Tagging gene and protein names in biomedical text. Export

@article{citeulike:137278, abstract = {MOTIVATION: The MEDLINE database of biomedical abstracts contains scientific knowledge about thousands of interacting genes and proteins. Automated text processing can aid in the comprehension and synthesis of this valuable information. The fundamental task of identifying gene and protein names is a necessary first step towards making full use of the information encoded in biomedical text. This remains a challenging task due to the irregularities and ambiguities in gene and protein nomenclature. We propose to approach the detection of gene and protein names in scientific abstracts as part-of-speech tagging, the most basic form of linguistic corpus annotation. RESULTS: We present a method for tagging gene and protein names in biomedical text using a combination of statistical and knowledge-based strategies. This method incorporates automatically generated rules from a transformation-based part-of-speech tagger, and manually generated rules from morphological clues, low frequency trigrams, indicator terms, suffixes and part-of-speech information. Results of an experiment on a test corpus of 56K MEDLINE documents demonstrate that our method to extract gene and protein names can be applied to large sets of MEDLINE abstracts, without the need for special conditions or human experts to predetermine relevant subsets. AVAILABILITY: The programs are available on request from the authors.}, address = {National Center for Biotechnology Information, NLM, NIH, Bethesda, Maryland 20894, USA. tanabe@ncbi.nlm.nih.gov}, author = {Tanabe, L. and Wilbur, W. J.}, citeulike-article-id = {137278}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/18.8.1124}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/18/8/1124}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/12176836}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=12176836}, doi = {10.1093/bioinformatics/18.8.1124}, issn = {1367-4803}, journal = {Bioinformatics}, keywords = {tbedl, text-mining}, month = {August}, number = {8}, pages = {1124--1132}, posted-at = {2005-05-03 02:31:51}, priority = {2}, title = {Tagging gene and protein names in biomedical text.}, url = {http://dx.doi.org/10.1093/bioinformatics/18.8.1124}, volume = {18}, year = {2002} }

TY - JOUR ID - citeulike:137278 L3 - citeulike-article-id:137278 N2 - MOTIVATION: The MEDLINE database of biomedical abstracts contains scientific knowledge about thousands of interacting genes and proteins. Automated text processing can aid in the comprehension and synthesis of this valuable information. The fundamental task of identifying gene and protein names is a necessary first step towards making full use of the information encoded in biomedical text. This remains a challenging task due to the irregularities and ambiguities in gene and protein nomenclature. We propose to approach the detection of gene and protein names in scientific abstracts as part-of-speech tagging, the most basic form of linguistic corpus annotation. RESULTS: We present a method for tagging gene and protein names in biomedical text using a combination of statistical and knowledge-based strategies. This method incorporates automatically generated rules from a transformation-based part-of-speech tagger, and manually generated rules from morphological clues, low frequency trigrams, indicator terms, suffixes and part-of-speech information. Results of an experiment on a test corpus of 56K MEDLINE documents demonstrate that our method to extract gene and protein names can be applied to large sets of MEDLINE abstracts, without the need for special conditions or human experts to predetermine relevant subsets. AVAILABILITY: The programs are available on request from the authors. IS - 8 JF - Bioinformatics SN - 1367-4803 AD - National Center for Biotechnology Information, NLM, NIH, Bethesda, Maryland 20894, USA. tanabe@ncbi.nlm.nih.gov EP - 1132 TI - Tagging gene and protein names in biomedical text. VL - 18 SP - 1124 KW - tbedl KW - text-mining AU - Tanabe, L AU - Wilbur, WJ PY - 2002/08// UR - http://dx.doi.org/10.1093/bioinformatics/18.8.1124 ER -