Bioinformatics Vol. 17 no. 90001 2001
Pages S234-S242
© 2001 Oxford University Press
Improved prediction of the number of residue contacts in proteins by recurrent neural networks
1 Department of Information and Computer
Science, Institute for Genomics and Bioinformatics, University of
California, Irvine, Irvine, CA 92697-3425, USA
2 Department of Biological Chemistry,
College of Medicine, University of California, Irvine
3 CIRB Biocomputing Unit and Lab. of
Biophysics, Dept. of Biology, University of Bologna, Bologna,
40126, Italy
Received on February 6, 2001
; revised on March 21, 2001
; accepted on March 21, 2001
Knowing the number of residue contacts in a protein is crucial for deriving constraints useful in modeling protein folding, protein structure, and/or scoring remote homology searches. Here we use an ensemble of bi-directional recurrent neural network architectures and evolutionary information to improve the state-of-the-art in contact prediction using a large corpus of curated data. The ensemble is used to discriminate between two different states of residue contacts, characterized by a contact number higher or lower than the average value of the residue distribution. The ensemble achieves performances ranging from 70.1% to 73.1% depending on the radius adopted to discriminate contacts (6Âto 12Â). These performances represent gains of 15% to 20% over the base line statistical predictors always assigning an aminoacid to the most numerous state, 3% to 7% better than any previous method. Combination of different radius predictors further improves the performance.
Server: http://promoter.ics.uci.edu/BRNN-PRED/
Contact: pfbaldi{at}ics.uci.edu
* To whom all correspondence should be addressed.
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  J. Song, H. Tan, K. Takemoto, and T. Akutsu HSEpred: predict half-sphere exposure from protein sequences Bioinformatics, July 1, 2008; 24(13): 1489 - 1497. [Abstract] [PDF]
|
|
|
|
 |
|
 M. Desclozeaux, I. N. Krylova, F. Horn, R. J. Fletterick, and H. A. Ingraham Phosphorylation and Intramolecular Stabilization of the Ligand Binding Domain in the Nuclear Receptor Steroidogenic Factor 1 Mol. Cell. Biol., October 15, 2002; 22(20): 7193 - 7203. [Abstract] [Full Text] [PDF]
|
|