Subcellular location prediction of proteins using support vector machines with alignment of block sequences utilizing amino acid composition
2007

Predicting Protein Locations in Cells

Sample size: 940 publication 10 minutes Evidence: high

Author Information

Author(s): Tamura Takeyuki, Akutsu Tatsuya

Primary Institution: Bioinformatics Center, Institute for Chemical Research, Kyoto University

Hypothesis

Can we improve the prediction of protein subcellular locations using a novel method that combines sequence alignment and amino acid composition?

Conclusion

The proposed method achieves higher prediction accuracies for plant proteins compared to existing predictors that rely solely on sequence information.

Supporting Evidence

  • The overall accuracy of the proposed method was 90.96%.
  • The average Matthew's correlation coefficient (MCC) was 0.8655.
  • The method outperformed existing predictors for chloroplast and mitochondrial proteins.

Takeaway

This study created a new way to guess where proteins go in a cell by looking at their building blocks and how they fit together, which works better than older methods.

Methodology

The study used support vector machines and fivefold cross-validation to evaluate the prediction accuracy based on amino acid composition and sequence alignment.

Limitations

The method is less effective for predicting locations of proteins destined for the nucleus and cytosol compared to other locations.

Statistical Information

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2105-8-466

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication