Extracting Relationship Both Gene2Disease and Gene2Gene from Biomedical Literatures

With the rapid advancement of biomedical science, the extraction of various types of information from biomedical literatures has become a major challenge. In this paper, we develop a system to extract the relationship both gene2disease and gene2gene using a combined approach including pattern, ontology-based and co-occurrence technology. Our system can easily find the relevant genes related to autism disease. Moreover, it can find indirect relationship between gene and gene by the network visualization. Experiment results show our system can achieve a recall of 81.1%, a precision of 76.9% and an F-score 78.9% in the gene2disease, and a recall of 84.5%, a precision of 87.5%, and an F-score 85.9% in the gene2gene for the test datasets.