Identification of potential riboswitch elements in Homo Sapiens mRNA 5’UTR sequences using Positive-Unlabeled machine learning
2023

Finding Potential Riboswitches in Human mRNA

Sample size: 48631 publication 10 minutes Evidence: moderate

Author Information

Author(s): Raymond William S., DeRoo Jacob, Munsky Brian

Primary Institution: Colorado State University

Hypothesis

Is there a H. Sapiens riboswitch dependent on only small molecule ligands?

Conclusion

The study identified 436 human mRNA 5'UTRs that may contain riboswitch elements, providing a basis for future experimental validation.

Supporting Evidence

  • 67,683 riboswitch sequences were used as positive examples.
  • 20 classifiers achieved validation accuracy ranging from 75% to 99%.
  • 436 sequences were identified as potential riboswitches by all classifiers.

Takeaway

Scientists used a computer program to find parts of human RNA that might work like switches, turning genes on or off, which could help us understand diseases better.

Methodology

Positive-unlabeled machine learning classifiers were trained on known riboswitch sequences and applied to human mRNA 5'UTR sequences.

Potential Biases

Potential bias in the training data due to reliance on known riboswitch sequences.

Limitations

The study is entirely computational and lacks experimental validation for the identified riboswitches.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1101/2023.11.23.568398

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication