Research Repository

A feature selection method for classification within functional genomics experiments based on the proportional overlapping score

Mahmoud, Osama and Harrison, Andrew and Perperoglou, Aris and Gul, Asma and Khan, Zardad and Metodiev, Metodi V and Lausen, Berthold (2014) 'A feature selection method for classification within functional genomics experiments based on the proportional overlapping score.' BMC Bioinformatics, 15 (1). 274-. ISSN 1471-2105

[img]
Preview
Text
1471-2105-15-274.pdf - Published Version
Available under License Creative Commons Attribution.

Download (591kB) | Preview

Abstract

Background: Microarray technology, as well as other functional genomics experiments, allow simultaneous measurements of thousands of genes within each sample. Both the prediction accuracy and interpretability of a classifier could be enhanced by performing the classification based only on selected discriminative genes. We propose a statistical method for selecting genes based on overlapping analysis of expression data across classes. This method results in a novel measure, called proportional overlapping score (POS), of a feature's relevance to a classification task.Results: We apply POS, along-with four widely used gene selection methods, to several benchmark gene expression datasets. The experimental results of classification error rates computed using the Random Forest, k Nearest Neighbor and Support Vector Machine classifiers show that POS achieves a better performance.Conclusions: A novel gene selection method, POS, is proposed. POS analyzes the expressions overlap across classes taking into account the proportions of overlapping samples. It robustly defines a mask for each gene that allows it to minimize the effect of expression outliers. The constructed masks along-with a novel gene score are exploited to produce the selected subset of genes.

Item Type: Article
Uncontrolled Keywords: Feature selection; Gene ranking; Microarray classification; Proportional overlap score; Gene mask; Minimum subset of genes
Subjects: Q Science > QA Mathematics
Q Science > QH Natural history > QH426 Genetics
Divisions: Faculty of Science and Health
Faculty of Science and Health > Mathematical Sciences, Department of
Faculty of Science and Health > Life Sciences, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 14 Aug 2014 07:54
Last Modified: 15 Jan 2022 00:25
URI: http://repository.essex.ac.uk/id/eprint/9960

Actions (login required)

View Item View Item