Abstract

BackgroundPredicting drug side effects is an important topic in the drug discovery. Although several machine learning methods have been proposed to predict side effects, there is still space for improvements. Firstly, the side effect prediction is a multi-label learning task, and we can adopt the multi-label learning techniques for it. Secondly, drug-related features are associated with side effects, and feature dimensions have specific biological meanings. Recognizing critical dimensions and reducing irrelevant dimensions may help to reveal the causes of side effects.MethodsIn this paper, we propose a novel method ‘feature selection-based multi-label k-nearest neighbor method’ (FS-MLKNN), which can simultaneously determine critical feature dimensions and construct high-accuracy multi-label prediction models.ResultsComputational experiments demonstrate that FS-MLKNN leads to good performances as well as explainable results. To achieve better performances, we further develop the ensemble learning model by integrating individual feature-based FS-MLKNN models. When compared with other state-of-the-art methods, the ensemble method produces better performances on benchmark datasets.ConclusionsIn conclusion, FS-MLKNN and the ensemble method are promising tools for the side effect prediction. The source code and datasets are available in the Additional file 1.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-015-0774-y) contains supplementary material, which is available to authorized users.

Highlights

  • Predicting drug side effects is an important topic in the drug discovery

  • Machine learning methods were applied to the drug side effect prediction, because of their capability of dealing with complicated data

  • We propose a novel method named ‘feature selection-based multi-label k-nearest neighbor method’ (FS-multi-label k-nearest neighbor’ (MLKNN)) for the side effect prediction

Read more

Summary

Introduction

Predicting drug side effects is an important topic in the drug discovery. Several machine learning methods have been proposed to predict side effects, there is still space for improvements. Recognizing critical dimensions and reducing irrelevant dimensions may help to reveal the causes of side effects. Drugs can help to treat diseases, but usually come with side effects or adverse reactions. Recognizing potential side effects helps to reduce costs and avoid risks in the drug discovery. Since researchers collected drug data and compile them in the public databases, computational methods were developed for the side effect prediction. Machine learning methods were applied to the drug side effect prediction, because of their capability of dealing with complicated data. Huang [6] combined drug targets, Zhang et al BMC Bioinformatics (2015) 16:365 inference-based method. Liu [14] determined molecular predictors of adverse drug reactions with causality analysis

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call