Three-stage prediction of protein ß-sheets by neural networks, alignments and graph algorithms
Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California Irvine, CA 92697, USA
*To whom correspondence should be addressed.
Motivation: Protein ß-sheets play a fundamental role in protein structure, function, evolution and bioengineering. Accurate prediction and assembly of protein ß-sheets, however, remains challenging because protein ß-sheets require formation of hydrogen bonds between linearly distant residues. Previous approaches for predicting ß-sheet topological features, such as ß-strand alignments, in general have not exploited the global covariation and constraints characteristic of ß-sheet architectures.
Results: We propose a modular approach to the problem of predicting/assembling protein ß-sheets in a chain by integrating both local and global constraints in three steps. The first step uses recursive neural networks to predict pairing probabilities for all pairs of interstrand ß-residues from profile, secondary structure and solvent accessibility information. The second step applies dynamic programming techniques to these probabilities to derive binding pseudoenergies and optimal alignments between all pairs of ß-strands. Finally, the third step uses graph matching algorithms to predict the ß-sheet architecture of the protein by optimizing the global pseudoenergy while enforcing strong global ß-strand pairing constraints. The approach is evaluated using cross-validation methods on a large non-homologous dataset and yields significant improvements over previous methods.
Availability: http://www.igb.uci.edu/servers/psss.html
Contact: pfbaldi{at}ics.uci.edu
Received on January 15, 2005; accepted on March 27, 2005
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  H. Ashkenazy and Y. Kliger Reducing phylogenetic bias in correlated mutation analysis Protein Eng. Des. Sel., January 12, 2010; (2010) gzp078v1. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 M. Lippi and P. Frasconi Prediction of protein {beta}-residue contacts by Markov logic networks with grounding-specific weights Bioinformatics, September 15, 2009; 25(18): 2326 - 2333. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 A. N. Tegge, Z. Wang, J. Eickholt, and J. Cheng NNcon: improved protein contact map prediction using 2D-recursive neural networks Nucleic Acids Res., July 1, 2009; 37(suppl_2): W515 - W518. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
A. Randall, J. Cheng, M. Sweredoski, and P. Baldi TMBpro: secondary structure, {beta}-contact and tertiary structure prediction of transmembrane {beta}-barrel proteins Bioinformatics, February 15, 2008; 24(4): 513 - 520. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
S. Hochreiter, M. Heusel, and K. Obermayer Fast model-based protein homology detection without alignment Bioinformatics, July 15, 2007; 23(14): 1728 - 1736. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
J. Cheng and P. Baldi A machine learning information retrieval approach to protein fold recognition Bioinformatics, June 15, 2006; 22(12): 1456 - 1463. [Abstract] [Full Text] [PDF]
|
|