Real value prediction of protein solvent accessibility using enhanced PSSM features
2008
Predicting Protein Solvent Accessibility Using Enhanced Features
Sample size: 500
publication
Evidence: high
Author Information
Author(s): Chang Darby Tien-Hao, Huang Hsuan-Yu, Syu Yu-Tang, Wu Chih-Peng
Primary Institution: National Cheng Kung University
Hypothesis
Can enhanced PSSM features improve the prediction of protein solvent accessibility?
Conclusion
The proposed method outperforms existing packages for predicting protein solvent accessibility.
Supporting Evidence
- The proposed method achieved a mean absolute error of 14.8% on the Barton dataset.
- The method outperformed five existing ASA predictors.
- The feature selection mechanism can be applied to other regression problems.
Takeaway
This study helps scientists predict how much of a protein is exposed to water, which is important for understanding how proteins work.
Methodology
The study enhances PSSM features and uses support vector regression to predict solvent accessibility.
Limitations
The method's performance may be affected by the datasets used for training and testing.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website