RNAstrand: reading direction of structured RNAs in multiple sequence alignments
2007

RNAstrand: Predicting Reading Direction of Structured RNAs

Sample size: 5886 publication Evidence: high

Author Information

Author(s): Kristin Reiche, Peter F. Stadler

Primary Institution: University of Leipzig

Hypothesis

Can a support vector machine accurately classify the reading direction of structured RNAs from multiple sequence alignments?

Conclusion

The RNAstrand tool significantly improves the classification accuracy of structured RNAs' reading directions compared to previous methods.

Supporting Evidence

  • RNAstrand achieves classification accuracies of 90% and above for most ncRNA families.
  • The tool is integrated into the RNAz package, enhancing its usability.
  • RNAstrand provides a two-fold reduction in misclassifications compared to naive approaches.

Takeaway

RNAstrand is a computer program that helps scientists figure out which way a piece of RNA is read, which is important for understanding how it works.

Methodology

The study used a support vector machine to classify RNA reading directions based on folding energies and structural conservation.

Potential Biases

The SVM model may be biased due to the training data being independent in different classes.

Limitations

RNAstrand may not perform well on alignments not recognized as structured RNA by RNAz.

Statistical Information

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1748-7188-2-6

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication