Text Detective: a rule-based system for gene annotation in biomedical texts
2005

Text Detective: A System for Gene Annotation in Biomedical Texts

Sample size: 940 publication Evidence: moderate

Author Information

Author(s): Tamames Javier, Christian Blaschke, Lynette Hirschman, Alfonso Valencia, Alexander Yeh

Primary Institution: Alma Bioinformatics S.L.

Hypothesis

Can a rule-based system effectively identify and normalize gene mentions in biomedical texts?

Conclusion

Text Detective achieves high precision and recall in identifying gene mentions in biomedical literature.

Supporting Evidence

  • Text Detective achieved 84% precision and 71% recall for gene identification.
  • The system is capable of annotating a wide range of biological entities.
  • Performance improves with longer texts due to more context information.

Takeaway

Text Detective is like a smart helper that finds and names genes in science articles, making it easier for researchers to understand them.

Methodology

The system uses a combination of rules and biological lexicons to identify and normalize gene mentions.

Potential Biases

Errors may concentrate in difficult cases where gene names are common acronyms.

Limitations

The system's performance can vary based on text length and the ambiguity of gene names.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2105-6-S1-S10

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication