Prediction of nuclear proteins using SVM and HMM models
2009

Predicting Nuclear Proteins Using SVM and HMM Models

Sample size: 10372 publication Evidence: high

Author Information

Author(s): Kumar Manish, Raghava Gajendra PS

Primary Institution: Bioinformatics Centre, Institute of Microbial Technology

Hypothesis

The study aims to develop a new method for predicting nuclear proteins with higher accuracy.

Conclusion

The study describes a highly accurate method for predicting nuclear proteins using a combination of SVM and HMM models.

Supporting Evidence

  • The hybrid method achieved an accuracy of 94.61%.
  • The method predicted 31.51% of proteins as nuclear in Saccharomyces cerevisiae.
  • NpPred outperformed existing methods on independent datasets.

Takeaway

Scientists created a new tool to help find proteins in cells that are important for keeping the cell's DNA safe and working properly.

Methodology

The study used Support Vector Machines (SVM) and Hidden Markov Models (HMM) to analyze protein sequences and predict nuclear localization.

Limitations

The method only considers steady-state localizations and does not account for proteins that enter the nucleus temporarily.

Statistical Information

P-Value

0.001

Statistical Significance

p<0.001

Digital Object Identifier (DOI)

10.1186/1471-2105-10-22

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication