An attention-based effective neural model for drug-drug interactions extraction

• Published in: BMC bioinformatics Vol. 18; no. 1; pp. 445 - 11
• Main Authors: Zheng, Wei, Lin, Hongfei, Luo, Ling, Zhao, Zhehuan, Li, Zhengguang, Zhang, Yijia, Yang, Zhihao, Wang, Jian
• Format: Journal Article
• Language: English
• Published: England BioMed Central 10-10-2017; BMC
• Subjects: Algorithms; Attention; Bioinformatics; Classification; Data mining; Databases as Topic; Datasets; Drug Interactions; Drug-drug interactions; Embedding; Humans; Learning; Linguistics; Long short-term memory; Machine translation; Medical errors; Models, Theoretical; Natural language processing; Neural networks; Neural Networks, Computer; Performance enhancement; Recurrent neural network; Recurrent neural networks; Side effects; State of the art; Support Vector Machine; System effectiveness; Text mining; Text mining; Long short-term memory; Drug-drug interactions; Recurrent neural network; Attention
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-017-1855-x

Drug-drug interactions (DDIs) often bring unexpected side effects. The clinical recognition of DDIs is a crucial issue for both patient safety and healthcare cost control. However, although text-mining-based systems explore various methods to classify DDIs, the classification performance with regard to DDIs in long and complex sentences is still unsatisfactory.
In this study, we propose an effective model that classifies DDIs from the literature by combining an attention mechanism and a recurrent neural network with long short-term memory (LSTM) units. In our approach, first, a candidate-drug-oriented input attention acting on word-embedding vectors automatically learns which words are more influential for a given drug pair. Next, the inputs merging the position- and POS-embedding vectors are passed to a bidirectional LSTM layer whose outputs at the last time step represent the high-level semantic information of the whole sentence. Finally, a softmax layer performs DDI classification.
Experimental results from the DDIExtraction 2013 corpus show that our system performs the best with respect to detection and classification (84.0% and 77.3%, respectively) compared with other state-of-the-art methods. In particular, for the Medline-2013 dataset with long and complex sentences, our F-score far exceeds those of top-ranking systems by 12.6%.
Our approach effectively improves the performance of DDI classification tasks. Experimental analysis demonstrates that our model performs better with respect to recognizing not only close-range but also long-range patterns among words, especially for long, complex and compound sentences.