R/clanc.predict.R

In yilinwu123/precision1: PaiREd miCrorna sImulation on Study desIgn for mOlecular classificatioN

#' Prediction with Classification to Nearest Centroids classifier
#'
#' Predict from a Classification to Nearest Centroids classifier fit.
#'
#' @references Alan R. Dabney, Author Notes.(2005) ClaNC: point-and-click software for classifying microarrays to nearest centroids,
#' https://academic.oup.com/bioinformatics/article/22/1/122/219377
#' @param clanc.intcv.model a Classification to Nearest Centroids classifier built with \code{clanc.intcv}.
#' @param pred.obj dataset to have its sample group predicted.
#' The dataset must have rows as probes and columns as samples.
#' It must have an equal number of probes as the dataset being trained.
#' @param pred.obj.group.id a vector of sample-group labels for each sample of the dataset to be predicted.
#' It must have an equal length to the number of samples as \code{pred.obj}.
#' @return a list of 3 elements:
#' \item{pred}{predicted sample group for each sample}
#' \item{mc}{a predicted misclassification error rate (external validation)}
#' \item{prob}{predicted probability for each sample}
#' @export
#' @keywords classification
#' @examples
#' set.seed(101)
#' biological.effect <- estimate.biological.effect(uhdata = uhdata.pl)
#' ctrl.genes <- unique(rownames(uhdata.pl))[grep("NC", unique(rownames(uhdata.pl)))]
#' biological.effect.nc <- biological.effect[!rownames(biological.effect) %in% ctrl.genes, ]
#' group.id <- substr(colnames(biological.effect.nc), 7, 7)
#'
#' biological.effect.train.ind <- colnames(biological.effect.nc)[c(sample(which(group.id == "E"), size = 64),
#'                                           sample(which(group.id == "V"), size = 64))]
#' biological.effect.test.ind <- colnames(biological.effect.nc)[!colnames(biological.effect.nc) %in% biological.effect.train.ind]
#'
#' biological.effect.nc.tr <- biological.effect.nc[, biological.effect.train.ind]
#' biological.effect.nc.te <- biological.effect.nc[, biological.effect.test.ind]
#'
#' clanc.int <- clanc.intcv(X = biological.effect.nc.tr,
#'                          y = substr(colnames(biological.effect.nc.tr), 7, 7),
#'                         kfold = 5, seed = 1)
#'
#' clanc.pred <- clanc.predict(clanc.intcv.model = clanc.int,
#'                            pred.obj = biological.effect.nc.te,
#'                            pred.obj.group.id = substr(colnames(biological.effect.nc.te), 7, 7))
#' clanc.int$mc
#' clanc.pred$mc
#'
#'


"clanc.predict" <- function(clanc.intcv.model, pred.obj, pred.obj.group.id){
  
  gene_names = rownames(pred.obj)
  pred <- predictClanc(pred.obj, gene_names, clanc.intcv.model$model)
  pred_class <- ifelse(pred == "1", "E", "V")
  mc <- tabulate.ext.err.func(pred_class, pred.obj.group.id)
  
  return(list(pred=pred_class, mc=mc))
}