TY - GEN
T1 - A recursive genetic algorithm to automatically select genes for cancer classification
AU - Mohamad, Mohd Saberi
AU - Omatu, Sigeru
AU - Deris, Safaai
AU - Yoshioka, Michifumi
PY - 2009
Y1 - 2009
N2 - Gene expression technology namely microarray, offers the ability to measure the expression levels of thousands of genes simultaneously in a biological organism. Microarray data are expected to be of significant help in the development of efficient cancer diagnosis and classification platform. The main problem that needs to be addressed is the selection of a small subset of genes that contributes to a disease from the thousands of genes measured on microarray that are inherently noisy. Most approaches from previous works have selected the numbers of genes manually and thus, have caused difficulty, especially for beginner biologists. Hence, this paper aims to automatically select a small subset of informative genes that is most relevant for the cancer classification. In order to achieve this aim, a recursive genetic algorithm has been proposed. Experimental results show that the gene subset is small in size and yield better classification accuracy as compared with other previous works as well as four methods experimented in this work. A list of informative genes in the best subsets is also presented for biological usage.
AB - Gene expression technology namely microarray, offers the ability to measure the expression levels of thousands of genes simultaneously in a biological organism. Microarray data are expected to be of significant help in the development of efficient cancer diagnosis and classification platform. The main problem that needs to be addressed is the selection of a small subset of genes that contributes to a disease from the thousands of genes measured on microarray that are inherently noisy. Most approaches from previous works have selected the numbers of genes manually and thus, have caused difficulty, especially for beginner biologists. Hence, this paper aims to automatically select a small subset of informative genes that is most relevant for the cancer classification. In order to achieve this aim, a recursive genetic algorithm has been proposed. Experimental results show that the gene subset is small in size and yield better classification accuracy as compared with other previous works as well as four methods experimented in this work. A list of informative genes in the best subsets is also presented for biological usage.
KW - Cancer classification
KW - Gene selection
KW - Genetic Algorithm
KW - Microarray data
KW - Recursive genetic algorithm
KW - Support vector machine
UR - http://www.scopus.com/inward/record.url?scp=58149116941&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=58149116941&partnerID=8YFLogxK
U2 - 10.1007/978-3-540-85861-4_20
DO - 10.1007/978-3-540-85861-4_20
M3 - Conference contribution
AN - SCOPUS:58149116941
SN - 9783540858607
T3 - Advances in Soft Computing
SP - 166
EP - 174
BT - 2nd International Workshop on Practical Applications of Computational Biology and Bioinformatics (IWPACBB 2008)
A2 - Corchado, Juan
A2 - De Paz, Juan
A2 - Rocha, Miguel
A2 - Riverola, Florentino Fernandez
ER -
