Adverse Drug Reaction Discovery Using a Tumor-Biomarker Knowledge Graph

Adverse drug reactions (ADRs) are a major public health concern, and early detection is crucial for drug development and patient safety. Together with the increasing availability of large-scale literature data, machine learning has the potential to predict unknown ADRs from current knowledge. By the machine learning methods, we constructed a Tumor-Biomarker Knowledge Graph (TBKG) which contains four types of node: Tumor, Biomarker, Drug, and ADR using biomedical literatures. Based on this knowledge graph, we not only discovered potential ADRs of antitumor drugs but also provided explanations. Experiments on real-world data show that our model can achieve 0.81 accuracy of three cross-validation and the ADRs discovery of Osimertinib was chosen for the clinical validation. Calculated ADRs of Osimertinib by our model consisted of the known ADRs which were in line with the official manual and some unreported rare ADRs in clinical cases. Results also showed that our model outperformed traditional co-occurrence methods. Moreover, each calculated ADRs were attached with the corresponding paths of “tumor-biomarker-drug” in the knowledge graph which could help to obtain in-depth insights into the underlying mechanisms. In conclusion, the tumor-biomarker knowledge-graph based approach is an explainable method for potential ADRs discovery based on biomarkers and might be valuable to the community working on the emerging field of biomedical literature mining and provide impetus for the mechanism research of ADRs.

[1]  Yi-Ping Phoebe Chen,et al.  Prediction of drug adverse events using deep learning in pharmaceutical discovery , 2020, Briefings Bioinform..

[2]  Versione,et al.  Common Terminology Criteria for Adverse Events , 2020, Definitions.

[3]  Jian Wang,et al.  Adverse drug reaction detection via a multihop self-attention mechanism , 2019, BMC Bioinformatics.

[4]  Arantza Casillas,et al.  Exploring Joint AB-LSTM With Embedded Lemmas for Adverse Drug Reaction Discovery , 2019, IEEE Journal of Biomedical and Health Informatics.

[5]  Yue Wang,et al.  Improving rare disease classification using imperfect knowledge graph , 2019, 2019 IEEE International Conference on Healthcare Informatics (ICHI).

[6]  Marco Roos,et al.  Drug prioritization using the semantic properties of a knowledge graph , 2019, Scientific Reports.

[7]  中国抗癌协会肺癌专业委员会 Chinese Society of Lung Cancer, Chin.  EGFR-TKI不良反应管理专家共识 , 2019, Zhongguo fei ai za zhi = Chinese journal of lung cancer.

[8]  Yaliang Li,et al.  CBN: Constructing a clinical Bayesian network based on data from the electronic medical record , 2018, J. Biomed. Informatics.

[9]  Jiaguo Huang,et al.  Drug-Induced Nephrotoxicity: Pathogenic Mechanisms, Biomarkers and Prevention Strategies. , 2018, Current drug metabolism.

[10]  Robert M Califf,et al.  Biomarker definitions and their applications , 2018, Experimental biology and medicine.

[11]  M. Pirmohamed,et al.  Biomarkers of adverse drug reactions , 2018, Experimental biology and medicine.

[12]  K. Patton,et al.  Adverse drug reactions , 2018, Anaesthesia.

[13]  Reena Philip,et al.  FDA Benefit‐Risk Assessment of Osimertinib for the Treatment of Metastatic Non‐Small Cell Lung Cancer Harboring Epidermal Growth Factor Receptor T790M Mutation , 2017, The oncologist.

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

[15]  Meng Wang,et al.  Safe Medicine Recommendation via Medical Knowledge Graph Embedding , 2017, ArXiv.

[16]  David Sontag,et al.  Learning a Health Knowledge Graph from Electronic Medical Records , 2017, Scientific Reports.

[17]  Meng Wang,et al.  PDD Graph: Bridging Electronic Medical Records and Biomedical Knowledge Graphs via Entity Linking , 2017, SEMWEB.

[18]  R. Shakya,et al.  Adverse Drug Reaction due to Cancer Chemotherapy and its Financial Burden in Different Hospitals of Nepal , 2017 .

[19]  Yong Hu,et al.  Improving drug safety: From adverse drug reaction knowledge discovery to clinical implementation. , 2016, Methods.

[20]  Hongfang Liu,et al.  Prioritizing Adverse Drug Reaction and Drug Repositioning Candidates Generated by Literature-Based Discovery , 2016, BCB.

[21]  Dejan Dinevski,et al.  Using Literature-Based Discovery to Explain Adverse Drug Effects , 2016, Journal of Medical Systems.

[22]  Avi Ma'ayan,et al.  Drug-induced adverse events prediction with the LINCS L1000 data , 2016, Bioinform..

[23]  A. Barabasi,et al.  Network-based in silico drug efficacy screening , 2016, Nature Communications.

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

[25]  Yoshihiro Yamanishi,et al.  Predicting drug side-effect profiles: a chemical fragment-based approach , 2011, BMC Bioinformatics.

[26]  E. Matthews,et al.  Prediction of drug-related cardiac adverse effects in humans--B: use of QSAR programs for early detection of drug-induced cardiac toxicities. , 2010, Regulatory toxicology and pharmacology : RTP.

[27]  Michael C. Wendl,et al.  Argonaute—a database for gene regulation by mammalian microRNAs , 2005, BMC Bioinformatics.

[28]  E. Oren,et al.  Potential role of pharmacogenomics in reducing adverse drug reactions: a systematic review. , 2001, JAMA.

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

[30]  M. Callon,et al.  Mapping the dynamics of science and technology : sociology of science in the real world , 1988 .

[31]  Weiguo Fan,et al.  Adverse drug event detection and extraction from open data: A deep learning approach , 2020, Inf. Process. Manag..

[32]  Kevin P. Murphy.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[33]  M. Callon,et al.  Mapping the Dynamics of Science and Technology , 1986 .