Discovering gene functional relationships using FAUN (Feature Annotation Using Nonnegative matrix factorization)
2010

FAUN: A Tool for Discovering Gene Functional Relationships

Sample size: 110 publication Evidence: moderate

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)

10.1186/1471-2105-11-S6-S14

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication