Mining gene-related information from biomedical literature

With biomedical literature continually expanding, searching PubMed for information about specific genes becomes increasingly difficult. Not only are thousands of results returned, but gene name ambiguity leads to many irrelevant hits. As a result, it is difficult for life scientists and gene curators to quickly get an overall picture about a specific gene from the literature. To alleviate this problem, we developed eGIFT (Extracting Genic Information From Text), which automatically identifies key information from the gene´s literature. eGIFT is a system which helps not only scientists surveying the results of high-throughput experiments to quickly extract information important to their hits, but also annotators to quickly find articles describing gene functions. We report evaluation of eGIFT on a set of 35 genes.