@@ -431,7 +431,7 @@ setMethod("crossValidate", "list",

               }

               # Check the number of outcome is the same

-              if ((measurements[[1]] |> dim())[1] != length(outcome)) {

+              if (((measurements[[1]] |> dim())[1] != length(outcome)) & length(outcome)>2) {

                   stop("outcome must have same number of samples as measurements")

               }

@@ -913,4 +913,4 @@ setMethod("predict", "ClassifyResult",

           function(object, newData)

           {

               object@modellingParams@predictParams@predictor(object@finalModel[[1]], newData)

-          })

\ No newline at end of file

+          })

@@ -56,7 +56,7 @@ setMethod("prevalTrainInterface", "DFrame",

               ###

               # Splitting measurements into a list of each of the assays

               ###

-              assayTrain <- sapply(unique(mcols(measurements)[["assay"]]), function(assay) measurements[, mcols(measurements)[["dataset"]] %in% assay], simplify = FALSE)

+              assayTrain <- sapply(unique(mcols(measurements)[["assay"]]), function(assay) measurements[, mcols(measurements)[["assay"]] %in% assay], simplify = FALSE)

               if(!"clinical" %in% names(assayTrain)) stop("Must have an assay called \"clinical\"")

@@ -72,7 +72,7 @@ setMethod("prevalTrainInterface", "DFrame",

                   measurements = assayTrain[usePreval],

                   modellingParams = params[usePreval],

                   MoreArgs = list(

-                      classes = classes,

+                      outcome = classes,

                       crossValParams = CVparams,

                       verbose = 0

                   ), 

@@ -98,7 +98,7 @@ setMethod("prevalTrainInterface", "DFrame",

               #fullTrain = cbind(assayTrain[["clinical"]][,selectedFeaturesClinical], prevalidationTrain[rownames(assayTrain[["clinical"]]), , drop = FALSE])

               prevalidationTrain <- S4Vectors::DataFrame(prevalidationTrain)

-              mcols(prevalidationTrain)$assay = "PCA"

+              mcols(prevalidationTrain)$assay = "prevalidation"

               mcols(prevalidationTrain)$feature = colnames(prevalidationTrain)

@@ -116,10 +116,10 @@ setMethod("prevalTrainInterface", "DFrame",

               # Fit classification model (from clinical in params)

               runTestOutput = runTest(

-                  fullTrain,

-                  classes = classes,

-                  training = seq_len(nrow(fullTrain)),

-                  testing = seq_len(nrow(fullTrain)),

+                  measurementsTrain = fullTrain,

+                  outcomeTrain = classes,

+                  measurementsTest = fullTrain,

+                  outcomeTest = classes,

                   modellingParams = finalModParam,

                   crossValParams = CVparams,

                   .iteration = 1,

@@ -134,12 +134,12 @@ setMethod("prevalTrainInterface", "DFrame",

               # Fit models with each datatype for use in prevalidated prediction later..

               prevalidationModels =  mapply(

                   runTest,

-                  measurements = assayTrain[usePreval],

+                  measurementsTrain = assayTrain[usePreval],

+                  outcomeTrain = classes,

+                  measurementsTest = assayTrain[usePreval],

+                  outTest = classes,

                   modellingParams = params[usePreval],

                   MoreArgs = list(

-                      classes = classes,

-                      training = seq_len(nrow(fullTrain)),

-                      testing =  seq_len(nrow(fullTrain)),

                       crossValParams = CVparams,

                       .iteration = 1,

                       verbose = 0

@@ -191,7 +191,7 @@ setMethod("prevalPredictInterface", c("prevalModel", "DFrame"),

                   extractPrevalidation()

               prevalidationPredict <- S4Vectors::DataFrame(prevalidationPredict)

-              mcols(prevalidationPredict)$assay = "PCA"

+              mcols(prevalidationPredict)$assay = "prevalidation"

               mcols(prevalidationPredict)$feature = colnames(prevalidationPredict)

               fullTest = cbind(assayTest[["clinical"]], prevalidationPredict[rownames(assayTest[["clinical"]]), , drop = FALSE])

@@ -117,8 +117,8 @@ function(measurementsTrain, outcomeTrain, measurementsTest, outcomeTest,

     featuresInfo <- .summaryFeatures(measurementsTrain)

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

     {

-      S4Vectors::mcols(measurementsTrain) <- featuresInfo[, c("Renamed Assay", "Renamed Feature")]

-      S4Vectors::mcols(measurementsTest) <- featuresInfo[, c("Renamed Assay", "Renamed Feature")]

+      #S4Vectors::mcols(measurementsTrain) <- featuresInfo[, c("Renamed Assay", "Renamed Feature")]

+      #S4Vectors::mcols(measurementsTest) <- featuresInfo[, c("Renamed Assay", "Renamed Feature")]

       colnames(measurementsTrain) <- colnames(measurementsTest) <- paste(featuresInfo[["Renamed Assay"]], featuresInfo[["Renamed Feature"]], sep = '')

     } else {

       colnames(measurementsTrain) <- colnames(measurementsTest) <- featuresInfo[, "Renamed Feature"]

@@ -330,4 +330,4 @@ setMethod("runTest", c("MultiAssayExperiment"),

   tablesAndClassesTest <- .MAEtoWideTable(measurementsTest, targets, outcomeColumns, restrict = NULL)

   runTest(tablesAndClassesTrain[["dataTable"]], tablesAndClassesTrain[["outcome"]],

           tablesAndClassesTest[["dataTable"]], tablesAndClassesTest[["outcome"]], ...)            

-})

\ No newline at end of file

+})

@@ -586,7 +586,7 @@

     featuresInfo <- S4Vectors::DataFrame(originalFeatures, renamedInfo)

     colnames(featuresInfo) <- c("Original Feature", "Renamed Feature")

   }

-  featuresInfo

+  cbind(originalInfo, featuresInfo)

 }

 # Function to identify the parameters of an S4 method.

@@ -776,4 +776,4 @@

 .dmvnorm_diag <- function(x, mean, sigma) { # Remove once sparsediscrim is reinstated to CRAN.

   exp(sum(dnorm(x, mean=mean, sd=sqrt(sigma), log=TRUE)))

-}

\ No newline at end of file

+}