The prediction of membrane protein structure and genome structural annotation
2003
Predicting Membrane Protein Structure
Sample size: 15
publication
10 minutes
Evidence: moderate
Author Information
Author(s): Pier Luigi Martelli, Piero Fariselli, Gianluca Tasco, Rita Casadio
Primary Institution: University of Bologna
Hypothesis
Can new methods accurately predict the structure of membrane proteins?
Conclusion
The study demonstrates that new prediction methods can accurately identify membrane protein structures with low false positive and negative rates.
Supporting Evidence
- New methods based on HMM and NN can predict membrane protein structures with high accuracy.
- False positive rates for the methods are low, with 10% for CINZIA and 3% for ENSEMBLE.
- The study suggests that about 20% of membrane proteins are alpha helical, while 1-2% are beta barrel.
Takeaway
Scientists created new tools to help find and understand proteins in cell membranes, which are important for many functions in living things.
Methodology
The study used hidden Markov models and neural networks to predict membrane protein topography.
Limitations
The methods may not be applicable to all types of membrane proteins and rely on existing sequence data.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website