Improving Protein Structure Predictions with Combined Methods
Author Information
Author(s): Jonathan G. Lees, Robert W. Janes
Primary Institution: Queen Mary, University of London
Hypothesis
Can combining sequence-based prediction methods with spectroscopic data improve the accuracy of protein secondary structure determinations?
Conclusion
Combining sequence prediction with experimentally determined spectroscopic methods for protein secondary structure content significantly enhances the accuracy of the overall results obtained.
Supporting Evidence
- Sequence prediction methods showed accuracies nearly comparable to spectroscopic methods.
- Combining spectroscopic and sequence techniques produced significant overall improvements in secondary structure determinations.
- The study demonstrated that using synchrotron radiation circular dichroism data with sequence methods also shows improvements.
Takeaway
This study shows that using both computer predictions and lab measurements together helps scientists figure out protein shapes better than using just one method.
Methodology
The study used neural network methods for sequence predictions and compared them with results from circular dichroism and infrared spectroscopy.
Limitations
The study may not cover all types of proteins, especially those with high β-sheet content.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website