Drug drug interaction extraction from biomedical literature using syntax convolutional neural network

By Zhehuan Zhao, Zhihao Yang, Ling Luo, Hongfei Lin, Jian Wang. 2016

192 citations recorded by the source corpus.

Motivation: Detecting drug-drug interaction (DDI) has become a vital part of public health safety. Therefore, using text mining techniques to extract DDIs from biomedical literature has received great attentions. However, this research is still at an early stage and its performance has much room to improve. Results: In this article, we present a syntax convolutional neural network (SCNN) based DDI extraction method. In this method, a novel word embedding, syntax word embedding, is proposed to employ the syntactic information of a sentence. Then the position and part of speech features are introduced to extend the embedding of each word. Later, auto-encoder is introduced to encode the traditional bag-of-words feature (sparse 0–1 vector) as the dense real value vector. Finally, a combination of embedding-based convolutional features and traditional features are fed to the softmax classifier to extract DDIs from biomedical literature. Experimental results on the DDIExtraction 2013 corpus show that SCNN obtains a better performance (an F-score of 0.686) than other state-of-the-art methods. Availability and Implementation: The source code is available for academic use at http://202.118.75.18:8080/DDI/SCNN-DDI.zip. Contact: yangzh@dlut.edu.cn Supplementary information: Supplementary data are available at Bioinformatics online.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Molecular Biology

Citations in the corpus

BioWordVec, improving biomedical word embeddings with subword information and MeSH (2019, methodology): “Since the DDI extraction is a multi-class relation extraction task, we compute the micro average to evaluate the overall performances 37,38 .”
Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities (2018, methodology): “duction algorithm on each data type to derive a feature vector for each drug [290, 295], followed by an aggregation of feature vectors of individual drugs to obtain integrated feature vectors of drug pairs.”
Multichannel Convolutional Neural Network for Biological Relation Extraction (2016, background): “[32] recently; they combined traditional CNN and external features such as contexts, shortest path, and part-of-speech to classify the interaction type and achieved an overall f-scores 68.”
Extracting Drug-Drug Interactions with Attention CNNs (2017, methodology): “No negative instance ﬁltering CNN (Liu et al., 2016) 75.29 60.37 67.01 MCCNN (Quan et al., 2016) - - 67.80 SCNN (Zhao et al., 2016) 68.5 61.0 64.5 Joint AB-LSTM (Sahu and Anand, 2017) (Liu et al., 2016) 75.72 64.66 69.75 MCCNN (Quan et al., 2016) 75.99 65.25 70.21 SCNN (Zhao et al., 2016) 72.5 the p”
Drug-Drug Interaction Extraction via Recurrent Neural Network with Multiple Attention Layers (2017, methodology): “We use the same metrics as in other drug-drug interaction extraction literature [9]–[13], [26] Then the overall precision, recall, and F1 score are calculated by Besides, we evaluate the captured feature with t-SNE [27], a visualizing and intuitive way to map a high dimensional vector into a 2 or…”
Deep learning for extracting protein-protein interactions from biomedical literature (2017, methodology): “Thus previous CNN-based methods have not achieved state-of-the-art performance in the PPI task (Zhao et al., 2016a).”