Hidden Markov Model Variants and their Application
2006

Hidden Markov Model Variants and their Application

publication Evidence: moderate

Author Information

Author(s): Stephen Winters-Hilt

Primary Institution: Department of Computer Science, University of New Orleans

Hypothesis

Markov statistical methods may make it possible to develop an unsupervised learning process that can automatically identify genomic structure in prokaryotes.

Conclusion

The study demonstrates that a gap-interpolating Markov model can improve gene prediction accuracy in prokaryotic genomes.

Supporting Evidence

  • The study developed software for augmented open reading frame characterization.
  • Using a bootstrap gene-annotation process, the study achieved high accuracy in gene prediction.
  • The gap-interpolating Markov model improved predictions by identifying motifs around start codons.

Takeaway

This study is about using special math models to help find genes in bacteria by looking at their DNA patterns.

Methodology

The study utilized Hidden Markov Models (HMMs) and gap-interpolating Markov models (gIMMs) for gene prediction in prokaryotic and eukaryotic genomes.

Limitations

The performance of the HMM is limited by its single gene assumption, particularly in alternatively spliced regions.

Digital Object Identifier (DOI)

10.1186/1471-2105-7-S2-S14

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication