Detecting Gene-Gene Interactions with Neural Networks
Author Information
Author(s): Motsinger-Reif Alison A, Fanelli Theresa J, Davis Anna C, Ritchie Marylyn D
Primary Institution: Bioinformatics Research Center, North Carolina State University
Hypothesis
Can Grammatical Evolution Neural Networks (GENN) effectively detect gene-gene interactions in the presence of common data errors?
Conclusion
GENN is a promising method to detect gene-gene interaction, even in the presence of common types of error found in real data.
Supporting Evidence
- GENN is robust to missing data and genotyping error.
- Phenocopy reduces the power of both GENN and MDR.
- GENN has higher power than MDR in some cases of genetic heterogeneity.
Takeaway
Scientists created a computer program that helps find connections between genes, even when the data is messy or incomplete.
Methodology
The study used Grammatical Evolution Neural Networks (GENN) to analyze simulated genetic data with various types of noise.
Limitations
The study primarily focused on specific types of noise and may not generalize to all genetic data scenarios.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website