Name
Abstract | ||
|---|---|---|
Secondary structure prediction is an important step in deter- mining the structure and function of the proteins. A funda- mental assumption of the current Bayesian secondary struc- ture prediction methods is the conditional independence of residues which occur in distinct segments (1). This assump- tion enables the exact calculation of posterior probabilities by using pre-determined probabilistic models. However, this assumption is clearly violated in the case of protein sequences due to the existence of structural motifs which rely on sequentially distant segments interacting in three- dimensional space, including β-sheets. It has been sug- gested that the inability to capture such nonlocal interac- tions may be the main reason for the low accuracy typically achieved in β-strand prediction (1), (2). Furthermore, the current Bayesian segmentations are based on the maximum a posteriori or marginal posterior mode searches, which re- turn a single segmentation that is optimal in some sense. In this paper, we introduce a new secondary structure predic- tion method based on a modified version of the well-known stack decoder. The proposed method is an N-best search al- gorithm which enables us to use the returned multiple seg- mentations to improve over a single segmentation. Also due to the way the segmentations are constructed it is possible to exploit the non-local interactions between β-strands in a sub-optimal way with the ultimate goal of increasing the overall prediction accuracy. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/ICASSP.2005.1416114 | ICASSP (4) |
Keywords | Field | DocType |
proteins,hmm,conditional independence,bayesian methods,search algorithm,sequences,signal processing,hydrogen,beta sheets,hidden markov models,probabilistic model,protein sequence,amino acids,image processing,probability,accuracy,decoding,posterior probability,three dimensional,amino acid sequence | Search algorithm,Pattern recognition,Conditional independence,Segmentation,Computer science,Posterior probability,Artificial intelligence,Maximum a posteriori estimation,Probabilistic logic,Hidden Markov model,Bayesian probability | Conference |
Volume | ISSN | ISBN |
4 | 1520-6149 | 0-7803-8874-7 |
Citations | PageRank | References |
0 | 0.34 | 2 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zafer Aydin | 1 | 109 | 10.27 |
| Toygar Akgun | 2 | 90 | 9.39 |
| Yucel Altunbasak | 3 | 1507 | 116.78 |