Contrast and variability in gene names

Contrast And Variability In Gene Names K. Bretonnel Cohen Center for Computational Pharmacology University of Colorado Health Sciences Center kevin.cohen@uchsc.edu Andrew E. Dolbey Center for Computational Pharmacology University of Colorado Health Sciences Center andrew.dolbey@uchsc.edu George K. Acquaah-Mensah Center for Computational Pharmacology University of Colorado Health Sciences Center george.acquaah-mensah@uchsc.edu Lawrence Hunter Center for Computational Pharmacology University of Colorado Health Sciences Center larry.hunter@uchsc.edu Abstract We studied contrast and variability in a corpus of gene names to identify potential heuristics for use in performing entity identification in the molecular biology domain. Based on our findings, we developed heuristics for mapping weakly matching gene names to their official gene names. We then tested these heuristics against a large body of Medline abstracts, and found that using these heuristics can increase recall, with varying levels of precision. Our findings also underscored the importance of good information retrieval and of the ability to disambiguate between genes, proteins, RNA, and a variety of other referents for performing entity identification with high precision. 1 Introduction Almost all current approaches to entity identification are actually not tackling the identification per se, but rather merely the (still difficult) location of named entities in text. The difference between these is that entity location consists of the (difficult enough) task of demarcation of the boundaries of names in text, whereas entity identification consists of the same thing, plus mapping the located names to the canonical entities that they refer to. In this paper we present data on variability in the orthographic representation of gene names, and then show how knowledge about that variability can be used for heuristics that increase recall in the entity identification task. (We use the term "gene name" as shorthand for "gene, protein, or RNA name.") To understand why it is important to be able to map located names to the canonical entities that they refer to, consider the outcome of running an information extraction routine with access only to entity location against a hypothetical document about rat somatotropin. It contains the synonymous names rat somatotropin, somatotropin, and growth hormone, all of which refer to the same biomolecule, whose canonical name we will assume to be somatotropin. (The document is hypothetical; somatotropin and its synonyms are not.) Suppose that the paper includes three separate assertions, of the form somatotropin is upregulated by X, transcription of rat somatotropin is blocked by Y, and growth hormone is expressed by cells of type Z. The system correctly extracts three assertions, but incorrectly attributes them to three separate biomolecules, only one of which is the canonical form. Now consider the outcome of running an information extraction routine with access to entity identification against the same document. Again, the system extracts three assertions, but this time all three assertions are correctly attributed to the same biomolecule, i.e. somatotropin. Krauthammer et al. (2000), who are arguably the only researchers who have attempted to do actual identification as we Association for Computational Linguistics. the Biomedical Domain, Philadelphia, July 2002, pp. 14-20. Proceedings of the Workshop …

Content truncated to 500 words