Directed acyclic graph kernels for structural RNA analysis
2008

New Method for Analyzing Structural RNA Sequences

Sample size: 7169 publication Evidence: high

Author Information

Author(s): Sato Kengo, Mituyama Toutai, Asai Kiyoshi, Sakakibara Yasubumi

Primary Institution: Japan Biological Informatics Consortium (JBIC)

Hypothesis

Can directed acyclic graphs improve the computation speed of stem kernels for RNA analysis?

Conclusion

The new method significantly increases the computation speed for stem kernels and can reliably measure structural RNA similarities.

Supporting Evidence

  • The new technique significantly reduces computation time for stem kernels.
  • Stem kernels can be applied to various kernel methods including SVMs.
  • The method outperformed existing methods in detecting known ncRNAs.

Takeaway

This study created a faster way to compare RNA sequences by using special graphs, making it easier to find important RNA types.

Methodology

The study developed directed acyclic graphs from base-pairing probability matrices to improve the computation of stem kernels.

Limitations

The method may not effectively detect unknown ncRNAs compared to existing methods.

Digital Object Identifier (DOI)

10.1186/1471-2105-9-318

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication