Abstract
The developments in large-scale monitoring of gene expression have made the reconstruction of gene regulatory networks (GRNs) feasible. Before one can infer the overall structures of GRNs, it is important to identify, for each gene in a network, which other genes can affect its expression and how they can affect it. Many existing methods to reconstructing GRNs are developed to generate hypotheses about the presence or absence of interactions between genes so that laboratory experiments can be performed afterwards for verification. Since, they are not intended to be used to predict if a gene has any interactions with other genes from an unseen sample. This makes statistical verification of the reliability of the discovered interactions difficult. In addition, some of them cannot make use of the temporal evidence in the data and also cannot take into account the directionality of regulation. For these reasons, we propose an effective data mining approach in this paper. For performance evaluation, it has been tested using real expression data. Experimental results show that it can be effective. The sequential associations discovered can reveal known gene regulatory relationships that could be used to infer the structures of GRNs.
Original language | English |
---|---|
Title of host publication | Proceedings - ICDM Workshops 2006 - 6th IEEE International Conference on Data Mining - Workshops |
Pages | 109-113 |
Number of pages | 5 |
Publication status | Published - 1 Dec 2006 |
Event | 6th IEEE International Conference on Data Mining - Workshops, ICDM 2006 - Hong Kong, Hong Kong Duration: 18 Dec 2006 → 18 Dec 2006 |
Conference
Conference | 6th IEEE International Conference on Data Mining - Workshops, ICDM 2006 |
---|---|
Country/Territory | Hong Kong |
City | Hong Kong |
Period | 18/12/06 → 18/12/06 |
ASJC Scopus subject areas
- General Engineering