Fast Network Component Analysis for Gene Regulation Networks
Chunqi Chang
Zhi Ding
Yeung Sam Hung
Fung, P.C.W.
Univ. of Hong Kong, Hong Kong;
This paper appears in: Machine Learning for Signal Processing, 2007 IEEE Workshop on
Publication Date: 27-29 Aug. 2007
On page(s): 21-26
Location: Thessaloniki,
ISSN: 1551-2541
ISBN: 978-1-4244-1566-3
INSPEC Accession Number: 9825843
Digital Object Identifier: 10.1109/MLSP.2007.4414276
Current Version Published: 2008-01-02
Abstract
New advancement in microarray technologies has made it possible to reconstruct gene regulation networks from mass gene expression data measured by microarray. Typically, gene regulation networks are sparse networks. This sparse topology knowledge can be exploited to develop algorithms for network reconstruction. In this direction, a method called network component analysis (NCA) has been developed recently. A major disadvantage of the original NCA algorithm is that it is very time consuming, and it also has convergence problem as an iterative approach. In this paper we propose several fast, non-iterative NCA algorithms. They are basically based on matrix computation. The algorithms demonstrate good performance when applied to a hypothetical and a real gene regulation network.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
