Frequency decomposition based gene clustering
- Authors: Rahman, Md Abdur , Chetty, Madhu , Bulach, Dieter , Wangikar, Pramod
- Date: 2015
- Type: Text , Conference paper
- Relation: 22nd International Conference on Neural Information Processing, ICONIP 2015; Istanbul, Turkey; 9th-12th November 2015 Vol. 9490, p. 170-181
- Full Text: false
- Reviewed:
- Description: Gene expressions have been commonly applied to understand the inherent underlying mechanism of known biological processes. Although the microarray gene expressions usually appear aperiodic, with proper signal processing techniques, its periodic components can be easily obtained. Thus, if expressions of interconnected (regulatory and regulated) genes are decomposed, at least one common frequency component will appear in these genes. Exploiting this novel concept, we propose a frequency decomposition approach for gene clustering to better understand the gene interconnection topology. This method, based on Hilbert Huang Transform (HHT) enables us to segregate every periodic component of the gene expressions. Next, a multilevel clustering is performed based on these frequency components. Unlike existing clustering algorithms, the proposed method assimilates a meaningful knowledge of the gene interactions topology. The information related to underlying gene interactions is vital and can prove useful in many existing evolutionary optimisation algorithms for genetic network reconstruction. We validate the entire approach by its application to a 15-gene synthetic network. © Springer International Publishing Switzerland 2015.
Modified global k-means algorithm for clustering in gene expression data sets
- Authors: Bagirov, Adil , Mardaneh, Karim
- Date: 2006
- Type: Text , Conference paper
- Relation: Paper presented at Intelligent Systems for Bioinformatics 2006, proceedings of the AI 2006 Workshop on Intelligent Systems of Bioinformatics, Hobart, Tasmania : 4th December, 2006
- Full Text:
- Reviewed:
- Description: Clustering in gene expression data sets is a challenging problem. Different algorithms for clustering of genes have been proposed. However due to the large number of genes only a few algorithms can be applied for the clustering of samples. k-means algorithm and its different variations are among those algorithms. But these algorithms in general can converge only to local minima and these local minima are significantly different from global solutions as the number of clusters increases. Over the last several years different approaches have been proposed to improve global search properties of k-means algorithm and its performance on large data sets. One of them is the global k-means algorithm. In this paper we develop a new version of the global k-means algorithm: the modified global k-means algorithm which is effective for solving clustering problems in gene expression data sets. We present preliminary computational results using gene expression data sets which demonstrate that the modified k-means algorithm improves and sometimes significantly results by k-means and global k-means algorithms.
- Description: E1
- Description: 2003001713