@Article{Rebholz-Schuhmann_Kim_Yan-Evalu_and_cross-2013,
  author =	 {Rebholz-Schuhmann, Dietrich and Kim, Jee-Hyub and Yan, Ying 
                  and Dixit, Abhishek and Friteyre, Caroline and Hoehndorf, 
                  Robert and Backofen, Rolf and Lewin, Ian},
  title =	 {Evaluation and cross-comparison of lexical entities of 
                  biological interest ({LexEBI})},
  journal =	 {PLoS One},
  year =	 {2013},
  volume =	 {8},
  number =	 {10},
  pages =	 {e75185},
  user =	 {backofen},
  pmid =	 {24124474},
  doi = 	 {10.1371/journal.pone.0075185},
  issn = 	 {1932-6203},
  abstract =	 {MOTIVATION: Biomedical entities, their identifiers and 
                  names, are essential in the representation of biomedical 
                  facts and knowledge. In the same way, the complete set of 
                  biomedical and chemical terms, i.e. the biomedical "term 
                  space" (the "Lexeome"), forms a key resource to achieve the 
                  full integration of the scientific literature with 
                  biomedical data resources: any identified named entity can 
                  immediately be normalized to the correct database entry. 
                  This goal does not only require that we are aware of all 
                  existing terms, but would also profit from knowing all their 
                  senses and their semantic interpretation (ambiguities, 
                  nestedness). RESULT: This study compiles a resource for 
                  lexical terms of biomedical interest in a standard format 
                  (called "LexEBI"), determines the overall number of terms, 
                  their reuse in different resources and the nestedness of 
                  terms. LexEBI comprises references for protein and gene 
                  entries and their term variants and chemical entities 
                  amongst other terms. In addition, disease terms have been 
                  identified from Medline and PubmedCentral and added to 
                  LexEBI. Our analysis demonstrates that the baseforms of 
                  terms from the different semantic types show only little 
                  polysemous use. Nonetheless, the term variants of protein 
                  and gene names (PGNs) frequently contain species mentions, 
                  which should have been avoided according to protein 
                  annotation guidelines. Furthermore, the protein and gene 
                  entities as well as the chemical entities, both do comprise 
                  enzymes leading to hierarchical polysemy, and a large 
                  portion of PGNs make reference to a chemical entity. 
                  Altogether, according to our analysis based on the Medline 
                  distribution, 401,869 unique PGNs in the documents contain a 
                  reference to 25,022 chemical entities, 3,125 disease terms 
                  or 1,576 species mentions. CONCLUSION: LexEBI delivers the 
                  complete biomedical and chemical Lexeome in a standardized 
                  representation (http://www.ebi.ac.uk/Rebholz-srv/LexEBI/). 
                  The resource provides the disease terms as open source 
                  content, and fully interlinks terms across resources.}
}