Identification of Drug–Side-Effect Association via Multiview Semisupervised Sparse Model | IEEE Journals & Magazine | IEEE Xplore

Identification of Drug–Side-Effect Association via Multiview Semisupervised Sparse Model


Impact Statement:Drugs serve as a critical tool in combating human diseases, and numerous unreleased drugs possess the potential for accompanying side effects. Consequently, the identific...Show More

Abstract:

The association between drugs and side effects encompasses information about approved medications and their documented adverse drug reactions. Traditional experimental ap...Show More
Impact Statement:
Drugs serve as a critical tool in combating human diseases, and numerous unreleased drugs possess the potential for accompanying side effects. Consequently, the identification of drug side effects has remained a focal point of research. However, previous investigations have tended to overlook the varying significance associated with distinct prior data, resulting in the adoption of inadequate data fusion techniques. To address this gap, we present an innovative approach for predicting drug side effects. Our method employs a multi-view semi-supervised sparse model, which proficiently integrates diverse prior data sources. Through rigorous evaluations conducted on three benchmark datasets, our approach consistently outperformed the most formidable methods by significant margins of 2.8%, 2.2%, and 2.4%, respectively.

Abstract:

The association between drugs and side effects encompasses information about approved medications and their documented adverse drug reactions. Traditional experimental approaches for studying this association tend to be time consuming and expensive. To represent all drug–side-effect associations, a bipartite network framework is employed. Consequently, numerous computational methods have been devised to tackle this problem, focusing on predicting new potential associations. However, a significant gap lies in the neglect of the multiview learning algorithm, which has the ability to integrate diverse information sources and enhance prediction accuracy. In our study, we have developed a novel predictor named multiview semisupervised sparse model (Mv3SM) to address the drug side effect prediction problem. Our approach aims to explore the distinctive characteristics of various view features obtained from fully paired multiview data and mitigate the influence of noisy data. To test the perfo...
Published in: IEEE Transactions on Artificial Intelligence ( Volume: 5, Issue: 5, May 2024)
Page(s): 2151 - 2162
Date of Publication: 12 September 2023
Electronic ISSN: 2691-4581

Funding Agency:


References

References is not available for this document.