R/analysis.R
get_synergy_subset_stats.Rd
Use this function to find for each possible subset of drug combinations out of a given list of synergies, the number of models that predicted it given the models' predictions. So, if for example the set of synergies is this one: {'A-B','C-D','E-F'}, we want to know how many models predicted none of them, just the single subsets (e.g. the {'A-B'}), the two-element subsets (e.g. the {'A-B','C-D'}) and all 3 of them.
get_synergy_subset_stats(model.predictions, synergies)
model.predictions | a |
---|---|
synergies | a character vector with elements the synergistic drug
combinations. Note that these synergies should be a subset of the column
names of the |
an integer vector with elements the number of models the predicted each synergy subset. The names attribute has the names of each synergistic drug combination subset, which are the drug combinations comma separated (e.g. 'A-B,C-D').
Note that if the synergies
vector has more than 10-15 elements, then
this function might take long time to execute even with an optimal
implementation of count_models_that_predict_synergies
.