A three-stage method to select informative genes from gene expression data in classifying cancer classes

Mohd Saberi Mohamad; Sigeru Omatu; Safaai Deris; Michifumi Yoshioka

doi:10.1109/ISMS.2010.39

A three-stage method to select informative genes from gene expression data in classifying cancer classes

Mohd Saberi Mohamad
, Sigeru Omatu
, Safaai Deris
, Michifumi Yoshioka

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

The process of gene selection for the cancer classification faces with a major problem due to the properties of the data such as the small number of samples compared to the huge number of genes, irrelevant genes, and noisy data. Hence, this paper aims to select a near-optimal (small) subset of informative genes that is most relevant for the cancer classification. To achieve the aim, a three-stage method has been proposed. It has three stages: 1) pre-selecting genes using a filter method; 2) optimizing the gene subset using a multi-objective hybrid method; 3) analyzing the frequency of appearance of each gene. By performing experiments on three public gene expression data sets, classification accuracies and the number of selected genes of the proposed method are better than those of other experimented methods and previous works. A list of informative genes in the final gene subsets is also presented for biological usage.

Original language	English
Title of host publication	ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation
Pages	158-163
Number of pages	6
DOIs	https://doi.org/10.1109/ISMS.2010.39
Publication status	Published - 2010
Externally published	Yes
Event	UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation, ISMS 2010 - Liverpool, United Kingdom Duration: Jan 27 2010 → Jan 29 2010

Publication series

Name	ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation

Conference

Conference	UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation, ISMS 2010
Country/Territory	United Kingdom
City	Liverpool
Period	1/27/10 → 1/29/10

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Cancer classification
Component
Gene expression data
Gene selection
Genetic algorithm
Three-stage method

ASJC Scopus subject areas

General Computer Science
Theoretical Computer Science

Access to Document

10.1109/ISMS.2010.39

Cite this

Mohamad, M. S., Omatu, S., Deris, S., & Yoshioka, M. (2010). A three-stage method to select informative genes from gene expression data in classifying cancer classes. In ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation (pp. 158-163). Article 5416103 (ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation). https://doi.org/10.1109/ISMS.2010.39

A three-stage method to select informative genes from gene expression data in classifying cancer classes. / Mohamad, Mohd Saberi; Omatu, Sigeru; Deris, Safaai et al.
ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation. 2010. p. 158-163 5416103 (ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Mohamad, MS, Omatu, S, Deris, S & Yoshioka, M 2010, A three-stage method to select informative genes from gene expression data in classifying cancer classes. in ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation., 5416103, ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation, pp. 158-163, UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation, ISMS 2010, Liverpool, United Kingdom, 1/27/10. https://doi.org/10.1109/ISMS.2010.39

Mohamad MS, Omatu S, Deris S, Yoshioka M. A three-stage method to select informative genes from gene expression data in classifying cancer classes. In ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation. 2010. p. 158-163. 5416103. (ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation). doi: 10.1109/ISMS.2010.39

Mohamad, Mohd Saberi ; Omatu, Sigeru ; Deris, Safaai et al. / A three-stage method to select informative genes from gene expression data in classifying cancer classes. ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation. 2010. pp. 158-163 (ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation).

@inproceedings{18d29a7f3a0446a58e86f63d343d50f5,

title = "A three-stage method to select informative genes from gene expression data in classifying cancer classes",

abstract = "The process of gene selection for the cancer classification faces with a major problem due to the properties of the data such as the small number of samples compared to the huge number of genes, irrelevant genes, and noisy data. Hence, this paper aims to select a near-optimal (small) subset of informative genes that is most relevant for the cancer classification. To achieve the aim, a three-stage method has been proposed. It has three stages: 1) pre-selecting genes using a filter method; 2) optimizing the gene subset using a multi-objective hybrid method; 3) analyzing the frequency of appearance of each gene. By performing experiments on three public gene expression data sets, classification accuracies and the number of selected genes of the proposed method are better than those of other experimented methods and previous works. A list of informative genes in the final gene subsets is also presented for biological usage.",

keywords = "Cancer classification, Component, Gene expression data, Gene selection, Genetic algorithm, Three-stage method",

author = "Mohamad, \{Mohd Saberi\} and Sigeru Omatu and Safaai Deris and Michifumi Yoshioka",

year = "2010",

doi = "10.1109/ISMS.2010.39",

language = "English",

isbn = "9780769539737",

series = "ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation",

pages = "158--163",

booktitle = "ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation",

note = "UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation, ISMS 2010 ; Conference date: 27-01-2010 Through 29-01-2010",

}

TY - GEN

T1 - A three-stage method to select informative genes from gene expression data in classifying cancer classes

AU - Mohamad, Mohd Saberi

AU - Omatu, Sigeru

AU - Deris, Safaai

AU - Yoshioka, Michifumi

PY - 2010

Y1 - 2010

N2 - The process of gene selection for the cancer classification faces with a major problem due to the properties of the data such as the small number of samples compared to the huge number of genes, irrelevant genes, and noisy data. Hence, this paper aims to select a near-optimal (small) subset of informative genes that is most relevant for the cancer classification. To achieve the aim, a three-stage method has been proposed. It has three stages: 1) pre-selecting genes using a filter method; 2) optimizing the gene subset using a multi-objective hybrid method; 3) analyzing the frequency of appearance of each gene. By performing experiments on three public gene expression data sets, classification accuracies and the number of selected genes of the proposed method are better than those of other experimented methods and previous works. A list of informative genes in the final gene subsets is also presented for biological usage.

AB - The process of gene selection for the cancer classification faces with a major problem due to the properties of the data such as the small number of samples compared to the huge number of genes, irrelevant genes, and noisy data. Hence, this paper aims to select a near-optimal (small) subset of informative genes that is most relevant for the cancer classification. To achieve the aim, a three-stage method has been proposed. It has three stages: 1) pre-selecting genes using a filter method; 2) optimizing the gene subset using a multi-objective hybrid method; 3) analyzing the frequency of appearance of each gene. By performing experiments on three public gene expression data sets, classification accuracies and the number of selected genes of the proposed method are better than those of other experimented methods and previous works. A list of informative genes in the final gene subsets is also presented for biological usage.

KW - Cancer classification

KW - Component

KW - Gene expression data

KW - Gene selection

KW - Genetic algorithm

KW - Three-stage method

UR - https://www.scopus.com/pages/publications/77950952766

UR - https://www.scopus.com/pages/publications/77950952766#tab=citedBy

U2 - 10.1109/ISMS.2010.39

DO - 10.1109/ISMS.2010.39

M3 - Conference contribution

AN - SCOPUS:77950952766

SN - 9780769539737

T3 - ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation

SP - 158

EP - 163

BT - ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation

T2 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation, ISMS 2010

Y2 - 27 January 2010 through 29 January 2010

ER -

A three-stage method to select informative genes from gene expression data in classifying cancer classes

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this