Concept extraction and association from cancer literature

摘要: There is a large and growing body of web accessible biomedical literature. As this electronic literature grows, so does the possibility that document analysis techniques can be used to automatically extract useful information from them, particularly in discovery key concepts dealing with genes, proteins, drugs, diseases associations among these concepts. VCGS (Vocabulary Cluster Generating System) was designed determine tokens subset namely cancer. Such has notable potential automate database construction biomedicine, instead relying on experts' analysis. This paper reports mechanisms for generating clusters tokens. A formal evaluation system, based 5338 Pubmed titles abstracts, been conducted against Swiss-Prot which are entered by experts hand.