Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs

Abstract

Objective: Adverse drug reaction (ADR) is one of the major causes of failure in drug development. Severe ADRs that go undetected until the post-marketing phase of a drug often lead to patient morbidity. Accurate prediction of potential ADRs is required in the entire life cycle of a drug, including early stages of drug design, different phases of clinical trials, and post-marketing surveillance.

Methods: Many studies have utilized either chemical structures or molecular pathways of the drugs to predict ADRs. Here, the authors propose a machine-learning-based approach for ADR prediction by integrating the phenotypic characteristics of a drug, including indications and other known ADRs, with the drug's chemical structures and biological properties, including protein targets and pathway information. A large-scale study was conducted to predict 1385 known ADRs of 832 approved drugs, and five machine-learning algorithms for this task were compared.

Results: This evaluation, based on a fivefold cross-validation, showed that the support vector machine algorithm outperformed the others. Of the three types of information, phenotypic data were the most informative for ADR prediction. When biological and phenotypic features were added to the baseline chemical information, the ADR prediction model achieved significant improvements in area under the curve (from 0.9054 to 0.9524), precision (from 43.37% to 66.17%), and recall (from 49.25% to 63.06%). Most importantly, the proposed model successfully predicted the ADRs associated with withdrawal of rofecoxib and cerivastatin.

Conclusion: The results suggest that phenotypic information on drugs is valuable for ADR prediction. Moreover, they demonstrate that different models that combine chemical, biological, or phenotypic information can be built from approved drugs, and they have the potential to detect clinically important ADRs in both preclinical and post-marketing phases.

Figure 1

Overview of the proposed framework for drug surveillance. Different combinations of features can be used for different phases of drug surveillance. Chemical structures and relevant proteins of drugs can be combined to predict potential adverse drug reactions (ADRs) in the early phase of drug development. As drug indication and other ADRs become available, they can be integrated with chemical and biological information for post-market surveillance.

Figure 2

Receiver operating characteristic curves in fivefold cross-validation for various feature sets using support vector machine: (1) chemical structures, ‘chem’; (2) biological properties, ‘bio’; (3) phenotypic properties, ‘pheno’; (4) chemical and biological properties, ‘chem+bio’; (5) chemical and phenotypic properties, ‘chem+pheno’; (6) chemical, biological, and phenotypic properties, ‘chem+bio+pheno’.

Figure 3

Receiver operating characteristic curves in fivefold cross-validation on various feature sets for common adverse drug reactions using support vector machine: (1) chemical structures, ‘chem’; (2) biological properties, ‘bio’; (3) phenotypic properties, ‘pheno’; (4) chemical and biological properties, ‘chem+bio’; (5) chemical and phenotypic properties, ‘chem+pheno’; (6) chemical, biological, and phenotypic properties, ‘chem+bio+pheno’.

Figure 4

Receiver operating characteristic curves for method comparison. KNN, K-nearest neighbor; LR, logistic regression; NB, naïve Bayes; RF, random forest; SVM, support vector machine.

Figure 5

Overlap of the true positive predictions using CHEM (chemical structure), BIO (biological properties), or PHENO (phenotypic properties) features.