Identify drug-drug interactions via deep learning: A real world study

Identifying drug-drug interactions (DDIs) is essential to prevent adverse effects from polypharmacy. Although deep learning has advanced DDI identification, the gap between powerful models and their lack of clinical application and evaluation has hindered clinical benefits. Here, we developed a Mult...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingyang Li, Yanpeng Zhao, Zhenting Wang, Chunyue Lei, Lianlian Wu, Yixin Zhang, Song He, Xiaochen Bo, Jian Xiao
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Journal of Pharmaceutical Analysis
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2095177925000115
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849318362896662528
author Jingyang Li
Yanpeng Zhao
Zhenting Wang
Chunyue Lei
Lianlian Wu
Yixin Zhang
Song He
Xiaochen Bo
Jian Xiao
author_facet Jingyang Li
Yanpeng Zhao
Zhenting Wang
Chunyue Lei
Lianlian Wu
Yixin Zhang
Song He
Xiaochen Bo
Jian Xiao
author_sort Jingyang Li
collection DOAJ
description Identifying drug-drug interactions (DDIs) is essential to prevent adverse effects from polypharmacy. Although deep learning has advanced DDI identification, the gap between powerful models and their lack of clinical application and evaluation has hindered clinical benefits. Here, we developed a Multi-Dimensional Feature Fusion model named MDFF, which integrates one-dimensional simplified molecular input line entry system sequence features, two-dimensional molecular graph features, and three-dimensional geometric features to enhance drug representations for predicting DDIs. MDFF was trained and validated on two DDI datasets, evaluated across three distinct scenarios, and compared with advanced DDI prediction models using accuracy, precision, recall, area under the curve, and F1 score metrics. MDFF achieved state-of-the-art performance across all metrics. Ablation experiments showed that integrating multi-dimensional drug features yielded the best results. More importantly, we obtained adverse drug reaction reports uploaded by Xiangya Hospital of Central South University from 2021 to 2023 and used MDFF to identify potential adverse DDIs. Among 12 real-world adverse drug reaction reports, the predictions of 9 reports were supported by relevant evidence. Additionally, MDFF demonstrated the ability to explain adverse DDI mechanisms, providing insights into the mechanisms behind one specific report and highlighting its potential to assist practitioners in improving medical practice.
format Article
id doaj-art-e02d272a3e7346688d5085e96d0b482f
institution Kabale University
issn 2095-1779
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Journal of Pharmaceutical Analysis
spelling doaj-art-e02d272a3e7346688d5085e96d0b482f2025-08-20T03:50:50ZengElsevierJournal of Pharmaceutical Analysis2095-17792025-06-0115610119410.1016/j.jpha.2025.101194Identify drug-drug interactions via deep learning: A real world studyJingyang Li0Yanpeng Zhao1Zhenting Wang2Chunyue Lei3Lianlian Wu4Yixin Zhang5Song He6Xiaochen Bo7Jian Xiao8Department of Pharmacy, Xiangya Hospital, Central South University, Changsha, 410008, ChinaAcademy of Military Medical Sciences, Beijing, 100850, ChinaDepartment of Pharmacy, People's Hospital of Qingshen, Meishan, Sichuan, 620460, ChinaNorth China University of Technology, No. 5 Jinyuonzhuang Rood, Shijingshan District, Beijing, 100144, ChinaAcademy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, 300072, ChinaAcademy of Military Medical Sciences, Beijing, 100850, ChinaAcademy of Military Medical Sciences, Beijing, 100850, China; Corresponding author.Academy of Military Medical Sciences, Beijing, 100850, China; Corresponding author.Department of Pharmacy, Xiangya Hospital, Central South University, Changsha, 410008, China; Institute for Rational and Safe Medication Practices, National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha, 410008, China; Corresponding author. Department of Pharmacy, Xiangya Hospital, Central South University, Changsha, 410008, China.Identifying drug-drug interactions (DDIs) is essential to prevent adverse effects from polypharmacy. Although deep learning has advanced DDI identification, the gap between powerful models and their lack of clinical application and evaluation has hindered clinical benefits. Here, we developed a Multi-Dimensional Feature Fusion model named MDFF, which integrates one-dimensional simplified molecular input line entry system sequence features, two-dimensional molecular graph features, and three-dimensional geometric features to enhance drug representations for predicting DDIs. MDFF was trained and validated on two DDI datasets, evaluated across three distinct scenarios, and compared with advanced DDI prediction models using accuracy, precision, recall, area under the curve, and F1 score metrics. MDFF achieved state-of-the-art performance across all metrics. Ablation experiments showed that integrating multi-dimensional drug features yielded the best results. More importantly, we obtained adverse drug reaction reports uploaded by Xiangya Hospital of Central South University from 2021 to 2023 and used MDFF to identify potential adverse DDIs. Among 12 real-world adverse drug reaction reports, the predictions of 9 reports were supported by relevant evidence. Additionally, MDFF demonstrated the ability to explain adverse DDI mechanisms, providing insights into the mechanisms behind one specific report and highlighting its potential to assist practitioners in improving medical practice.http://www.sciencedirect.com/science/article/pii/S2095177925000115Drug-drug interactionsDeep learningHealth careMulti-dimensional feature fusion
spellingShingle Jingyang Li
Yanpeng Zhao
Zhenting Wang
Chunyue Lei
Lianlian Wu
Yixin Zhang
Song He
Xiaochen Bo
Jian Xiao
Identify drug-drug interactions via deep learning: A real world study
Journal of Pharmaceutical Analysis
Drug-drug interactions
Deep learning
Health care
Multi-dimensional feature fusion
title Identify drug-drug interactions via deep learning: A real world study
title_full Identify drug-drug interactions via deep learning: A real world study
title_fullStr Identify drug-drug interactions via deep learning: A real world study
title_full_unstemmed Identify drug-drug interactions via deep learning: A real world study
title_short Identify drug-drug interactions via deep learning: A real world study
title_sort identify drug drug interactions via deep learning a real world study
topic Drug-drug interactions
Deep learning
Health care
Multi-dimensional feature fusion
url http://www.sciencedirect.com/science/article/pii/S2095177925000115
work_keys_str_mv AT jingyangli identifydrugdruginteractionsviadeeplearningarealworldstudy
AT yanpengzhao identifydrugdruginteractionsviadeeplearningarealworldstudy
AT zhentingwang identifydrugdruginteractionsviadeeplearningarealworldstudy
AT chunyuelei identifydrugdruginteractionsviadeeplearningarealworldstudy
AT lianlianwu identifydrugdruginteractionsviadeeplearningarealworldstudy
AT yixinzhang identifydrugdruginteractionsviadeeplearningarealworldstudy
AT songhe identifydrugdruginteractionsviadeeplearningarealworldstudy
AT xiaochenbo identifydrugdruginteractionsviadeeplearningarealworldstudy
AT jianxiao identifydrugdruginteractionsviadeeplearningarealworldstudy