lung73 {scaleboot}

Clustering of 73 Lung Tumors

Description

Bootstrapping hierarchical clustering of the DNA microarray data set of 73 lung tissue samples each containing 916 observed genes.

Usage

data(lung73)

Format

lung73.pvclust and lung.pvclust are objects of class "pvclust" defined in pvclust of Suzuki and Shimodaira (2006).

lung73.sb and lung.sb are an object of class "scalebootv" of length 72.

Details

The microarray dataset of Garber et al. (2001) is reanalyzed in Suzuki and Shimodaira (2006), and is found in data(lung) of the pvclust package. We reanalyze it, again, by the script shown in Examples. The result of pvclust is stored in lung73.pvclust and lung.pvclust, and model fitting to bootstrap probabilities by the scaleboot package is stored in lung73.sb and lung.sb. A wide scale range is used in lung73.pvclust and lung73.sb, and the default scale range of pvclust is used in lung.pvclust and lung.sb. The microarray dataset is not included in data(lung73), but it is found in data(lung) of the pvclust package.

Source

Garber, M. E. et al. (2001) Diversity of gene expression in adenocarcinoma of the lung, Proceedings of the National Academy of Sciences, 98, 13784-13789 (dataset is available from http://genome-www.stanford.edu/lung_cancer/adeno/).

References

Suzuki, R. and Shimodaira, H. (2006). pvclust: An R package for hierarchical clustering with p-values, Bioinformatics, 22, 1540-1542 (software is available from CRAN or http://stat.sys.i.kyoto-u.ac.jp/prog/pvclust/).

See Also

sbpvclust, sbfit.pvclust

Examples

## Not run: 
## Parallel setup
library(parallel)
length(cl <- makeCluster(detectCores()))
## script to create lung73.pvclust and lung73.sb
## multiscale bootstrap resampling of hierarchical clustering
library(pvclust)
data(lung)
### default pvclust scales
lung.pvclust <- pvclust(lung, nboot=10000, parallel=cl)
lung.sb <- sbfit(lung.pvclust,cluster=cl) # model fitting
### wider range of scales than pvclust default
sa <- 9^seq(-1,1,length=13) 
lung73.pvclust <- pvclust(lung,r=1/sa,nboot=10000,parallel=cl) 
lung73.sb <- sbfit(lung73.pvclust,cluster=cl) # model fitting

## End(Not run)

## replace si/au/bp entries in pvclust object
library(pvclust)
data(lung73) # loading the previously computed bootstrap

### the original pvclust result
plot(lung.pvclust, print.pv = c("si", "au", "bp"), cex=0.5, cex.pv=0.5)
pvrect(lung.pvclust, pv="si") #  (defualt pvclust uses pv="au")

### default pvclust scales with p-values of k=2
lung.k2 <- sbpvclust(lung73.pvclust,lung73.sb, k=2)
plot(lung.k2, print.pv = c("si", "au", "bp"), cex=0.5, cex.pv=0.5)
pvrect(lung.k2, pv="si")

### wider scales with p-values of k=3 (default of scaleboot)
lung73.k3 <- sbpvclust(lung73.pvclust,lung73.sb)
plot(lung73.k3, print.pv = c("si", "au", "bp"), cex=0.5, cex.pv=0.5)
pvrect(lung73.k3, pv="si")

## diagnostics of fitting

### diagnose edges 61,...,69
lung73.sb[61:69] # print fitting details
plot(lung73.sb[61:69]) # plot curve fitting
summary(lung73.sb[61:69]) # print raw(=bp)/si/au p-values

### diagnose edge 67
lung73.sb[[67]] # print fitting
plot(lung73.sb[[67]],legend="topleft") # plot curve fitting
summary(lung73.sb[[67]]) # print au p-values