Display Settings:


Send to:

Choose Destination
See comment in PubMed Commons below
Genome Biol. 2003;4(1):R6. Epub 2003 Jan 6.

Towards reconstruction of gene networks from expression data by supervised learning.

Author information

  • 1Microarray Informatics Group, European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK. lev@ebi.ac.uk



Microarray experiments are generating datasets that can help in reconstructing gene networks. One of the most important problems in network reconstruction is finding, for each gene in the network, which genes can affect it and how. We use a supervised learning approach to address this question by building decision-tree-related classifiers, which predict gene expression from the expression data of other genes.


We present algorithms that work for continuous expression levels and do not require a priori discretization. We apply our method to publicly available data for the budding yeast cell cycle. The obtained classifiers can be presented as simple rules defining gene interrelations. In most cases the extracted rules confirm the existing knowledge about cell-cycle gene expression, while hitherto unknown relationships can be treated as new hypotheses.


All the relations between the considered genes are consistent with the facts reported in the literature. This indicates that the approach presented here is valid and that the resulting rules can be used as elements for building and explaining gene networks.

[PubMed - indexed for MEDLINE]
Free PMC Article

Images from this publication.See all images (2)Free text

Figure 1
Figure 2
PubMed Commons home

PubMed Commons

How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for BioMed Central Icon for PubMed Central
    Loading ...
    Write to the Help Desk