## ----set.up, include=FALSE, echo=FALSE, message=FALSE, warning=FALSE----------
knitr::opts_chunk$set(message=FALSE, collapse = TRUE, comment="")

# R packages
library(SummarizedExperiment)
library(pheatmap)
library(devtools)
load_all()

## ----load.data----------------------------------------------------------------
# Load pre-computed feature set
data(sim_FS)
 
# Load pre-computed input scores
data(sim_Scores)

## ----heatmap------------------------------------------------------------------
mat <- SummarizedExperiment::assay(sim_FS)
pheatmap::pheatmap(mat[1:100, ], color = c("white", "red"), cluster_rows = FALSE, cluster_cols = FALSE)

## ----ks.method----------------------------------------------------------------
ks_topn_l <- CaDrA::candidate_search(
  FS = sim_FS,
  input_score = sim_Scores,
  method = "ks_pval",          # Use Kolmogorow-Smirnow scoring function 
  method_alternative = "less", # Use one-sided hypothesis testing
  weights = NULL,              # If weights is provided, perform a weighted-KS test
  search_method = "both",      # Apply both forward and backward search
  top_N = 3,                   # Evaluate top 3 starting points for the search
  max_size = 10,               # Allow at most 10 features in meta-feature matrix
  do_plot = FALSE,             # We will plot it AFTER finding the best hits
  best_score_only = FALSE      # Return all results from the search
)

# Now we can fetch the feature set of top N features that corresponded to the best scores over the top N search
ks_topn_best_meta <- topn_best(ks_topn_l)

# Visualize best meta-feature result
meta_plot(topn_best_list = ks_topn_best_meta)

## ----wilcox.method------------------------------------------------------------
wilcox_topn_l <- CaDrA::candidate_search(
  FS = sim_FS,
  input_score = sim_Scores,
  method = "wilcox_pval",      # Use Wilcoxon Rank-Sum scoring function
  method_alternative = "less", # Use one-sided hypothesis testing
  search_method = "both",      # Apply both forward and backward search
  top_N = 3,                   # Evaluate top 3 starting points for the search
  max_size = 10,               # Allow at most 10 features in meta-feature matrix
  do_plot = FALSE,             # We will plot it AFTER finding the best hits
  best_score_only = FALSE      # Return all results from the search
)

# Now we can fetch the feature set of top N feature that corresponded to the best scores over the top N search
wilcox_topn_best_meta <- topn_best(topn_list = wilcox_topn_l)

# Visualize best meta-feature result
meta_plot(topn_best_list = wilcox_topn_best_meta)

## ----revealer.method----------------------------------------------------------
revealer_topn_l <- CaDrA::candidate_search(
  FS = sim_FS,
  input_score = sim_Scores,
  method = "revealer",         # Use REVEALER's CMI scoring function
  search_method = "both",      # Apply both forward and backward search
  top_N = 3,                   # Evaluate top 3 starting points for the search
  max_size = 10,               # Allow at most 10 features in meta-feature matrix
  do_plot = FALSE,             # We will plot it AFTER finding the best hits
  best_score_only = FALSE      # Return all results from the search
)

# Now we can fetch the ESet of top feature that corresponded to the best scores over the top N search
revealer_topn_best_meta <- topn_best(topn_list = revealer_topn_l)

# Visualize best meta-feature result
meta_plot(topn_best_list = revealer_topn_best_meta)

## ----custom.method------------------------------------------------------------
# A customized function using ks-test
customized_ks_rowscore <- function(FS, input_score, meta_feature=NULL, alternative="less", metric="pval"){
  
  # Check if meta_feature is provided
  if(!is.null(meta_feature)){
    # Getting the position of the known meta features
    locs <- match(meta_feature, row.names(FS))
    
    # Taking the union across the known meta features
    if(length(meta_feature) > 1) {
      meta_vector <- as.numeric(ifelse(colSums(FS[meta_feature,]) == 0, 0, 1))
    }else{
      meta_vector <- as.numeric(FS[meta_feature,])
    }
    
    # Remove the meta features from the binary feature matrix
    # and taking logical OR btw the remaining features with the meta vector
    FS <- base::sweep(FS[-locs, , drop=FALSE], 2, meta_vector, `|`)*1
    
    # Check if there are any features that are all 1s generated from
    # taking the union between the matrix
    # We cannot compute statistics for such features and thus they need
    # to be filtered out
    if(any(rowSums(FS) == ncol(FS))){
      warning("Features with all 1s generated from taking the matrix union ",
              "will be removed before progressing...\n")
      FS <- FS[rowSums(FS) != ncol(FS), , drop=FALSE]
    }
  }
  
  # KS is a ranked-based method
  # So we need to sort input_score from highest to lowest values
  input_score <- sort(input_score, decreasing=TRUE)
  
  # Re-order the matrix based on the order of input_score
  FS <- FS[, names(input_score), drop=FALSE]  
  
  # Compute the scores using the KS method
  ks <- apply(FS, 1, function(r){ 
    x = input_score[which(r==1)]; 
    y = input_score[which(r==0)];
    res <- ks.test(x, y, alternative=alternative)
    return(c(res$statistic, res$p.value))
  })
  
  # Obtain score statistics
  stat <- ks[1,]
  
  # Obtain p-values and change values of 0 to the machine lowest value 
  # to avoid taking -log(0)
  pval <- ks[2,]
  pval[which(pval == 0)] <- .Machine$double.xmin
  
  # Compute the -log(pval)
  # Make sure scores has names that match the row names of FS object
  pval <- -log(pval)
  
  # Determine which metric to returned the scores
  if(metric == "pval"){
    scores <- pval
  }else{
    scores <- stat
  }
  
  names(scores) <- rownames(FS)
  
  return(scores)
  
}

# Search for best features using a custom-defined function
custom_topn_l <- CaDrA::candidate_search(
  FS = SummarizedExperiment::assay(sim_FS),
  input_score = sim_Scores,
  method = "custom",                        # Use custom scoring function
  custom_function = customized_ks_rowscore, # Use a customized scoring function
  custom_parameters = NULL,                 # Additional parameters to pass to custom_function
  search_method = "both",                   # Apply both forward and backward search
  top_N = 3,                                # Evaluate top 3 starting points for the search
  max_size = 10,                            # Allow at most 10 features in meta-feature matrix
  do_plot = FALSE,                          # We will plot it AFTER finding the best hits
  best_score_only = FALSE                   # Return all results from the search
)

# Now we can fetch the feature set of top N feature that corresponded to the best scores over the top N search
custom_topn_best_meta <- topn_best(topn_list = custom_topn_l)

# Visualize best meta-feature result
meta_plot(topn_best_list = custom_topn_best_meta)

## ----RsessionInfo-------------------------------------------------------------
sessionInfo()