@@ -72,6 +72,7 @@ Collate:

     'interfaceXGB.R'

     'performancePlot.R'

     'plotFeatureClasses.R'

+    'precisionPathway.R'

     'prepareData.R'

     'previousSelection.R'

     'previousTrained.R'

@@ -76,6 +76,7 @@ exportMethods(models)

 exportMethods(performance)

 exportMethods(performancePlot)

 exportMethods(plotFeatureClasses)

+exportMethods(precisionPathwayTrain)

 exportMethods(predictions)

 exportMethods(prepareData)

 exportMethods(rankingPlot)

@@ -35,6 +35,9 @@ setClassUnion("DataFrameOrNULL", c("DataFrame", "NULL"))

 setClassUnion("tabular", c("data.frame", "DataFrame", "matrix"))

 setClassUnion("tabularOrList", c("tabular", "list"))

+# List-like assay data

+setClassUnion("MultiAssayExperimentOrList", c("MultiAssayExperiment", "list"))

+

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

 #

 # Params

@@ -22,14 +22,18 @@

 #' @param extraParams A list of parameters that will be used to overwrite default settings of transformation, selection, or model-building functions or

 #' parameters which will be passed into the data cleaning function. The names of the list must be one of \code{"prepare"},

 #' \code{"select"}, \code{"train"}, \code{"predict"}. To remove one of the defaults (see the article titled Parameter Tuning Presets for crossValidate and Their Customisation on

-#' the website), specify the list element to be \code{NULL}.

+#' the website), specify the list element to be \code{NULL}. For the valid element names in the \code{"prepare"} list, see \code{?prepareData}.

+#' @param clinicalPredictors If \code{measurements} is a \code{MultiAssayExperiment},

+#' a character vector of features to use in modelling. This allows avoidance of things like sample IDs,

+#' sample acquisition dates, etc. which are not relevant for outcome prediction.

 #' @param nFeatures The number of features to be used for classification. If this is a single number, the same number of features will be used for all comparisons

 #' or assays. If a numeric vector these will be optimised over using \code{selectionOptimisation}. If a named vector with the same names of multiple assays, 

 #' a different number of features will be used for each assay. If a named list of vectors, the respective number of features will be optimised over. 

 #' Set to NULL or "all" if all features should be used.

 #' @param selectionMethod Default: \code{"auto"}. A character vector of feature selection methods to compare. If a named character vector with names corresponding to different assays, 

 #' and performing multiview classification, the respective selection methods will be used on each assay. If \code{"auto"}, t-test (two categories) / F-test (three or more categories) ranking

-#' and top \code{nFeatures} optimisation is done. Otherwise, the ranking method is per-feature Cox proportional hazards p-value.

+#' and top \code{nFeatures} optimisation is done. Otherwise, the ranking method is per-feature Cox proportional hazards p-value. \code{NULL} is also a valid value, meaning that no

+#' indepedent feature selection will be performed (but implicit selection might still happen with the classifier).

 #' @param selectionOptimisation A character of "Resubstitution", "Nested CV" or "none" specifying the approach used to optimise \code{nFeatures}.

 #' @param performanceType Default: \code{"auto"}. If \code{"auto"}, then balanced accuracy for classification or C-index for survival. Otherwise, any one of the

 #' options described in \code{\link{calcPerformance}} may otherwise be specified.

@@ -93,7 +97,7 @@ setGeneric("crossValidate", function(measurements, outcome, ...)

 #' @rdname crossValidate

 #' @export

-setMethod("crossValidate", "DataFrame", 

+setMethod("crossValidate", "DataFrame",

           function(measurements,

                    outcome,

                    nFeatures = 20,

@@ -110,12 +114,15 @@ setMethod("crossValidate", "DataFrame",

           {

               # Check that data is in the right format, if not already done for MultiAssayExperiment input.

-              prepParams <- list(measurements, outcome)

-              if("prepare" %in% names(extraParams))

-                prepParams <- c(prepParams, extraParams[["prepare"]])

-              measurementsAndOutcome <- do.call(prepareData, prepParams)

-              measurements <- measurementsAndOutcome[["measurements"]]

-              outcome <- measurementsAndOutcome[["outcome"]]

+              if(!"assay" %in% S4Vectors::mcols(measurements)) # Assay is put there by prepareData for MultiAssayExperiment, skip if present. 

+              {

+                prepParams <- list(measurements, outcome, clinicalPredictors)

+                if("prepare" %in% names(extraParams))

+                  prepParams <- c(prepParams, extraParams[["prepare"]])

+                measurementsAndOutcome <- do.call(prepareData, prepParams)

+                measurements <- measurementsAndOutcome[["measurements"]]

+                outcome <- measurementsAndOutcome[["outcome"]]

+              }

               # Ensure performance type is one of the ones that can be calculated by the package.

               if(!performanceType %in% c("auto", .ClassifyRenvir[["performanceTypes"]]))

@@ -305,9 +312,10 @@ setMethod("crossValidate", "DataFrame",

 #' @rdname crossValidate

 #' @export

 # One or more omics data sets, possibly with clinical data.

-setMethod("crossValidate", "MultiAssayExperiment",

+setMethod("crossValidate", "MultiAssayExperimentOrList",

           function(measurements,

-                   outcome, 

+                   outcome,

+                   clinicalPredictors = NULL,

                    nFeatures = 20,

                    selectionMethod = "auto",

                    selectionOptimisation = "Resubstitution",

@@ -321,7 +329,7 @@ setMethod("crossValidate", "MultiAssayExperiment",

                    characteristicsLabel = NULL, extraParams = NULL)

           {

               # Check that data is in the right format, if not already done for MultiAssayExperiment input.

-              prepParams <- list(measurements, outcome)

+              prepParams <- list(measurements, outcome, clinicalPredictors)

               if("prepare" %in% names(extraParams))

                 prepParams <- c(prepParams, extraParams[["prepare"]])

               measurementsAndOutcome <- do.call(prepareData, prepParams)

@@ -408,76 +416,6 @@ setMethod("crossValidate", "matrix", # Matrix of numeric measurements.

                             characteristicsLabel = characteristicsLabel, extraParams = extraParams)

           })

-# This expects that each table is about the same set of samples and thus

-# has the same number of rows as every other table.

-#' @rdname crossValidate                                                            

-#' @export

-setMethod("crossValidate", "list",

-          function(measurements,

-                   outcome, 

-                   nFeatures = 20,

-                   selectionMethod = "auto",

-                   selectionOptimisation = "Resubstitution",

-                   performanceType = "auto",

-                   classifier = "auto",

-                   multiViewMethod = "none",

-                   assayCombinations = "all",

-                   nFolds = 5,

-                   nRepeats = 20,

-                   nCores = 1,

-                   characteristicsLabel = NULL, extraParams = NULL)

-          {

-              # Check data type is valid

-              if (!(all(sapply(measurements, class) %in% c("data.frame", "DataFrame", "matrix")))) {

-                  stop("assays must be of type data.frame, DataFrame or matrix")

-              }

-              

-              # Check the list is named

-              if (is.null(names(measurements))) {

-                  stop("Measurements must be a named list.")

-              }

-              

-              # Check same number of samples for all datasets

-              if (!length(unique(sapply(measurements, nrow))) == 1) {

-                  stop("All datasets must have the same samples.")

-              }

-              

-              # Check the number of outcome is the same

-              if (!all(sapply(measurements, nrow) == length(outcome)) && !is.character(outcome)) {

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

-              }

-              

-              df_list <- sapply(measurements, S4Vectors::DataFrame, check.names = FALSE)

-              

-              df_list <- mapply(function(meas, nam){

-                  S4Vectors::mcols(meas)$assay <- nam

-                  S4Vectors::mcols(meas)$feature <- colnames(meas)

-                  meas

-              }, df_list, names(df_list))

-              

-              

-              combined_df <- do.call("cbind", df_list) 

-              colnames(combined_df) <- S4Vectors::mcols(combined_df)$feature

-

-

-              

-              crossValidate(measurements = combined_df,

-                            outcome = outcome, 

-                            nFeatures = nFeatures,

-                            selectionMethod = selectionMethod,

-                            selectionOptimisation = selectionOptimisation,

-                            performanceType = performanceType,

-                            classifier = classifier,

-                            multiViewMethod = multiViewMethod,

-                            assayCombinations = assayCombinations,

-                            nFolds = nFolds,

-                            nRepeats = nRepeats,

-                            nCores = nCores,

-                            characteristicsLabel = characteristicsLabel, extraParams = extraParams)

-          })

-

-

-

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

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

 cleanNFeatures <- function(nFeatures, measurements){

@@ -1126,9 +1064,9 @@ train.list <- function(x, outcomeTrain, ...)

 #' @rdname crossValidate

 #' @method train MultiAssayExperiment

 #' @export

-train.MultiAssayExperiment <- function(x, outcome, ...)

+train.MultiAssayExperiment <- function(x, outcome, clinicalPredictors = NULL, ...)

           {

-              prepArgs <- list(x, outcome)

+              prepArgs <- list(x, outcome, clinicalPredictors)

               extraInputs <- list(...)

               prepExtras <- trainExtras <- numeric()

               if(length(extraInputs) > 0)

@@ -1167,7 +1105,7 @@ predict.trainedByClassifyR <- function(object, newData, ...)

     newData <- do.call(cbind, newData)

     } else if(is(newData, "MultiAssayExperiment"))

             {

-              newData <- prepareData(newData, useFeatures = allFeatureNames(object))

+              newData <- prepareData(newData, clinicalPredictors = subset(allFeatureNames(object), assay == "clinical")[, "feature"])

               # Some classifiers dangerously use positional matching rather than column name matching.

               # newData columns are sorted so that the right column ordering is guaranteed.

     }

new file mode 100644

@@ -0,0 +1,77 @@

+# Basically, an ordered list of cross-validations.

+

+setGeneric("precisionPathwayTrain", function(measurements, class, ...)

+    standardGeneric("precisionPathwayTrain"))

+

+#' @rdname precisionPathwayTrain

+#' @export

+setMethod("precisionPathwayTrain", "MultiAssayExperiment", 

+          function(measurements, class, clinicalPredictors = NULL, ..., fixedAssays = "clinical",

+                   confidenceCutoff = 0.8, minAssaySamples = 10,

+                   nFeatures = 20, selectionMethod = setNames(c(NULL, rep("t-test", length(measurements))), c("clinical", names(measurements))),

+                   classifier = setNames(c("elasticNetGLM", rep("randomForest", length(measurements))), c("clinical", names(measurements))),

+                   nFolds = 5, nRepeats = 20, nCores = 1)

+          {

+              prepArgs <- list(measurements, class, clinicalPredictors)              

+              extraInputs <- list(...)

+              prepExtras <- numeric()

+              if(length(extraInputs) > 0)

+                prepExtras <- which(names(extraInputs) %in% .ClassifyRenvir[["prepareDataFormals"]])

+              if(length(prepExtras) > 0)

+                prepArgs <- append(prepArgs, extraInputs[prepExtras])

+              measurementsAndClass <- do.call(prepareData, prepArgs)

+              

+             .precisionPathwayTrain(measurementsAndClass[["measurements"]], measurementsAndClass[["outcome"]],

+                                    fixedAssays = fixedAssays, confidenceCutoff = confidenceCutoff,

+                                    minAssaySamples = minAssaySamples, nFeatures = nFeatures,

+                                    selectionMethod = selectionMethod, classifier = classifier,

+                                    nFolds = nFolds, nRepeats = nRepeats, nCores = nCores)

+          })

+

+#' @rdname precisionPathwayTrain

+#' @export

+setMethod("precisionPathwayTrain", "list", 

+          function(measurements, class, clinicalPredictors = NULL, fixedAssays = "clinical",

+                   confidenceCutoff = 0.8, minAssaySamples = 10,

+                   nFeatures = 20, selectionMethod = setNames(c(NULL, rep("t-test", length(measurements))), c("clinical", names(measurements))),

+                   classifier = setNames(c("elasticNetGLM", rep("randomForest", length(measurements))), c("clinical", names(measurements))),

+                   nFolds = 5, nRepeats = 20, nCores = 1, ...)

+          {

+            # One of the tables must be named "clinical".

+            if (!any(names(measurements) == "clinical"))

+              stop("One of the tables must be named \"clinical\".")

+              

+            .precisionPathwayTrain(measurements = combined_df, class = class)

+          })

+

+# Internal method which carries out all of the processing, obtaining reformatted data from the

+# MultiAssayExperiment and list (of basic rectangular tables) S4 methods.

+.precisionPathwayTrain <- function(measurements, class, fixedAssays = "clinical",

+                   confidenceCutoff = 0.8, minAssaySamples = 10,

+                   nFeatures = 20, selectionMethod = setNames(c(NULL, rep("t-test", length(measurements))), c("clinical", names(measurements))),

+                   classifier = setNames(c("elasticNetGLM", rep("randomForest", length(measurements))), c("clinical", names(measurements))),

+                   nFolds = 5, nRepeats = 20, nCores = 1, ...)

+          {

+            # Step 1: Separate the vector classes from the table of measurements, if not already separate.

+            prepArgs <- list(measurements, class, clinicalPredictors)              

+            extraInputs <- list(...)

+            prepExtras <- numeric()

+            if(length(extraInputs) > 0)

+              prepExtras <- which(names(extraInputs) %in% .ClassifyRenvir[["prepareDataFormals"]])

+            if(length(prepExtras) > 0)

+              prepArgs <- append(prepArgs, extraInputs[prepExtras])

+            

+            measurementsAndClass <- do.call(prepareData, prepArgs)

+            measurements <- measurementsAndClass[["measurements"]]

+            class <- measurementsAndClass[["outcome"]]

+            

+            # Step 2: Determine all valid permutations of assays, taking into account the

+            # assays to be used and which assays, if any, must be included.

+            assayIDs <- unique(S4Vectors::mcols(measurements)[["assay"]])

+            assaysPermutations <- .permutations(assayIDs, fixed = data.frame(seq_along(fixedAssays), fixedAssays))

+            

+            # Step 3: Build a classifier for each assay using all of the samples.

+            modelsList <- crossValidate(measurements, class, nFeatures, selectionMethod,

+                                        classifier = classifier, nFolds = nFolds,

+                                        nRepeats = nRepeats, nCores = nCores)

+        }

\ No newline at end of file

@@ -18,15 +18,13 @@

 #' @param outcomeColumns If \code{measurements} is a \code{MultiAssayExperiment}, the

 #' names of the column (class) or columns (survival) in the table extracted by \code{colData(data)}

 #' that contain(s) the each individual's outcome to use for prediction.

-#' @param useFeatures If \code{measurements} is a \code{MultiAssayExperiment},

-#' a two-column table of features to use. The first column must have assay names

-#' and the second column must have feature names found for that assay. \code{"clinical"} is

-#' also a valid assay name and refers to the clinical data table. \code{"all"} is a special

-#' keyword that means all features (passing any other filters) of that assay will be used 

-#' for modelling. Otherwise, a character vector of feature names to use suffices.

+#' @param clinicalPredictors If \code{measurements} is a \code{MultiAssayExperiment},

+#' a character vector of features to use in modelling. This allows avoidance of things like sample IDs,

+#' sample acquisition dates, etc. which are not relevant for outcome prediction.

 #' @param maxMissingProp Default: 0.0. A proportion less than 1 which is the maximum

 #' tolerated proportion of missingness for a feature to be retained for modelling.

-#' @param topNvariance Default: NULL. An integer number of most variable features to subset to.

+#' @param topNvariance Default: NULL. An integer number of most variable features per assay to subset to.

+#' Assays with less features won't be reduced in size.

 #' @param ... Variables not used by the \code{matrix} nor the

 #' \code{MultiAssayExperiment} method which are passed into and used by the

 #' \code{DataFrame} method.

@@ -58,18 +56,16 @@ setMethod("prepareData", "data.frame",

 #' @rdname prepareData

 #' @export

 setMethod("prepareData", "DataFrame",

-  function(measurements, outcome, useFeatures = "all", maxMissingProp = 0.0, topNvariance = NULL)

+  function(measurements, outcome, clinicalPredictors = NULL, maxMissingProp = 0.0, topNvariance = NULL)

 {

   if(is.null(rownames(measurements)))

   {

     warning("'measurements' DataFrame must have sample identifiers as its row names. Generating generic ones.")

     rownames(measurements) <- paste("Sample", seq_len(nrow(measurements)))

-  }      

-            

-  if(useFeatures != "all") # Subset to only the desired ones.

-    measurements <- measurements[, useFeatures]

-

+  }

+      

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

+  # Need to check if input data was DataFrame because names might not be valid from user.

   if(!all(colnames(measurements) == make.names(colnames(measurements))))

   {

     warning("Unsafe feature names in input data. Converted into safe names.")

@@ -129,6 +125,19 @@ setMethod("prepareData", "DataFrame",

     else # Three columns. Therefore, counting process data.

       outcome <- survival::Surv(outcome[, 1], outcome[, 2], outcome[, 3])

   }

+  

+  if(!is.null(clinicalPredictors))

+  {

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

+    {

+      clinicalIndices <- which(mcols(measurements)$assay == "clinical")

+      usePredictors <- intersect(clinicalIndices, which(mcols(measurements)$feature %in% clinicalPredictors))

+      dropIndices <- setdiff(clinicalIndices, usePredictors)

+      if(length(dropIndices) > 0) measurements <- measurements[, -dropIndices]

+    } else { # The DataFrame is entirely clinical data.

+      measurements <- measurements[, clinicalPredictors]

+    }

+  }  

   # Remove samples with indeterminate outcome.

   dropSamples <- which(is.na(outcome) | is.null(outcome))

@@ -146,11 +155,18 @@ setMethod("prepareData", "DataFrame",

   if(length(dropFeatures) > 0)

     measurements <- measurements[, -dropFeatures]

-  # Use only the most variable features.

+  # Use only the most N variable features per assay.

   if(!is.null(topNvariance))

   {

-    mostVariance <- order(apply(measurements, 2, var, na.rm = TRUE), decreasing = TRUE)[1:topNvariance]

-    measurements <- measurements[, mostVariance]

+    if(is.null(mcols(measurements)$assay)) assays <- rep(1, ncol(measurements)) else assays <- mcols(measurements)$assay

+    do.call(cbind, lapply(unqiue(assays), function(assay)

+    {

+      assayColumns <- which(assays == assay)    

+      if(length(assayColumns) < topNvariance)

+        measurements[, assayColumns]

+      else

+        measurements[, assayColumns][order(apply(measurements[, assayColumns], 2, var, na.rm = TRUE), decreasing = TRUE)[1:topNvariance]]  

+    }))

   }

   list(measurements = measurements, outcome = outcome)

@@ -159,71 +175,74 @@ setMethod("prepareData", "DataFrame",

 #' @rdname prepareData

 #' @export

 setMethod("prepareData", "MultiAssayExperiment",

-  function(measurements, outcomeColumns = NULL, useFeatures = "all", ...)

+  function(measurements, outcomeColumns = NULL, clinicalPredictors = NULL, ...)

 {

-  if(is.character(useFeatures)) useFeatures <- data.frame(assay = names(measurements), feature = "all")

-  omicsTargets <- setdiff(useFeatures[, "assay"], "clinical")

-  if(length(omicsTargets) > 0)

-  {

-    if(any(anyReplicated(measurements[, , omicsTargets])))

-      stop("Data set contains replicates. Please remove or average replicate observations and try again.")

-  }

-  

-  if(!is.null(outcomeColumns) && !all(outcomeColumns %in% colnames(MultiAssayExperiment::colData(measurements))))

+  if(is.null(clinicalPredictors))

+    stop("'clinicalPredictors' must be a vector of informative clinical features (i.e. not sample IDs, sampling dates, etc.) to consider for classification.")      

+

+  if(any(anyReplicated(measurements[, , omicsTargets])))

+    stop("Data set contains replicates. Please remove or average replicate observations and try again.")

+ 

+  if(is.null(outcomeColums))

+    stop("'outcomeColumns' is a mandatory parameter but was not specified.")

+      

+  if(!all(outcomeColumns %in% colnames(MultiAssayExperiment::colData(measurements))))

     stop("Not all column names specified by 'outcomeColumns' found in clinical table.")  

-  if(!all(useFeatures[, "assay"] %in% c(names(measurements), "clinical")))

-    stop("Some assay names in first column of 'useFeatures' are not assay names in 'measurements' or \"clinical\".")

-  clinicalColumnsDataset <- colnames(MultiAssayExperiment::colData(measurements))

-  if("clinical" %in% useFeatures[, "assay"])

-  {

-    clinicalRows <- useFeatures[, "assay"] == "clinical"      

-    clinicalColumns <- useFeatures[clinicalRows, "feature"]

-    if(length(clinicalColumns) == 1 && clinicalColumns == "all")

-      clinicalColumns <- setdiff(clinicalColumnsDataset, outcomeColumns)

-    useFeatures <- useFeatures[!clinicalRows, ]

-  } else {

-    clinicalColumns <- NULL

-  }

-  

-  if(nrow(useFeatures) > 0)

-  {

-    measurements <- measurements[, , unique(useFeatures[, "assay"])]

-    # Get all desired measurements tables and clinical columns (other than the columns representing outcome).

-    # These form the independent variables to be used for making predictions with.

-    # Variable names will have names like RNA_BRAF for traceability.

-    dataTable <- MultiAssayExperiment::wideFormat(measurements, colDataCols = union(clinicalColumns, outcomeColumns))

-    rownames(dataTable) <- dataTable[, "primary"]

-    S4Vectors::mcols(dataTable)[, "sourceName"] <- gsub("colDataCols", "clinical", S4Vectors::mcols(dataTable)[, "sourceName"])

-    colnames(S4Vectors::mcols(dataTable))[1] <- "assay"

+  # Get all desired measurements tables and clinical columns.

+  # These form the independent variables to be used for making predictions with.

+  # Variable names will have names like RNA_BRAF for traceability.

+  dataTable <- MultiAssayExperiment::wideFormat(measurements, colDataCols = union(clinicalPredictors, outcomeColumns))

+  rownames(dataTable) <- dataTable[, "primary"]

+  S4Vectors::mcols(dataTable)[, "sourceName"] <- gsub("colDataCols", "clinical", S4Vectors::mcols(dataTable)[, "sourceName"])

+  colnames(S4Vectors::mcols(dataTable))[1] <- "assay"

-    # Sample information variable names not included in column metadata of wide table but only as row names of it.

-    # Create a combined column named "feature" which has feature names of the assays as well as the clinical.

-    S4Vectors::mcols(dataTable)[, "feature"] <- as.character(S4Vectors::mcols(dataTable)[, "rowname"])

-    missingIndices <- is.na(S4Vectors::mcols(dataTable)[, "feature"])

-    S4Vectors::mcols(dataTable)[missingIndices, "feature"] <- colnames(dataTable)[missingIndices]

+  # Sample information variable names not included in column metadata of wide table but only as row names of it.

+  # Create a combined column named "feature" which has feature names of the assays as well as the clinical.

+  S4Vectors::mcols(dataTable)[, "feature"] <- as.character(S4Vectors::mcols(dataTable)[, "rowname"])

+  missingIndices <- is.na(S4Vectors::mcols(dataTable)[, "feature"])

+  S4Vectors::mcols(dataTable)[missingIndices, "feature"] <- colnames(dataTable)[missingIndices]

-    # Finally, a column annotation recording variable name and which table it originated from for all of the source tables.

-    S4Vectors::mcols(dataTable) <- S4Vectors::mcols(dataTable)[, c("assay", "feature")]

+  # Finally, a column annotation recording variable name and which table it originated from for all of the source tables.

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

-    # Subset to only the desired features.

-    useFeaturesSubset <- useFeatures[useFeatures[, "feature"] != "all", ]

-    if(nrow(useFeaturesSubset) > 0)

-    {

-      uniqueAssays <- unique(useFeatures[, "assay"])

-      for(filterAssay in uniqueAssays)

-      {

-        dropFeatures <- S4Vectors::mcols(dataTable)[, "assay"] == filterAssay &

-                        !S4Vectors::mcols(dataTable)[, "feature"] %in% useFeatures[useFeatures[, 1] == filterAssay, 2]

-        dataTable <- dataTable[, !dropFeatures]

-      }

-    }

-    dataTable <- dataTable[, -match("primary", colnames(dataTable))]

-  } else { # Must have only been clinical data.

-    dataTable <- MultiAssayExperiment::colData(measurements)

-    S4Vectors::mcols(dataTable) <- DataFrame(assay = "clinical", feature = colnames(dataTable))

-  }

+  # Do other filtering and preparation in DataFrame function.

+  prepareData(dataTable, outcomeColumns, clinicalPredictors = NULL, ...)

+})

+

+#' @rdname prepareData

+#' @export

+setMethod("prepareData", "list",

+  function(measurements, outcome = NULL, clinicalPredictors = NULL, ...)

+{

+  # Check the list is named.

+  if(is.null(names(measurements)))

+    stop("'measurements' must be a named list.")

+

+  # If clinical table is present, features to use must be user-specified.            

+  if("clinical" %in% names(measurements) && is.null(clinicalPredictors))

+    stop("Because one provided table in the list is named \"clinical\", 'clinicalPredictors' must be a vector of informative clinical features (i.e. not sample IDs, sampling dates, etc.) to consider for classification.")

+

+  # Check data type is valid.

+  if(!(all(sapply(measurements, class) %in% c("data.frame", "DataFrame", "matrix"))))

+    stop("assays in the list must be of type data.frame, DataFrame or matrix")

+              

+  # Check same number of samples for all datasets

+  if (!length(unique(sapply(measurements, nrow))) == 1)

+    stop("All datasets must have the same samples.")

+      

+  if("clinical" %in% names(measurements))

+    measurements[["clinical"]] <- measurements[["clinical"]][, clinicalPredictors]

+             

+  allMetadata <- mapply(function(measurementsOne, assayID) {

+                        data.frame(assay = assayID, feature = colnames(measurementsOne))

+                        }, measurements, names(measurements))

+  allMeasurements <- do.call("cbind", measurements)

+  # Different assays e.g. mRNA, protein could have same feature name e.g. BRAF.

+  colnames(allMeasurements) <- paste(allMetadata[, "assay"], allMetadata[, "feature"], sep = '_')

+  allDataFrame <- DataFrame(allMeasurements)

+  S4Vectors::mcols(allMeasurements) <- allMetadata

   # Do other filtering and preparation in DataFrame function.

-  prepareData(dataTable, outcomeColumns, useFeatures = "all", ...)

+  prepareData(dataTable, outcome, clinicalPredictors = NULL, ...)

 })

\ No newline at end of file

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

 \alias{crossValidate,DataFrame-method}

 \alias{crossValidate,MultiAssayExperiment-method,}

 \alias{crossValidate,data.frame-method}

-\alias{crossValidate,MultiAssayExperiment-method}

-\alias{crossValidate,list-method}

+\alias{crossValidate,MultiAssayExperimentOrList-method}

 \alias{train.matrix}

 \alias{train.data.frame}

 \alias{train.DataFrame}

@@ -35,9 +34,10 @@ crossValidate(measurements, outcome, ...)

   extraParams = NULL

 )

-\S4method{crossValidate}{MultiAssayExperiment}(

+\S4method{crossValidate}{MultiAssayExperimentOrList}(

   measurements,

   outcome,

+  clinicalPredictors = NULL,

   nFeatures = 20,

   selectionMethod = "auto",

   selectionOptimisation = "Resubstitution",

@@ -86,23 +86,6 @@ crossValidate(measurements, outcome, ...)

   extraParams = NULL

 )

-\S4method{crossValidate}{list}(

-  measurements,

-  outcome,

-  nFeatures = 20,

-  selectionMethod = "auto",

-  selectionOptimisation = "Resubstitution",

-  performanceType = "auto",

-  classifier = "auto",

-  multiViewMethod = "none",

-  assayCombinations = "all",

-  nFolds = 5,

-  nRepeats = 20,

-  nCores = 1,

-  characteristicsLabel = NULL,

-  extraParams = NULL

-)

-

 \method{train}{matrix}(x, outcomeTrain, ...)

 \method{train}{data.frame}(x, outcomeTrain, ...)

@@ -122,7 +105,7 @@ crossValidate(measurements, outcome, ...)

 \method{train}{list}(x, outcomeTrain, ...)

-\method{train}{MultiAssayExperiment}(x, outcome, ...)

+\method{train}{MultiAssayExperiment}(x, outcome, clinicalPredictors = NULL, ...)

 \method{predict}{trainedByClassifyR}(object, newData, ...)

 }

@@ -146,7 +129,8 @@ Set to NULL or "all" if all features should be used.}

 \item{selectionMethod}{Default: \code{"auto"}. A character vector of feature selection methods to compare. If a named character vector with names corresponding to different assays, 

 and performing multiview classification, the respective selection methods will be used on each assay. If \code{"auto"}, t-test (two categories) / F-test (three or more categories) ranking

-and top \code{nFeatures} optimisation is done. Otherwise, the ranking method is per-feature Cox proportional hazards p-value.}

+and top \code{nFeatures} optimisation is done. Otherwise, the ranking method is per-feature Cox proportional hazards p-value. \code{NULL} is also a valid value, meaning that no

+indepedent feature selection will be performed (but implicit selection might still happen with the classifier).}

 \item{selectionOptimisation}{A character of "Resubstitution", "Nested CV" or "none" specifying the approach used to optimise \code{nFeatures}.}

@@ -172,7 +156,11 @@ with each element being a vector of assays to combine. Special value \code{"all"

 \item{extraParams}{A list of parameters that will be used to overwrite default settings of transformation, selection, or model-building functions or

 parameters which will be passed into the data cleaning function. The names of the list must be one of \code{"prepare"},

 \code{"select"}, \code{"train"}, \code{"predict"}. To remove one of the defaults (see the article titled Parameter Tuning Presets for crossValidate and Their Customisation on

-the website), specify the list element to be \code{NULL}.}

+the website), specify the list element to be \code{NULL}. For the valid element names in the \code{"prepare"} list, see \code{?prepareData}.}

+

+\item{clinicalPredictors}{If \code{measurements} is a \code{MultiAssayExperiment},

+a character vector of features to use in modelling. This allows avoidance of things like sample IDs,

+sample acquisition dates, etc. which are not relevant for outcome prediction.}

 \item{x}{Same as \code{measurements} but only training samples.}

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

 \alias{prepareData,DataFrame-method}

 \alias{prepareData,MultiAssayExperiment-method}

 \alias{prepareData,data.frame-method}

+\alias{prepareData,list-method}

 \title{Convert Different Data Classes into DataFrame and Filter Features}

 \usage{

 \S4method{prepareData}{matrix}(measurements, outcome, ...)

@@ -15,12 +16,19 @@

 \S4method{prepareData}{DataFrame}(

   measurements,

   outcome,

-  useFeatures = "all",

+  clinicalPredictors = NULL,

   maxMissingProp = 0,

   topNvariance = NULL

 )

-\S4method{prepareData}{MultiAssayExperiment}(measurements, outcomeColumns = NULL, useFeatures = "all", ...)

+\S4method{prepareData}{MultiAssayExperiment}(

+  measurements,

+  outcomeColumns = NULL,

+  clinicalPredictors = NULL,

+  ...

+)

+

+\S4method{prepareData}{list}(measurements, outcome = NULL, clinicalPredictors = NULL, ...)

 }

 \arguments{

 \item{measurements}{Either a \code{\link{matrix}}, \code{\link{DataFrame}}

@@ -37,17 +45,15 @@ a character string, or vector of such strings, containing column name(s) of colu

 containing either classes or time and event information about survival. If column names

 of survival information, time must be in first column and event status in the second.}

-\item{useFeatures}{If \code{measurements} is a \code{MultiAssayExperiment},

-a two-column table of features to use. The first column must have assay names

-and the second column must have feature names found for that assay. \code{"clinical"} is

-also a valid assay name and refers to the clinical data table. \code{"all"} is a special

-keyword that means all features (passing any other filters) of that assay will be used 

-for modelling. Otherwise, a character vector of feature names to use suffices.}

+\item{clinicalPredictors}{If \code{measurements} is a \code{MultiAssayExperiment},

+a character vector of features to use in modelling. This allows avoidance of things like sample IDs,

+sample acquisition dates, etc. which are not relevant for outcome prediction.}

 \item{maxMissingProp}{Default: 0.0. A proportion less than 1 which is the maximum

 tolerated proportion of missingness for a feature to be retained for modelling.}

-\item{topNvariance}{Default: NULL. An integer number of most variable features to subset to.}

+\item{topNvariance}{Default: NULL. An integer number of most variable features per assay to subset to.

+Assays with less features won't be reduced in size.}

 \item{outcomeColumns}{If \code{measurements} is a \code{MultiAssayExperiment}, the

 names of the column (class) or columns (survival) in the table extracted by \code{colData(data)}