Automatic classification of protein functions from the literature
2003
Automatic Classification of Protein Functions from the Literature
Sample size: 254
publication
Evidence: moderate
Author Information
Author(s): Christian Blaschke, Alfonso Valencia
Primary Institution: CNB-CSIC, Madrid, Spain
Conclusion
The study presents a system for automatic classification of protein functions that enhances the annotation process by linking terms to relevant literature.
Supporting Evidence
- The system can automatically suggest classifications for new entities based on published knowledge.
- It provides links to documents that justify the proposed relations for human experts.
- The methodology allows for the clustering of genes based on literature similarities.
Takeaway
This study created a computer program that helps scientists figure out what proteins do by reading lots of scientific papers and finding important words.
Methodology
The system uses statistical information extraction techniques to analyze text and identify significant terms related to genes and proteins.
Limitations
The system struggles with ambiguities in gene and protein names and the lack of strict nomenclature.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website