Advancement in predicting interactions between drugs used to treat psoriasis and its comorbidities by integrating molecular and clinical resources

OBJECTIVE Drug-drug interactions (DDIs) can result in adverse and potentially life-threatening health consequences; however, it is challenging to predict potential DDIs in advance. We introduce a new computational approach to comprehensively assess the drug pairs which may be involved in specific DDI types by combining information from large-scale gene expression (984 transcriptomic datasets), molecular structure (2159 drugs), and medical claims (150 million patients). MATERIALS AND METHODS Features were integrated using ensemble machine learning techniques, and we evaluated the DDIs predicted with a large hospital-based medical records dataset. Our pipeline integrates information from >30 different resources, including >10 000 drugs and >1.7 million drug-gene pairs. We applied our technique to predict interactions between 37 611 drug pairs used to treat psoriasis and its comorbidities. RESULTS Our approach achieves >0.9 area under the receiver operator curve (AUROC) for differentiating 11 861 known DDIs from 25 750 non-DDI drug pairs. Significantly, we demonstrate that the novel DDIs we predict can be confirmed through independent data sources and supported using clinical medical records. CONCLUSIONS By applying machine learning and taking advantage of molecular, genomic, and health record data, we are able to accurately predict potential new DDIs that can have an impact on public health.

[1]  B. Stricker,et al.  Hospitalisations and emergency department visits due to drug–drug interactions: a literature review , 2007, Pharmacoepidemiology and drug safety.

[2]  Xiaohui Yao,et al.  Mining and visualizing high-order directional drug interaction effects using the FAERS database , 2020, BMC Medical Informatics and Decision Making.

[3]  Wen Zhang,et al.  A multimodal deep learning framework for predicting drug-drug interaction events , 2020, Bioinform..

[4]  M. Namazi,et al.  The remarkable beneficial effect of adding oral simvastatin to topical betamethasone for treatment of psoriasis: a double-blind, randomized, placebo-controlled study. , 2010, Nigerian journal of medicine : journal of the National Association of Resident Doctors of Nigeria.

[5]  David W Bates,et al.  High-priority drug-drug interaction clinical decision support overrides in a newly implemented commercial computerized provider order-entry system: Override appropriateness and adverse drug events , 2020, J. Am. Medical Informatics Assoc..

[6]  Joseph Hanlon,et al.  Clinical consequences of polypharmacy in elderly , 2014, Expert opinion on drug safety.

[7]  Li Wang,et al.  A Modified Skip-Gram Algorithm for Extracting Drug-Drug Interactions from AERS Reports , 2020, Comput. Math. Methods Medicine.

[8]  J. Koo,et al.  Safety considerations with combination therapies for psoriasis , 2020, Expert opinion on drug safety.

[9]  Jocelyn R. Wilder,et al.  Changes in Prescription and Over-the-Counter Medication and Dietary Supplement Use Among Older Adults in the United States, 2005 vs 2011. , 2016, JAMA internal medicine.

[10]  Lei Wang,et al.  Translational High‐Dimensional Drug Interaction Discovery and Validation Using Health Record Databases and Pharmacokinetics Models , 2018, Clinical pharmacology and therapeutics.

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

[12]  R. Altman,et al.  Informatics confronts drug-drug interactions. , 2013, Trends in pharmacological sciences.

[13]  S. Wyke,et al.  Epidemiology of multimorbidity and implications for health care, research, and medical education: a cross-sectional study , 2012, The Lancet.

[14]  Michael Schroeder,et al.  SuperCYP: a comprehensive database on Cytochrome P450 enzymes including a tool for analysis of CYP-drug interactions , 2009, Nucleic Acids Res..

[15]  George Hripcsak,et al.  Feasibility of Prioritizing Drug–Drug-Event Associations Found in Electronic Health Records , 2015, Drug Safety.

[16]  Yow-Ming C Wang,et al.  Biological Products for the Treatment of Psoriasis: Therapeutic Targets, Pharmacodynamics and Disease-Drug-Drug Interaction Implications , 2014, The AAPS Journal.

[17]  Constantin F. Aliferis,et al.  Extracting Drug-Drug Interaction Articles from MEDLINE to Improve the Content of Drug Databases , 2005, AMIA.

[18]  H. Sletvold,et al.  Potential drug-to-drug interactions: a cross-sectional study among older patients discharged from hospital to home care , 2018, Safety in Health.

[19]  Hongkang Mei,et al.  Systematic Prediction of Pharmacodynamic Drug-Drug Interactions through Protein-Protein-Interaction Network , 2013, PLoS Comput. Biol..

[20]  Wu Yi Zheng,et al.  Drug-drug interactions and their harmful effects in hospitalised patients: a systematic review and meta-analysis , 2017, European Journal of Clinical Pharmacology.

[21]  Heng-Yi Wu,et al.  Extraction of Pharmacokinetic Evidence of Drug–Drug Interactions from the Literature , 2014, PloS one.

[22]  Russ B. Altman,et al.  A novel signal detection algorithm for identifying hidden drug-drug interactions in adverse event reports , 2012, J. Am. Medical Informatics Assoc..

[23]  P. Vollenweider,et al.  Prevalence and determinants of polypharmacy in Switzerland: data from the CoLaus study , 2017, BMC Health Services Research.

[24]  Jessica S. Ancker,et al.  Effects of workload, work complexity, and repeated alerts on alert fatigue in a clinical decision support system , 2017, BMC Medical Informatics and Decision Making.

[25]  Doheon Lee,et al.  Predicting Pharmacodynamic Drug-Drug Interactions through Signaling Propagation Interference on Protein-Protein Interaction Networks , 2015, PloS one.

[26]  B. Strober,et al.  Characterization of disease burden, comorbidities, and treatment use in a large, US‐based cohort: Results from the Corrona Psoriasis Registry , 2018, Journal of the American Academy of Dermatology.

[27]  Yan Tang,et al.  Identifying Methamphetamine Dependence Using Regional Homogeneity in BOLD Signals , 2020, Comput. Math. Methods Medicine.

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

[29]  J. Sundquist,et al.  An Increasing Trend in the Prevalence of Polypharmacy in Sweden: A Nationwide Register-Based Study , 2020, Frontiers in Pharmacology.

[30]  Jingcheng Du,et al.  Gene2vec: distributed representation of genes based on co-expression , 2018, BMC Genomics.

[31]  M. van den Akker,et al.  Trends in multimorbidity and polypharmacy in the Flemish-Belgian population between 2000 and 2015 , 2019, PloS one.

[32]  Nigam H. Shah,et al.  Mining clinical text for signals of adverse drug-drug interactions , 2014, J. Am. Medical Informatics Assoc..

[34]  L. Køber,et al.  Trends in warfarin use and its associations with thromboembolic and bleeding rates in a population with atrial fibrillation between 1996 and 2011 , 2018, PloS one.

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

[36]  E. Hak,et al.  Trends in polypharmacy and dispensed drugs among adults in the Netherlands as compared to the United States , 2019, PloS one.

[37]  T. Ohkusa,et al.  Treatment of functional dyspepsia with antianxiety or antidepressive agents: systematic review , 2005, Journal of Gastroenterology.

[38]  B. Patel,et al.  Topical corticosteroid compounding: effects on physicochemical stability and skin penetration rate. , 1989, Journal of the American Academy of Dermatology.

[39]  Patrick M. Wilson,et al.  Neighborhood socioeconomic disadvantage is associated with multimorbidity in a geographically-defined community , 2020, BMC Public Health.

[40]  V. Shirinsky,et al.  Efficacy of simvastatin in plaque psoriasis: A pilot study. , 2007, Journal of the American Academy of Dermatology.

[41]  E. Weirich.  Dermatopharmacology of salicylic acid. I. Range of dermatotherapeutic effects of salicylic acid. , 1975, Dermatologica.

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

[43]  Reza Safdari,et al.  Computational prediction of drug-drug interactions based on drugs functional similarities , 2017, J. Biomed. Informatics.

[44]  Elizabeth J Horn,et al.  National Psoriasis Foundation clinical consensus on psoriasis comorbidities and recommendations for screening. , 2008, Journal of the American Academy of Dermatology.

[45]  L. Wienkers,et al.  Predicting in vivo drug interactions from in vitro drug discovery data , 2005, Nature Reviews Drug Discovery.

[46]  Lang Li,et al.  Mining Directional Drug Interaction Effects on Myopathy Using the FAERS Database , 2018, IEEE Journal of Biomedical and Health Informatics.

[47]  M. Lebwohl,et al.  Psoriasis: Which therapy for which patient: Psoriasis comorbidities and preferred systemic agents. , 2019, Journal of the American Academy of Dermatology.

[48]  L. Di,et al.  In Vitro and In Vivo Methods to Assess Pharmacokinetic Drug-Drug Interactions in Drug Discovery and Development. , 2019, Biopharmaceutics & drug disposition.

[49]  Supinya Dechanont,et al.  Hospital admissions/visits associated with drug–drug interactions: a systematic review and meta‐analysis , 2014, Pharmacoepidemiology and drug safety.

[50]  Yi-Cheng Tu,et al.  Characterization of the mechanism of drug-drug interactions from PubMed using MeSH terms , 2017, PloS one.

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

[52]  Bruce Guthrie,et al.  The rising tide of polypharmacy and drug-drug interactions: population database analysis 1995–2010 , 2015, BMC Medicine.

[53]  Olivier Bodenreider,et al.  The Unified Medical Language System (UMLS): integrating biomedical terminology , 2004, Nucleic Acids Res..

[54]  A. Barabasi,et al.  Drug—target network , 2007, Nature Biotechnology.

[55]  R. Day,et al.  Life‐threatening drug interactions: what the physician needs to know , 2017, Internal medicine journal.

[56]  Thang Nguyen Tat,et al.  Efficacy of Adding Oral Simvastatin to Topical Therapy for Treatment of Psoriasis: The Vietnamese Experience , 2019, Open access Macedonian journal of medical sciences.

[57]  D. Haggstrom,et al.  Polypharmacy and patterns of prescription medication use among cancer survivors , 2018, Cancer.

[58]  L. Rybak.  Furosemide ototoxicity: Clinical and experimental aspects , 1985, The Laryngoscope.

[59]  Paloma Martínez,et al.  The DDI corpus: An annotated corpus with pharmacological substances and drug-drug interactions , 2013, J. Biomed. Informatics.

[60]  Kalpana Raja,et al.  Drug Repurposing Prediction for Immune-Mediated Cutaneous Diseases using a Word-Embedding-Based Machine Learning Approach. , 2019, The Journal of investigative dermatology.

[61]  Michel Dumontier,et al.  Toward a complete dataset of drug-drug interaction information from publicly available sources , 2015, J. Biomed. Informatics.