In RC-88/CaDrA: Candidate Driver Analysis

knitr::opts_chunk$set(message=FALSE, collapse = TRUE, comment="")
library(SummarizedExperiment)
library(CaDrA)

The CaDrA package currently provides four scoring functions to search for subsets of genomic features that are likely associated with a specific outcome of interest (e.g., protein expression, pathway activity, etc.)

1. Kolmogorov-Smirnov Method (ks)
2. Conditional Mutual Information Method (revealer)
3. Wilcoxon Rank-Sum Method (wilcox)
4. Custom - An User's Provided Scoring Function (custom)

Below, we run candidate_search() over the top 3 starting features using each of the four scoring functions described above.

Important Note:

• The legacy function topn_eval() is equivalent to the recommended candidate_search() function

Load packages

library(CaDrA)

Load required datasets

1. A binary features matrix also known as Feature Set (such as somatic mutations, copy number alterations, chromosomal translocations, etc.) The 1/0 row vectors indicate the presence/absence of ‘omics’ features in the samples. The Feature Set must be an object of class SummarizedExperiment from SummarizedExperiment package)
2. A vector of continuous scores (or input_score) representing a functional response of interest (such as protein expression, pathway activity, etc.)

# Load pre-computed feature set
data(sim_FS)

# Load pre-computed input scores
data(sim_Scores)

Kolmogorov-Smirnov scoring method

See ?ks_rowscore for more details

ks_topn_l <- CaDrA::candidate_search(
  FS = sim_FS,
  input_score = sim_Scores,
  method = "ks_pval",          # Use Kolmogorow-Smirnow scoring function 
  weight = NULL,               # If weight is provided, perform a weighted-KS test
  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 = 7,                # Allow at most 7 features in meta-feature matrix
  do_plot = FALSE,             # We will plot it AFTER finding the best hits
  best_score_only = FALSE      # Return meta-feature, its observed input scores and corresponding best score
)

# 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)

Wilcoxon Rank-Sum scoring method

See ?wilcox_rowscore for more details

wilcox_topn_l <- CaDrA::candidate_search(
  FS = sim_FS,
  input_score = sim_Scores,
  method = "wilcox_pval",      # Use Wilcoxon Rank-Sum scoring function
  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 = 7,                # Allow at most 7 features in meta-feature matrix
  do_plot = FALSE,             # We will plot it AFTER finding the best hits
  best_score_only = FALSE      # Return meta-feature, its observed input scores and corresponding best score
)

# 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)

Conditional Mutual Information scoring method

See ?revealer_rowscore for more details

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 = 7,                # Allow at most 7 features in meta-feature matrix
  do_plot = FALSE,             # We will plot it AFTER finding the best hits
  best_score_only = FALSE      # Return meta-feature, its observed input scores and corresponding best score
)

# 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 - An user's provided scoring method

See ?custom_rowscore for more details

# A customized function using ks-test function
customized_rowscore <- function(FS_mat, input_score, alternative){

  ks <- apply(FS_mat, 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 and p-values from KS method
  stat <- ks[1,]
  pval <- ks[2,]

  # Compute the -log scores for pval
  scores <- -log(pval)
  names(scores) <- rownames(FS_mat)

  # Re-order FS in a decreasing order (from most to least significant)
  # This comes in handy when doing the top-N evaluation of
  # the top N 'best' features
  scores <- scores[order(scores, decreasing=TRUE)]

  return(scores)

}

# Search for best features using a custom-defined function
custom_topn_l <- CaDrA::candidate_search(
  FS = sim_FS,
  input_score = sim_Scores,
  method = "custom",                                # Use custom scoring function
  custom_function = customized_rowscore,            # Use a customized scoring function
  custom_parameters = list(alternative = "less"),   # 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 = 7,                                     # Allow at most 7 features in meta-feature matrix
  do_plot = FALSE,                                  # We will plot it AFTER finding the best hits
  best_score_only = FALSE                           # Return meta-feature, its observed input scores and corresponding best score
)

# 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)

SessionInfo

sessionInfo()

RC-88/CaDrA documentation built on March 28, 2023, 12:18 a.m.