predict_model {ttgsea}

R Documentation

Model prediction

Description

From the result of the function "ttgsea", we can predict enrichment scores. For each new term, lemmatized text, predicted enrichment score, Monte Carlo p-value and adjusted p-value are provided. The function "token_vector" is used for encoding as we did for training. Of course, mapping from tokens to integers should be the same.

Usage

predict_model(object, new_text, num_simulations = 1000,
              adj_p_method = "fdr")

Arguments

object	result of "ttgsea"
new_text	new text data
num_simulations	number of simulations for Monte Carlo p-value (default: 1000)
adj_p_method	correction method (default: "fdr")

Value

table for lemmatized text, predicted enrichment score, MC p-value and adjusted p-value

Author(s)

Dongmin Jung

See Also

stats::p.adjust

Examples

library(reticulate)
if (keras::is_keras_available() & reticulate::py_available()) {
  library(fgsea)
  data(examplePathways)
  data(exampleRanks)
  names(examplePathways) <- gsub("_", " ",
                            substr(names(examplePathways), 9, 1000))
  set.seed(1)
  fgseaRes <- fgsea(examplePathways, exampleRanks)
  
  num_tokens <- 1000
  length_seq <- 30
  batch_size <- 32
  embedding_dims <- 50
  num_units <- 32
  epochs <- 1
  
  ttgseaRes <- fit_model(fgseaRes, "pathway", "NES",
                         model = bi_gru(num_tokens,
                                        embedding_dims,
                                        length_seq,
                                        num_units),
                         num_tokens = num_tokens,
                         length_seq = length_seq,
                         epochs = epochs,
                         batch_size = batch_size,
                         use_generator = FALSE)
  
  set.seed(1)
  predict_model(ttgseaRes, "Cell Cycle")
}

---