golubMerge: Data from the Golub et al (1999) Paper

In CAMAN: Finite Mixture Models and Meta-Analysis Tools - Based on C.A.MAN

Data from the Golub et al (1999) Paper

Description

The data are from Golub et al. These are the combined training samples and test samples. There are 47 patients with acute lymphoblastic leukemia (ALL) and 25 patients with acute myeloid leukemia (AML). The samples were assayed using Affymetrix Hgu6800 chips and data on the expression of 7129 genes (Affymetrix probes) are available. The data were obtained from the Web site listed below and transformed slightly. Two objects are in the workspace when the data is loaded: golubMerge.exprs and sample.labels.

Usage

data("golubMerge")

Format

A matrix with 7129 rows (for the genes) and 72 columns (for the patients).

Note

The data also appear in the Bioconductor package golubEsets in a different format. See Schlattmann (2009) for details on how to handle this type of data.

Source

This data is a variant of the data from the Bioconductor golubEsets package.

References

Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression Monitoring, Science, 531-537, 1999, T. R. Golub and D. K. Slonim and P. Tamayo and C. Huard and M. Gaasenbeek and J. P. Mesirov and H. Coller and M.L. Loh and J. R. Downing and M. A. Caligiuri and C. D. Bloomfield and E. S. Lander

Schlattmann, P. (2009). Medical Applications of Finite Mixture Models. Berlin: Springer.

Examples

## Not run: 
## microarray analysis example
data(golubMerge)
idxALL <- which(sample.labels== "ALL")
idxAML <- which(sample.labels == "AML")
pvals <- apply(golubMerge.exprs, 1, function(x){t.test(x[idxAML],x[idxALL])[[3]]})
zvals <- qnorm(1-pvals)
hist(zvals,100)
### Z-values are gaussian distributed, mix identifies a mixture of gaussians. 
mix <- mixalg(obs=zvals, family="gaussian", startk=25)
hist(mix)

### get False discovery rate (Not-differential expressed genes are in component 1)
getFDR(mix, threshold=.4)

## End(Not run)

CAMAN documentation built on Sept. 22, 2023, 5:12 p.m.