A novel deep sequential learning architecture for drug drug interaction prediction using DDINet

Abstract Drug drug Interactions (DDI) present considerable challenges in healthcare, often resulting in adverse effects or decreased therapeutic efficacy. This article proposes a novel deep sequential learning architecture called DDINet to predict and classify DDIs between pairs of drugs based on di...

Full description

Saved in:
Bibliographic Details
Main Authors: Anindya Halder, Biswanath Saha, Moumita Roy, Sukanta Majumder
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-93952-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850054414166917120
author Anindya Halder
Biswanath Saha
Moumita Roy
Sukanta Majumder
author_facet Anindya Halder
Biswanath Saha
Moumita Roy
Sukanta Majumder
author_sort Anindya Halder
collection DOAJ
description Abstract Drug drug Interactions (DDI) present considerable challenges in healthcare, often resulting in adverse effects or decreased therapeutic efficacy. This article proposes a novel deep sequential learning architecture called DDINet to predict and classify DDIs between pairs of drugs based on different mechanisms viz., Excretion, Absorption, Metabolism, and Excretion rate (higher serum level) etc. Chemical features such as Hall Smart, Amino Acid count and Carbon types are extracted from each drug (pairs) to apply as an input to the proposed model. Proposed DDINet incorporates attention mechanism and deep sequential learning architectures, such as Long Short-Term Memory and gated recurrent unit. It utilizes the Rcpi toolkit to extract biochemical features of drugs from their chemical composition in Simplified Molecular-Input Line-Entry System format. Experiments are conducted on publicly available DDI datasets from DrugBank and Kaggle. The model’s efficacy in predicting and classifying DDIs is evaluated using various performance measures. The experimental results show that DDINet outperformed eight counterpart techniques achieving $$95.42\%$$ overall accuracy which is also statistically confirmed by Confidence Interval tests and paired t-tests. This architecture may act as an effective computational technique for drug drug interaction with respect to mechanism which may act as a complementary tool to reduce costly wet lab experiments for DDI prediction and classification.
format Article
id doaj-art-e27e153701694b2f9922cbe2741edff1
institution DOAJ
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e27e153701694b2f9922cbe2741edff12025-08-20T02:52:16ZengNature PortfolioScientific Reports2045-23222025-03-0115111510.1038/s41598-025-93952-zA novel deep sequential learning architecture for drug drug interaction prediction using DDINetAnindya Halder0Biswanath Saha1Moumita Roy2Sukanta Majumder3Department of Computer Application, School of Technology, North-Eastern Hill University, Tura CampusDepartment of Computer Application, School of Technology, North-Eastern Hill University, Tura CampusDepartment of Computer Science and Engineering, University of KalyaniDepartment of Computer Science and Engineering, University of KalyaniAbstract Drug drug Interactions (DDI) present considerable challenges in healthcare, often resulting in adverse effects or decreased therapeutic efficacy. This article proposes a novel deep sequential learning architecture called DDINet to predict and classify DDIs between pairs of drugs based on different mechanisms viz., Excretion, Absorption, Metabolism, and Excretion rate (higher serum level) etc. Chemical features such as Hall Smart, Amino Acid count and Carbon types are extracted from each drug (pairs) to apply as an input to the proposed model. Proposed DDINet incorporates attention mechanism and deep sequential learning architectures, such as Long Short-Term Memory and gated recurrent unit. It utilizes the Rcpi toolkit to extract biochemical features of drugs from their chemical composition in Simplified Molecular-Input Line-Entry System format. Experiments are conducted on publicly available DDI datasets from DrugBank and Kaggle. The model’s efficacy in predicting and classifying DDIs is evaluated using various performance measures. The experimental results show that DDINet outperformed eight counterpart techniques achieving $$95.42\%$$ overall accuracy which is also statistically confirmed by Confidence Interval tests and paired t-tests. This architecture may act as an effective computational technique for drug drug interaction with respect to mechanism which may act as a complementary tool to reduce costly wet lab experiments for DDI prediction and classification.https://doi.org/10.1038/s41598-025-93952-zDrug drug interactionDeep learningAttention mechanismRecurrent neural networkGated recurrent unit
spellingShingle Anindya Halder
Biswanath Saha
Moumita Roy
Sukanta Majumder
A novel deep sequential learning architecture for drug drug interaction prediction using DDINet
Scientific Reports
Drug drug interaction
Deep learning
Attention mechanism
Recurrent neural network
Gated recurrent unit
title A novel deep sequential learning architecture for drug drug interaction prediction using DDINet
title_full A novel deep sequential learning architecture for drug drug interaction prediction using DDINet
title_fullStr A novel deep sequential learning architecture for drug drug interaction prediction using DDINet
title_full_unstemmed A novel deep sequential learning architecture for drug drug interaction prediction using DDINet
title_short A novel deep sequential learning architecture for drug drug interaction prediction using DDINet
title_sort novel deep sequential learning architecture for drug drug interaction prediction using ddinet
topic Drug drug interaction
Deep learning
Attention mechanism
Recurrent neural network
Gated recurrent unit
url https://doi.org/10.1038/s41598-025-93952-z
work_keys_str_mv AT anindyahalder anoveldeepsequentiallearningarchitecturefordrugdruginteractionpredictionusingddinet
AT biswanathsaha anoveldeepsequentiallearningarchitecturefordrugdruginteractionpredictionusingddinet
AT moumitaroy anoveldeepsequentiallearningarchitecturefordrugdruginteractionpredictionusingddinet
AT sukantamajumder anoveldeepsequentiallearningarchitecturefordrugdruginteractionpredictionusingddinet
AT anindyahalder noveldeepsequentiallearningarchitecturefordrugdruginteractionpredictionusingddinet
AT biswanathsaha noveldeepsequentiallearningarchitecturefordrugdruginteractionpredictionusingddinet
AT moumitaroy noveldeepsequentiallearningarchitecturefordrugdruginteractionpredictionusingddinet
AT sukantamajumder noveldeepsequentiallearningarchitecturefordrugdruginteractionpredictionusingddinet