FAUN: A Tool for Discovering Gene Functional Relationships
Author Information
Author(s): Tjioe Elina, Berry Michael W, Homayouni Ramin
Primary Institution: University of Tennessee
Hypothesis
Can nonnegative matrix factorization (NMF) effectively extract functional relationships among genes from biomedical literature?
Conclusion
FAUN assists researchers in efficiently using biomedical literature and provides utilities for knowledge discovery.
Supporting Evidence
- FAUN was tested on three manually constructed gene document collections.
- FAUN achieved classification accuracies of 98%, 88.2%, and 86.4% for three datasets.
- FAUN allows for the discovery of novel gene relationships from literature.
Takeaway
FAUN is a computer program that helps scientists find connections between genes by looking at scientific articles.
Methodology
FAUN uses nonnegative matrix factorization to analyze gene document collections and extract functional relationships.
Limitations
The interpretation of NMF factors can be non-intuitive, and the software may not handle all high-throughput genomic data effectively.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website