ADDI: Recommending alternatives for drug-drug interactions with negative health effects

Investigating the interactions among various drugs is an indispensable issue in the field of computational biology. Scientific literature represents a rich source for the retrieval of knowledge about the interactions between drugs. Predicting drug-drug interaction (DDI) types will help biologists to evade hazardous drug interactions and support them in discovering potential alternatives that increase therapeutic efficacy and reduce toxicity. In this paper, we propose a general-purpose method called ADDI (standing for Alternative Drug-Drug Interaction) that applies deep learning on PubMed abstracts to predict interaction types among drugs. As an application, ADDI recommends alternatives for drug-drug interactions (DDIs) which have Negative Health Effects Types (NHETs). ADDI clearly outperforms state-of-the-art methods, on average by 13%, with respect to accuracy by using only the textual content of the online PubMed papers. Additionally, manual evaluation of ADDI indicates high precision in recommending alternatives for DDIs with NHETs.

[1]  Yuen-Hsien Tseng,et al.  Text mining techniques for patent analysis , 2007, Inf. Process. Manag..

[2]  Narjes Rohani,et al.  Drug-Drug Interaction Predicting by Neural Network Using Integrated Similarity , 2019, Scientific Reports.

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

[4]  Changiz Eslahchi,et al.  ISCMF: Integrated similarity-constrained matrix factorization for drug–drug interaction prediction , 2020, Network Modeling Analysis in Health Informatics and Bioinformatics.

[5]  Weinan Zhang,et al.  Improving Negative Sampling for Word Representation using Self-embedded Features , 2017, WSDM.

[6]  G. Keller,et al.  Drug-induced QT Interval Prolongation in the Intensive Care Unit. , 2018, Current clinical pharmacology.

[7]  Charu C. Aggarwal,et al.  Mining Text Data , 2012 .

[8]  Jinyan Li,et al.  DDI-PULearn: a positive-unlabeled learning method for large-scale prediction of drug-drug interactions , 2019, BMC Bioinformatics.

[9]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[10]  Ronen Feldman,et al.  Book Reviews: The Text Mining Handbook: Advanced Approaches to Analyzing Unstructured Data by Ronen Feldman and James Sanger , 2008, CL.

[11]  J. Hurkmans,et al.  REVERSAL OF THE EFFECT OF α‐METHYLDOPA BY MONOAMINE OXIDASE INHIBITORS , 1963 .

[12]  Albert-László Barabási,et al.  Network-based prediction of drug combinations , 2019, Nature Communications.

[13]  Francisco M. Couto,et al.  Text Mining for Bioinformatics Using Biomedical Literature , 2019, Encyclopedia of Bioinformatics and Computational Biology.

[14]  Hugo Caselles-Dupré,et al.  Word2vec applied to recommendation: hyperparameters matter , 2018, RecSys.

[15]  Russ B. Altman,et al.  Discovery and Explanation of Drug-Drug Interactions via Text Mining , 2011, Pacific Symposium on Biocomputing.

[16]  Stefan Decker,et al.  Drug-Drug Interaction Prediction Based on Knowledge Graph Embeddings and Convolutional-LSTM Network , 2019, BCB.

[17]  Jun Zhao,et al.  How to Generate a Good Word Embedding , 2015, IEEE Intelligent Systems.

[18]  A. Hauschild,et al.  Improved survival with vemurafenib in melanoma with BRAF V600E mutation. , 2011, The New England journal of medicine.

[19]  D. Blowey,et al.  Diuretics in the treatment of hypertension , 2016, Pediatric Nephrology.

[20]  Meng Zhang,et al.  Neural Network Methods for Natural Language Processing , 2017, Computational Linguistics.

[21]  Lei Chen,et al.  Identification of Drug-Drug Interactions Using Chemical Interactions , 2017 .

[22]  Zhiyong Lu,et al.  ezTag: tagging biomedical concepts via interactive learning , 2018, Nucleic Acids Res..

[23]  Zhongming Zhao,et al.  Machine learning-based prediction of drug-drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties. , 2014, Journal of the American Medical Informatics Association : JAMIA.

[24]  M. Slevin,et al.  The Clinical Pharmacology of Etoposide and Teniposide , 1987, Clinical pharmacokinetics.

[25]  C. Haffajee,et al.  Antiarrhythmic agents and proarrhythmia , 2000, Critical care medicine.

[26]  Brooks M. Boyd,et al.  A phase I, randomized, open-label, single-dose, 3-period crossover study to evaluate the drug-drug interaction between ZX008 (fenfluramine HCl oral solution) and a regimen of stiripentol, clobazam, and valproate in healthy subjects , 2018, International journal of clinical pharmacology and therapeutics.

[27]  Claudio Moraga,et al.  The Influence of the Sigmoid Function Parameters on the Speed of Backpropagation Learning , 1995, IWANN.

[28]  Siu-Ming Yiu,et al.  Detecting drug communities and predicting comprehensive drug–drug interactions via balance regularized semi-nonnegative matrix factorization , 2019, Journal of Cheminformatics.

[29]  J. Tímár,et al.  Inhibition of epidermal growth factor receptor improves antitumor efficacy of vemurafenib in BRAF-mutant human melanoma in preclinical model , 2018, Melanoma research.

[30]  Diane S. Aschenbrenner,et al.  Drug Therapy in Nursing , 2001 .

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

[32]  Gurpreet Singh Lehal,et al.  A Survey of Text Mining Techniques and Applications , 2009 .

[33]  S. Linnebur,et al.  Evaluating the risk of QTc prolongation associated with antidepressant use in older adults: a review of the evidence , 2018, Therapeutic advances in drug safety.

[34]  Carol Friedman,et al.  Drug-drug interaction through molecular structure similarity analysis , 2012, J. Am. Medical Informatics Assoc..

[35]  Jaewoo Kang,et al.  Drug drug interaction extraction from the literature using a recursive neural network , 2018, PloS one.

[36]  Bo Luo,et al.  Mining Adverse Drug Side-Effects from Online Medical Forums , 2012, 2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology.

[37]  Alfonso Valencia,et al.  Text-mining approaches in molecular biology and biomedicine. , 2005, Drug discovery today.

[38]  Yen S. Low,et al.  Text Mining for Adverse Drug Events: the Promise, Challenges, and State of the Art , 2014, Drug Safety.

[39]  Allan Kuchinsky,et al.  GLay: community structure analysis of biological networks , 2010, Bioinform..

[40]  Zhenchao Jiang,et al.  Drug-drug interaction extraction from biomedical literature using support vector machine and long short term memory networks , 2017, Inf. Sci..

[41]  R. Sharan,et al.  INDI: a computational framework for inferring drug interactions and their associated recommendations , 2012, Molecular systems biology.

[42]  A. Valencia,et al.  Text Mining for Drugs and Chemical Compounds: Methods, Tools and Applications , 2011, Molecular informatics.

[43]  S. Vilar,et al.  Detection of Drug-Drug Interactions by Modeling Interaction Profile Fingerprints , 2013, PloS one.

[44]  Vassilis Virvilis,et al.  Literature mining, ontologies and information visualization for drug repurposing , 2011, Briefings Bioinform..

[45]  Sheng Qian,et al.  Leveraging genetic interactions for adverse drug-drug interaction prediction , 2019, PLoS Comput. Biol..

[46]  Sara K Quinney,et al.  Opportunities and Challenges of Using Big Data to Detect Drug‐Drug Interaction Risk , 2019, Clinical pharmacology and therapeutics.

[47]  Yanqing Zhang,et al.  Using Word2Vec to process big text data , 2015, 2015 IEEE International Conference on Big Data (Big Data).

[48]  Razvan Pascanu,et al.  A simple neural network module for relational reasoning , 2017, NIPS.

[49]  E. Bonmassar,et al.  Focus on Fotemustine. , 2006, Journal of experimental & clinical cancer research : CR.

[50]  Z. Cao,et al.  Mining drug–disease relationships as a complement to medical genetics‐based drug repositioning: Where a recommendation system meets genome‐wide association studies , 2015, Clinical pharmacology and therapeutics.

[51]  Timothy J Mitchison,et al.  Anti-Microtubule Drugs. , 2016, Methods in molecular biology.

[52]  David S. Wishart,et al.  DrugBank 5.0: a major update to the DrugBank database for 2018 , 2017, Nucleic Acids Res..

[53]  John Elder,et al.  Practical Text Mining and Statistical Analysis for Non-structured Text Data Applications , 2012 .

[54]  Yi Pan,et al.  Predicting Drug-Drug Interactions Based on Integrated Similarity and Semi-Supervised Learning , 2020, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[55]  Jun'ichi Tsujii,et al.  GENIA corpus - a semantically annotated corpus for bio-textmining , 2003, ISMB.

[56]  Omer Levy,et al.  Improving Distributional Similarity with Lessons Learned from Word Embeddings , 2015, TACL.

[57]  Nigel H. Greig,et al.  Brain uptake and anticancer activities of vincristine and vinblastine are restricted by their low cerebrovascular permeability and binding to plasma constituents in rat , 2008, Cancer Chemotherapy and Pharmacology.

[58]  Chitta Baral,et al.  Discovering drug–drug interactions: a text-mining and reasoning approach based on properties of drug metabolism , 2010, Bioinform..

[59]  Danny Ho,et al.  Towards an early software estimation using log-linear regression and a multilayer perceptron model , 2013, J. Syst. Softw..

[60]  Andrea Cipriani,et al.  Comparative efficacy and tolerability of 32 oral antipsychotics for the acute treatment of adults with multi-episode schizophrenia: a systematic review and network meta-analysis , 2019, The Lancet.

[61]  Jianying Hu,et al.  Label Propagation Prediction of Drug-Drug Interactions Based on Clinical Side Effects , 2015, Scientific Reports.

[62]  Jeffrey M Schussler,et al.  Drug-induced QT interval prolongation: mechanisms and clinical management , 2012, Therapeutic advances in drug safety.

[63]  Dan M Roden,et al.  Efficacy of Flecainide in the Treatment of Catecholaminergic Polymorphic Ventricular Tachycardia: A Randomized Clinical Trial , 2017, JAMA cardiology.

[64]  Andreas Hotho,et al.  A Brief Survey of Text Mining , 2005, LDV Forum.

[65]  Jae Yong Ryu,et al.  Deep learning improves prediction of drug–drug and drug–food interactions , 2018, Proceedings of the National Academy of Sciences.