Drug drug interaction extraction from the literature using a recursive neural network

• Published in: PloS one Vol. 13; no. 1; p. e0190926
• Main Authors: Lim, Sangrak, Lee, Kyubum, Kang, Jaewoo
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 26.01.2018; Public Library of Science (PLoS)
• Subjects: Artificial intelligence; Artificial neural networks; Bioinformatics; Biology and Life Sciences; Biomedical materials; Classification; Classifiers; Computer and Information Sciences; Computer science; Containment; Data mining; Data Mining - methods; Data Mining - statistics & numerical data; Drug interaction; Drug Interactions; Drug-Related Side Effects and Adverse Reactions; Drugs; Engineering; Engineering and Technology; Feature extraction; Humans; In vivo methods and tests; Language; Medicine and Health Sciences; Methods; Mining; Natural Language Processing; Neural networks; Neural Networks, Computer; Pharmacokinetics; Semantics; Social Sciences; Support Vector Machine; Texts
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0190926

Detecting drug-drug interactions (DDI) is important because information on DDIs can help prevent adverse effects from drug combinations. Since there are many new DDI-related papers published in the biomedical domain, manually extracting DDI information from the literature is a laborious task. However, text mining can be used to find DDIs in the biomedical literature. Among the recently developed neural networks, we use a Recursive Neural Network to improve the performance of DDI extraction. Our recursive neural network model uses a position feature, a subtree containment feature, and an ensemble method to improve the performance of DDI extraction. Compared with the state-of-the-art models, the DDI detection and type classifiers of our model performed 4.4% and 2.8% better, respectively, on the DDIExtraction Challenge'13 test data. We also validated our model on the PK DDI corpus that consists of two types of DDIs data: in vivo DDI and in vitro DDI. Compared with the existing model, our detection classifier performed 2.3% and 6.7% better on in vivo and in vitro data respectively. The results of our validation demonstrate that our model can automatically extract DDIs better than existing models.