Comparison of Gene Selection and Machine Learning for Tumor Classification

Qingzhong Liu, Andrew H. Sung, Bernardete M. Ribeiro

2006

Abstract

Class prediction and feature selection are two learning tasks that are strictly paired in the search of molecular profiles from microarray data. In this paper, we apply the recursive gene selection proposed in our previous paper to six types of micaroarray gene expression data for tumor classification. In comparison with other two well-known gene selections, SVM-RFE (Support Vector Machine Recursive Feature Elimination) and T-test, our method outperforms best. The kernel type and kernel parameters are critical to the classification performances for the kernel classifiers. Our experiments indicate that RBF kernel classifiers are pretty good under low feature dimensions; their performances increase initially and then decrease as the feature dimension increases.

References

  1. Brown,P. and Botstein,D. (1999) Exploring the New World of the Genome with DNA Microarrays. Nature Genetics Supplement, 21, 33-37.
  2. Quackenbush,J. (2001) Computational Analysis of Microarray Data, Nature Rev. Genetic, 2, 418-427.
  3. Armitage,P. and Berry,G. (1994) Statistical Methods in Medical Research, Blackwell.
  4. Jaeger,J., Sengupta,R. and Ruzzo,W.(2003) Improved Gene Selection for Classification of Microarray, Pacific Symposium on Biocomputing 8, 53-64.
  5. Guyon,I, Weston, J., Barnhill,S. and Vapnik,V. (2002) Gene Selection for Cancer Classification using Support Vector Machines, Machine Learning, 46(1-3), 389-422.
  6. Peng,H, Long,F. and Ding, C. (2005) Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy, IEEE Trans. on Pattern Analysis and Machine Intelligence, 27(8),1226-1238.
  7. Liu,Q. and Sung,A.H. (2006) Recursive Feature Addition for Gene Selection, Proc. of IEEE - IJCNN 2006, Vancouver, Canada.
  8. Golub, T. et al. (1999) Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression, Science, 286, 531-537.
  9. Shipp,M. et al. (2002) Diffuse Large B-Cell Lymphoma Outcome Prediction by Gene Expression Profiling and Supervised Machine Learning, Nature Medicine, 8(1), 68-74.
  10. Singh,D. et al. (2002) Gene Expression Correlates of Clinical Prostate Cancer Behavior, Cancer Cell, 1(2), 227-235.
  11. Alon,U. et al. (1999) Broad Patterns of Gene Expression Revealed by Clustering Analysis of Tumor and Normal Colon Tissues Probed by Oligonucleotide Arrays, Proc. Natl. Acad.. Sci. USA, Cell Biology, 96, 6745-6750.
  12. Pomeroy,S.L. et al. (2002) Prediction of Central Nervous System Embryonal Tumor Outcome based on Gene Expression, Letters to Nature, Nature, 415, 436-442.
  13. Van,L.J. et al.(2002) Gene expression profiling predicts clinical outcome of breast cancer, Letters to Nature, Nature, 415, 530-536.
  14. Vapnik,V. (1998) Statistical Learning Theory, John Wiley.
  15. Schlesinger,M. and Hlavac,V. (2002) Ten Lectures on Statistical and Structural Pattern Recognition, Kluwer Academic Publishers.
  16. Heijden,F., Duin,R., Ridder,D. and Tax,D. (2004) Classification, Parameter Estimation and State Estimation, John Wiley.
  17. Taylor,J. and Cristianini,N. (2004) Kernel Methods for Pattern Analysis, Cambridge University Press.
  18. Webb,A. (2002) Statistical Pattern Recognition, John Wiley & Sons, New York.
  19. Tan,P., Steinbach,M. and Kumar,V. (2005) Introduction to Data Mining, AddisonWesley, 76-79.
  20. Scholkopf,B., Guyon,I., Weston,J. (2003) Statistical Learning and Kernel Methods in Bioinformatics, Artificial Intelligence and Heuristic Methods in Bioinformatics, P. Frascoin and R. Shamir (Eds.) IOS press, 2003
Download


Paper Citation


in Harvard Style

Liu Q., H. Sung A. and M. Ribeiro B. (2006). Comparison of Gene Selection and Machine Learning for Tumor Classification . In Proceedings of the 2nd International Workshop on Biosignal Processing and Classification - Volume 1: BPC, (ICINCO 2006) ISBN 978-972-8865-67-2, pages 13-22. DOI: 10.5220/0001219700130022


in Bibtex Style

@conference{bpc06,
author={Qingzhong Liu and Andrew H. Sung and Bernardete M. Ribeiro},
title={Comparison of Gene Selection and Machine Learning for Tumor Classification},
booktitle={Proceedings of the 2nd International Workshop on Biosignal Processing and Classification - Volume 1: BPC, (ICINCO 2006)},
year={2006},
pages={13-22},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001219700130022},
isbn={978-972-8865-67-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Workshop on Biosignal Processing and Classification - Volume 1: BPC, (ICINCO 2006)
TI - Comparison of Gene Selection and Machine Learning for Tumor Classification
SN - 978-972-8865-67-2
AU - Liu Q.
AU - H. Sung A.
AU - M. Ribeiro B.
PY - 2006
SP - 13
EP - 22
DO - 10.5220/0001219700130022