Dependency and AMR Embeddings for Drug-Drug Interaction Extraction from Biomedical Literature

Drug-drug interaction (DDI) is an unexpected change in a drug's effect on the human body when the drug and a second drug are co-prescribed and taken together. As many DDIs are frequently reported in biomedical literature, it is important to mine DDI information from literature to keep DDI knowledge up to date. One of the SemEval challenges in the year 2011 and 2013 was designed to tackle the task where the best system achieved an F1 score of 0.80. In this paper, we propose to utilize dependency embeddings and Abstract Meaning Representation (AMR) embeddings as features for extracting DDIs. Our contribution is two-fold. First, we employed dependency embeddings, previously shown effective for sentence classification, for DDI extraction. The dependency embeddings incorporated structural syntactic contexts into the embeddings, which were not present in the conventional word embeddings. Second, we proposed a novel syntactic embedding approach using AMR. AMR aims to abstract away from syntactic idiosyncrasies and attempts to capture only the core meaning of a sentence, which could potentially improve DDI extraction from sentences. Two classifiers (Support Vector Machine and Random Forest) taking these embedding features as input were evaluated on the DDIExtraction 2013 challenge corpus. The experimental results show the effectiveness of dependency and AMR embeddings in the DDI extraction task. The best performance was obtained by combining word, dependency and AMR embeddings (F1 score=0.84).

[1]  Diane L. Seger,et al.  Adverse Drug Event Rates in Six Community Hospitals and the Potential Impact of Computerized Physician Order Entry for Prevention , 2009, Journal of General Internal Medicine.

[2]  Majid Rastegar-Mojarad,et al.  UWM-TRIADS: Classifying Drug-Drug Interactions with Two-Stage SVM and Post-Processing , 2013, SemEval@NAACL-HLT.

[3]  Xiaolong Wang,et al.  Drug-Drug Interaction Extraction via Convolutional Neural Networks , 2016, Comput. Math. Methods Medicine.

[4]  P. Shekelle,et al.  The effectiveness of computerized order entry at reducing preventable adverse drug events and medication errors in hospital settings: a systematic review and meta-analysis , 2014, Systematic Reviews.

[5]  Alberto Díaz,et al.  NIL_UCM: Extracting Drug-Drug interactions from text through combination of sequence and tree kernels , 2013, SemEval@NAACL-HLT.

[6]  Alberto Lavelli,et al.  FBK-irst : A Multi-Phase Kernel Based Approach for Drug-Drug Interaction Detection and Classification that Exploits Linguistic Information , 2013, *SEMEVAL.

[7]  David S. Wishart,et al.  DrugBank 4.0: shedding new light on drug metabolism , 2013, Nucleic Acids Res..

[8]  Jari Björne,et al.  UTurku: Drug Named Entity Recognition and Drug-Drug Interaction Extraction Using SVM Classification and Domain Knowledge , 2013, *SEMEVAL.

[9]  Suresh Manandhar,et al.  Dependency Based Embeddings for Sentence Classification Tasks , 2016, NAACL.

[10]  Hongfei Lin,et al.  Drug drug interaction extraction from biomedical literature using syntax convolutional neural network , 2016, Bioinform..

[11]  Hongfang Liu,et al.  A Topic-modeling Based Framework for Drug-drug Interaction Classification from Biomedical Text , 2016, AMIA.

[12]  Mariana L. Neves,et al.  WBI-DDI: Drug-Drug Interaction Extraction using Majority Voting , 2013, *SEMEVAL.

[13]  Noah A. Smith,et al.  Toward Abstractive Summarization Using Semantic Representations , 2018, NAACL.

[14]  Heng Ji,et al.  Building a Fine-Grained Entity Typing System Overnight for a New X (X = Language, Domain, Genre) , 2016, ArXiv.

[15]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[16]  Philipp Koehn,et al.  Abstract Meaning Representation for Sembanking , 2013, LAW@ACL.

[17]  Xiang Zhang,et al.  Character-level Convolutional Networks for Text Classification , 2015, NIPS.

[18]  Pamela F. Jones,et al.  Computational and Mathematical Methods in Medicine , 2011, Comput. Math. Methods Medicine.

[19]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[20]  Chuan Wang,et al.  A Transition-based Algorithm for AMR Parsing , 2015, NAACL.

[21]  C. L. Preston,et al.  Stockley's drug interactions : , 2017 .

[22]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[23]  Haibin Liu,et al.  Extracting drug-drug interactions from literature using a rich feature-based linear kernel approach , 2015, AMIA.

[24]  Joseph E Ibrahim,et al.  Systematic Review of the Prevalence of Medication Errors Resulting in Hospitalization and Death of Nursing Home Residents , 2017, Journal of the American Geriatrics Society.

[25]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[26]  Ulf Leser,et al.  WBI-NER: The impact of domain-specific features on the performance of identifying and classifying mentions of drugs , 2013, *SEMEVAL.

[27]  Senén Barro,et al.  Do we need hundreds of classifiers to solve real world classification problems? , 2014, J. Mach. Learn. Res..

[28]  M. Makary,et al.  Medical error—the third leading cause of death in the US , 2016, British Medical Journal.

[29]  J. James.  A New, Evidence-based Estimate of Patient Harms Associated with Hospital Care , 2013, Journal of patient safety.

[30]  Jaime G. Carbonell,et al.  A Discriminative Graph-Based Parser for the Abstract Meaning Representation , 2014, ACL.

[31]  Claudio Giuliano,et al.  Exploiting Shallow Linguistic Information for Relation Extraction from Biomedical Literature , 2006, EACL.

[32]  V. Padmanabhan,et al.  Net increase in stimulatory input resulting from a decrease in inhibin B and an increase in activin A may contribute in part to the rise in follicular phase follicle-stimulating hormone of aging cycling women. , 1998, The Journal of clinical endocrinology and metabolism.

[33]  Majid Rastegar-Mojarad,et al.  Extraction and classification of drug-drug interaction from biomedical text using a twostage classifier , 2013 .

[34]  Paloma Martínez,et al.  SemEval-2013 Task 9 : Extraction of Drug-Drug Interactions from Biomedical Texts (DDIExtraction 2013) , 2013, *SEMEVAL.

[35]  Omer Levy,et al.  Dependency-Based Word Embeddings , 2014, ACL.

[36]  Ming Zhou,et al.  Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification , 2014, ACL.

[37]  Juliane Fluck,et al.  SCAI: Extracting drug-drug interactions using a rich feature vector , 2013, SemEval@NAACL-HLT.

[38]  Stewart E. Glaspole.  Stockley’s Drug Interactions , 2018 .

[39]  Jun Zhao,et al.  Relation Classification via Convolutional Deep Neural Network , 2014, COLING.

[40]  Isabel Segura-Bedmar,et al.  The 1st DDIExtraction-2011 challenge task: Extraction of Drug-Drug Interactions from biomedical texts , 2011 .

[41]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[42]  Xiaochang Peng,et al.  Addressing the Data Sparsity Issue in Neural AMR Parsing , 2017, EACL.