LoCo: A New Scoring Function for Protein Structure Prediction
Author Information
Author(s): Moughon Stewart E, Samudrala Ram
Primary Institution: University of Washington
Hypothesis
Can a new scoring function improve the accuracy and speed of protein structure prediction?
Conclusion
The LoCo scoring function demonstrates superior accuracy and speed for protein structure prediction compared to existing methods.
Supporting Evidence
- LoCo outperformed all other functions in Cα RMSD rank of the best-scoring decoy.
- Statistically significant p-values < 0.05 for 26 out of the 29 other functions considered.
- LoCo is fast, requiring on average less than 6 microseconds per residue for interaction and scoring.
Takeaway
The LoCo function helps scientists predict how proteins fold by quickly scoring their shapes, making it easier to find the right structure.
Methodology
LoCo was trained on a large set of experimentally determined structures and optimized using standard sets of modeled structures, or 'decoys.'
Limitations
The study primarily focuses on main chain conformations and does not account for side chain interactions.
Statistical Information
P-Value
< 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