Integrative Mining-Based Associate Analysis System Of TCM Syndrome And Molecule Biology Knowledge

The amount of biomedical data in different disciplines is growing at an exponential rate. Integrating these significant knowledge sources to generate novel hypotheses for systems biology research is difficult. Traditional Chinese Medicine (TCM) is a completely different discipline, and is a complementary knowledge system to modern biomedical science. This paper uses a significant TCM bibliographic literature database in China, together with Medline, to integrate text mining and analyze the relationship between syndrome and gene is of great significance. Information Extraction (IE) is an important technique of Text Mining. It locations the structure of the corresponding data unit of unstructured natural language version, so that free text data transform into the corresponding structured data. IE is the preliminary steps and foundation of Text Mining and the text mining system based on IE is a trend of the research.This paper does some research on biomedical literature combining practice and method, based on the systemic analysis and expatiation to the concept and the correlative technique of Text Mining. We improved the Bubble-bootstrapping method and used it to extract the gene name, since it has been proved that the method has a perfect performance in the extraction of the Chinese entity name. After the experiment on the 2000 English abstracts, it is obvious that the Bubble-bootstrapping method has good foreground in the field of English entity name Extraction.Furthermore, this paper uses TCM literature and Medline to find the relationship between syndrome and gene. We designed and implemented a Integrative mining-based associate analysis system of TCM syndrome and molecule biology knowledge named Medisco-3S. This system is constituted of literature download module, entity name recognition module, relation building module, visualization and networks analysis module.