Predicting neurological Adverse Drug Reactions based on biological, chemical and phenotypic properties of drugs using machine learning models

Adverse drug reactions (ADRs) have become one of the primary reasons for the failure of drugs and a leading cause of deaths. Owing to the severe effects of ADRs, there is an urgent need for the generation of effective models which can accurately predict ADRs during early stages of drug development based on integration of various features of drugs. In the current study, we have focused on neurological ADRs and have used various properties of drugs that include biological properties (targets, transporters and enzymes), chemical properties (substructure fingerprints), phenotypic properties (side effects (SE) and therapeutic indications) and a combinations of the two and three levels of features. We employed relief-based feature selection technique to identify relevant properties and used machine learning approach to generated learned model systems which would predict neurological ADRs prior to preclinical testing. Additionally, in order to explain the efficiency and applicability of the models, we tested them to predict the ADRs for already existing anti-Alzheimer drugs and uncharacterized drugs, respectively in side effect resource (SIDER) database. The generated models were highly accurate and our results showed that the models based on chemical (accuracy 93.20%), phenotypic (accuracy 92.41%) and combination of three properties (accuracy 94.18%) were highly accurate while the models based on biological properties (accuracy 82.11%) were highly informative.

[1]  R. A. Lucas,et al.  Serotonin Syndrome With Standard-Dose Vilazodone (Viibryd ® ) Monotherapy , 2014 .

[2]  K. O'brien,et al.  Disabling neurological complications of amiodarone. , 1985, Australian and New Zealand journal of medicine.

[3]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[4]  A. Fliri,et al.  Analysis of System Structure–Function Relationships , 2007, ChemMedChem.

[5]  Cathy H. Wu,et al.  UniProt: the Universal Protein knowledgebase , 2004, Nucleic Acids Res..

[6]  Roderick E. Hubbard,et al.  3D structure and the drug-discovery process , 2005 .

[7]  P. Barach,et al.  Clarifying Adverse Drug Events: A Clinician's Guide to Terminology, Documentation, and Reporting , 2004, Annals of Internal Medicine.

[8]  D. Ingram,et al.  Metabolic and neurologic consequences of chronic lopinavir/ritonavir administration to C57BL/6 mice. , 2010, Antiviral research.

[9]  A. Bender,et al.  Analysis of Pharmacology Data and the Prediction of Adverse Drug Reactions and Off‐Target Effects from Chemical Structure , 2007, ChemMedChem.

[10]  S. Thamarai Selvi,et al.  Early Detection of Breast Cancer using SVM Classifier Technique , 2009, ArXiv.

[11]  Dragos Horvath,et al.  Predicting ADME properties and side effects: the BioPrint approach. , 2003, Current opinion in drug discovery & development.

[12]  R. Spector,et al.  Serious adverse reactions associated with sulindac. , 1982, Archives of internal medicine.

[13]  CHUN WEI YAP,et al.  PaDEL‐descriptor: An open source software to calculate molecular descriptors and fingerprints , 2011, J. Comput. Chem..

[14]  E. Kurzrock,et al.  Adverse reactions of nitrofurantoin, trimethoprim and sulfamethoxazole in children. , 2004, The Journal of urology.

[15]  M. Chandar,et al.  Severe Generalized Weakness, Paralysis, and Aphasia following Administration of Irinotecan and Oxaliplatin during FOLFIRINOX Chemotherapy , 2015, Case Reports in Oncology.

[16]  L. Cregler Adverse health consequences of cocaine abuse. , 1989, Journal of the National Medical Association.

[17]  Rouslan A. Moro,et al.  Support Vector Machines (SVM) as a Technique for Solvency Analysis , 2008 .

[18]  C. Miller,et al.  Optic-nerve degeneration in Alzheimer's disease. , 1986, The New England journal of medicine.

[19]  A. Bénard-Laribière,et al.  Severe adverse effects of bromocriptine in lactation inhibition: a pharmacovigilance survey , 2015, BJOG : an international journal of obstetrics and gynaecology.

[20]  M. Aapro,et al.  Early clinical studies with docetaxel , 1995 .

[21]  Rok Blagus,et al.  SMOTE for high-dimensional class-imbalanced data , 2013, BMC Bioinformatics.

[22]  Ian H. Witten,et al.  WEKA - Experiences with a Java Open-Source Project , 2010, J. Mach. Learn. Res..

[23]  J. Chen,et al.  Predicting adverse side effects of drugs , 2011, BMC Genomics.

[24]  R. Girdwood Abnormalities of Vitamin B12 and Folic Acid Metabolism—their Influence on the Nervous System , 1968, Proceedings of the Nutrition Society.

[25]  L. Goldstein,et al.  Neuropsychiatric manifestations associated with azithromycin in two brothers , 2010, European Journal of Clinical Pharmacology.

[26]  R. Maganti,et al.  Neurotoxic effects associated with antibiotic use: management considerations. , 2011, British journal of clinical pharmacology.

[27]  F. Vianello,et al.  Severe Acute Axonal Neuropathy following Treatment with Arsenic Trioxide for Acute Promyelocytic Leukemia: a Case Report , 2016, Mediterranean journal of hematology and infectious diseases.

[28]  Tao Jiang,et al.  ChemmineR: a compound mining framework for R , 2008, Bioinform..

[29]  V. Parisi Correlation between morphological and functional retinal impairment in patients affected by ocular hypertension, glaucoma, demyelinating optic neuritis and Alzheimer’s disease , 2003, Seminars in ophthalmology.

[30]  Muin J. Khoury,et al.  Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes , 2010, BMC Medical Informatics Decis. Mak..

[31]  Bin Chen,et al.  PubChem BioAssays as a data source for predictive models. , 2010, Journal of molecular graphics & modelling.

[32]  Dapeng Wu,et al.  A RELIEF Based Feature Extraction Algorithm , 2008, SDM.

[33]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[34]  A. M. Tomé,et al.  Quinolones: review of psychiatric and neurological adverse reactions. , 2011, Drug safety.

[35]  Feng Liu,et al.  Predicting drug side effects by multi-label learning and ensemble learning , 2015, BMC Bioinformatics.

[36]  S. Schroeder,et al.  How Many Hours Is Enough? An Old Profession Meets a New Generation , 2004, Annals of Internal Medicine.

[37]  W. Bechstein,et al.  Neurotoxicity of calcineurin inhibitors: impact and clinical management , 2000, Transplant international : official journal of the European Society for Organ Transplantation.

[38]  Hua Xu,et al.  Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs , 2012, J. Am. Medical Informatics Assoc..

[39]  P. Bork,et al.  A side effect resource to capture phenotypic effects of drugs , 2010, Molecular systems biology.

[40]  Ganesh Bagler,et al.  Phenotypic side effects prediction by optimizing correlation with chemical and target profiles of drugs. , 2015, Molecular bioSystems.

[41]  R. Pirker,et al.  Neurological monitoring of neurotoxicity induced by paclitaxel/cisplatin chemotherapy. , 1997, European journal of cancer.

[42]  M. Aapro,et al.  Early clinical studies with docetaxel. Docetaxel Investigators Group. , 1995, European journal of cancer.

[43]  David S. Wishart,et al.  DrugBank: a comprehensive resource for in silico drug discovery and exploration , 2005, Nucleic Acids Res..