Gene function prediction based on genomic context clustering and discriminative learning: an application to bacteriophages
2007

Automated Gene Function Prediction for Bacteriophages

Sample size: 296 publication Evidence: moderate

Author Information

Author(s): Li Jason, Halgamuge Saman K, Kells Christopher I, Tang Sen-Lin

Primary Institution: University of Melbourne

Hypothesis

Can an automated system predict gene functions in bacteriophage genomes using genomic context clustering and discriminative learning?

Conclusion

The proposed system effectively predicts gene functions in bacteriophages with an average accuracy of around 80%.

Supporting Evidence

  • The system achieved an average prediction accuracy of ~80% across nine gene functions.
  • Functional predictions were made for three uncharacterized genes and twelve genes that could not be identified by sequence alignment.
  • The method may be extended to other microbial genomes due to shared characteristics.

Takeaway

This study created a computer program that helps scientists figure out what genes do in viruses that infect bacteria, using patterns in their DNA.

Methodology

The study used a system called SynFPS that clusters genomes based on gene distribution and employs a Support Vector Machine for predictions.

Limitations

The method may not be applicable to genomes that do not share similar characteristics with bacteriophages.

Digital Object Identifier (DOI)

10.1186/1471-2105-8-S4-S6

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication