Gene expression data analysis with the clustering method based on an improved quantum-behaved Particle Swarm Optimization

Microarray technology has been widely applied in study of measuring gene expression levels for thousands of genes simultaneously. In this technology, gene cluster analysis is useful for discovering the function of gene because co-expressed genes are likely to share the same biological function. Many...

Full description

Saved in:
Bibliographic Details
Published in:Engineering applications of artificial intelligence Vol. 25; no. 2; pp. 376 - 391
Main Authors: Sun, Jun, Chen, Wei, Fang, Wei, Wun, Xiaojun, Xu, Wenbo
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.03.2012
Subjects:
Algorithms
Clustering
Computer simulation
Gene expression
Gene expression data
Genes
Mathematical analysis
Mathematical models
Optimization
Particle Swarm Optimization (PSO)
Quantum-behaved Particle Swarm Optimization (QPSO)
Gene expression data
Clustering
Quantum-behaved Particle Swarm Optimization (QPSO)
Particle Swarm Optimization (PSO)
ISSN:0952-1976, 1873-6769
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Microarray technology has been widely applied in study of measuring gene expression levels for thousands of genes simultaneously. In this technology, gene cluster analysis is useful for discovering the function of gene because co-expressed genes are likely to share the same biological function. Many clustering algorithms have been used in the field of gene clustering. This paper proposes a new scheme for clustering gene expression datasets based on a modified version of Quantum-behaved Particle Swarm Optimization (QPSO) algorithm, known as the Multi-Elitist QPSO (MEQPSO) model. The proposed clustering method also employs a one-step K-means operator to effectively accelerate the convergence speed of the algorithm. The MEQPSO algorithm is tested and compared with some other recently proposed PSO and QPSO variants on a suite of benchmark functions. Based on the computer simulations, some empirical guidelines have been provided for selecting the suitable parameters of MEQPSO clustering. The performance of MEQPSO clustering algorithm has been extensively compared with several optimization-based algorithms and classical clustering algorithms over several artificial and real gene expression datasets. Our results indicate that MEQPSO clustering algorithm is a promising technique and can be widely used for gene clustering.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0952-1976
1873-6769
DOI:10.1016/j.engappai.2011.09.017