Multi-class subcellular location prediction for bacterial proteins

Paul D. Taylor, Teresa K. Attwood, Darren R. Flower

Research output: Contribution to journalArticlepeer-review

Abstract

Two algorithms, based onBayesian 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.
Original languageEnglish
Pages (from-to)260-264
Number of pages5
JournalBioinformation
Volume1
Issue number7
Publication statusPublished - 2006

Bibliographical note

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.

Keywords

  • Bayesian network
  • prediction method
  • subcellular location
  • membrane protein
  • periplasmic protein
  • secreted protein

Fingerprint

Dive into the research topics of 'Multi-class subcellular location prediction for bacterial proteins'. Together they form a unique fingerprint.

Cite this