Prediction of adverse drug reactions based on knowledge graph embedding

Background Adverse drug reactions (ADRs) are an important concern in the medication process and can pose a substantial economic burden for patients and hospitals. Because of the limitations of clinical trials, it is difficult to identify all possible ADRs of a drug before it is marketed. We developed a new model based on data mining technology to predict potential ADRs based on available drug data. Method Based on the Word2Vec model in Nature Language Processing, we propose a new knowledge graph embedding method that embeds drugs and ADRs into their respective vectors and builds a logistic regression classification model to predict whether a given drug will have ADRs. Result First, a new knowledge graph embedding method was proposed, and comparison with similar studies showed that our model not only had high prediction accuracy but also was simpler in model structure. In our experiments, the AUC of the classification model reached a maximum of 0.87, and the mean AUC was 0.863. Conclusion In this paper, we introduce a new method to embed knowledge graph to vectorize drugs and ADRs, then use a logistic regression classification model to predict whether there is a causal relationship between them. The experiment showed that the use of knowledge graph embedding can effectively encode drugs and ADRs. And the proposed ADRs prediction system is also very effective.

[1]  K. Kikuchi,et al.  Detection of Anti-mitochondrial Antibodies Accompanied by Drug-induced Hepatic Injury due to Atorvastatin , 2019, Internal medicine.

[2]  Jianying Hu,et al.  Predicting adverse drug reactions through interpretable deep learning framework , 2018, BMC Bioinformatics.

[3]  Malorye Allison,et al.  Reinventing clinical trials , 2012, Nature Biotechnology.

[4]  K. Olden,et al.  Adderall Induced Acute Liver Injury: A Rare Case and Review of the Literature , 2013, Case reports in gastrointestinal medicine.

[5]  I. Edwards,et al.  Adverse drug reactions: definitions, diagnosis, and management , 2000, The Lancet.

[6]  G. De Velasco,et al.  Three case reports , 2019, Medicine.

[7]  T. Ide,et al.  Immune-mediated Drug-induced Liver Injury Caused by Laninamivir Octanoate Hydrate , 2019, Internal medicine.

[8]  Sergio E. Wong,et al.  Adverse Drug Reaction Prediction Using Scores Produced by Large-Scale Drug-Protein Target Docking on High-Performance Computing Machines , 2014, PloS one.

[9]  J. Hirsch,et al.  Cost of Prescription Drug–Related Morbidity and Mortality , 2018, The Annals of pharmacotherapy.

[10]  William M. Lee,et al.  Features and Outcomes of 899 Patients With Drug-Induced Liver Injury: The DILIN Prospective Study. , 2015, Gastroenterology.

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

[12]  Zhiyong Lu,et al.  A survey of current trends in computational drug repositioning , 2016, Briefings Bioinform..

[13]  D. Bojanic,et al.  Keynote review: in vitro safety pharmacology profiling: an essential tool for successful drug development. , 2005, Drug discovery today.

[14]  G. Thiéfin,et al.  Hépatite aiguë pseudo-angiocholitique probablement induite par la tamsulosine , 2006 .

[15]  Salma Jamal,et al.  Predicting neurological Adverse Drug Reactions based on biological, chemical and phenotypic properties of drugs using machine learning models , 2017, Scientific Reports.

[16]  Vít Novácek,et al.  Facilitating prediction of adverse drug reactions by using knowledge graphs and multi‐label learning models , 2019, Briefings Bioinform..

[17]  Weihua Yuan,et al.  Adverse Drug Reaction Predictions Using Stacking Deep Heterogeneous Information Network Embedding Approach , 2018, Molecules.

[18]  L. Feldman,et al.  Hepatotoxicity and Recurrent NSTEMI While on Pembrolizumab for Metastatic Giant Cell Bone Tumor , 2019, The American journal of the medical sciences.

[19]  Dongsheng Cao,et al.  Integrating Multiple Evidence Sources to Predict Adverse Drug Reactions Based on a Systems Pharmacology Model , 2015, CPT: pharmacometrics & systems pharmacology.

[20]  Michael J. Keiser,et al.  Large Scale Prediction and Testing of Drug Activity on Side-Effect Targets , 2012, Nature.

[21]  M. Fukuoka,et al.  Successful Desensitization with Crizotinib after Crizotinib-induced Liver Injury in ROS1-rearranged Lung Adenocarcinoma , 2019, Internal medicine.

[22]  R. Pieters,et al.  Trovafloxacin-Induced Liver Injury: Lack in Regulation of Inflammation by Inhibition of Nucleotide Release and Neutrophil Movement , 2018, Toxicological sciences : an official journal of the Society of Toxicology.

[23]  Hilde van der Togt,et al.  Publisher's Note , 2003, J. Netw. Comput. Appl..

[24]  Yi-Ping Phoebe Chen,et al.  Machine learning on adverse drug reactions for pharmacovigilance. , 2019, Drug discovery today.

[25]  David W. Ritchie,et al.  GESSE: Predicting Drug Side Effects from Drug-Target Relationships , 2015, J. Chem. Inf. Model..

[26]  K. Cummings,et al.  Hepatotoxicity after sevoflurane anaesthesia: a new twist to an old story. , 2019, British journal of anaesthesia.

[27]  J. Kluwe,et al.  Severe Acute Liver Injury Following Therapeutic Doses of Acetaminophen in a Patient With Spinal Muscular Atrophy. , 2018, American journal of therapeutics.

[28]  M. Koopmanschap,et al.  Epidemiology of Adverse Drug Reactions in Europe: A Review of Recent Observational Studies , 2015, Drug Safety.

[29]  H. Sayar,et al.  Severe cholestasis due to azathioprine in Behcet’s disease , 2019, BMJ Case Reports.

[30]  R. Levine,et al.  Argatroban therapy in heparin-induced thrombocytopenia with hepatic dysfunction. , 2006, Chest.

[31]  Jianying Hu,et al.  Molecular Docking for Prediction and Interpretation of Adverse Drug Reactions. , 2018, Combinatorial chemistry & high throughput screening.

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

[33]  Sung Wook Lee,et al.  [Drug Induced Liver Injury by Prophylactic Administration of Albendazole]. , 2019, The Korean journal of gastroenterology = Taehan Sohwagi Hakhoe chi.

[34]  R. Krauss,et al.  When good drugs go bad , 2007, Nature.

[35]  M. Podhola,et al.  Hepatic Injury Induced by a Single Dose of Nivolumab - a Case Report and Literature Review. , 2019, Klinicka onkologie : casopis Ceske a Slovenske onkologicke spolecnosti.

[36]  Zina M. Ibrahim,et al.  Knowledge graph prediction of unknown adverse drug reactions and validation in electronic health records , 2017, Scientific Reports.

[37]  Peer Bork,et al.  The SIDER database of drugs and side effects , 2015, Nucleic Acids Res..

[38]  Weida Tong,et al.  DILIrank: the largest reference drug list ranked by the risk for developing drug-induced liver injury in humans. , 2016, Drug Discovery Today.