Identification of histone modifications in biomedical text for supporting epigenomic research
2009
Identifying Histone Modifications in Biomedical Text
Sample size: 1000
publication
Evidence: high
Author Information
Author(s): Corinna Kolářik, Roman Klinger, Martin Hofmann-Apitius
Primary Institution: Fraunhofer Institute Algorithms and Scientific Computing (SCAI)
Hypothesis
No approach has been published so far for identifying histone modifications in text.
Conclusion
The developed approach highly improves the retrieval of articles describing histone modifications.
Supporting Evidence
- The approach achieved F1 measures of 0.84 on the training corpus and 0.81 on an independent test corpus.
- The standardization process enabled the correct transformation of 96% of terms from the training corpus.
- The study identified over 24,600 abstracts related to epigenomics in PubMed.
Takeaway
This study created a method to find mentions of histone modifications in scientific texts, which helps researchers discover new information faster.
Methodology
The study used Conditional Random Fields (CRF) for identifying histone modifications and standardizing terms.
Limitations
The study faced challenges with the lack of comprehensive terminologies for histone modifications.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website