A Study and Analysis of Gene Drug Association for Diabetic Gene - A Text Mining Approach

The explosive growth of genomic data has lead to the growth of published literature of genomic text submitted by researchers all over the world. The literature database like Medline has grown tremendously in the upcoming years. Analyzing the literature for finding association of biological components has become an important domain area. The analysis of gene drug association from text has become an important research area in the field of biomedical text mining. This paper provides with a detailed study on various methods used for gene drug association discovery. The methodology for analysis of gene, drug associations related to diabetic disease using Dictionary-based term identification approach consists of two main important phases. The first phase makes use of the preprocessing text mining techniques like stop word removal, tokenization and stemming. The second phase corpus is constructed for analyzing gene drugs associations using dictionary based approach.