期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2013
卷号：4
期号：1
页码：571-575
语种：English
出版社：Ayushmaan Technologies
摘要：Authors frequently use dissimilar names to refer to the samegene or protein names across articles. Identifying the alternatenames for the same gene/protein would help biologists to fndand use relevant literature. Biomedical databases are usuallyconstructed and maintained by domain experts but need morehuman physical involvement. Many biological databases such asSWISSPROT, GenBank, GOLD, UniGene and Karyn’s Genomeinclude synonyms, but these databases may not be always up-todate. Therefore, it is necessary to automate this process becauseof the increasing number of discovered genes and proteins. Thefast increase of machine readable biomedical text documents leadsto the growth of semi computerized or computerized informationextraction techniques used to extract meaningful information suchas extraction of synonymous Gene or protein names. This paperstudies existing methods for identifying these name variations andproposes a new method by treating Gene Synonym Identifcationproblem as information extraction problem.
