A modified harmony search method for biclustering microarray gene expression data. (2016)

• Record Type: Journal Article
• Authors: Balamurugan, R.; Natarajan, A.M.; Premalatha, K.
• Is Part Of: International journal of data mining and bioinformatics. Volume 16:Number 4(2016)
• Page Start: 269
• Page End: 289
• Publication Date: 2016
• Subjects: biclustering -- gene expression data -- gene ontology -- harmony search -- Levy flight -- pitch adjusting rate -- microarrays -- bioinformatics; Data mining -- Periodicals; Bioinformatics -- Periodicals; 006.312
• Languages: English
• ISSNs: 1748-5673

Abstract

Microarray experiments generate vast amounts of data, leading to new requirements and challenges for bioinformatics. The crucial step in considering gene expression data is to discover a group of genes that have similar patterns. Biclustering is a two-dimensional clustering problem where the genes and samples are grouped simultaneously. Latest research showed that biclustering has a great potential in finding marker genes that are associated with certain tissues or diseases. Here, we present an efficient biclustering algorithm called Modified Harmony Search (MHS) method. The MHS algorithm includes a step for generating the new solution by using levy flight. Levy flight increases the diversity of the solutions of harmony search (HS) algorithm and the Pitch Adjusting Rate (PAR) is changed dynamically to escape from local optima. To know the performance of the MHS, it is applied on various benchmark optimisation functions and the benchmark gene expression data sets. The experimental results show that the MHS outperforms HS in optimisation functions and biclustering problems. Also, this work determines the biological relevance of the biclusters with Gene Ontology in terms of function, process and component.