Discovering Semantic Features in Literature for Gene Associations
Author Information
Author(s): Monica Chagoyen, Pedro Carmona-Saez, Hagit Shatkay, Jose M Carazo, Alberto Pascual-Montano
Primary Institution: Centro Nacional de Biotecnologia – CSIC, Madrid, Spain
Hypothesis
Can automated text mining tools effectively analyze literature to assist in the interpretation of biological data?
Conclusion
The method can create literature profiles from relevant documents for sets of genes, aiding in the exploration of functional associations and clustering.
Supporting Evidence
- The method successfully created literature profiles for 575 genes.
- Semantic features were identified that help in understanding gene functions.
- The approach allows for clustering genes based on their literature profiles.
Takeaway
This study shows how we can use computer programs to read lots of scientific papers and find connections between genes, helping scientists understand how they work together.
Methodology
The study used non-negative matrix factorization (NMF) to create literature profiles from gene-related documents.
Limitations
The method requires a collection of relevant literature, which may not always be available.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website