BLProt: prediction of bioluminescent proteins based on support vector machine and relieff feature selection
2011

BLProt: Predicting Bioluminescent Proteins

Sample size: 300 publication 10 minutes Evidence: high

Author Information

Author(s): Kandaswamy Krishna Kumar, Pugalenthi Ganesan, Hazrati Mehrnaz Khodam, Kalies Kai-Uwe, Martinetz Thomas

Primary Institution: University of Lübeck

Hypothesis

Can a Support Vector Machine (SVM) effectively predict bioluminescent proteins from their primary sequences?

Conclusion

BLProt can accurately identify bioluminescent proteins from sequence information, achieving over 80% accuracy.

Supporting Evidence

  • BLProt achieved 80% accuracy from testing.
  • The model was trained on 300 bioluminescent and 300 non-bioluminescent proteins.
  • BLProt outperformed traditional methods like BLAST and HMM in predicting bioluminescent proteins.

Takeaway

Scientists created a computer program that can guess which proteins glow in the dark, helping researchers save time and effort.

Methodology

The study used a Support Vector Machine trained on a dataset of bioluminescent and non-bioluminescent proteins, applying feature selection techniques.

Potential Biases

Potential bias in the dataset selection and feature extraction methods could affect the predictions.

Limitations

The model's performance may vary with different datasets and it relies on the quality of the input sequences.

Statistical Information

P-Value

0.001

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2105-12-345

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication