Beyond Bioinformatics

Title

Multi-class subcellular location prediction for bacterial proteins

Authors

Paul D. Taylor ^{1, 2} ,Teresa K. Attwood ² and Darren R. Flower ^1,*

Affiliation

1. The Jenner Institute, University of Oxford, Compton, Newbury, Berkshire, RG20 7NN, UK; 2. Faculty of Life Sciences & School of Computer Science, The University of Manchester, Oxford Road, Manchester M13 9PT, UK.

Email

darren.flower@jenner.ac.uk; * Corresponding author

Phone

+44 1635 577954

Fax

+44 1635 577908

Article Type

Prediction Model

Date

received November 10,2006; accepted November 22, 2006; published online November 24, 2006

Abstract

Two algorithms, based on Bayesian Networks (BNs), for bacterial subcellular location prediction, are explored in this paper: one predicts all locations for Gram+ bacteria and the other all locations for Gram- bacteria. Methods were evaluated using different numbers of residues (from the N-terminal 10 residues to the whole sequence) and residue representation (amino acid-composition, percentage amino acid-composition or normalised amino acid-composition). The accuracy of the best resulting BN was compared to PSORTB. The accuracy of this multi-location BN was roughly comparable to PSORTB; the difference in predictions is low, often less than 2%. The BN method thus represents both an important new avenue of methodological development for subcellular location prediction and a potentially value new tool of true utilitarian value for candidate subunit vaccine selection.

Keywords

Bayesian networks; prediction method; subcellular location; membrane protein; periplasmic protein; secreted protein

Citation

Edited by

P. Kangueane

ISSN

0973-2063

Publisher

Biomedical Informatics Publishing Group

Copyright

Publisher

Copyright Transfer Agreement

The authors of published articles in Bioinformation automatically transfer the copyright to the publisher upon formal acceptance. However, the authors reserve right to use the information contained in the article for non commercial purposes.

License

This is an open-access article, which permits unrestricted use, distribution, and reproduction in any medium, for non-commercial purposes, provided the original author and source are credited.