BioProspecting: novel marker discovery obtained by mining the bibleome
2009

Discovering Genetic Markers Using Medical Literature

Sample size: 27000 publication Evidence: moderate

Author Information

Author(s): Elkin Peter L, Tuttle Mark S, Trusko Brett E, Brown Steven H

Primary Institution: Center for Biomedical Informatics, Mount Sinai School of Medicine

Hypothesis

Can mining the medical literature reveal novel relationships between genes, proteins, drugs, and disorders?

Conclusion

The study identified over 54 million potentially novel relationships between genes, proteins, drugs, and disorders from the medical literature.

Supporting Evidence

  • The study identified 468,371,305 relationships within the 27,000 NEJM articles.
  • Over 54 million relationships were potentially novel, indicating new connections not previously documented.
  • The methodology utilized natural language processing to analyze the literature.

Takeaway

Researchers looked at a lot of medical articles to find new connections between genes and diseases, which could help in understanding and treating illnesses.

Methodology

The study parsed full-text articles from the New England Journal of Medicine using a Multi-threaded Clinical Vocabulary Server to identify relationships between genes, proteins, drugs, and disorders.

Limitations

The study is limited to the articles available from the New England Journal of Medicine and may not represent the entire medical literature.

Digital Object Identifier (DOI)

10.1186/1471-2105-10-S2-S9

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication