ranked_combs: Rank combinations.

In combiroc: Selection and Ranking of Omics Biomarkers Combinations Made Easy

Rank combinations.

Description

A function to rank combinations by a Youden index and select them if they have a min SE and/or SP.

Usage

ranked_combs(combo_table, min_SE = 0, min_SP = 0)

Arguments

combo_table	a data.frame with SE, SP and number of composing markers for each combination (returned by se_sp()).
min_SE	a numeric that specifies the min value of SE that a combination must have to be filtered-in.
min_SP	a numeric that specifies the min value of SP that a combination must have to be filtered-in.

Details

This function is meant to help the user in finding the best combinations (in the first rows) and allows also (not mandatory) the SE/SP-dependent filtering of combinations.

Value

a named list containing:

• $table, a data.frame with ranked combination, reporting: SE, SP, number of markers composing the combination and the score.

• $bubble_chart, a dot plot showing the selected 'gold' combinations

Examples

## Not run: 
demo_data # combiroc built-in demo data (proteomics data from Zingaretti et al. 2012 - PMC3518104)

combs <- combi(data= demo_data, signalthr=450, combithr=1, case_class='A')  # compute combinations
                                                                  # compute SE and SP
                                                               # of each combination



# To rank combinations by Youden index and filter-out the ones with SE < min_SE and SP < min_SP

rc <- ranked_combs(combo_table= combs, min_SE=40, min_SP=80)
rc$table # to visualize the selected gold combinations through a data.frame
rc$bubble_chart # to visualize the selected gold combinations through a data.frame

## End(Not run)

combiroc documentation built on July 9, 2023, 5:56 p.m.