An evolutionary method for learning HMM structure: prediction of protein secondary structure
2007

Evolving Hidden Markov Models for Protein Structure Prediction

Sample size: 1662 publication 10 minutes Evidence: moderate

Author Information

Author(s): Won Kyoung-Jae, Hamelryck Thomas, PrĂ¼gel-Bennett Adam, Krogh Anders

Primary Institution: Bioinformatics Centre, Department of Molecular Biology, University of Copenhagen

Hypothesis

Can an evolutionary method improve the design of Hidden Markov Models (HMMs) for predicting protein secondary structure?

Conclusion

The evolutionary method successfully designs HMM topologies that improve prediction quality for protein secondary structures.

Supporting Evidence

  • The evolved HMM captures features of protein sequence and structure.
  • The method improved previously suggested evolutionary methods.
  • The predictor shows good performance under single-sequence conditions.
  • Probabilistic information on predictions is provided by the evolved HMM.

Takeaway

This study shows a way to automatically create better models for predicting how proteins fold, which helps scientists understand proteins better.

Methodology

The study used Genetic Algorithms to evolve the structure of HMMs for protein secondary structure prediction.

Potential Biases

The results may be biased due to the specific dataset used for training and testing.

Limitations

The method is relatively slow and requires significant computational resources.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2105-8-357

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication