A dictionary to identify small molecules and drugs in free text. Export

@article{citeulike:5803108, abstract = {MOTIVATION: From the scientific community, a lot of effort has been spent on the correct identification of gene and protein names in text, while less effort has been spent on the correct identification of chemical names. Dictionary-based term identification has the power to recognize the diverse representation of chemical information in the literature and map the chemicals to their database identifiers. RESULTS: We developed a dictionary for the identification of small molecules and drugs in text, combining information from UMLS, MeSH, ChEBI, DrugBank, KEGG, HMDB and ChemIDplus. Rule-based term filtering, manual check of highly frequent terms and disambiguation rules were applied. We tested the combined dictionary and the dictionaries derived from the individual resources on an annotated corpus, and conclude the following: (i) each of the different processing steps increase precision with a minor loss of recall; (ii) the overall performance of the combined dictionary is acceptable (precision 0.67, recall 0.40 (0.80 for trivial names); (iii) the combined dictionary performed better than the dictionary in the chemical recognizer OSCAR3; (iv) the performance of a dictionary based on ChemIDplus alone is comparable to the performance of the combined dictionary. AVAILABILITY: The combined dictionary is freely available as an XML file in Simple Knowledge Organization System format on the web site http://www.biosemantics.org/chemlist.}, author = {Hettne, Kristina M. and Stierum, Rob H. and Schuemie, Martijn J. and Hendriksen, Peter J. and Schijvenaars, Bob J. and Mulligen, Erik van M. and Kleinjans, Jos and Kors, Jan A.}, citeulike-article-id = {5803108}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btp535}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/25/22/2983.abstract}, citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/25/22/2983.full.pdf}, citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/19759196}, citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=19759196}, day = {15}, doi = {10.1093/bioinformatics/btp535}, issn = {1367-4811}, journal = {Bioinformatics (Oxford, England)}, keywords = {dictionary, metabolite, mining, miranda, molecule, text}, month = {November}, number = {22}, pages = {2983--2991}, posted-at = {2009-09-18 21:10:48}, priority = {2}, title = {A dictionary to identify small molecules and drugs in free text.}, url = {http://dx.doi.org/10.1093/bioinformatics/btp535}, volume = {25}, year = {2009} }

TY - JOUR ID - citeulike:5803108 L3 - citeulike-article-id:5803108 N2 - MOTIVATION: From the scientific community, a lot of effort has been spent on the correct identification of gene and protein names in text, while less effort has been spent on the correct identification of chemical names. Dictionary-based term identification has the power to recognize the diverse representation of chemical information in the literature and map the chemicals to their database identifiers. RESULTS: We developed a dictionary for the identification of small molecules and drugs in text, combining information from UMLS, MeSH, ChEBI, DrugBank, KEGG, HMDB and ChemIDplus. Rule-based term filtering, manual check of highly frequent terms and disambiguation rules were applied. We tested the combined dictionary and the dictionaries derived from the individual resources on an annotated corpus, and conclude the following: (i) each of the different processing steps increase precision with a minor loss of recall; (ii) the overall performance of the combined dictionary is acceptable (precision 0.67, recall 0.40 (0.80 for trivial names); (iii) the combined dictionary performed better than the dictionary in the chemical recognizer OSCAR3; (iv) the performance of a dictionary based on ChemIDplus alone is comparable to the performance of the combined dictionary. AVAILABILITY: The combined dictionary is freely available as an XML file in Simple Knowledge Organization System format on the web site http://www.biosemantics.org/chemlist. IS - 22 JF - Bioinformatics (Oxford, England) SN - 1367-4811 EP - 2991 TI - A dictionary to identify small molecules and drugs in free text. VL - 25 SP - 2983 KW - dictionary KW - metabolite KW - mining KW - miranda KW - molecule KW - text AU - Hettne, Kristina AU - Stierum, Rob AU - Schuemie, Martijn AU - Hendriksen, Peter AU - Schijvenaars, Bob AU - Mulligen, Erik van AU - Kleinjans, Jos AU - Kors, Jan PY - 2009/11/15/ UR - http://dx.doi.org/10.1093/bioinformatics/btp535 ER -