Developing Controlled Vocabularies for Metabolomics Using Text Mining
Author Information
Author(s): Irena Spasić, Daniel Schober, Susanna-Assunta Sansone, Dietrich Rebholz-Schuhmann, Douglas B Kell, Norman W Paton
Primary Institution: The University of Manchester
Hypothesis
Can text mining facilitate the rapid development of controlled vocabularies for metabolomics technologies?
Conclusion
Text mining can efficiently expand controlled vocabularies by acquiring terms from scientific literature.
Supporting Evidence
- The initial controlled vocabularies for NMR and GC were compiled manually, providing 243 and 152 terms respectively.
- A total of 5,699 and 2,612 new terms were acquired automatically from the literature for NMR and GC.
- Full-text articles, especially the Materials and Methods sections, were identified as the major source of technology-specific terms.
Takeaway
This study shows how computers can help scientists quickly gather important words and phrases used in research about metabolites, making it easier to share information.
Methodology
The study used text mining to automatically extract terms from scientific literature, focusing on the Materials and Methods sections of articles.
Limitations
The study primarily focused on two specific technologies (NMR and GC) and may not generalize to all metabolomics technologies.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website