Document Citation |
Title:
A Mutation-centric Approach To Identifying Pharmacogenomic Relations In Text.
Author(s):
Rance B, Doughty E, Demner-Fushman D, Kann MG, Bodenreider O.
Institution(s):
1) National Library of Medicine, Bethesda, MD 20894, USA
2) University of Maryland, Baltimore County, Baltimore, MD 21250, USA
Source:
Journal of Biomedical Informatics. June 2012;45(5):835-841.
Abstract:
Objectives: To explore the notion of mutation-centric pharmacogenomic relation extraction and to evaluate
our approach against reference pharmacogenomic relations.
Methods: From a corpus of MEDLINE abstracts relevant to genetic variation, we identify co-occurrences
between drug mentions extracted using MetaMap and RxNorm, and genetic variants extracted by
EMU. The recall of our approach is evaluated against reference relations curated manually in PharmGKB.
We also reviewed a random sample of 180 relations in order to evaluate its precision.
Results: One crucial aspect of our strategy is the use of biological knowledge for identifying specific
genetic variants in text, not simply gene mentions. On the 104 reference abstracts from PharmGKB,
the recall of our mutation-centric approach is 33-46%. Applied to 282,000 abstracts from MEDLINE,
our approach identifies pharmacogenomic relations in 4534 abstracts, with a precision of 65%.
Conclusions: Compared to a relation-centric approach, our mutation-centric approach shows similar
recall, but slightly lower precision. We show that both approaches have limited overlap in their results,
but are complementary and can be used in combination. Rather than a solution for the automatic curation
of pharmacogenomic knowledge, we see these high-throughput approaches as tools to assist biocurators
in the identification of pharmacogenomic relations of interest from the published literature. This
investigation also identified three challenging aspects of the extraction of pharmacogenomic relations,
namely processing full-text articles, sequence validation of DNA variants and resolution of genetic variants
to reference databases, such as dbSNP.
Publication Type: JOURNAL
More about this article: