Abstract
Computing methods that allow the efficient and accurate processing of experimentally gathered data play a crucial role in biological research. The aim of this paper is to present a supervised learning strategy which combines concepts stemming from coding theory and Bayesian networks for classifying and predicting pathological conditions based on gene expression data collected from micro-arrays. Specifically, we propose the adoption of the Minimum Description Length (MDL) principle as a useful heuristic for ranking and selecting relevant features. Our approach has been successfully applied to the Acute Leukemia dataset and compared with different methods proposed by other researchers.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hardimann, G.: Microarray methods and applications: Nuts & bolts. DNA Press (2003)
Barron, A., Rissanen, J., Yu, B.: The minimum description length principle in coding and modelling. IEEE Transactions on Information Theory 44, 2743–2760 (1998)
Golub, T.R., et al.: Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression Monitoring. Science 286, 531–537 (1999)
Liberati, D., Bittanti, S., Garatti, S.: Unsupervised Mining of Genes Classifying Leukemia. In: Wang, J. (ed.) Enciclopedia of Data Warehousing and Mining. Idea Group, Hershey (2005)
Kononenko, I.: On biases in estimatine multi-valued attributes. In: IJCAI 1995, pp. 1034–1040 (1995)
Friedman, N., Geiger, D., Goldszmidt, M.: Bayesian Network Classifiers. Machine Learning 29, 131–161 (1997)
Keogh, E., Pazzani, M.J.: Learning the structure of augmented Bayesian classifiers. International Journal on Artificial Intelligence Tools 11(4), 587–601 (2002)
Cheng, G., Greiner, R.: Comparing Bayesian Network Classifiers. In: Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence. Morgan Kaufmann Publishers, Inc., San Francisco (1999)
Yarmus, J.S.: ABN: A Fast, Greedy Bayesian Network Classifier (2003), http://otn.oracle.com/products/bi/pdf/adaptive_bayes_net.pdf
Chow, M.L., Moler, E.J., Mian, I.S.: Identifying marker genes in transcription profiling data using a mixture of feature relevance experts. Physiol Genomics 5, 99–111 (2001)
Moos, P.J., Raetz, E.A., Carlson, M.A., Szabo, A., Smith, F.E., Willman, C., Wei, Q., Hunger, S.P., Carroll, W.L.: Identification of gene expression profiles that segregate patients with childhood leukaemia. Clinical Cancer Research 8, 3118–3130 (2002)
Crawford, A.W., Beckerle, M.C.: Purification and characterization of zyxin, an 82000-Dalton component of adherents junctions. The Journal of Biological Chemistry 266(9), 5847–5853 (1991)
Li, X., Rao, S.Q., Wang, Y.D., Gong, B.S.: Gene mining: a novel and powerful ensemble decision approach to hunting for disease genes using microarray expression profiling. Nucleic Acids Research 32, 2685–2694 (2004)
Valdes, et al. (eds.): Seventeenth International Conference on Industrial & Engineering Applications on Artificial Intelligence & Expert Systems (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bosin, A., Dessì, N., Liberati, D., Pes, B. (2006). Learning Bayesian Classifiers from Gene-Expression MicroArray Data. In: Bloch, I., Petrosino, A., Tettamanzi, A.G.B. (eds) Fuzzy Logic and Applications. WILF 2005. Lecture Notes in Computer Science(), vol 3849. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11676935_37
Download citation
DOI: https://doi.org/10.1007/11676935_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-32529-1
Online ISBN: 978-3-540-32530-7
eBook Packages: Computer ScienceComputer Science (R0)