Significantly improved prediction of subcellular localization by integrating text and protein sequence data

Computational prediction of protein subcellular localization is a challenging problem. Several approaches have been presented during the past few years; some attempt to cover a wide variety of localizations, while others focus on a small number of localizations and on specific organisms. We present...

Full description

Saved in:
Bibliographic Details
Published inPacific Symposium on Biocomputing. Pacific Symposium on Biocomputing p. 16
Main Authors Höglund, Annette, Blum, Torsten, Brady, Scott, Dönnes, Pierre, Miguel, John San, Rocheford, Matthew, Kohlbacher, Oliver, Shatkay, Hagit
Format Journal Article
LanguageEnglish
Published United States 2006
Subjects
Artificial Intelligence
Computer Simulation
Databases, Protein
Models, Biological
Proteins - genetics
Proteins - metabolism
Subcellular Fractions - metabolism
Online AccessGet more information

Cover

More Information
Summary:Computational prediction of protein subcellular localization is a challenging problem. Several approaches have been presented during the past few years; some attempt to cover a wide variety of localizations, while others focus on a small number of localizations and on specific organisms. We present a comprehensive system, integrating protein sequence-derived data and text-based information. Itis tested on three large data sets, previously used by leading prediction methods. The results demonstrate that our system performs significantly better than previously reported results, for a wide range of eukaryotic subcellular localizations.
ISSN:2335-6936