pairwise.stability: Pairwise Stability Metrics

In cdeterman/OmicsMarkeR: Classification and Feature Selection for 'Omics' Datasets

Description

Conducts all pairwise comparisons of features selected following bootstrapping. Also known as the data perturbation ensemble approach.

Usage

pairwise.stability(features, stability.metric, nc)

Arguments

features	A matrix of selected features
stability.metric	string indicating the type of stability metric.
nc	Optional argument to be used with 'kuncheva' stability. Refers to the number of variables in original data. Available options are "jaccard" (Jaccard Index/Tanimoto Distance), "sorensen" (Dice-Sorensen's Index), "ochiai" (Ochiai's Index), "pof" (Percent of Overlapping Features), "kuncheva" (Kuncheva's Stability Measures), "spearman" (Spearman Rank Correlation), and "canberra" (Canberra Distance) @param nc Number of variables in original dataset

Value

A list is returned containing:

comparisons	Matrix of pairwise comparisons
overall	The average of all pairwise comparisons

Author(s)

Charles Determan Jr

References

He. Z. & Weichuan Y. (2010) Stable feature selection for biomarker discovery. Computational Biology and Chemistry 34 215-225.

Examples

# pairwise.stability demo

# For demonstration purposes only!!!
some.numbers <- seq(20)

# matrix of Metabolites identified (e.g. 5 trials)
features <- 
    replicate(5, paste("Metabolite", sample(some.numbers, 10), sep="_"))

# nc may be omitted unless using kuncheva
pairwise.stability(features, "jaccard")

cdeterman/OmicsMarkeR documentation built on May 13, 2019, 2:35 p.m.