R/diff.R
get_avg_activity_diff_based_on_specific_synergy_prediction.Rd
Given a specific drug combination, this function splits the models to
good (those that predicted that particular combination, i.e. found it
as synergistic - a value of 1 in the model.predictions
) and
bad (those that found it as non-synergistic - a value of 0 in the
model.predictions
). The models whose predicted value for that synergy is marked as
NA are excluded from the analysis. Then, for each network node, the
function finds the node's average activity in each of the two model groups (a
value in the [0,1] interval) and then subtracts the bad group's average
activity value from the good one, taking into account the given penalty
factor and the number of models in each respective model group.
get_avg_activity_diff_based_on_specific_synergy_prediction( model.predictions, models.stable.state, drug.comb, penalty = 0 )
model.predictions | a |
---|---|
models.stable.state | a |
drug.comb | string. The drug combination which will be used to split
the models. It must be included in the column names of the |
penalty | value between 0 and 1 (inclusive). A value of 0 means no penalty and a value of 1 is the strickest possible penalty. Default value is 0. This penalty is used as part of a weighted term to the difference in a value of interest (e.g. activity or link operator difference) between two group of models, to account for the difference in the number of models from each respective model group. |
a numeric vector with values in the [-1,1] interval (minimum and maximum possible average difference) and with the names attribute representing the name of the nodes.
So, if a node has a value close to -1 it means that on average, this node is more inhibited in the models that predicted the specific drug combination given, whereas a value closer to 1 means that the node is more activated in these models. A value closer to 0 indicates that the activity of that node is not so much different between the models that predicted the synergy and those that did not and so it won't not be a node of interest when searching for synergy biomarkers - nodes whose activity is important for the manifestation of the synergy.
Other average data difference functions:
get_avg_activity_diff_based_on_mcc_clustering()
,
get_avg_activity_diff_based_on_synergy_set_cmp()
,
get_avg_activity_diff_based_on_tp_predictions()
,
get_avg_activity_diff_mat_based_on_mcc_clustering()
,
get_avg_activity_diff_mat_based_on_specific_synergy_prediction()
,
get_avg_activity_diff_mat_based_on_tp_predictions()
,
get_avg_link_operator_diff_based_on_synergy_set_cmp()
,
get_avg_link_operator_diff_mat_based_on_mcc_clustering()
,
get_avg_link_operator_diff_mat_based_on_specific_synergy_prediction()
,
get_avg_link_operator_diff_mat_based_on_tp_predictions()