Inferring a Transcriptional Regulatory Network from Gene Expression Data Using Nonlinear Manifold Embedding
2011

Predicting Gene Interactions Using Kernel Embedding

Sample size: 1446 publication Evidence: high

Author Information

Author(s): Zare Hossein, Kaveh Mostafa, Khodursky Arkady

Primary Institution: National Institutes of Health, Bethesda, Maryland, United States of America

Hypothesis

Can kernel embedding techniques improve the prediction of transcriptional regulatory networks?

Conclusion

The KEREN method effectively predicts interactions between transcription factors and target genes by capturing geometric patterns in gene expression data.

Supporting Evidence

  • The KEREN method outperformed existing methods in predicting gene interactions.
  • Kernel embedding techniques effectively capture nonlinear dependencies in gene expression data.
  • The study utilized a large dataset of gene expression profiles across various conditions.

Takeaway

This study shows a new way to find out how genes talk to each other using a special math technique that looks at their behavior together.

Methodology

The study used kernel embedding techniques to analyze gene expression data and predict regulatory interactions.

Potential Biases

Potential bias due to the operon structure of genes was addressed by excluding operons from the analysis.

Limitations

The method relies on the availability of interactome data, which may not always be accessible.

Participant Demographics

The study focused on Escherichia coli as the model organism.

Digital Object Identifier (DOI)

10.1371/journal.pone.0021969

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication