superpc.train.Rd
Computes feature scores for \(p_{path}\) features of a pathway via a linear model fit.
superpc.train( data, type = c("survival", "regression", "categorical"), s0.perc = NULL )
data | A list of test data:
|
---|---|
type | What model relates |
s0.perc | A stabilization parameter on the interval \([0,1]\). This is
an internal argument to each of the called functions. The default value is
|
A list containing:
feature.scores
: The scaled \(p\)-dimensional score
vector: each value has been divided by its respective standard deviation
plus epsilon (governed by s0.perc
). NA
values returned by
the logistic model are replaced with 0.
type
: The argument for type
.
s0.perc
: The user-supplied value of s0.perc
, or the
internally-calculated default value from the chosen model.
call
: The output of match.call
for the user-
supplied function arguments.
This function is a switch
call to
coxTrain_fun
(for type = "survival"
),
olsTrain_fun
(for type = "regression"
), or
glmTrain_fun
(for type = "categorical"
).
# DO NOT CALL THIS FUNCTION DIRECTLY. # Use SuperPCA_pVals() instead if (FALSE) { data("colon_pathwayCollection") data("colonSurv_df") colon_OmicsSurv <- CreateOmics( assayData_df = colonSurv_df[,-(2:3)], pathwayCollection_ls = colon_pathwayCollection, response = colonSurv_df[, 1:3], respType = "surv" ) asthmaGenes_char <- getTrimPathwayCollection(colon_OmicsSurv)[["KEGG_ASTHMA"]]$IDs data_ls <- list( x = t(getAssay(colon_OmicsSurv))[asthmaGenes_char, ], y = getEventTime(colon_OmicsSurv), censoring.status = getEvent(colon_OmicsSurv), featurenames = asthmaGenes_char ) superpc.train( data = data_ls, type = "surv" ) }