Difference between revisions of "LocTree2 - Protein sub-cellular localization prediction for all domains of life"

From Rost Lab Open
(No difference)

Revision as of 19:52, 9 June 2012

Introduction

LocTree2 is a novel method to predict protein localization for all domains of life.

The novel aspects include:

  • the stunning number of 18 predicted classes for Eukaryota
  • 6 classes for Bacteria and 3 classes for Archaea
  • incorporation of no other information than of evolutionary profiles
  • very accurate in distinction membrane/water-soluble globular proteins
  • high robustness against sequencing errors
  • top performance even for protein fragments

Methods

Our framework combines three different systems of classification trees to predict the localization classes (Archaea: 3 classes; Bacteria: 6; Eukaryota: 18) File:Example.jpg

Input

Prediction algorithm

Contact

For questions, please contact localization@rostlab.org