GalgoR main function — galgo • galgoR

galgo accepts an expression matrix and a survival object to find robust gene expression signatures related to a given outcome

galgo(
  population = 30,
  generations = 2,
  nCV = 5,
  usegpu = FALSE,
  distancetype = "pearson",
  TournamentSize = 2,
  period = 1825,
  OS,
  prob_matrix,
  res_dir = "",
  save_pop_partial_callback = default_callback,
  save_pop_final_callback = base_return_pop_callback,
  report_callback = base_report_callback,
  start_gen_callback = base_start_gen_callback,
  end_gen_callback = base_end_gen_callback,
  verbose = 2
)

Arguments

population	a number indicating the number of solutions in the population of solutions that will be evolved
generations	a number indicating the number of iterations of the galgo algorithm
nCV	number of cross-validation sets
usegpu	`logical` default to `FALSE`, set to `TRUE` if you wish to use gpu computing (`gpuR` package must be properly installed and loaded)
distancetype	character, it can be `'pearson'` (centered pearson), `'uncentered'` (uncentered pearson), `'spearman'` or `'euclidean'`
TournamentSize	a number indicating the size of the tournaments for the selection procedure
period	a number indicating the outcome period to evaluate the RMST
OS	a `survival` object (see `Surv` function from the `survival` package)
prob_matrix	a `matrix` or `data.frame`. Must be an expression matrix with features in rows and samples in columns
res_dir	a `character` string indicating where to save the intermediate and final output of the algorithm
save_pop_partial_callback	optional callback function between iterations
save_pop_final_callback	optional callback function for the last iteration
report_callback	optional callback function
start_gen_callback	optional callback function for the beginning of the run
end_gen_callback	optional callback function for the end of the run
verbose	select the level of information printed during galgo execution

Value

an object of type 'galgo.Obj' that corresponds to a list with the elements $Solutions and $ParetoFront. $Solutions is a $l x (n + 5)$ matrix where $n$ is the number of features evaluated and $l$ is the number of solutions obtained. The submatrix $l x n$ is a binary matrix where each row represents the chromosome of an evolved solution from the solution population, where each feature can be present (1) or absent (0) in the solution. Column $n +1$ represent the $k$ number of clusters for each solutions. Column $n+2$ to $n+5$ shows the SC Fitness and Survival Fitness values, the solution rank, and the crowding distance of the solution in the final pareto front respectively. For easier interpretation of the 'galgo.Obj', the output can be reshaped using the toList and toDataFrame functions

Examples

if (FALSE) {
#Load data
rna_luad <- use_rna_luad()
TCGA_expr <- rna_luad$TCGA$expression_matrix
TCGA_clinic <- rna_luad$TCGA$pheno_data
OS <- survival::Surv(time=TCGA_clinic$time,event=TCGA_clinic$status)

#Run galgo
output <- galgoR::galgo(generations = 10 ,population = 30, prob_matrix = TCGA_expr, OS = OS)
outputDF <- toDataFrame(output)
outputList <- toList(output)
}