genesrf Bioinformatics Unit   -   CNIO


GeneSrF: gene selection with random forests (v. 20070524)

GeneSrF is a web tool for gene selection in classification problems that uses random forest. Two approaches for gene selection are used: one is targeted towards identifying small, non-redundant sets of genes that have good predictive performance. The second is a more heuristic graphical approach that can be used to identify large sets of genes (including redundant genes) related to the outcome of interest. The first approach is described in detail in this paper. The R code is available as an R package from CRAN or from this link. For further details see the help.

To use this web tool you need to provide two files, one with the gene expression data and one with the class labels, and press "Submit".

Input files

Expression data file: (?)
Class file: (?)

Type of gene identifier and species

This information is used to provide clickable links (that take you to the one-query-version of our IDConverter) in the results.

Type of ID for gene names Organism
Affymetrix ID Human (Homo sapiens)
Clone ID (IMAGE Consortium) Mouse (Mus musculus)
GenBank Accession Rat (Rattus norvegicus)
Ensembl Gene None of the above
Unigene cluster
RefSeq RNA
RefSeq peptide
Entrez Gene
HUGO Gene Name
None of the above

Push the "Submit" to start execution.


Citing GeneSrF

If you use GeneSrF, please cite it in your publications. Please provide the URL and the publication:

Diaz-Uriarte, R. 2007. GeneSrF and varSelRF: a web-based tool and R package for gene selection and classification using random forest. BMC Bioinformatics 2007, 8:328.

Source code availability

See Launchpad repository for GeneSrF and Launchpad repository for varSelRF. See also the project page.

[Python Powered] [R Project for Statistical Computing]

Send comments to webmaster