| Summary: | 碩士 === 長庚大學 === 資訊管理研究所 === 94 === With the completion of Human Genome Project, we have entered the Post-Genomic Era. Therefore, Scholars have been gradually focusing on the interactive relationship among proteins, genes, chromosomes and diseases through functional gene set rather than gene sequence. From past medical researches, it is known that many diseases are caused by mal-functioning genes. If we can identify the relationship between a disease and its related genes, it is possible to find the mechanism and causality of the disease. From the large volume of accumulated bio-medical literatures that have been accumulated, the candidate genes of a disease and the annotations of the genes can be analyzed for comprehending their causal relationship, either computationally or manually. Accordingly, a new method of treatment for the disease can be analyzed.
The goal of this research is to develop a computational tool to help analyze the relationship between the disease and genes through text mining technique. The tool allows mining literature to establish new, potentially meaningful relations between a given starting concept (a disease name) of interest and other concepts (genes). This thesis also provides a new function to help analyze the relationship between the chromosomes and genes.
|
|---|
