Prediction of amyloid fibril-forming segments based on a support vector machine
2009

Predicting Amyloid Fibril-Forming Segments

Sample size: 2452 publication Evidence: moderate

Author Information

Author(s): Tian Jian, Wu Ningfeng, Guo Jun, Fan Yunliu

Primary Institution: Biotechnology Research Institute, Chinese Academy of Agricultural Sciences, Beijing, PR China

Hypothesis

Can we identify hexpeptides associated with amyloid fibrillar aggregates using a support vector machine?

Conclusion

The Pafig method is effective for identifying hexpeptides linked to fibrillar aggregates and can aid in large-scale proteomic analyses.

Supporting Evidence

  • Pafig achieved an overall accuracy of 81% in predicting fibril-forming hexpeptides.
  • 5.08% of the predicted hexpeptides showed a high aggregation propensity.
  • The method was validated using a 10-fold cross-validation approach.

Takeaway

This study created a tool that helps find tiny parts of proteins that can clump together and cause diseases.

Methodology

The study used a support vector machine trained on a dataset of hexpeptides to predict aggregation propensity.

Limitations

The model may overlook structural features of proteins and the training dataset is small compared to the total number of hexpeptides.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2105-10-S1-S45

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication