Inferring the transcriptional modules using penalized matrix decomposition

Authors:
Chun-Hou Zheng;Lei Zhang;To-Yee Ng;Chi Keung Shiu;Shu-Lin Wang
Affiliations:
Intelligent Computing Lab, Hefei Institute of Intelligent Machines, Chinese Academy of Sciences, Anhui, China and Biometrics Research Center, Dept. of Computing, The Hong Kong Polytechnic Universi ...;Biometrics Research Center, Dept. of Computing, The Hong Kong Polytechnic University, Hong Kong, China;Biometrics Research Center, Dept. of Computing, The Hong Kong Polytechnic University, Hong Kong, China;Biometrics Research Center, Dept. of Computing, The Hong Kong Polytechnic University, Hong Kong, China;Intelligent Computing Lab, Hefei Institute of Intelligent Machines, Chinese Academy of Sciences, Anhui, China and School of Computer and Communication, Hunan University, Changsha, Hunan, China
Venue:
ICIC'10 Proceedings of the Advanced intelligent computing theories and applications, and 6th international conference on Intelligent computing
Year:
2010

Citing 3
Cited 1

Multi-way clustering of microarray data using probabilistic sparse matrix factorization

Bioinformatics
The discovery of transcriptional modules by a two-stage matrix decomposition approach

Bioinformatics
Tumor clustering using nonnegative matrix factorization with gene selection

IEEE Transactions on Information Technology in Biomedicine - Special section on biomedical informatics

Extracting plants core genes responding to abiotic stresses by penalized matrix decomposition

Computers in Biology and Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes to use the penalized matrix decomposition (PMD) to discover the transcriptional modules from microarray data. With the sparsity constraint on the decomposition factors, metagenes can be extracted from the gene expression data and they can well capture the intrinsic patterns of genes with the similar functions. Meanwhile, the PMD factors of each gene are good indicators of the cluster it belongs to. Compared with traditional methods, our method can cluster genes of the similar functions but without similar expression profiles. It can also assign a gene into different modules.