New Protein Energy Model Using Evolutionary Information
Author Information
Author(s): Dong Qiwen, Wang Xiaolong, Lin Lei
Primary Institution: Harbin Institute of Technology
Hypothesis
Can knowledge-based mean force potentials at the profile level improve protein structure prediction?
Conclusion
Profile-level statistical potentials provide better discrimination for protein structure prediction than residue-level potentials.
Supporting Evidence
- Profile-level potentials outperform residue-level potentials in fold assessment.
- Distance-dependent and accessible surface potentials showed significant improvements.
- Profile-level potentials can improve the performance of threading methods.
Takeaway
This study shows that using information about how proteins have evolved can help us better predict their shapes.
Methodology
The study developed four types of profile-level statistical potentials and evaluated their performance using various protein structure models.
Potential Biases
Potential biases may arise from the selection of training and testing datasets.
Limitations
The performance may vary based on the dataset used for evaluation.
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