Literature DB >> 17570862

Learning biophysically-motivated parameters for alpha helix prediction.

Blaise Gassend1, Charles W O'Donnell, William Thies, Andrew Lee, Marten van Dijk, Srinivas Devadas.   

Abstract

BACKGROUND: Our goal is to develop a state-of-the-art protein secondary structure predictor, with an intuitive and biophysically-motivated energy model. We treat structure prediction as an optimization problem, using parameterizable cost functions representing biological "pseudo-energies". Machine learning methods are applied to estimate the values of the parameters to correctly predict known protein structures.
RESULTS: Focusing on the prediction of alpha helices in proteins, we show that a model with 302 parameters can achieve a Qalpha value of 77.6% and an SOValpha value of 73.4%. Such performance numbers are among the best for techniques that do not rely on external databases (such as multiple sequence alignments). Further, it is easier to extract biological significance from a model with so few parameters.
CONCLUSION: The method presented shows promise for the prediction of protein secondary structure. Biophysically-motivated elementary free-energies can be learned using SVM techniques to construct an energy cost function whose predictive performance rivals state-of-the-art. This method is general and can be extended beyond the all-alpha case described here.

Entities:  

Mesh:

Year:  2007        PMID: 17570862      PMCID: PMC1892091          DOI: 10.1186/1471-2105-8-S5-S3

Source DB:  PubMed          Journal:  BMC Bioinformatics        ISSN: 1471-2105            Impact factor:   3.169


  26 in total

1.  The Protein Data Bank.

Authors:  H M Berman; J Westbrook; Z Feng; G Gilliland; T N Bhat; H Weissig; I N Shindyalov; P E Bourne
Journal:  Nucleic Acids Res       Date:  2000-01-01       Impact factor: 16.971

2.  Predicting transmembrane protein topology with a hidden Markov model: application to complete genomes.

Authors:  A Krogh; B Larsson; G von Heijne; E L Sonnhammer
Journal:  J Mol Biol       Date:  2001-01-19       Impact factor: 5.469

3.  A novel method of protein secondary structure prediction with high segment overlap measure: support vector machine approach.

Authors:  S Hua; Z Sun
Journal:  J Mol Biol       Date:  2001-04-27       Impact factor: 5.469

4.  Exploiting the past and the future in protein secondary structure prediction.

Authors:  P Baldi; S Brunak; P Frasconi; G Soda; G Pollastri
Journal:  Bioinformatics       Date:  1999-11       Impact factor: 6.937

5.  Prediction of protein secondary structure at 80% accuracy.

Authors:  T N Petersen; C Lundegaard; M Nielsen; H Bohr; J Bohr; S Brunak; G P Gippert; O Lund
Journal:  Proteins       Date:  2000-10-01

6.  Cascaded multiple classifiers for secondary structure prediction.

Authors:  M Ouali; R D King
Journal:  Protein Sci       Date:  2000-06       Impact factor: 6.725

7.  HMMSTR: a hidden Markov model for local sequence-structure correlations in proteins.

Authors:  C Bystroff; V Thorsson; D Baker
Journal:  J Mol Biol       Date:  2000-08-04       Impact factor: 5.469

Review 8.  Review: protein secondary structure prediction continues to rise.

Authors:  B Rost
Journal:  J Struct Biol       Date:  2001 May-Jun       Impact factor: 2.867

9.  Secondary structure prediction with support vector machines.

Authors:  J J Ward; L J McGuffin; B F Buxton; D T Jones
Journal:  Bioinformatics       Date:  2003-09-01       Impact factor: 6.937

10.  EVA: continuous automatic evaluation of protein structure prediction servers.

Authors:  V A Eyrich; M A Martí-Renom; D Przybylski; M S Madhusudhan; A Fiser; F Pazos; A Valencia; A Sali; B Rost
Journal:  Bioinformatics       Date:  2001-12       Impact factor: 6.937

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.