Predictability of Rules in HIV-1 Protease Cleavage Site Analysis
Symbolic rules play an important role in HIV-1 protease cleavage site prediction. Recently, some studies have done on extraction of the prediction rules with some success. In this paper, we demonstrated a decompositional approach for rule extraction from nonlinear neural networks. We also compared the prediction rules to the ones extracted by other approaches and methods. Empirical experiments are also shown.
KeywordsPrediction Rule Association Rule Mining Decompositional Approach Rule Extraction Trained Neural Network
- 4.Fu, L.: Neural Networks in Computer Intelligence. McGraw Hill, Inc., New York (1994)Google Scholar
- 7.Lumini, A., Loris, N.: Machine learning for hiv-1 protease cleavage site prediction. In: Proceedings of Artificial Intelligence and Application (AIA 2005) (2005)Google Scholar
- 8.Narayanan, A., Wu, X., Yang, Z.R.: Mining viral protease data to extract cleavage knowledge. Bioinformatics 18(Suppl.1), S5–S13 (2002)Google Scholar
- 10.Setino, R., Liu, H.: Understanding neural networks via rule extraction. In: Proceedings of the 14th International Conference on Neural Networks, vol. (1), pp. 480–485 (1995)Google Scholar