Thesaurus-based disambiguation of gene symbols

Bob JA Schijvenaars¹ , Barend Mons¹ , Marc Weeber¹ , Martijn J Schuemie¹ , Erik M van Mulligen¹ , Hester M Wain² and Jan A Kors¹

¹Department of Medical Informatics, Erasmus University Medical Center Rotterdam, P.O. Box 1738, 3000 DR Rotterdam, The Netherlands

²HUGO Gene Nomenclature Committee, Department of Biology, University College London, Wolfson House, 4 Stephenson Way, London NW1 2HE, UK

author email corresponding author email

BMC Bioinformatics 2005, 6:149doi:10.1186/1471-2105-6-149


Published:	16 June 2005

Abstract

Background

Massive text mining of the biological literature holds great promise of relating disparate information and discovering new knowledge. However, disambiguation of gene symbols is a major bottleneck.

Results

We developed a simple thesaurus-based disambiguation algorithm that can operate with very little training data. The thesaurus comprises the information from five human genetic databases and MeSH. The extent of the homonym problem for human gene symbols is shown to be substantial (33% of the genes in our combined thesaurus had one or more ambiguous symbols), not only because one symbol can refer to multiple genes, but also because a gene symbol can have many non-gene meanings. A test set of 52,529 Medline abstracts, containing 690 ambiguous human gene symbols taken from OMIM, was automatically generated. Overall accuracy of the disambiguation algorithm was up to 92.7% on the test set.

Conclusion

The ambiguity of human gene symbols is substantial, not only because one symbol may denote multiple genes but particularly because many symbols have other, non-gene meanings. The proposed disambiguation approach resolves most ambiguities in our test set with high accuracy, including the important gene/not a gene decisions. The algorithm is fast and scalable, enabling gene-symbol disambiguation in massive text mining applications.