[BioC] Discretization

Sean Davis sdavis2 at mail.nih.gov
Tue May 13 22:16:33 CEST 2008

On Tue, May 13, 2008 at 4:12 PM, Andrej Kastrin
<andrej.kastrin at gmail.com> wrote:
> Dear all,
>  I'm experimenting with machine learning algorithms in microarray domain
> which require discrete feature space. I'm looking for a paper or any other
> type of reference dealing with discretization of continuous gene expression
> data.  If somebody is aware on it, please reply to my post.

Check out this paper:

1: Nat Methods. 2007 Nov;4(11):911-3. Epub 2007 Sep 30.

A gene expression bar code for microarray data.

Zilliox MJ, Irizarry RA.

W. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns
Hopkins Bloomberg School of Public Health, 615 N. Wolfe Street, Baltimore,
Maryland 21205, USA.

The ability to measure genome-wide expression holds great promise for
characterizing cells and distinguishing diseased from normal tissues. Thus far,
microarray technology has been useful only for measuring relative expression
between two or more samples, which has handicapped its ability to
classify tissue
types. Here we present a method that can successfully predict tissue type based
on data from a single hybridization. A preliminary web-tool is available online

PMID: 17906632

There are, I'm sure, many ways to approach the problem, though,
depending on your needs.


More information about the Bioconductor mailing list