ProMiner: rule-based protein and gene entity recognition
2005

ProMiner: A System for Recognizing Protein and Gene Names

Sample size: 250 publication Evidence: high

Author Information

Author(s): Daniel Hanisch, Katrin Fundel, Heinz-Theodor Mevissen, Ralf Zimmer, Juliane Fluck

Primary Institution: Fraunhofer Institute SCAI

Hypothesis

The ProMiner system can effectively identify protein and gene names in biomedical text using a rule-based approach.

Conclusion

The ProMiner system achieved high F-measures in identifying protein and gene names, particularly excelling in the fly and yeast organisms.

Supporting Evidence

  • The ProMiner system achieved an F-measure of approximately 0.8 for mouse and fly, and about 0.9 for yeast.
  • The system was tested on a benchmark set of 250 biomedical abstracts.
  • ProMiner's performance was evaluated in the context of the BioCreAtIvE challenge.

Takeaway

ProMiner is like a smart helper that finds names of proteins and genes in scientific papers, making it easier for scientists to gather information.

Methodology

The ProMiner system uses a pre-processed synonym dictionary and a rule-based approach to identify protein and gene names in biomedical texts.

Potential Biases

Potential biases may arise from the reliance on curated dictionaries and the ambiguity of gene names.

Limitations

The performance of ProMiner may vary based on the organism due to differences in naming conventions and ambiguities.

Digital Object Identifier (DOI)

10.1186/1471-2105-6-S1-S14

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication