get_best_wbound: Get the Best Tunning Parameter

In korkutlab/reflect: REcurrent Features LEveraged for Combination Therapy

Description

This employs a permutation approach to select the tuning parameter, which controls sparsity of features through L1 regularization. Note this calculation may take a long time.

Usage

get_best_wbound(
  mat_value,
  dissimilarity = c("squared.distance", "absolute.value"),
  wbounds = NULL,
  nperms = 10,
  min_number_features = 10
)

Arguments

mat_value	A matrix of expression/alteration with samples as rows and features as columns.
dissimilarity	A string for the type of dissimilarity, either "squared.distance" or "absolute.value". Default "squared.distance".
wbounds	The sequence of tuning parameters to consider. If NULL, then a default sequence seq(1.1, sqrt(ncol(mat_value)), 100) will be used. If non-null, should be greater than 1.
nperms	The number of permutations to perform. Default 10.
min_number_features	The minimal number of features that the best wbound could generate. Only wbounds that generates more than this number of features can considered. Default 10.

Value

df_gapstat	A data frame that contains columns: Wbound, NumberFeatures, GapStat, SD.
best_wbound	The best tunning parameter whose gap statistic is within one-standard-error to the left of the maximum gap statistic.

Examples

library(reflect)
mat_value <- egfr_data$mat_value
gapstat_bestwbound <- get_best_wbound(mat_value)
gapstat_bestwbound$best_wbound

korkutlab/reflect documentation built on July 5, 2021, 7:38 a.m.