Automatic extraction of gene and protein synonyms from MEDLINE and journal articles.

@article{citeulike:406776, abstract = {Genes and proteins are often associated with multiple names, and more names are added as new functional or structural information is discovered. Because authors often alternate between these synonyms, information retrieval and extraction benefits from identifying these synonymous names. We have developed a method to extract automatically synonymous gene and protein names from MEDLINE and journal articles. We first identified patterns authors use to list synonymous gene and protein names. We developed SGPE (for synonym extraction of gene and protein names), a software program that recognizes the patterns and extracts from MEDLINE abstracts and full-text journal articles candidate synonymous terms. SGPE then applies a sequence of filters that automatically screen out those terms that are not gene and protein names. We evaluated our method to have an overall precision of 71\% on both MEDLINE and journal articles, and 90\% precision on the more suitable full-text articles alone}, address = {Department of Medical Informatics, Columbia University, New York, NY 10032, USA.}, author = {Yu, H. and Hatzivassiloglou, V. and Friedman, C. and Rzhetsky, A. and Wilbur, W. J. }, citeulike-article-id = {406776}, issn = {1531-605X}, journal = {Proc AMIA Symp}, keywords = {information-extraction}, pages = {919--923}, posted-at = {2005-11-24 02:52:31}, priority = {2}, title = {Automatic extraction of gene and protein synonyms from MEDLINE and journal articles.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/12463959}, year = {2002} }

TY - JOUR ID - citeulike:406776 L3 - citeulike-article-id:406776 TI - Automatic extraction of gene and protein synonyms from MEDLINE and journal articles. JF - Proc AMIA Symp SP - 919 EP - 923 AD - Department of Medical Informatics, Columbia University, New York, NY 10032, USA. SN - 1531-605X N2 - Genes and proteins are often associated with multiple names, and more names are added as new functional or structural information is discovered. Because authors often alternate between these synonyms, information retrieval and extraction benefits from identifying these synonymous names. We have developed a method to extract automatically synonymous gene and protein names from MEDLINE and journal articles. We first identified patterns authors use to list synonymous gene and protein names. We developed SGPE (for synonym extraction of gene and protein names), a software program that recognizes the patterns and extracts from MEDLINE abstracts and full-text journal articles candidate synonymous terms. SGPE then applies a sequence of filters that automatically screen out those terms that are not gene and protein names. We evaluated our method to have an overall precision of 71% on both MEDLINE and journal articles, and 90% precision on the more suitable full-text articles alone KW - information-extraction AU - Yu, H AU - Hatzivassiloglou, V AU - Friedman, C AU - Rzhetsky, A AU - Wilbur, WJ PY - 2002/// UR - http://view.ncbi.nlm.nih.gov/pubmed/12463959 ER -