A Systematic Investigation of Computation Models for Predicting Adverse Drug Reactions (ADRs)

Background Early and accurate identification of adverse drug reactions (ADRs) is critically important for drug development and clinical safety. Computer-aided prediction of ADRs has attracted increasing attention in recent years, and many computational models have been proposed. However, because of the lack of systematic analysis and comparison of the different computational models, there remain limitations in designing more effective algorithms and selecting more useful features. There is therefore an urgent need to review and analyze previous computation models to obtain general conclusions that can provide useful guidance to construct more effective computational models to predict ADRs. Principal Findings In the current study, the main work is to compare and analyze the performance of existing computational methods to predict ADRs, by implementing and evaluating additional algorithms that have been earlier used for predicting drug targets. Our results indicated that topological and intrinsic features were complementary to an extent and the Jaccard coefficient had an important and general effect on the prediction of drug-ADR associations. By comparing the structure of each algorithm, final formulas of these algorithms were all converted to linear model in form, based on this finding we propose a new algorithm called the general weighted profile method and it yielded the best overall performance among the algorithms investigated in this paper. Conclusion Several meaningful conclusions and useful findings regarding the prediction of ADRs are provided for selecting optimal features and algorithms.

• Publication year

  2014

• Venue

  PLoS ONE

• Publication date

  2014-09-02

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1371/journal.pone.0105889PMID 25180585PMCID 4152017
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Prediction of adverse drug reactions by a network based external link prediction method

  2013cited by this paper
• Computational Study of Drugs by Integrating Omics Data with Kernel Methods

  2013cited by this paper
• Identification of chemogenomic features from drug–target interaction networks using interpretable classifiers

  2012cited by this paper
• Prediction of Drug-Target Interactions and Drug Repositioning via Network-Based Inference

  2012cited by this paper
• Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs

  2012cited by this paper
• Drug-target interaction prediction by random walk on the heterogeneous network.

  2012cited by this paper
• Gaussian interaction profile kernels for predicting drug-target interaction

  2011influential reference
• Predicting Adverse Drug Events Using Pharmacological Network Models

  2011influential reference
• Network Neighbors of Drug Targets Contribute to Drug Side-Effect Similarity

  2011cited by this paper
• Predicting adverse side effects of drugs

  2011cited by this paper
• Link prediction in bipartite graphs using internal links and weighted projection

  2011cited by this paper
• Network-Based Relating Pharmacological and Genomic Spaces for Drug Target Identification

  2010cited by this paper
• Semi-supervised drug-protein interaction prediction from heterogeneous biological spaces

  2010cited by this paper
• An Algorithmic Framework for Predicting Side Effects of Drugs

  2010cited by this paper
• Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework

  2010cited by this paper
• Fast and Scalable Algorithms for Semi-supervised Link Prediction on Static and Dynamic Graphs

  2010cited by this paper
• A side effect resource to capture phenotypic effects of drugs

  2010cited by this paper
• Supervised prediction of drug–target interactions using bipartite local models

  2009cited by this paper
• Supervised Bipartite Graph Inference

  2008cited by this paper
• Drug Target Identification Using Side-Effect Similarity

  2008cited by this paper
• Prediction of drug–target interaction networks from the integration of chemical and genomic spaces

  2008cited by this paper
• DrugBank: a knowledgebase for drugs, drug actions and drug targets

  2007cited by this paper
• An introduction to ROC analysis

  2006influential reference
• SVM vs regularized least squares classification

  2004cited by this paper
• Matrix analysis - for scientists and engineers

  2004cited by this paper
• The Use of the World Health Organisation Anatomical Therapeutic Chemical/Defined Daily Dose Methodology in Canada

  2004cited by this paper
• A social network caught in the Web

  2003cited by this paper
• Development of a chemical structure comparison method for integrated analysis of chemical and genomic information in the metabolic pathways.

  2003cited by this paper
• KEGG: Kyoto Encyclopedia of Genes and Genomes

  2000cited by this paper
• The Medical Dictionary for Regulatory Activities (MedDRA)

  1999cited by this paper
• An Information-Theoretic Definition of Similarity

  1998cited by this paper
• Coupling genetic algorithm with a grid search method to solve mixed integer nonlinear programming problems

  1996cited by this paper
• A critical investigation of recall and precision as measures of retrieval system performance

  1989influential reference

• Genetics-Driven Personalized Disease Progression Model

  2025cites this paper
• Mining Real-World Big Data to Characterize Adverse Drug Reaction Quantitatively: Mixed Methods Study

  2024cites this paper
• An extensive survey on the use of supervised machine learning techniques in the past two decades for prediction of drug side effects

  2023cites this paper
• Networks and Algorithms in Heterogeneous Network-based Methods for Drug-target Interaction Prediction: A Survey and Comparison

  2022cites this paper
• Current advances in biopharmaceutical informatics: guidelines, impact and challenges in the computational developability assessment of antibody therapeutics

  2022cites this paper
• Primum non nocere: In silico prediction of adverse drug reactions of antidepressant drugs

  2021cites this paper
• Alternatives to Animal Experiments in Research and Regulatory Testing

  2021cites this paper
• A compound attributes-based predictive model for drug induced liver injury in humans

  2020cites this paper
• Literature based discovery of alternative TCM medicine for adverse reactions to depression drugs

  2020cites this paper
• Computational models for the prediction of adverse cardiovascular drug reactions

  2019cites this paper
• Prediction of Adverse Drug Reactions by Combining Biomedical Tripartite Network and Graph Representation Model.

  2019cites this paper
• The impact of serious adverse drug reactions: a population‐based study of a decade of hospital admissions in New South Wales, Australia

  2017cites this paper
• A kernel matrix dimension reduction method for predicting drug-target interaction

  2017cites this paper
• Networks and Pathways in Systems Pharmacology

  2017cites this paper
• Drug side-effect prediction using machine learning methods

  2017cites this paper
• Systems biology approaches for identifying adverse drug reactions and elucidating their underlying biological mechanisms

  2016cites this paper
• An eigenvalue transformation technique for predicting drug-target interaction

  2015cites this paper
• Inductive matrix completion for predicting adverse drug reactions (ADRs) integrating drug–target interactions

  2015cites this paper