ABSTRACT
Pancreatitis is a relatively serious disease caused by the self-digestion of trypsin in the pancreas. The generation of diseases is closely related to gene and phenotype information. Generally, gene-phenotype relations are mainly obtained through clinical experiments, but the cost is huge. With the amount of published biomedical literature increasing exponentially, it carries a wealth of disease-related gene and phenotype information. This study provided an effective way to obtain disease-related gene and phenotype information. To our best knowledge, this work first attempted to explore relationships between genotype and phenotype about the pancreatitis from the computational perspective. It mined 6152 genes and 76,753 pairs of genotype and phenotype extracted from the biomedical literature about pancreatitis using text mining. Based on the above 76,753 pairs, the study proposed an improved normalized point-wise mutual information (REL-NPMI) model to optimize gene-phenotype relations related to pancreatitis, and obtained 12,562 gene-phenotype pairs which may be related to pancreatitis. The extracted top 20 results were validated and evaluated. The experimental results show that the method is promising for exploring pancreatitis' molecular mechanism, thus it provides a computational way for studying pancreatitis' disease pathogenesis. Data resources and the Pancreatitis Gene-Phenotype Association Database are available at http://114.116.4.45:8081/and resources are also available at https://github.com/polipoptbe8023/REL-NPMI.git.
