ks_topn_l <- CaDrA::candidate_search(
  FS = sim_FS,
  input_score = sim_Scores,
  method = "ks_pval",          # Use Kolmogorov-Smirnov 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_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_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)

knnmi_topn_l <- CaDrA::candidate_search(
  FS = sim_FS,
  input_score = sim_Scores,
  method = "knnmi",            # Use knnmi 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
knnmi_topn_best_meta <- topn_best(topn_list = knnmi_topn_l)

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

corr_topn_l <- CaDrA::candidate_search(
  FS = SummarizedExperiment::assay(sim_FS),
  input_score = sim_Scores,
  method = "correlation",      # Use correlation scoring function
  cmethod = "spearman",        # Use spearman correlation scoring function
  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
corr_topn_best_meta <- topn_best(topn_list = corr_topn_l)

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

# A customized function using ks-test
customized_ks_rowscore <- function(FS, input_score, weights=NULL, meta_feature=NULL, alternative="less", metric="pval"){
  
 metric <- match.arg(metric)
  alternative <- match.arg(alternative)
  
  # 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(locs) > 1) {
      meta_vector <- as.numeric(ifelse(colSums(FS[locs,]) == 0, 0, 1))
    }else{
      meta_vector <- as.numeric(FS[locs, , drop=FALSE])
    }
    
    # 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))){
      verbose("Features with all 1s generated from taking the matrix union ",
              "will be removed before progressing...\n")
      FS <- FS[rowSums(FS) != ncol(FS), , drop=FALSE]
      # If no features remained after filtering, exist the function
      if(nrow(FS) == 0) return(NULL)
    }
  }
    
  # 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]  
  
  # Check if weights is provided
  if(length(weights) > 0){
    # Check if weights has any labels or names
    if(is.null(names(weights)))
      stop("The weights object must have names or labels that ",
           "match the labels of input_score\n")

    # Make sure its labels or names match the
    # the labels of input_score 
    weights <- as.numeric(weights[names(input_score)])
  }

  # Get the alternative hypothesis testing method
  alt_int <- switch(alternative, two.sided=0L, less=1L, greater=-1L, 1L)

  # Compute the ks statistic and p-value per row in the matrix
  ks <- .Call(ks_genescore_mat_, FS, weights, alt_int)

  # Obtain score statistics from KS method
  # Change values of 0 to the machine lowest value to avoid taking -log(0)
  stat <- ks[1,]

  # Obtain p-values from KS method
  # 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 scores according to the provided metric
  scores <- ifelse(rep(metric, nrow(FS)) %in% "pval", -log(pval), 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
  weights = NULL,                           # If weights is provided, perform a weighted 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 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
CaDrA::meta_plot(topn_best_list = custom_topn_best_meta)

# Evaluate results across top N features you started from
CaDrA::topn_plot(custom_topn_l) 

topn_res <- CaDrA::candidate_search(
  FS = sim_FS,
  input_score = sim_Scores,
  method = "ks_pval",          # Use Kolmogorov-Smirnov 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 7 starting points for each search
  max_size = 10,               # Maximum size a meta-feature matrix can extend to
  do_plot = FALSE,             # Plot after finding the best features
  best_score_only = FALSE      # Return all results from the search
)

## Fetch the meta-feature set corresponding to its best scores over top N features searches
topn_best_meta <- topn_best(topn_res)

# Visualize the best results with the meta-feature plot
meta_plot(topn_best_list = topn_best_meta)

# Evaluate results across top N features you started from
topn_plot(topn_res)