subsampleAnalysis: Assesses the stability of groups by subsampling

In cbg-ethz/TiMEx: Finding Mutually Exclusive Groups of Alterations in Cancer Datasets

Description

subsampleAnalysis subsamples the set of patients and assess the stability of the identified mutually exclusive groups.

Usage

subsampleAnalysis(subsampl, noReps, signifGroups)

Arguments

subsampl	a vector with subsampling frequencies
noReps	number of repetitions of subsampling. Default is 100.
signifGroups	result structure with the significant groups, as returned by either TiMEx or findSignifCliques

Details

As this function runs TiMEx many times sequentially, it is computationally very intensive. For a version of this function which can be directly ran on a cluster, please contact me (see e-mail below).

For example, after loading data(ovarianOutput) and running

counts<-subsampleAnalysis(subsampl=c(0.3,0.5,0.8), signifGroups=signifGroups)

counts[[1]][[3]] will represent the relative counts of the identified mutually exclusive groups of size 3 for a subsampling frequency of 30%, for both fdr and bonf (bonferroni) multiple correction methods.

Value

list with as many elements as subsampling frequencies provided. Each element is further a list with as many elemenets as number of sizes of the significantly mutually exclusive groups identified. Aditionally, bonf and fdr are two lists corresponding to each of these elements, representing different multiple correction methods. Finally, each element is a vector of subsampling frequencies of the significantly mutually exclusive groups identified. For an example, see Details above.

Author(s)

Simona Cristea, [e-mail]

References

Constantinescu et al.: TiMEx: A Waiting Time Model for Mutually Exclusive Cancer Alterations. Bioinformatics (2015).

See Also

the wrapper function TiMEx for identifying mutually exclusive groups in a binary dataset with the TiMEx model, ovarianSubsampling, breastSubsampling, gbmDendrixSubsampling, and gbmMuexSubsampling for examples of outputs after performing the subsampling analysis.

Examples

# running this function is time-intensive
data(ovarianOutput)
## Not run: subsampleOvarian<-subsampleAnalysis(c(0.3,0.5,0.8),ovarianOutput)

cbg-ethz/TiMEx documentation built on May 13, 2019, 1:50 p.m.