Computing Gap statistics to identify the optimal number of subtypes

Description

Compute Gap statistics to identify the optimal number of subtypes

Usage

compGapStats(ge.CRC, ntops=c(2, 4, 8, 12, 16, 20)*1000, K.max=6, nboot=100)
figGAP(gapsmat, gapsSE)

Arguments

Details

GAP statistic is a popular method to estimate the number of clusters in a set of data by comparing the change in observed and expected within-cluster dispersion. To identify the optimal number of clusters, GAP statistic can be computed for k=1 to K.max with nboot bootstraps for ntops top variable genes in the AMC data set.

The function figGAP is designed to visualize GAP curves.

Value

This function will return a list including gapsmat (a numeric matrix of GAP statistics) and gapsSE (standard errors of means of the GAP statistics).

Author(s)

Xin Wang xw264@cam.ac.uk

References

De Sousa E Melo, F. and Wang, X. and Jansen, M. et al. Poor prognosis colon cancer is defined by a molecularly distinct subtype and precursor lesion. accepted

Tibshirani, Robert andWalther, Guenther and Hastie, Trevor (2001). Estimating the number of clusters in a data set via the gap statistic. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 63(2), 411-423.

Examples

data(ge.CRC, package="DeSousa2013")
ge.CRC <- ge.all[selPbs, ]
gaps <- compGapStats(ge.CRC, ntops=c(2, 4)*1000, K.max=6, nboot=10)
figGAP(gaps$gapsmat, gaps$gapsSE)

Results

R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> library(DeSousa2013)

> png(filename="/home/ddbj/snapshot/RGM3/R_BC/result/DeSousa2013/compGapStats.Rd_%03d_medium.png", width=480, height=480)
> ### Name: compGapStats
> ### Title: Computing Gap statistics to identify the optimal number of
> ###   subtypes
> ### Aliases: compGapStats figGAP
> 
> ### ** Examples
> 
> data(ge.CRC, package="DeSousa2013")
> ge.CRC <- ge.all[selPbs, ]
> gaps <- compGapStats(ge.CRC, ntops=c(2, 4)*1000, K.max=6, nboot=10)
> figGAP(gaps$gapsmat, gaps$gapsSE)
> 
> 
> 
> 
> 
> dev.off()
null device 
          1 
>