关键词: 蛋白质搜索, 关键字, 二元组, 信息整合, NCBI, Binding DB

Abstract: With the rapid development of biological science and technology, people know more and more about the basic substance, protein. However, the more information, the more difficulties people meet in searching. To get it efficient and precise message of protein, this paper designs a method to extract the information through NCBI and Binding DB for example. The method is about obtaining efficient information with no redundancy. It extracts keywords to form bigram from the information entry which is searched, and then divides it into groups. In each group, the detailed keyword extraction and grouping information is done, and cycles the processes till N-gram is generated, so that it achieves the purpose of getting rid of redundancy and integrates the ordering of information.


Key words: information search for protein, keywords, bigram, information integration, NCBI, Binding DB