A novel relative space based gene feature extraction and cancer recognition

Authors:
Xinguo Lu;Yaping Lin;Haijun Wang;Siwang Zhou;Xiaolong Li
Affiliations:
School of Computer and Communication, Hunan University, Changsha, China;School of Software, Hunan University, Changsha, China and School of Computer and Communication, Hunan University, Changsha, China;School of Computer and Communication, Hunan University, Changsha, China;School of Computer and Communication, Hunan University, Changsha, China;School of Computer and Communication, Hunan University, Changsha, China
Venue:
PAKDD'07 Proceedings of the 11th Pacific-Asia conference on Advances in knowledge discovery and data mining
Year:
2007

Citing 4
Cited 0

Evolving Connectionist Systems: Methods and Applications in Bioinformatics, Brain Study and Intelligent Machines

Evolving Connectionist Systems: Methods and Applications in Bioinformatics, Brain Study and Intelligent Machines
Machine learning in DNA microarray analysis for cancer classification

APBC '03 Proceedings of the First Asia-Pacific bioinformatics conference on Bioinformatics 2003 - Volume 19
Subspace clustering for high dimensional data: a review

ACM SIGKDD Explorations Newsletter - Special issue on learning from imbalanced datasets
Using most similarity tree based clustering to select the top most discriminating genes for cancer detection

ICAISC'06 Proceedings of the 8th international conference on Artificial Intelligence and Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recognizing patient samples with gene expression profiles is used to cancer diagnosis and therapy. In the high dimensional, huge redundant and noisy gene expression data the cancerogenic factor's locality is studied. Using gene feature transformation a relative space to a cancer is built and a least spread space with least energy to the cancer is extracted. And it is proven that the cancer is able to be recognized in the least spread space and a cancer classification with least spread space (CCLSS) is proposed. In the Leukemia dataset and Colon dataset the correlation between the recognition rate and the rank of least spread space is explored, then the optimal least spread spaces to AML/ALL and to tumor colon tissue (TCT)/normal colon tissue (NCT) are extracted. At last using LOOCV the experiments with different classification algorithms are conducted and the results show CCLSS makes better precision than traditional classification algorithms.