Lu Zhiyong, Cohen K Bretonnel, Hunter Lawrence
Center for Computational Pharmacology, School of Medicine, University of Colorado, Aurora, CO 80045 USA.
Pac Symp Biocomput. 2006:52-63.
A Gene Reference Into Function (GeneRIF) is a concise phrase describing a function of a gene in the Entrez Gene database. Applying techniques from the area of natural language processing known as automatic summarization, it is possible to link the Entrez Gene database, the Gene Ontology, and the biomedical literature. A system was implemented that automatically suggests a sentence from a PubMed/MEDLINE abstract as a candidate GeneRIF by exploiting a gene's GO annotations along with location features and cue words. Results suggest that the method can significantly increase the number of GeneRIF annotations in Entrez Gene, and that it produces qualitatively more useful GeneRIFs than other methods.
基因功能参考(GeneRIF)是Entrez基因数据库中描述基因功能的简洁短语。应用自然语言处理领域中称为自动摘要的技术,可以将Entrez基因数据库、基因本体论和生物医学文献联系起来。通过利用基因的基因本体注释以及位置特征和提示词,实现了一个系统,该系统自动从PubMed/MEDLINE摘要中推荐一个句子作为候选基因功能参考。结果表明,该方法可以显著增加Entrez基因中基因功能参考注释的数量,并且与其他方法相比,它产生的基因功能参考在质量上更有用。