Identifying interactions between chemical entities in biomedical text

• Main Authors: Lamurias Andre, Ferreira João D., Couto Francisco M.
• Format: Article
• Language: English
• Published: De Gruyter 2014-12-01
• Series: Journal of Integrative Bioinformatics
• Online Access: https://doi.org/10.1515/jib-2014-247

Interactions between chemical compounds described in biomedical text can be of great importance to drug discovery and design, as well as pharmacovigilance. We developed a novel system, “Identifying Interactions between Chemical Entities” (IICE), to identify chemical interactions described in text. Kernel-based Support Vector Machines first identify the interactions and then an ensemble classifier validates and classifies the type of each interaction. This relation extraction module was evaluated with the corpus released for the DDI Extraction task of SemEval 2013, obtaining results comparable to stateof- the-art methods for this type of task. We integrated this module with our chemical named entity recognition module and made the whole system available as a web tool at www.lasige.di.fc.ul.pt/webtools/iice.