Evolving Hidden Markov Models for Protein Structure Prediction
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)
Want to read the original?
Access the complete publication on the publisher's website