Brain Cancer Antibody Display Classification

Madara Gasparovica, Ludmila Aleksejeva

Abstract


This article explores real data on brain cancer. This type of biological data has a few particularities like a great number of attributes – antibodies and genes. However the number of entries is rather small because the data have to be obtained from real patients. This process is time consuming and very costly. Due to that, this research provides detailed data description as well as analyzes their particularities, type and structure. Correspondingly, classification rules are also difficult to discover. This research is dedicated to finding applications of classification methods aimed at determining interconnections that could be used to classify brain cancer. Working exactly with such unique data has a great practical value, because the data obtained can be used in future to continue the research and in practical diagnostics with the possibility to offer the data to biologists for interpretation. To speed up the obtaining of interconnections, only important attributes were used. Various methods of interconnection determination were employed. Conclusions about this type of data analysis, obtaining classification rules and the precision of obtained rules are made and directions of future work are outlined.

Keywords


antibody display; classification; data mining; IF_THEN rules

Full Text:

PDF

References


T.R. Golub, D.K. Slonim et.al. Huerta, Molecular Classification of Cancer: Class Discovery and Class prediction by gene expression Monitoring, Science, vol. 286, pp. 531-537, 1999.

S.A. Vinterbo, E.-Y. Kim, L. Ohno – Machado, Small, fuzzy and interpretable gene expression based

S.-Y. Ho, C.-H. Hsieg, H.-M. Chen, H.-L. Huang, Interpretable gene expression classifier with an accurate and compact fuzzy rule base for microarray data analysis, BioSystems, vol. 85, pp.165-176, 2006.

G. Schaefer, Fuzzy Rule-Based Classification Systems and Their Application in the Medical Domain: 16th International Conference on Soft Computing MENDEL 2010, June 23-25, 2010, Brno, Czech Republic. Brno University of Technology, pp. 229-235.

Gasparoviča M., Novoselova N., Aleksejeva L. Using Fuzzy Logic to Solve Bioinformatics Tasks //Scientific Journal of Riga Technical University. Issue 5, Computer Science. Information Technology and Management Science, vol.44, pp.99-105, 2010.

Popular Medical Encyclopedia. –Rīga : Galvenā enciklopēdiju redakcija. pp. 623, 1984 (in Latvian).

Kalniņa Z, Siliņa K, Meistere I, Zayakin P, Rivosh A, Ābols A, Leja M, Minenkova O, Schadendorf D and Linē A. Evaluation of T7 and Lambda phage display systems for survey of autoantibody profiles in cancer patients. J. Immunol. Methods, vol. 334(1-2) pp.37-50, 2008.

Hühn J., Hüllermeier E. FURIA: an algorithm for unordered fuzzy rule induction// Data Mining and Knowledge Discovery, Springer Netherlands, Computer Science, Volume: 19, Issue: 3, pp. 293-319, 2009.

Cohen W. Fast effective rule induction // Proceedings of the 12th International Conference on Machine Learning, ICML, pp. 115 – 123, 1995.

Kaburlasos V. G., Athanasiadis I. N., Mitkas P. A. Fuzzy lattice reasoning (FLR) classifier and its application for ambient ozone estimation, International Journal of Approximate Reasoning, Volume 45, Issue 1, pp. 152-188, 2007.

Gaines B.R., Compton P. Induction of Ripple-Down Rules Applied to Modeling Large Databases. J. Intell. Inf. Syst., vol. 5, issue 3, pp. 211-228, 1995.

Frank E., Witten I.H. Generating Accurate Rule Sets Without Global Optimization // Fifteenth International Conference on Machine Learning, pp. 144-151, 1998.

Holte R.C. Very simple classification rules perform well on most commonly used datasets. Machine Learning. Vol. 11, pp. 63-91.

Hall M., Frank E., Holmes G., Pfahringer B., Reutemann P, Witten I.H. The WEKA Data Mining Software:An Update. SIGKDD Explorations, vol.11, issue 1, 2009.




DOI: http://dx.doi.org/10.17770/etr2011vol2.971

Refbacks

  • There are currently no refbacks.