@@ -3,8 +3,8 @@ Type: Package

 Title: A framework for cross-validated classification problems, with

        applications to differential variability and differential

        distribution testing

-Version: 3.1.15

-Date: 2022-08-31

+Version: 3.1.16

+Date: 2022-09-12

 Author: Dario Strbenac, Ellis Patrick, John Ormerod, Graham Mann, Jean Yang

 Maintainer: Dario Strbenac <dario.strbenac@sydney.edu.au>

 VignetteBuilder: knitr

@@ -102,7 +102,7 @@ setMethod("crossValidate", "DataFrame",

               outcome <- measurementsAndOutcome[["outcome"]]

               # Which data-types or data-views are present?

-              assayIDs <- unique(mcols(measurements)[, "assay"])

+              assayIDs <- unique(mcols(measurements)$assay)

               if(is.null(assayIDs)) assayIDs <- 1

               checkData(measurements, outcome)

@@ -450,7 +450,7 @@ setMethod("crossValidate", "list",

 ######################################

 cleanNFeatures <- function(nFeatures, measurements){

     #### Clean up

-    if(!is.null(mcols(measurements)))

+    if(!is.null(mcols(measurements)$assay))

       obsFeatures <- unlist(as.list(table(mcols(measurements)[, "assay"])))

     else obsFeatures <- ncol(measurements)

     if(is.null(nFeatures) || length(nFeatures) == 1 && nFeatures == "all") nFeatures <- as.list(obsFeatures)

@@ -467,7 +467,7 @@ cleanNFeatures <- function(nFeatures, measurements){

 ######################################

 cleanSelectionMethod <- function(selectionMethod, measurements){

     #### Clean up

-    if(!is.null(mcols(measurements)))

+    if(!is.null(mcols(measurements)$assay))

       obsFeatures <- unlist(as.list(table(mcols(measurements)[, "assay"])))

     else return(list(selectionMethod))

@@ -483,7 +483,7 @@ cleanSelectionMethod <- function(selectionMethod, measurements){

 ######################################

 cleanClassifier <- function(classifier, measurements){

     #### Clean up

-    if(!is.null(mcols(measurements)))

+    if(!is.null(mcols(measurements)$assay))

       obsFeatures <- unlist(as.list(table(mcols(measurements)[, "assay"])))

     else return(list(classifier))

@@ -55,9 +55,9 @@ setMethod("prepareData", "DataFrame",

     measurements <- measurements[, useFeatures]

   # Won't ever be true if input data was MultiAssayExperiment because wideFormat already produces valid names.  

-  if(!all.equal(colnames(measurements), make.names(colnames(measurements))))

+  if(all.equal(colnames(measurements), make.names(colnames(measurements))) != TRUE)

   {

-    mcols(measurements)[, "feature"] <- colnames(measurements) # Save the originals.

+    mcols(measurements)$feature <- colnames(measurements) # Save the originals.

     colnames(measurements) <- make.names(colnames(measurements)) # Ensure column names are safe names.

   }

@@ -272,7 +272,7 @@ input data. Autmomatically reducing to smaller number.")

   {

     if(!is.null(rankedFeaturesIndices))

     {

-      if(is.null(S4Vectors::mcols(measurementsTrain)))

+      if(is.null(S4Vectors::mcols(measurementsTrain)) || !"assay" %in% colnames(S4Vectors::mcols(measurementsTrain)))

       {

         rankedFeatures <- originalFeatures[rankedFeaturesIndices]

       } else {

@@ -282,7 +282,8 @@ input data. Autmomatically reducing to smaller number.")

     } else { rankedFeatures <- NULL}

     if(!is.null(selectedFeaturesIndices))

     {

-      if(is.null(S4Vectors::mcols(measurementsTrain))){

+      if(is.null(S4Vectors::mcols(measurementsTrain)) || !"assay" %in% colnames(S4Vectors::mcols(measurementsTrain)))

+      {

         selectedFeatures <- originalFeatures[selectedFeaturesIndices]

       } else {

         featureColumns <- na.omit(match(c("assay", "feature"), colnames(S4Vectors::mcols(measurementsTrain))))  

@@ -78,7 +78,8 @@ setMethod("runTests", "DataFrame", function(measurements, outcome, crossValParam

     stop("Some data elements are missing and classifiers don't work with missing data. Consider imputation or filtering.")            

   originalFeatures <- colnames(measurements)

-  if("feature" %in% colnames(S4Vectors::mcols(measurements))) originalFeatures <- S4Vectors::mcols(measurements)[, c("assay", "feature")]                 

+  if("assay" %in% colnames(S4Vectors::mcols(measurements)))

+      originalFeatures <- S4Vectors::mcols(measurements)[, c("assay", "feature")]                 

   splitDataset <- prepareData(measurements, outcome, ...)

   measurements <- splitDataset[["measurements"]]

   outcome <- splitDataset[["outcome"]]

@@ -17,7 +17,7 @@

 #' design to compare. Can be any characteristic that all results share.

 #' @param metric Default: "Sample Error". The sample-wise metric to plot.

 #' @param featureValues If not NULL, can be a named factor or named numeric

-#' vector specifying some variable of interest to plot underneath the above the

+#' vector specifying some variable of interest to plot above the

 #' heatmap.

 #' @param featureName A label describing the information in

 #' \code{featureValues}. It must be specified if \code{featureValues} is.

@@ -40,7 +40,9 @@ elasticNetGLMparams <- function() {

 # Support Vector Machine

 SVMparams = function() {

-    trainParams <- TrainParams(SVMtrainInterface, tuneParams = list(kernel = c("linear", "polynomial", "radial", "sigmoid"), cost = 10^(-3:3), performanceType = "Balanced Error"))

+    trainParams <- TrainParams(SVMtrainInterface,

+                   tuneParams = list(kernel = c("linear", "polynomial", "radial", "sigmoid"),

+                                     cost = 10^(-3:3), performanceType = "Balanced Error"))

     predictParams <- PredictParams(SVMpredictInterface)

     return(list(trainParams = trainParams, predictParams = predictParams))