A three-stage method to select informative genes for cancer classification
Microarray technology has provided biologists with the ability to measure the expression levels of thousands of genes in a single experiment. One of the urgent issues in the use of microarray data is the selection of a small subset of genes from the thousands of genes in the data that contributes to...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
2010
|
| Subjects: |
| _version_ | 1796855960112726016 |
|---|---|
| author | Mohamad, Mohd. Saberi Omatu, Sigeru Yoshioka, Michifumi Deris, Safaai |
| author_facet | Mohamad, Mohd. Saberi Omatu, Sigeru Yoshioka, Michifumi Deris, Safaai |
| author_sort | Mohamad, Mohd. Saberi |
| collection | ePrints |
| description | Microarray technology has provided biologists with the ability to measure the expression levels of thousands of genes in a single experiment. One of the urgent issues in the use of microarray data is the selection of a small subset of genes from the thousands of genes in the data that contributes to a disease. This selection process is difficult due to many irrelevant genes, noisy genes, and the availability of the small number of samples compared to the huge number of genes (high-dimensional data). In this study, we propose a three-stage gene selection method to select a small subset of informative genes that is most relevant for the cancer classification. It has three stages: 1) pre-selecting genes using a filter method to produce a subset of genes; 2) optimising the gene subset using a multi-objective hybrid method to yield near-optimal gene subsets; 3) analyzing the frequency of appearance of each gene in the different near-optimal gene subsets to produce a small subset of informative genes. The experimental results show that our proposed method is capable in selecting the small subset to obtain better classification accuracies than other related previous works as well as five methods experimented in this work. Additionally, a list of informative genes in the final gene subsets is also presented for biological usage. |
| first_indexed | 2024-03-05T18:36:20Z |
| format | Article |
| id | utm.eprints-22832 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T18:36:20Z |
| publishDate | 2010 |
| record_format | dspace |
| spelling | utm.eprints-228322018-03-15T01:07:55Z http://eprints.utm.my/22832/ A three-stage method to select informative genes for cancer classification Mohamad, Mohd. Saberi Omatu, Sigeru Yoshioka, Michifumi Deris, Safaai QA Mathematics Microarray technology has provided biologists with the ability to measure the expression levels of thousands of genes in a single experiment. One of the urgent issues in the use of microarray data is the selection of a small subset of genes from the thousands of genes in the data that contributes to a disease. This selection process is difficult due to many irrelevant genes, noisy genes, and the availability of the small number of samples compared to the huge number of genes (high-dimensional data). In this study, we propose a three-stage gene selection method to select a small subset of informative genes that is most relevant for the cancer classification. It has three stages: 1) pre-selecting genes using a filter method to produce a subset of genes; 2) optimising the gene subset using a multi-objective hybrid method to yield near-optimal gene subsets; 3) analyzing the frequency of appearance of each gene in the different near-optimal gene subsets to produce a small subset of informative genes. The experimental results show that our proposed method is capable in selecting the small subset to obtain better classification accuracies than other related previous works as well as five methods experimented in this work. Additionally, a list of informative genes in the final gene subsets is also presented for biological usage. 2010 Article PeerReviewed Mohamad, Mohd. Saberi and Omatu, Sigeru and Yoshioka, Michifumi and Deris, Safaai (2010) A three-stage method to select informative genes for cancer classification. International Journal of Innovative Computing Information and Control, 6 (1). 117 - 125. ISSN 1349-4198 http://www.academia.edu/1320488/A_THREE-STAGE_METHOD_TO_SELECT_INFORMATIVE_GENES_FOR_CANCER_CLASSIFICATION |
| spellingShingle | QA Mathematics Mohamad, Mohd. Saberi Omatu, Sigeru Yoshioka, Michifumi Deris, Safaai A three-stage method to select informative genes for cancer classification |
| title | A three-stage method to select informative genes for cancer classification |
| title_full | A three-stage method to select informative genes for cancer classification |
| title_fullStr | A three-stage method to select informative genes for cancer classification |
| title_full_unstemmed | A three-stage method to select informative genes for cancer classification |
| title_short | A three-stage method to select informative genes for cancer classification |
| title_sort | three stage method to select informative genes for cancer classification |
| topic | QA Mathematics |
| work_keys_str_mv | AT mohamadmohdsaberi athreestagemethodtoselectinformativegenesforcancerclassification AT omatusigeru athreestagemethodtoselectinformativegenesforcancerclassification AT yoshiokamichifumi athreestagemethodtoselectinformativegenesforcancerclassification AT derissafaai athreestagemethodtoselectinformativegenesforcancerclassification AT mohamadmohdsaberi threestagemethodtoselectinformativegenesforcancerclassification AT omatusigeru threestagemethodtoselectinformativegenesforcancerclassification AT yoshiokamichifumi threestagemethodtoselectinformativegenesforcancerclassification AT derissafaai threestagemethodtoselectinformativegenesforcancerclassification |