Literature search tool for the extraction of disease-associated genes using frequent itemset mining
Understanding the role of genetics is very important for the in-depth study of a disease. Even though lots of information about gene-disease association is available, it is difficult even for an expert user to manually extract it from the huge volume of literature. Therefore, this work introduces a novel extraction tool that can identify disease associated genes from the literature using text-mining algorithm. Here, Hidden Markov Model is combined with a rule-based Named Entity Recognition approach to identify gene symbols from the literature. This will predict the good candidate genes for the disease which will help in the further analysis of the disease.