C4.5: programs for machine learning
C4.5: programs for machine learning
Identifying gene regulatory networks from experimental data
RECOMB '99 Proceedings of the third annual international conference on Computational molecular biology
Hi-index | 0.00 |
In this paper, we propose a novel data mining algorithm for reconstructing gene regulatory networks (GRNs) from microarray data. By making use of the proposed probabilistic measure, it is able to mine noisy, high dimensional expression data for interesting association patterns of genes without the need for additional feature selection procedures. Moreover, it can make explicit hidden patterns discovered for possible biological interpretation and also predict gene expression patterns in the unseen tissue samples. Experimental results on real expression data show that it is very effective and the discovered association patterns reveal biologically meaningful regulatory relationships of genes that could help users reconstructing the underlying structures of GRNs.