next up previous
Next: Introduction

Application of multiple sequence alignment profiles to improve protein secondary structure prediction.

James A. Cuff 1,2 and G. J. Barton 2\dag

1. Laboratory of Molecular Biophysics, Rex Richards Building, South Parks Road, Oxford, OX1 3QU, UK

2. European Molecular Biology Laboratory - European Bioinformatics Institute. Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK

\dagCorresponding Author: G. J. Barton, EMBL-European Bioinformatics Institute,
Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK.

Keywords: protein, secondary structure prediction, multiple sequence alignment, profiles, PSSM.

Abstract:

The effect of training a neural network secondary structure prediction algorithm with different types of multiple sequence alignment profiles derived from the same sequences, is shown to provide a range of accuracy from 70.5% to 76.4%. The best accuracy of 76.4% (standard deviation 8.4%), is 3.1% (Q3) and 4.4% (SOV2) better than the PHD algorithm run on the same set of 406 sequence non-redundant proteins that were not used to train either method. Residues predicted by the new method with a confidence value of 5 or greater, have an average Q3 accuracy of 84%, and cover 68% of the residues. Relative solvent accessibility based on a two state model, for 25, 5 and 0% accessibility are predicted at 76.2, 79.8 and 86.6% accuracy respectively. The source of the improvements obtained from training with different representations of the same alignment data are described in detail. The new Jnet prediction method resulting from this study is available in the Jpred secondary structure prediction server, and as a stand-alone computer program from: http://barton.ebi.ac.uk/



 
next up previous
Next: Introduction
James Cuff
2001-06-29