Abstract
Prediction of peroxisomal matrix proteins generally depends on the presence of one of two distinct motifs at the end of the amino acid sequence. PTS1 peroxisomal proteins have a well conserved tripeptide at the C-terminal end. However, the preceding residues in the sequence arguably play a crucial role in targeting the protein to the peroxisome. Previous work in applying machine learning to the prediction of peroxisomal matrix proteins has failed to capitalize on the full extent of these dependencies. We benchmark a range of machine learning algorithms, and show that a classifier – based on the Support Vector Machine – produces more accurate results when dependencies between the conserved motif and the preceding section are exploited. We publish an updated and rigorously curated data set that results in increased prediction accuracy of most tested models.
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
Amery, L., Fransen, M., De Nys, K., Mannaerts, G.P., Van Veldhoven, P.P.: Mitochondrial and peroxisomal targeting of 2-methylacyl-coa racemase in humans. J. Lipid Res. 41(11), 1752–1759 (2000)
Bodén, M., Hawkins, J.: Prediction of subcellular localisation using sequencebiased recurrent networks. Bioinformatics (2005) (accepted pending minor revision)
Emanuelsson, O., Elofsson, A., von Heijne, G., Cristobal, S.: In silico prediction of the peroxisomal proteome in fungi, plants and animals. Journal of Molecular Biology 330(2), 443–456 (2003)
Jones, J.M., Morrell, J.C., Gould, S.J.: Multiple distinct targeting signals in integral peroxisomal membrane proteins. Journal of Cell Biology 153(6), 1141–1150 (2001)
Lametschwandtner, G., Brocard, C., Fransen, M., Van Veldhoven, P., Berger, J., Hartig, A.: The difference in recognition of terminal tripeptides as peroxisomal targeting signal 1 between yeast and human is due to different affinities of their receptor pex5p to the cognate signal and to residues adjacent to it. Journal of Biological Chemistry 273(50), 33635–33643 (1998)
Neuberger, G., Maurer-Stroh, S., Eisenhaber, B., Hartig, A., Eisenhaber, F.: Motif refinement of the peroxisomal targeting signal 1 and evaluation of taxon-specific differences. Journal of Molecular Biology 328(3), 567–579 (2003)
Witten, H., Frank, E.: Data Mining: Practical machine learning tools with Java implementations. Morgan Kaufmann, San Francisco (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wakabayashi, M., Hawkins, J., Maetschke, S., Bodén, M. (2005). Exploiting Sequence Dependencies in the Prediction of Peroxisomal Proteins. In: Gallagher, M., Hogan, J.P., Maire, F. (eds) Intelligent Data Engineering and Automated Learning - IDEAL 2005. IDEAL 2005. Lecture Notes in Computer Science, vol 3578. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11508069_59
Download citation
DOI: https://doi.org/10.1007/11508069_59
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26972-4
Online ISBN: 978-3-540-31693-0
eBook Packages: Computer ScienceComputer Science (R0)