Using Text Mining to Improve Genome Annotation
Author Information
Author(s): Aerts Stein, Haeussler Maximilian, van Vooren Steven, Griffith Obi L, Hulpiau Paco, Jones Steven JM, Montgomery Stephen B, Bergman Casey M
Primary Institution: Laboratory of Neurogenetics, Department of Molecular and Developmental Genetics, VIB, Leuven, Belgium
Hypothesis
Can text-mining technologies enhance the regulatory annotation process in genome biology?
Conclusion
Text-mining technologies can be successfully integrated with genome annotation systems, increasing the availability of annotated cis-regulatory data.
Supporting Evidence
- Text-mining can identify relevant publications with high cis-regulatory content.
- The study estimates that at least 30,000 papers contain unannotated cis-regulatory data.
- DNA sequences can be extracted from full-text articles and mapped to genome sequences.
Takeaway
This study shows that computers can help scientists find important information in research papers about how genes are controlled, making it easier to understand genetics.
Methodology
The study developed text-mining strategies to identify relevant publications and extract sequence information to assist the regulatory annotation process.
Potential Biases
Potential biases may arise from the selection of papers and the accuracy of the text-mining algorithms.
Limitations
The study relies on the accuracy of text extraction and the completeness of the literature management system.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website