Discovering gene annotations in biomedical text databases

Currently, most of the discovered biological and biomedical knowledge is available as textual data in scientific papers. And, locating and curating information about a genomic entity from the biomedical literature requires vast amounts of human effort. In this paper, we present an automated genomic entity annotation system, GEANN, which information about the characteristics of genes and gene products in paper abstracts from PubMed, and translates the discovered knowledge into Gene Ontology concepts, a widely-used standardized vocabulary of genomic traits. GEANN utilizes textual extraction patterns, and a semantic matching framework to locate phrases matching to a pattern and produce gene ontology annotations for genes and gene products. We present an extensive experimental evaluation of GEANN. In our experiments, GEANN has reached to the precision level of 78% at the recall level of 61%. The best precision is obtained in cellular component and molecular function subontologies, while th...

• Type: Journal
• Year: 2008
• Where: BMCBI
• Authors: Ali Cakmak, Gultekin Özsoyoglu
• Keywords: BMCBI 2008, Gene Ontology, Gene Products, Genomic Entity