Research Large-scale extraction of gene interactions from full text literature using

MOTIVATION: A complete repository of gene-gene interactions is key for understanding cellular processes, human disease, and drug response. These gene-gene interactions include both protein-protein interactions as well as transcription factor interactions. The majority of known interactions are found in the biomedical literature. Interac-tion databases, such as BioGRID and ChEA, annotate these gene-gene interactions; however, curation becomes difficult as the litera-ture grows exponentially. DeepDive is a trained system for extract-ing information from a variety of sources, including text. In this work, we used DeepDive to extract both protein-protein and transcription factor interactions from over 100,000 full text PLOS articles. METHODS: We built an extractor for gene-gene interactions that identified candidate gene-gene relations within an input sentence. For each candidate relation, DeepDive computed a probability that the relation was a correct interaction. We evaluated this system against the DIP protein interaction database and against randomly curated extractions. RESULTS: Our system achieved 76 % precision and 49 % recall in extracting direct and indirect interactions involving gene symbols co-occurring in a sentence. For randomly curated extractions, the sys-tem achieved between 62 % and 83 % precision based on direct or indirect interactions, as well as sentence-level and document-level precision. Overall, our system extracted 3356 unique gene pairs using 724 features from over 100,000 full text articles. Contact