Computational models for the prediction of adverse cardiovascular drug reactions

Abstract

Background Predicting adverse drug reactions (ADRs) has become very important owing to the huge global health burden and failure of drugs. This indicates a need for prior prediction of probable ADRs in preclinical stages which can improve drug failures and reduce the time and cost of development thus providing efficient and safer therapeutic options for patients. Though several approaches have been put forward for in silico ADR prediction, there is still room for improvement. Methods In the present work, we have used machine learning based approach for cardiovascular (CV) ADRs prediction by integrating different features of drugs, biological (drug transporters, targets and enzymes), chemical (substructure fingerprints) and phenotypic (therapeutic indications and other identified ADRs), and their two and three level combinations. To recognize quality and important features, we used minimum redundancy maximum relevance approach while synthetic minority over-sampling technique balancing method was used to introduce a balance in the training sets. Results This is a rigorous and comprehensive study which involved the generation of a total of 504 computational models for 36 CV ADRs using two state-of-the-art machine-learning algorithms: random forest and sequential minimization optimization. All the models had an accuracy of around 90% and the biological and chemical features models were more informative as compared to the models generated using chemical features. Conclusions The results obtained demonstrated that the predictive models generated in the present study were highly accurate, and the phenotypic information of the drugs played the most important role in drug ADRs prediction. Furthermore, the results also showed that using the proposed method, different drugs properties can be combined to build computational predictive models which can effectively predict potential ADRs during early stages of drug development. Electronic supplementary material The online version of this article (10.1186/s12967-019-1918-z) contains supplementary material, which is available to authorized users.

Application Progress of Organoids in Colorectal Cancer

“…Adverse effects of drugs, especially organ toxicity, are the main reasons for drug development failure and withdrawal after marketing ( Jamal et al, 2019 ). The current general cell screening and animal model screening often cannot accurately predict adverse reactions in the human body.…”

Computational healthcare: Present and future perspectives (Review)

“…One of the most difficult steps in the process of drug development is the prediction of adverse effects. It has been reported that computational modeling using machine learning is useful for predicting adverse effects (65). Moreover, it is possible to manufacture synthetic patients and data artificially by analyzing existing data using machine learning techniques (66,67).…”

Combining a Pharmacological Network Model with a Bayesian Signal Detection Algorithm to Improve the Detection of Adverse Drug Events

“…However, DPA ignores the influence of a confounding bias in the analysis, which may lead to false positives and an under-detection of ADEs ( DuMouchel, et al, 2013 ; Candore, et al, 2015 ). To overcome these limitations, machine learning algorithms and other methods have been used to detect ADEs using SRSs; some network-based methods and machine learning algorithms have been developed to predict ADEs using different public databases ( Cami, et al, 2011 ; Liu, et al, 2012 ; Cheng, et al, 2013 ; Lin, et al, 2013 ; Davazdahemami and Delen, 2018 ; Jamal, et al, 2019 ). For example, a pharmacological network model (PNM) was developed to predict new and unknown drug-ADE associations ( Cami, et al, 2011 ).…”

“…Liu et al integrated the phenotypic characteristics of drugs (i.e., indications and known adverse drug reactions), chemical structures, and biological properties of protein targets and pathway information, and used five machine learning methods to predict ADEs ( Liu, et al, 2012 ). Moreover, Jamal et al integrated the biological, chemical, and phenotypic features of drugs and used machine learning methods (random forest and sequential minimum optimization) to predict cardiovascular adverse reactions ( Jamal, et al, 2019 ). Their results showed that the phenotypic data showed the best prediction effect and that drugs with similar chemical structures were more likely to exhibit similar ADEs.…”