Abstract
Search of selection at molecular level is typically done with neutrality tests. However, non selective factors can cause similar effects on tests results. In order to make the influence of particular non selective forces weaker, a battery of such tests can be applied and the combination of results could be considered as inputs to a properly trained classifier. Success of such approach depends on two issues: appropriate expert knowledge to be used during training of the classifier and the choice of the most suitable machine learning method, which generalizes the acquired knowledge to unknown cases. Comparison of connectionist and rule-based rough set approaches in this role is the main goal of the paper.
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
Bonnen, P.E., Story, M.D., Ashorn, C.L., Buchholz, T.A., Weil, M.M., Nelson, D.L.: Haplotypes at ATM identify coding-sequence variation and indicate a region of extensive linkage disequilibrium. American Journal of Human Genetics 67(6), 1437–1451 (2000)
Bonnen, P.E., Wang, P.J., Kimmel, M., Chakraborty, R., Nelson, D.L.: Haplotype and linkage disequilibrium architecture for human cancer-associated genes. Genome Research 12(12), 1846–1853 (2002)
Cyran, K.A.: Rough sets in the interpretation of statistical tests outcomes for genes under hypothetical balancing selection. In: Kryszkiewicz, M., Peters, J.F., Rybiński, H., Skowron, A. (eds.) RSEISP 2007. LNCS (LNAI), vol. 4585, pp. 716–725. Springer, Heidelberg (2007)
Cyran, K.A.: Quasi dominance rough set approach in testing for traces of natural selection at molecular level. In: Cyran, K.A., Kozielski, S., Peters, J.F., Stańczyk, U., Wakulicz-Deja, A. (eds.) Man-Machine Interactions. AISC, vol. 59, pp. 163–172. Springer, Heidelberg (2009)
Cyran, K.A.: Classical and dominance - based rough sets in the search for denes under balancing selection. In: Peters, J.F., Skowron, A. (eds.) Transactions on Rough Sets XI. LNCS, vol. 5946, pp. 53–65. Springer, Heidelberg (2010)
Cyran, K.A.: Artificial Intelligence, Branching Processes and Coalescent Methods in Evolution of Humans and Early Life, vol. 32(1B). Silesian University of Technology, Gliwice (2011)
Cyran, K.A., Polańska, J., Kimmel, M.: Testing for signatures of natural selection at molecular genes level. Journal of Medical Informatics and Technologies 8, 31–39 (2004)
Fu, Y.X.: Statistical tests of neutrality of mutations against population growth, hitchhiking and background selection. Genetics 147(2), 915–925 (1997)
Fu, Y.X., Li, W.H.: Statistical tests of neutrality of mutations. Genetics 133(3), 693–709 (1993)
Greco, S., Matarazzo, B., Slowinski, R.: Rough approximation of preference relation by dominance relations. European Journal of Operational Research 117(1), 63–83 (1999)
Hudson, R.R., Kreitman, M., Aguade, M.: A test of neutral molecular evolution based on nucleotide data. Genetics 116(1), 153–159 (1987)
Kelly, J.K.: A test of neutrality based on interlocus associations. Genetics 146(3), 1197–1206 (1997)
Kimura, M.: The Neutral Theory of Molecular Evolution. Cambridge University Press, Cambridge (1983)
Nielsen, R.: Statistical tests of selective neutrality in the age of genomics. Heredity 86, 641–647 (2001)
Pawlak, Z.: Rough sets. International Journal of Information and Computer Sciences 11(5), 341–356 (1982)
Raghu, P.P., Yegnanrayana, B.: Supervised texture classification using a probabilistic neural network and constraint satisfaction model. IEEE Transactions on Neural Networks 9(3), 516–522 (1998)
Trikka, D., Fang, Z., Renwick, A., Jones, S.H., Chakraborty, R., Kimmel, M., Nelson, D.L.: Complex SNP-based haplotypes in three human helicases: implications for cancer association studies. Genome Research 12(4), 627–639 (2002)
Wall, J.D.: Recombination and the power of statistical tests of neutrality. Genetics Research 74(1), 65–79 (1999)
Weaver, S., Baird, L., PolyCarpou, M.M.: An analytical framework for local feedforward networks. IEEE Transactions on Neural Networks 9(3), 473–482 (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Cyran, K.A., Kimmel, M. (2014). Comparison of Connectionist and Rough Set Based Knowledge Discovery Methods in Search for Selection in Genes Implicated in Human Familial Cancer. In: Gruca, D., Czachórski, T., Kozielski, S. (eds) Man-Machine Interactions 3. Advances in Intelligent Systems and Computing, vol 242. Springer, Cham. https://doi.org/10.1007/978-3-319-02309-0_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-02309-0_17
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-02308-3
Online ISBN: 978-3-319-02309-0
eBook Packages: EngineeringEngineering (R0)