An interpretable machine learning framework for adverse drug reaction prediction from drug-target interactions

Aug 4, 2026

Upload by Aurelia

Adverse drug reactions (ADRs) challenge patient safety and healthcare systems, while mechanistic causes remain incompletely understood in current post-marketing pharmacovigilance. This study develops an interpretable machine learning framework that integrates drug-target interaction data with Yellow Card Scheme ADR reports. Disproportionality analysis derives significant ADR signals, then trains Random Forest classifiers across System Organ Class categories, using SMOTE and Tomek for imbalance and Bayesian optimisation for hyperparameters. Feature importance drives interpretability and is validated with DisGeNET and compared against SIDER, achieving ROC AUC up to 0.94.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages21

Reading Time53 min

AccessFree to download

Abstract

Background

Objective

Methods

Results

Conclusions

Introduction

University of Birmingham An interpretable machine learning framework for adverse drug reaction prediction from drug-target interactions Roberts-Nuttall, Joseph; Jones, Alan M. ; Castellani, Marco; Pham, Duc DOI: 10.1371/journal.pone.0340900 License: Creative Commons: Attribution (CC BY) Document Version Publisher's PDF, also known as Version of record Citation for published version (Harvard): Roberts-Nuttall, J, Jones, AM, Castellani, M & Pham, D 2026, 'An interpretable machine learning framework for adverse drug reaction prediction from drug-target interactions', PLOS ONE, vol. 21, no. 1, e0340900 . [https://doi.org/10.1371/journal.pone.0340900](https://doi.org/10.1371/journal.pone.0340900) Link to publication on Research at Birmingham portal General rights Unless a licence is specified above, all rights (including copyright and moral rights) in this document are retained by the authors and/or the copyright holders. The express permission of the copyright holder must be obtained for any use of this material other than for purposes permitted by law. •Users may freely distribute the URL that is used to identify this publication. •Users may download and/or print one copy of the publication from the University of Birmingham research portal for the purpose of private study or non-commercial research. •User may use extracts from the document in line with the concept of ‘fair dealing’ under the Copyright, Designs and Patents Act 1988 (?) •Users may not further distribute the material nor use it for the purposes of commercial gain. Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive. If you believe that this is the case for this document, [please contact UBIRA@lists.bham.ac.uk](please contact UBIRA@lists.bham.ac.uk) providing details and we will remove access to the work immediately and investigate. Download date: 26. Feb. 2026 OPEN ACCESS Citation: Roberts-Nuttall J, Jones AM, Castellani M, Pham D (2026) An interpretable machine learning framework for adverse drug reaction prediction from drug-target interactions. PLoS One 21(1): e0340900 . [https://doi.org/10.1371/journal.pone.0340900](https://doi.org/10.1371/journal.pone.0340900) Editor: Ali Awadallah Saeed, National University, SUDAN Received: September 3, 2025 Accepted: December 28, 2025 Published: January 30, 2026 Copyright: © 2026 Roberts-Nuttall et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data availability statement: All data and code used in this study are publicly available and on GitHub at: [https://github.com/Joeroberts1601/](https://github.com/Joeroberts1601/)[ ](https://github.com/Joeroberts1601/)[Random_Forest_ADR_Prediction](Random_Forest_ADR_Prediction All relevant)[ All relevant](Random_Forest_ADR_Prediction All relevant)[ ](Random_Forest_ADR_Prediction All relevant)data are within the paper and its Supporting Information files. RESEARCH ARTICLE An interpretable machine learning framework for adverse drug reaction prediction from drug-target interactions Joseph Roberts-Nuttall1*, Alan M. Jones2*, Marco Castellani1, Duc Pham1 1 School of Mechanical Engineering, University of Birmingham, Edgbaston, United Kingdom, 2 School of Pharmacy, University of Birmingham, Edgbaston, United Kingdom * [j](j.robertsnuttall@gmail.com)[.robertsnuttall@gmail.com](j.robertsnuttall@gmail.com) (JRN); [a.m.jones.2@bham.ac.uk](a.m.jones.2@bham.ac.uk) (AMJ) Abstract B

FAQs

What data sources are used to build the ADR prediction framework?

Drug-target interaction data come from STITCH, and ADR reports are collected from the Yellow Card Scheme (YCS).

How does the method handle class imbalance and tune model hyperparameters?

It addresses imbalance using SMOTE and Tomek, and uses Bayesian optimisation to refine Random Forest hyperparameters.

How is interpretability achieved and validated?

Feature importance scores provide interpretability, and top features are validated using known target-disease associations from DisGeNET and compared with SIDER to assess added value from real-world data.

Aug 4, 2026

Upload by Aurelia