Protein networks markedly improve prediction of subcellular localization in multiple eukaryotic species

Nucleic Acids Res. 2008 Nov;36(20):e136. doi: 10.1093/nar/gkn619. Epub 2008 Oct 4.

Abstract

The function of a protein is intimately tied to its subcellular localization. Although localizations have been measured for many yeast proteins through systematic GFP fusions, similar studies in other branches of life are still forthcoming. In the interim, various machine-learning methods have been proposed to predict localization using physical characteristics of a protein, such as amino acid content, hydrophobicity, side-chain mass and domain composition. However, there has been comparatively little work on predicting localization using protein networks. Here, we predict protein localizations by integrating an extensive set of protein physical characteristics over a protein's extended protein-protein interaction neighborhood, using a classification framework called 'Divide and Conquer k-Nearest Neighbors' (DC-kNN). These predictions achieve significantly higher accuracy than two well-known methods for predicting protein localization in yeast. Using new GFP imaging experiments, we show that the network-based approach can extend and revise previous annotations made from high-throughput studies. Finally, we show that our approach remains highly predictive in higher eukaryotes such as fly and human, in which most localizations are unknown and the protein network coverage is less substantial.

Publication types

  • Evaluation Study
  • Research Support, N.I.H., Extramural
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Animals
  • Cell Compartmentation
  • Green Fluorescent Proteins / analysis
  • Humans
  • Protein Interaction Mapping*
  • Proteins / analysis*
  • Saccharomyces cerevisiae Proteins / analysis

Substances

  • Proteins
  • Saccharomyces cerevisiae Proteins
  • Green Fluorescent Proteins