HHMMiR: efficient de novo prediction of microRNAs using hierarchical hidden Markov models
2009

HHMMiR: A New Method for Predicting MicroRNAs

Sample size: 527 publication Evidence: moderate

Author Information

Author(s): Kadri Sabah, Veronica Hinman, Panayiotis Benos

Primary Institution: Carnegie Mellon University

Hypothesis

Can a Hierarchical Hidden Markov Model (HHMM) effectively predict microRNA hairpins without relying on evolutionary conservation?

Conclusion

The HHMMiR algorithm achieved an average sensitivity of 84% and specificity of 88%, indicating its effectiveness in predicting miRNA genes across various species.

Supporting Evidence

  • The algorithm was trained on 527 human miRNA precursors and tested on various species.
  • HHMMiR predicted 85% of animal precursors and showed high specificity in predictions.
  • The model performed better than existing methods in most datasets.

Takeaway

The study created a new tool that helps find tiny RNA molecules called microRNAs in different organisms, even when their DNA isn't similar.

Methodology

The study used a Hierarchical Hidden Markov Model to predict miRNA hairpins based on structural and sequence information.

Potential Biases

The model may be biased towards the training data, particularly if the data is not representative of all possible miRNA structures.

Limitations

The model's performance may vary based on the initialization and the absence of certain base pairs or indels in sequences.

Statistical Information

P-Value

0.03

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2105-10-S1-S35

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication