage"),

+  kcdf=c("Gaussian", "Poisson", "none"),

   rnaseq=FALSE,

   abs.ranking=FALSE,

   min.sz=1,

@@ -214,6 +272,13 @@ setMethod("gsva", signature(expr="matrix", gset.idx.list="list"),

   verbose=TRUE)

 {

   method <- match.arg(method)

+  kcdf <- match.arg(kcdf)

+

+  if (!missing(rnaseq))

+    warning("The argument 'rnaseq' is deprecated and will be removed in the next release of GSVA. Please use the 'kcdf' argument instead.")

+

+  if (!missing(kernel))

+    warning("The argument 'kernel' is deprecated and will be removed in the next release of GSVA. Please use the 'kcdf' argument instead.")

   ## filter out genes with constant expression values

   sdGenes <- apply(expr, 1, sd)

@@ -242,13 +307,25 @@ setMethod("gsva", signature(expr="matrix", gset.idx.list="list"),

                                          min.sz=max(1, min.sz),

                                          max.sz=max.sz)

-  .gsva(expr, mapped.gset.idx.list, method, rnaseq, abs.ranking, no.bootstraps,

+  if (!missing(kcdf)) {

+    if (kcdf == "Gaussian") {

+      rnaseq <- FALSE

+      kernel <- TRUE

+    } else if (kcdf == "Poisson") {

+      rnaseq <- TRUE

+      kernel <- TRUE

+    } else

+      kernel <- FALSE

+  }

+

+  .gsva(expr, mapped.gset.idx.list, method, kcdf, rnaseq, abs.ranking, no.bootstraps,

         bootstrap.percent, parallel.sz, parallel.type,

         mx.diff, tau, kernel, ssgsea.norm, verbose)

 })

 .gsva <- function(expr, gset.idx.list,

   method=c("gsva", "ssgsea", "zscore", "plage"),

+  kcdf=c("Gaussian", "Poisson", "none"),

   rnaseq=FALSE,

   abs.ranking=FALSE,

   no.bootstraps=0, 

@@ -261,6 +338,9 @@ setMethod("gsva", signature(expr="matrix", gset.idx.list="list"),

   ssgsea.norm=TRUE,

   verbose=TRUE)

 {

+  if (no.bootstraps > 0)

+    warning("The 'no.bootstraps' and 'bootstrap.percent' arguments are experimental and will be deprecated and will dissapear in the following release of GSVA.")

+

 	if(length(gset.idx.list) == 0){

 		stop("The gene set list is empty!  Filter may be too stringent.")

 	}

@@ -98,16 +98,13 @@ argumentsDataInput <- function(id) {

           12,

           selectInput("method", "Choose method:",

                       c("gsva","ssgsea","zscore","plage")),

-          radioButtons("rnaseq", "Rnaseq:",

-                       c("False" = FALSE,

-                         "True" = TRUE)),

+          selectInput("kcdf", "Choose kcdf:",

+                      c("Gaussian","Poisson","none")),

           radioButtons("absRanking", "abs.ranking:",

                        c("False" = FALSE,

                          "True" = TRUE)),

           numericInput("minSz","min.sz:",value = 1),

           numericInput("maxSz","max.sz (Write 0 for infinite):",value = 0),

-          numericInput("noBootstraps","no.bootstraps:",value = 0),

-          numericInput("bootstrapPercent","bootstrap.percent:",value = .632),

           numericInput("parallelSz","parallel.sz:",value = 0),

           selectInput("parallelType", "parallel.type:",

                       c("SOCK","MPI","NWS")),

@@ -125,9 +122,6 @@ argumentsDataInput <- function(id) {

           conditionalPanel(

             condition = "input.method == 'zscore' || input.method == 'plage'"

           ),

-          radioButtons("kernel", "kernel:",

-                       c("True" = TRUE,

-                         "False" = FALSE)),

           radioButtons("ssgseaNorm", "ssgsea.norm:",

                        c("True" = TRUE,

                          "False" = FALSE)),

@@ -255,10 +249,10 @@ gsva_generation <- function(input, output, session, newY, genes,varMaxsz) {

   #GSVA Generation

   withProgress(message = 'Runing GSVA', value = 0, {

     incProgress(1, detail = "This may take a while...")

-    generated_gsva <<- gsva(newY, genes, method = input$method, rnaseq = as.logical(input$rnaseq), abs.ranking = as.logical(input$absRanking),

-                            min.sz = input$minSz, max.sz = varMaxsz, no.bootstraps = input$noBootstraps, bootstrap.percent = input$bootstrapPercent, 

-                            parallel.sz = input$parallelSz, parallel.type = input$parallelType, mx.diff = as.logical(input$mxDiff), tau = selectedTau, kernel = as.logical(input$kernel),

-                            ssgsea.norm = as.logical(input$ssgseaNorm), verbose = as.logical(input$verbose)) #Result asignation

+    generated_gsva <<- gsva(newY, genes, method=input$method, kcdf=input$kcdf, abs.ranking=as.logical(input$absRanking),

+                            min.sz=input$minSz, max.sz=varMaxsz, parallel.sz=input$parallelSz, parallel.type=input$parallelType,

+                            mx.diff=as.logical(input$mxDiff), tau=selectedTau, ssgsea.norm=as.logical(input$ssgseaNorm),

+                            verbose=as.logical(input$verbose))

   })

 }

@@ -16,6 +16,7 @@ Estimates GSVA enrichment scores.

 \usage{

 \S4method{gsva}{ExpressionSet,list}(expr, gset.idx.list, annotation,

     method=c("gsva", "ssgsea", "zscore", "plage"),

+    kcdf=c("Gaussian", "Poisson", "none"),

     rnaseq=FALSE,

     abs.ranking=FALSE,

     min.sz=1,

@@ -31,6 +32,7 @@ Estimates GSVA enrichment scores.

     verbose=TRUE)

 \S4method{gsva}{ExpressionSet,GeneSetCollection}(expr, gset.idx.list, annotation,

     method=c("gsva", "ssgsea", "zscore", "plage"),

+    kcdf=c("Gaussian", "Poisson", "none"),

     rnaseq=FALSE,

     abs.ranking=FALSE,

     min.sz=1,

@@ -46,6 +48,7 @@ Estimates GSVA enrichment scores.

     verbose=TRUE)

 \S4method{gsva}{matrix,GeneSetCollection}(expr, gset.idx.list, annotation,

     method=c("gsva", "ssgsea", "zscore", "plage"),

+    kcdf=c("Gaussian", "Poisson", "none"),

     rnaseq=FALSE,

     abs.ranking=FALSE,

     min.sz=1,

@@ -61,6 +64,7 @@ Estimates GSVA enrichment scores.

     verbose=TRUE)

 \S4method{gsva}{matrix,list}(expr, gset.idx.list, annotation,

     method=c("gsva", "ssgsea", "zscore", "plage"),

+    kcdf=c("Gaussian", "Poisson", "none"),

     rnaseq=FALSE,

     abs.ranking=FALSE,

     min.sz=1,

@@ -97,12 +101,15 @@ Estimates GSVA enrichment scores.

                 while in the case of \code{plage} they are used to calculate the singular value decomposition

                 (SVD) over the genes in the gene set and use the coefficients of the first right-singular vector

                 as pathway activity profile.}

-  \item{rnaseq}{Logical flag set by default to \code{rnaseq=FALSE} to inform whether the input gene

-                expression data are continues values, such as fluorescent units in logarithmic scale

-                from microarray experiments or some other kind of continuous value derived from

-                RNA-seq counts such as log-CPMs, log-RPKMs or log-TPMs. This flag should be set to

-                \code{rnaseq=TRUE} only when the values of the input gene expression data are integer

-                counts.}

+  \item{kcdf}{Character string denoting the kernel to use during the non-parametric estimation of the

+              cumulative distribution function of expression levels across samples when \code{method="gsva"}.

+              By default, \code{kcdf="Gaussian"} which is suitable when input expression values are continuous,

+              such as microarray fluorescent units in logarithmic scale, RNA-seq log-CPMs, log-RPKMs or log-TPMs.

+              When input expression values are integer counts, such as those derived from RNA-seq experiments,

+              then this argument should be set to \code{kcdf="Poisson"}. This argument supersedes arguments

+              \code{rnaseq} and \code{kernel}, which are deprecated and will be removed in the next release.}

+  \item{rnaseq}{This argument has been deprecated and will be removed in the next release. Please use the

+                argument \code{kcdf} instead.}

   \item{abs.ranking}{Flag used only when \code{mx.diff=TRUE}. When \code{abs.ranking=FALSE} (default)

             a modified Kuiper statistic is used to calculate enrichment scores, taking the magnitude

             difference between the largest positive and negative random walk deviations. When

@@ -131,10 +138,8 @@ Estimates GSVA enrichment scores.

              (\enc{H�nzelmann}{Hanzelmann} et al., 2013) and the \code{ssgsea} (Barbie et al., 2009) methods. By default,

              this \code{tau=1} when \code{method="gsva"} and \code{tau=0.25} when \code{method="ssgsea"} just

              as specified by Barbie et al. (2009) where this parameter is called \code{alpha}.}

-  \item{kernel}{Logical, set to \code{TRUE} when the GSVA method employes a kernel non-parametric

-                estimation of the empirical cumulative distribution function (default) and \code{FALSE}

-                when this function is directly estimated from the observed data. This last option is

-                justified in the limit of the size of the sample by the so-called Glivenko-Cantelli theorem.}

+  \item{kernel}{This argument has been deprecated and will be removed in the next release. Please use the

+                argument \code{kcdf} instead.}

   \item{ssgsea.norm}{Logical, set to \code{TRUE} (default) with \code{method="ssgsea"} runs the SSGSEA method

                      from Barbie et al. (2009) normalizing the scores by the absolute difference between

                      the minimum and the maximum, as described in their paper. When \code{ssgsea.norm=FALSE}

@@ -154,16 +159,6 @@ identifiers in the input expression data leading to a filtered collection of

 gene sets. This collection can be further filtered to require a minimun and/or

 maximum size of the gene sets for which we want to calculate GSVA enrichment

 scores, by using the arguments \code{min.sz} and \code{max.sz}.

-

-The name of the argument \code{rnaseq} can be misleading. When set to \code{rnaseq=FALSE}, the

-nonparametric estimation of the cumulative density function of the expression profile of

-each gene across samples is done using Gaussian kernels suited for continuous values. These were

-initially thought to be only microarray fluorescent units in logarithmic scale but nowadays these

-may also correspond to continuous values derived from RNA-seq experiments such as log-CPMs,

-log-RPKMs or log-TPMs. When \code{rnaseq=TRUE}, Poisson kernels are used instead and therefore,

-this option is only suitable when the input gene expression matrix is formed by integer counts.

-This implies that \code{rnaseq=FALSE} may also be used even when the expression data comes from

-a RNA-seq experiment. The name of this argument may change in the future to avoid this confusion.

 }

 \value{

 A gene-set by sample matrix of GSVA enrichment scores.

@@ -841,15 +841,18 @@ canonicalC2BroadSets <- GeneSetCollection(c(canonicalC2BroadSets, MSY, XiE))

 canonicalC2BroadSets

 @

 We calculate now GSVA enrichment scores for these gene sets using first the microarray

-data and then the RNA-seq data. Note that the only requirement to do the latter is to

-set the argument \Robject{rnaseq=TRUE} which is \Robject{FALSE} by default.

+data and then the RNA-seq integer count data. Note that the only requirement to do the

+latter is to set the argument \Robject{kcdf="Poisson"} which is \Robject{"Gaussian"} by

+default. Note, however, that if our RNA-seq derived expression levels would be continous,

+such as log-CPMs, log-RPKMs or log-TPMs, the the default value of the \Robject{kcdf}

+argument should remain unchanged.

 <<<>>=

 esmicro <- gsva(huangArrayRMAnoBatchCommon_eset, canonicalC2BroadSets, min.sz=5, max.sz=500,

-                mx.diff=TRUE, verbose=FALSE, rnaseq=FALSE, parallel.sz=1)$es.obs

+                mx.diff=TRUE, verbose=FALSE, parallel.sz=1)$es.obs

 dim(esmicro)

 esrnaseq <- gsva(pickrellCountsArgonneCQNcommon_eset, canonicalC2BroadSets, min.sz=5, max.sz=500,

-                 mx.diff=TRUE, verbose=FALSE, rnaseq=TRUE, parallel.sz=1)$es.obs

+                 kcdf="Poisson", mx.diff=TRUE, verbose=FALSE, parallel.sz=1)$es.obs

 dim(esrnaseq)

 @

 To compare expression values from both technologies we are going to transform