Abstract
There are some neural network applications in proteomics; however, design and use of a neural network depends on the nature of the problem and the dataset studied. Bayesian framework is a consistent learning paradigm for a feed-forward neural network to infer knowledge from experimental data. Bayesian regularization automates the process of learning by pruning the unnecessary weights of a feed-forward neural network, a technique of which has been shown in this paper and applied to detect the glycosylation sites in epidermal growth factor-like repeat proteins involving in cancer as a case study. After applying the Bayesian framework, the number of network parameters decreased by 47.62%. The model performance comparing to One Step Secant method increased more than 34.92%. Bayesian learning produced more consistent outcomes than one step secant method did; however, it is computationally complex and slow, and the role of prior knowledge and its correlation with model selection should be further studied.
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
Appella, E., Weber, I.T., Blasi, F.: Structure and Function of Epidermal Growth Factor-Like Regions in Proteins. FEBS Lett. 231, 1–4 (1988)
Bairoch, A., Apweiler, R., Wu, C.H., Barker, W.C., Boeckmann, B., Ferro, S., Gasteiger, E., Huang, H., Lopez, R., Magrane, M., Martin, M.J., Natale, D.A., O’Donovan, C., Redaschi, N., Yeh, L.S.: The Universal Protein Resource (UniProt). Nucleic Acids Res. 33, 154–159 (2005)
Baldi, P., Brunak, S., Chauvin, Y., Andersen, C.A., Nielsen, H.: Assessing the Accuracy of Prediction Algorithms for Classification: An Overview. Bioinformatics 16, 412–424 (2000)
Battiti, R.: First and Second Order Methods for Learning: Between Steepest Descent and Newton’s Method. Neural Computation 4, 141–166 (1992)
Bateman, A., Coin, L., Durbin, R., Finn, R.D., Hollich, V., Griffiths-Jones, S., Khanna, A., Marshall, M., Moxon, S., Sonnhammer, E.L., Studholme, D.J., Yeats, C., Eddy, S.R.: The Pfam Protein Families Database. Nucleic Acids Res. 32, 138–141 (2004)
Bishop, C., Neural Network, M.: for Pattern Recognition. Oxford University Press, Oxford (1995)
Cai, Y.D., Yu, H., Chou, K.C.: Artificial Neural Network Method for Predicting the Specificity of GalNAc-Transferase. J. Protein Chem. 16, 689–700 (1997)
Davis, C.G.: The Many Faces of Epidermal Growth Factor Repeats. New Biol. 5, 410–419 (1997)
Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley Pub. Co., Reading (1989)
Gupta, R., Birch, H., Kristoffer, R., Brunak, S., Hansen, J.E.: O-GLYCBASE Version 4.0: A Revised Database of O-Glycosylated Proteins. Nuc. Acid. Res. 27, 370–372 (1999)
Gupta, R., Brunak, S.: Prediction of Glycosylation across the Human Proteome and the Correlation to Protein Function. In: Pac. Symp. Biocomput., pp. 310–322 (2002)
Hakamori, S.: Glycosylation Defining Malignancy: New Wine in an Old Bottle. PNAS 99, 10231–10233 (2002)
Haltiwanger, R.S., Lowe, J.B.: Role of Glycosylation in Development. Annu. Rev. Biochem. 73, 491–537 (2004)
Hansen, J.E., Lund, O., Nielsen, J.O., Brunak, S.: O-GLYCBASE: A Revised Database of O-glycosylated Proteins. Nuc. Acid. Res. 24, 248–252 (1996)
Heitzler, P., Simpson, P.: Altered Epidermal Growth Factor-Like Sequences Provide Evi- dence for a Role of Notch as a Receptor in Cell Fate Decisions. Development 117, 1113–1123 (1993)
Hulo, N., Sigrist, C.J.A., Le Saux, V., Langendijk-Genevaux, P.S., Bordoli, L., Gattiker, A., De Castro, E., Bucher, P., Bairoch, A.: Recent improvements to the PROSITE database. Nucl. Acids. Res. 32, 134–137 (2004)
Julenius, K., Molgaard, A., Gupta, R., Brunak, S.: Prediction, Conservation Analysis, and Structural Characterization of Mammalian Mucin-Type O-Glycosylation Sites. Glycobiol- ogy. 15, 153–164 (2005)
Lin, K., May, A.C.W., Taylor, W.R.: Amino Acid Encoding Schemes from Protein Structure Alignments: Multi-Dimensional Vectors to Describe Residue Types. J. Theor. Biol. 216, 361–365 (2002)
Lis, H., Sharon, N.: Protein Glycosylation: Structural and Functional Aspects. Eur. J. Bio- chem. 218, 1–27 (1993)
MacKay, D.J.: A Practical Bayesian Framework for Backprop Networks. Neural Computation 4, 448–472 (1992)
MacKay, D.J.: Bayesian Interpolation. Neural Computation 4, 415–447 (1992)
Marshall, R.D.: Glycoproteins. Annu. Rev. Biochem., 673–702 (1972)
Riis, S.K., Krogh, A.: Improving Prediction of Protein Secondary Structure Using Struc- tured Neural Network and Multiple Sequence Alignments. J. Comp. Biol. 3, 163–183 (1996)
Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, Heidelberg (1995)
Zadeh, L.A.: Fuzzy Sets. Information and Control 8, 338–353 (1965)
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
Shaneh, A., Butler, G. (2006). Bayesian Learning for Feed-Forward Neural Network with Application to Proteomic Data: The Glycosylation Sites Detection of the Epidermal Growth Factor-Like Proteins Associated with Cancer as a Case Study. In: Lamontagne, L., Marchand, M. (eds) Advances in Artificial Intelligence. Canadian AI 2006. Lecture Notes in Computer Science(), vol 4013. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11766247_10
Download citation
DOI: https://doi.org/10.1007/11766247_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34628-9
Online ISBN: 978-3-540-34630-2
eBook Packages: Computer ScienceComputer Science (R0)