BO-LSTM: classifying relations via long short-term memory networks along biomedical ontologies.

Journal: BMC bioinformatics
Published Date:

Abstract

BACKGROUND: Recent studies have proposed deep learning techniques, namely recurrent neural networks, to improve biomedical text mining tasks. However, these techniques rarely take advantage of existing domain-specific resources, such as ontologies. In Life and Health Sciences there is a vast and valuable set of such resources publicly available, which are continuously being updated. Biomedical ontologies are nowadays a mainstream approach to formalize existing knowledge about entities, such as genes, chemicals, phenotypes, and disorders. These resources contain supplementary information that may not be yet encoded in training data, particularly in domains with limited labeled data.

Authors

  • Andre Lamurias
    LaSIGE, Faculdade de Ciências, Universidade de Lisboa, Lisboa, Portugal.
  • Diana Sousa
    LASIGE, Faculdade de Ciências, Universidade de Lisboa, Lisboa, 1749 016, Portugal.
  • Luka A Clarke
    BioFIG - Centre for Biodiversity, Functional and Integrative Genomics, Faculdade de Ciências, Universidade de Lisboa, Lisboa, Portugal.
  • Francisco M Couto
    Departamento de Informática, Faculdade de Ciências, Universidade de Lisboa, Portugal.