GSgalgoR main function

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,
distancetype = "pearson", TournamentSize = 2, period = 1825,
OS, prob_matrix, res_dir = "", start_galgo_callback = callback_default,
end_galgo_callback = callback_base_return_pop,
report_callback = callback_base_report,
start_gen_callback = callback_default,
end_gen_callback = callback_default,
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
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
start_galgo_callback	optional callback function for the start of the galgo execution
end_galgo_callback	optional callback function for the end of the galgo execution
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 to_list and to_dataframe functions

Examples

# load example dataset
library(breastCancerTRANSBIG)
data(transbig)
Train <- transbig
rm(transbig)
#> Warning: object 'transbig' not found

expression <- Biobase::exprs(Train)
clinical <- Biobase::pData(Train)
OS <- survival::Surv(time = clinical$t.rfs, event = clinical$e.rfs)

# We will use a reduced dataset for the example
expression <- expression[sample(seq_len(nrow(expression)), 100), ]

# Now we scale the expression matrix
expression <- t(scale(t(expression)))

# Run galgo
output <- GSgalgoR::galgo(generations = 5, population = 15,
prob_matrix = expression, OS = OS)
#> Using CPU for computing pearson distance
#> Generation 1 Non-dominated solutions:
#>           k                      rnkIndex    CrowD
#> result.3  2 0.14882360  69.46322        1      Inf
#> result.4  9 0.00656122 264.62890        1      Inf
#> result.10 4 0.07773017 192.97399        1 1.695167
#> Generation 2 Non-dominated solutions:
#>           k                      rnkIndex    CrowD
#> result.3  2 0.14882360  69.46322        1      Inf
#> result.1  7 0.02571842 372.07256        1      Inf
#> result.10 4 0.07773017 192.97399        1 1.106057
#> result.13 5 0.03596436 205.87446        1 0.824781
#> Generation 3 Non-dominated solutions:
#>           k                      rnkIndex     CrowD
#> result.3  2 0.14882360  69.46322        1       Inf
#> result.1  7 0.02571842 372.07256        1       Inf
#>           4 0.06304767 212.49021        1 0.8401363
#>           3 0.08357203  77.11589        1 0.8206758
#> result.10 4 0.07773017 192.97399        1 0.5063178
#> Generation 4 Non-dominated solutions:
#>           k                      rnkIndex     CrowD
#> result.3  2 0.14882360  69.46322        1       Inf
#> result.1  7 0.02571842 372.07256        1       Inf
#>           4 0.06304767 212.49021        1 0.8494499
#>           3 0.08357203  77.11589        1 0.8334064
#> result.10 4 0.07773017 192.97399        1 0.5099930
#> Generation 5 Non-dominated solutions:
#>           k                      rnkIndex     CrowD
#> result.1  7 0.02571842 372.07256        1       Inf
#>           2 0.16568616  44.93058        1       Inf
#>           2 0.13112577  85.75740        1 0.6696392
#>           8 0.04581630 287.44268        1 0.6687258
#>           2 0.08329750 164.24513        1 0.6272345
#>           4 0.06304767 212.49021        1 0.4575554
#> result.3  2 0.14882360  69.46322        1 0.3282574
#> result.10 4 0.07773017 192.97399        1 0.2585055
outputDF <- to_dataframe(output)
outputList <- to_list(output)