prostate {integrativeME}R Documentation

Prostate cancer data, a subset data set from Stephenson et al. (2005) study

Description

Clinical and a subset of gene expression data from the Stephenson et al. (2005) study.

Usage

data(prostate)

Format

A list containing the following components:

type
vector of lenth 79 indicating the class of the patients (0 = recurrence, 1 = no recurrence).
cont
data matrix with 79 rows and 500 columns. The gene expression of 500 randomly sampled transcripts (for memory allocation reasons, see details).
indep
data matrix with 79 rows and 8 columns. The measurements of 8 clinical variables. The discrete data are suitable for a MElogreg or MEindep model in the mixture of experts methodology.
loc
data matrix with 79 rows and 7 columns. The measurements of 7 clinical variables. The discrete data are suitable for a MEloc model in the mixture of experts methodology.
loc.ind
indicates the location variable.

Details

The data set from Stephenson et al. (2005) was built from tissue samples obtained from 79 patients all treated by radical prostatectomy. There were 37 samples which were classified as recurrent and 42 as non-recurrent primary prostate tumor. Samples were snap frozen and gene expression analysis was carried out using the Affymetrix U133A human gene array which has 22,283 features. After a prefiltering step, the analyzed data set contained 7,884 features. The clinical data and microarray data were measured on the same set of 79 patients.

For the location model, variables 'semi-vesicle invasion' and 'lymph node involvement' were merged into a single categorical variable (called the location variable).

Source

The data set was obtained upon request to the authors of the study. The original data with 7,884 transcripts can be downloaded as an .RData file from http://www.math.univ-toulouse.fr/~lecao/package.html

References

Stephenson, A.J., Smith, A., Kattan, M.W., Satagopan, J., Reuter, V.E., Scardino, P.T. and Gerald, W.L. (2005). Integration of gene expression profiling and clinical variables to predict prostate carcinoma recurrence after radical prostatectomy. Cancer, 104, 2, 290-298.

Hunt, L. and Jorgensen, M. (1999). Mixture model clustering using the MULTIMIX program. Australian & New Zealand Journal of Statistics, 41, 2, 154–171.


[Package integrativeME version 1.1 Index]