Prediction Of Drug-drug Interactions Research Articles

Enhancing Knowledge Graph Embedding with Hierarchical Self-Attention and Graph Neural Network Techniques for Drug-Drug Interaction Prediction in Virtual Reality Environments

In biomedicine, the critical task is to decode Drug–Drug Interactions (DDIs) from complex biomedical texts. The scientific community employs Knowledge Graph Embedding (KGE) methods, enhanced with advanced neural network technologies, including capsule networks. However, existing methodologies primarily focus on the structural details of individual entities or relations within Biomedical Knowledge Graphs (BioKGs), overlooking the overall structural context of BioKGs, molecular structures, positional features of drug pairs, and their critical Relational Mapping Properties. To tackle the challenges identified, this study presents HSTrHouse an innovative hierarchical self-attention BioKGs embedding framework. This architecture integrates self-attention mechanisms with advanced neural network technologies, including Convolutional Neural Network (CNN) and Graph Neural Network (GNN), for enhanced computational modeling in biomedical contexts. The model bifurcates the BioKGs into entity and relation layers for structural analysis. It employs self-attention across these layers, utilizing PubMedBERT and CNN for position feature extraction, and a GNN for drug pair molecular structure analysis. Then, we connect the position and molecular structure features to integrate them into the self-attention calculation of entity and relation. After that, the output of the self-attention layer is combined with the connected vectors of the position feature and molecular structure feature to obtain the final representation vector, and finally, to model the Relational Mapping Properties (RMPs), the representation vector is embedded into the complex vector space using Householder projections to obtain the BioKGs model. The paper validates HSTrHouse’s efficacy by comparing it with advanced models on three standard BioKGs for DDIs research.

DeepARV: ensemble deep learning to predict drug-drug interaction of clinical relevance with antiretroviral therapy

Drug-drug interaction (DDI) may result in clinical toxicity or treatment failure of antiretroviral therapy (ARV) or comedications. Despite the high number of possible drug combinations, only a limited number of clinical DDI studies are conducted. Computational prediction of DDIs could provide key evidence for the rational management of complex therapies. Our study aimed to assess the potential of deep learning approaches to predict DDIs of clinical relevance between ARVs and comedications. DDI severity grading between 30,142 drug pairs was extracted from the Liverpool HIV Drug Interaction database. Two feature construction techniques were employed: 1) drug similarity profiles by comparing Morgan fingerprints, and 2) embeddings from SMILES of each drug via ChemBERTa, a transformer-based model. We developed DeepARV-Sim and DeepARV-ChemBERTa to predict four categories of DDI: i) Red: drugs should not be co-administered, ii) Amber: interaction of potential clinical relevance manageable by monitoring/dose adjustment, iii) Yellow: interaction of weak relevance and iv) Green: no expected interaction. The imbalance in the distribution of DDI severity grades was addressed by undersampling and applying ensemble learning. DeepARV-Sim and DeepARV-ChemBERTa predicted clinically relevant DDI between ARVs and comedications with a weighted mean balanced accuracy of 0.729 ± 0.012 and 0.776 ± 0.011, respectively. DeepARV-Sim and DeepARV-ChemBERTa have the potential to leverage molecular structures associated with DDI risks and reduce DDI class imbalance, effectively increasing the predictive ability on clinically relevant DDIs. This approach could be developed for identifying high-risk pairing of drugs, enhancing the screening process, and targeting DDIs to study in clinical drug development.

Development of a physiologically based pharmacokinetic model of fostemsavir and its pivotal application to support dosing in pregnancy.

It is critical to understand the impact of significant physiological changes during pregnancy on the extent of maternal and fetal drug exposure. Fostemsavir (FTR) is a prodrug of temsavir (TMR) and is approved in combination with other antiretrovirals for multi-drug-resistant human immunodeficiency virus (HIV) infections. This physiologically based pharmacokinetic model (PBPK) study was used to estimate TMR PK in pregnant populations during each trimester of pregnancy to inform FTR dosing. A PBPK model was developed and validated for TMR using PK data collected following intravenous TMR and oral FTR dosing (immediate-release and extended-release tablets) in healthy volunteers. Predicted TMR concentration-time profiles accurately predicted the reported clinical data and variability in healthy (dense data) and pregnant (sparse data) populations. Predicted versus observed TMR geometric mean (CV%) clearance following intravenous administration was 18.01 (29) versus 17 (21) (L/h). Predicted versus observed TMR AUC0-inf (ng.h/mL) in healthy volunteers following FTR administration of the extended-release tablet were 9542 (66) versus 7339 (33). The validated TMR PBPK model was then applied to predict TMR PK in a population of pregnant individuals during each trimester. Simulations showed TMR AUC in pregnant individuals receiving FTR 600 mg twice daily was decreased by 25% and 38% in the second and third trimesters, respectively. However, TMR exposure remained within the range observed in nonpregnant adults with no need for dose adjustment. The current PBPK model can also be applied for the prediction of local tissue concentrations and drug-drug interactions in pregnancy.

DRGATAN: Directed relation graph attention aware network for asymmetric drug-drug interaction prediction

DRGATAN: Directed relation graph attention aware network for asymmetric drug-drug interaction prediction

SubGE-DDI: A new prediction model for drug-drug interaction established through biomedical texts and drug-pairs knowledge subgraph enhancement.

Biomedical texts provide important data for investigating drug-drug interactions (DDIs) in the field of pharmacovigilance. Although researchers have attempted to investigate DDIs from biomedical texts and predict unknown DDIs, the lack of accurate manual annotations significantly hinders the performance of machine learning algorithms. In this study, a new DDI prediction framework, Subgraph Enhance model, was developed for DDI (SubGE-DDI) to improve the performance of machine learning algorithms. This model uses drug pairs knowledge subgraph information to achieve large-scale plain text prediction without many annotations. This model treats DDI prediction as a multi-class classification problem and predicts the specific DDI type for each drug pair (e.g. Mechanism, Effect, Advise, Interact and Negative). The drug pairs knowledge subgraph was derived from a huge drug knowledge graph containing various public datasets, such as DrugBank, TwoSIDES, OffSIDES, DrugCentral, EntrezeGene, SMPDB (The Small Molecule Pathway Database), CTD (The Comparative Toxicogenomics Database) and SIDER. The SubGE-DDI was evaluated from the public dataset (SemEval-2013 Task 9 dataset) and then compared with other state-of-the-art baselines. SubGE-DDI achieves 83.91% micro F1 score and 84.75% macro F1 score in the test dataset, outperforming the other state-of-the-art baselines. These findings show that the proposed drug pairs knowledge subgraph-assisted model can effectively improve the prediction performance of DDIs from biomedical texts.

Comparison of Commonly Used and New Methods to Determine Small Molecule Non-Specific Binding to Human Liver Microsomes

Accurate measurement of non-specific binding of a drug candidate to human liver microsomes (HLM) can be critical for the accurate determination of key enzyme kinetic parameters such as Michaelis-Menton (Km), reversible inhibition (Ki), or inactivation (KI) constants. Several methods have been developed to determine non-specific binding of small molecules to HLM, such as rapid equilibrium dialysis (RED), ultrafiltration (UF), HLM bound to magnetizable beads (HLM-beads), ultracentrifugation (UC), the linear extrapolation stability assay (LESA), and the Transil™ system. Despite various differences in methodology between these methods, it is generally presumed that similar free fraction values (fu,mic) should be generated. To evaluate this hypothesis, a test set of 9 compounds were selected, representing low (high fu,mic value) and significant (low fu,mic value) HLM binding, respectively, across HLM concentrations tested in this manuscript. The fu,mic values were determined using a single compound concentration (1.0 µM) and three HLM concentrations (0.025, 0.50, and 1.0 mg/mL). When the HLM non-specific binding event is not extensive resulting in high fu,mic values, all methods generated similar fu,mic values. However, fu,mic values varied markedly across assay formats when high binding to HLM occurred, where fu,mic values differed by up to 33-fold depending on the method used. Potential causes for such discrepancies across the various methods employed, practical implications related to conduct the different assays, and implications to clinical drug-drug interaction (DDI) predictions are discussed.

Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning

BackgroundDiscovering potential drug-drug interactions (DDIs) is a long-standing challenge in clinical treatments and drug developments. Recently, deep learning techniques have been developed for DDI prediction. However, they generally require a huge number of samples, while known DDIs are rare.MethodsIn this work, we present KnowDDI, a graph neural network-based method that addresses the above challenge. KnowDDI enhances drug representations by adaptively leveraging rich neighborhood information from large biomedical knowledge graphs. Then, it learns a knowledge subgraph for each drug-pair to interpret the predicted DDI, where each of the edges is associated with a connection strength indicating the importance of a known DDI or resembling strength between a drug-pair whose connection is unknown. Thus, the lack of DDIs is implicitly compensated by the enriched drug representations and propagated drug similarities.ResultsHere we show the evaluation results of KnowDDI on two benchmark DDI datasets. Results show that KnowDDI obtains the state-of-the-art prediction performance with better interpretability. We also find that KnowDDI suffers less than existing works given a sparser knowledge graph. This indicates that the propagated drug similarities play a more important role in compensating for the lack of DDIs when the drug representations are less enriched.ConclusionsKnowDDI nicely combines the efficiency of deep learning techniques and the rich prior knowledge in biomedical knowledge graphs. As an original open-source tool, KnowDDI can help detect possible interactions in a broad range of relevant interaction prediction tasks, such as protein-protein interactions, drug-target interactions and disease-gene interactions, eventually promoting the development of biomedicine and healthcare.

Dual-Channel Learning Framework for Drug-Drug Interaction Prediction via Relation-Aware Heterogeneous Graph Transformer

Identifying novel drug-drug interactions (DDIs) is a crucial task in pharmacology, as the interference between pharmacological substances can pose serious medical risks. In recent years, several network-based techniques have emerged for predicting DDIs. However, they primarily focus on local structures within DDI-related networks, often overlooking the significance of indirect connections between pairwise drug nodes from a global perspective. Additionally, effectively handling heterogeneous information present in both biomedical knowledge graphs and drug molecular graphs remains a challenge for improved performance of DDI prediction. To address these limitations, we propose a Transformer-based relatIon-aware Graph rEpresentation leaRning framework (TIGER) for DDI prediction. TIGER leverages the Transformer architecture to effectively exploit the structure of heterogeneous graph, which allows it direct learning of long dependencies and high-order structures. Furthermore, TIGER incorporates a relation-aware self-attention mechanism, capturing a diverse range of semantic relations that exist between pairs of nodes in heterogeneous graph. In addition to these advancements, TIGER enhances predictive accuracy by modeling DDI prediction task using a dual-channel network, where drug molecular graph and biomedical knowledge graph are fed into two respective channels. By incorporating embeddings obtained at graph and node levels, TIGER can benefit from structural properties of drugs as well as rich contextual information provided by biomedical knowledge graph. Extensive experiments conducted on three real-world datasets demonstrate the effectiveness of TIGER in DDI prediction. Furthermore, case studies highlight its ability to provide a deeper understanding of underlying mechanisms of DDIs.

MKG-FENN: A Multimodal Knowledge Graph Fused End-to-End Neural Network for Accurate Drug–Drug Interaction Prediction

Taking incompatible multiple drugs together may cause adverse interactions and side effects on the body. Accurate prediction of drug-drug interaction (DDI) events is essential for avoiding this issue. Recently, various artificial intelligence-based approaches have been proposed for predicting DDI events. However, DDI events are associated with complex relationships and mechanisms among drugs, targets, enzymes, transporters, molecular structures, etc. Existing approaches either partially or loosely consider these relationships and mechanisms by a non-end-to-end learning framework, resulting in sub-optimal feature extractions and fusions for prediction. Different from them, this paper proposes a Multimodal Knowledge Graph Fused End-to-end Neural Network (MKGFENN) that consists of two main parts: multimodal knowledge graph (MKG) and fused end-to-end neural network (FENN). First, MKG is constructed by comprehensively exploiting DDI events-associated relationships and mechanisms from four knowledge graphs of drugs-chemical entities, drug-substructures, drugs-drugs, and molecular structures. Correspondingly, a four channels graph neural network is designed to extract high-order and semantic features from MKG. Second, FENN designs a multi-layer perceptron to fuse the extracted features by end-to-end learning. With such designs, the feature extractions and fusions of DDI events are guaranteed to be comprehensive and optimal for prediction. Through extensive experiments on real drug datasets, we demonstrate that MKG-FENN exhibits high accuracy and significantly outperforms state-of-the-art models in predicting DDI events. The source code and supplementary file of this article are available on: https://github.com/wudi1989/MKG-FENN.

Role of Artificial Intelligence in Drug Discovery to Revolutionize the Pharmaceutical Industry: Resources, Methods and Applications

Abstract: Traditional drug discovery methods such as wet-lab testing, validations, and synthetic techniques are time-consuming and expensive. Artificial Intelligence (AI) approaches have progressed to the point where they can have a significant impact on the drug discovery process. Using massive volumes of open data, artificial intelligence methods are revolutionizing the pharmaceutical industry. In the last few decades, many AI-based models have been developed and implemented in many areas of the drug development process. These models have been used as a supplement to conventional research to uncover superior pharmaceuticals expeditiously. Drug research and development to repurposing and productivity benefits in the pharmaceutical business through clinical trials. AI is studied in this article for its numerous potential uses. We have discussed how AI can be put to use in the pharmaceutical sector, specifically for predicting a drug's toxicity, bioactivity, and physicochemical characteristics, among other things. In this review article, we have discussed its application to a variety of problems, including de novo drug discovery, target structure prediction, interaction prediction, and binding affinity prediction. AI for predicting drug interactions and nanomedicines were also considered.

A physiologically-based pharmacokinetic/pharmacodynamic modeling approach for drug-drug-gene interaction evaluation of S-warfarin with fluconazole.

Warfarin is a widely used anticoagulant, and its S-enantiomer has higher potency compared to the R-enantiomer. S-warfarin is mainly metabolized by cytochrome P450 (CYP) 2C9, and its pharmacological target is vitamin K epoxide reductase complex subunit 1 (VKORC1). Both CYP2C9 and VKORC1 have genetic polymorphisms, leading to large variations in the pharmacokinetics (PKs) and pharmacodynamics (PDs) of warfarin in the population. This makes dosage management of warfarin difficult, especially in the case of drug-drug interactions (DDIs). This study provides a whole-body physiologically-based pharmacokinetic/PD (PBPK/PD) model of S-warfarin for predicting the effects of drug-drug-gene interactions on S-warfarin PKs and PDs. The PBPK/PD model of S-warfarin was developed in PK-Sim and MoBi. Drug-dependent parameters were obtained from the literature or optimized. Of the 34 S-warfarin plasma concentration-time profiles used, 96% predicted plasma concentrations within twofold range compared to observed data. For S-warfarin plasma concentration-time profiles with CYP2C9 genotype, 364 of 386 predicted plasma concentration values (~94%) fell within the twofold of the observed values. This model was tested in DDI predictions with fluconazole as CYP2C9 perpetrators, with all predicted DDI area under the plasma concentration-time curve to the last measurable timepoint (AUClast ) ratio within twofold of the observed values. The anticoagulant effect of S-warfarin was described using an indirect response model, with all predicted international normalized ratio (INR) within twofold of the observed values. This model also incorporates a dose-adjustment method that can be used for dose adjustment and predict INR when warfarin is used in combination with CYP2C9 perpetrators.

Physiologically based pharmacokinetic modeling of imatinib and N-desmethyl imatinib for drug-drug interaction predictions.

The first-generation tyrosine kinase inhibitor imatinib has revolutionized the development of targeted cancer therapy and remains among the frontline treatments, for example, against chronic myeloid leukemia. As a substrate of cytochrome P450 (CYP) 2C8, CYP3A4, and various transporters, imatinib is highly susceptible to drug-drug interactions (DDIs) when co-administered with corresponding perpetrator drugs. Additionally, imatinib and its main metabolite N-desmethyl imatinib (NDMI) act as inhibitors of CYP2C8, CYP2D6, and CYP3A4 affecting their own metabolism as well as the exposure of co-medications. This work presents the development of a parent-metabolite whole-body physiologically based pharmacokinetic (PBPK) model for imatinib and NDMI used for the investigation and prediction of different DDI scenarios centered around imatinib as both a victim and perpetrator drug. Model development was performed in PK-Sim® using a total of 60 plasma concentration-time profiles of imatinib and NDMI in healthy subjects and cancer patients. Metabolism of both compounds was integrated via CYP2C8 and CYP3A4, with imatinib additionally transported via P-glycoprotein. The subsequently developed DDI network demonstrated good predictive performance. DDIs involving imatinib and NDMI were simulated with perpetrator drugs rifampicin, ketoconazole, and gemfibrozil as well as victim drugs simvastatin and metoprolol. Overall, 12/12 predicted DDI area under the curve determined between first and last plasma concentration measurements (AUClast ) ratios and 12/12 predicted DDI maximum plasma concentration (Cmax ) ratios were within twofold of the respective observed ratios. Potential applications of the final model include model-informed drug development or the support of model-informed precision dosing.

Attention-Based Learning for Predicting Drug-Drug Interactions in Knowledge Graph Embedding Based on Multisource Fusion Information

Drug combinations can reduce drug resistance and side effects and enable the improvement of disease treatment efficacy. Therefore, how to effectively identify drug-drug interactions (DDIs) is a challenging problem. Currently, there exist several approaches that leverage advanced representation learning and graph-based techniques for DDIs prediction. While these methods have demonstrated promising results, a limited number of approaches effectively utilize the potential of knowledge graphs (KGs), which provide information on drug attributes and multirelation among entities. In this work, we introduce a novel attention-based KGs representation learning framework. To encode drug SMILES sequence, a pretrained model is used, while molecular structure information is mapped as the initialization of nodes within the KG using a message-passing neural network. Additionally, the knowledge-aware graph attention network is employed to capture the drug and its topological neighbor representation in the KG representation module. To prevent the oversmoothing problem, the residual layer is used in the DDI prediction module. Comprehensive experiments on several datasets have demonstrated that the proposed method outperforms the state-of-the-art algorithms on the DDI prediction task across a range of evaluation metrics. It achieves an accuracy of 0.924 and an AUC of 0.9705 on the KEGG dataset and attains an ACC of 0.9777 and an AUC of 0.9959 on the OGB-biokg dataset. These experimental findings affirm that our approach is a dependable model for predicting the association of drugs.

AutoDDI: Drug-Drug Interaction Prediction With Automated Graph Neural Network.

Drug-drug interaction (DDI) has attracted widespread attention because when incompatible drugs are taken together, DDI will lead to adverse effects on the body, such as drug poisoning or reduced drug efficacy. The adverse effects of DDI are closely determined by the molecular structures of the drugs involved. To represent drug data effectively, researchers usually treat the molecular structure of drugs as a molecule graph. Then, previous studies can use the handcrafted graph neural network (GNN) model to learn the molecular graph representations of drugs for DDI prediction. However, in the field of bioinformatics, manually designing GNN architectures for specific molecular structure datasets is time-consuming and depends on expert experience. To address this problem, we propose an automatic drug-drug interaction prediction method named AutoDDI that can efficiently and automatically design the GNN architecture for drug-drug interaction prediction without manual intervention. To this end, we first design an effective search space for drug-drug interaction prediction by revisiting various handcrafted GNN architectures. Then, to efficiently and automatically design the optimal GNN architecture for each drug dataset from the search space, a reinforcement learning search algorithm is adopted. The experiment results show that AutoDDI can achieve the best performance on two real-world datasets. Moreover, the visual interpretation results of the case study show that AutoDDI can effectively capture drug substructure for drug-drug interaction prediction.

Quantitative prediction of CYP3A induction-mediated drug-drug interactions in clinical practice

There have been no reports on the quantitative prediction of CYP3A induction-mediated decreases in AUC and Cmax for drug candidates identified as a “victims” of CYP3A induction. Our previous study separately evaluated the fold-induction of hepatic and intestinal CYP3A by known inducers using clinical induction data and revealed that we were able to quantitatively predict the AUC ratio (AUCR) of a few CYP3A substrates in the presence and absence of CYP3A inducers. In the present study, we investigate the predictability of AUCR and also Cmax ratio (CmaxR) in additional 54 clinical studies. The fraction metabolized by CYP3A (fm), the intestinal bioavailability (Fg), and the hepatic intrinsic clearance (CLint) of substrates were determined by the in vitro experiments as well as clinical data used for calculating AUCR and CmaxR. The result showed that 65–69% and 65–67% of predictions were within 2-fold of observed AUCR and CmaxR, respectively. A simulation using multiple parameter combinations suggested that the variability of fm and Fg within a certain range might have a minimal impact on the calculation output. These findings suggest that clinical AUCR and CmaxR of CYP3A substrates can be quantitatively predicted from the preclinical stage.

Artificial intelligence-driven drug interaction prediction

Artificial intelligence (AI) is developing at a rapid pace and this has led to revolutionary changes in many fields, including healthcare. Drug interaction prediction, which evaluates possible interactions between various medications to guarantee patient safety and maximize therapeutic outcomes is a crucial component of healthcare. This work investigates the use of artificial intelligence (AI) methods for predicting drug interactions, with a particular emphasis on the combination of natural language processing, knowledge graphs, and machine learning algorithms. The manual curation and experimental research that are frequently used in traditional drug interaction prediction methods limit their scalability and real-time applicability. On the other hand, artificial intelligence (AI) methods use molecular data, electronic health records, and large-scale healthcare data to improve the precision and effectiveness of drug interaction prediction. Deep neural networks and ensemble approaches are two examples of machine learning models that are essential for evaluating various datasets and spotting complex patterns related to drug interactions.

Prediction of multiple types of drug interactions based on multi-scale fusion and dual-view fusion.

Potential drug-drug interactions (DDI) can lead to adverse drug reactions (ADR), and DDI prediction can help pharmacy researchers detect harmful DDI early. However, existing DDI prediction methods fall short in fully capturing drug information. They typically employ a single-view input, focusing solely on drug features or drug networks. Moreover, they rely exclusively on the final model layer for predictions, overlooking the nuanced information present across various network layers. To address these limitations, we propose a multi-scale dual-view fusion (MSDF) method for DDI prediction. More specifically, MSDF first constructs two views, topological and feature views of drugs, as model inputs. Then a graph convolutional neural network is used to extract the feature representations from each view. On top of that, a multi-scale fusion module integrates information across different graph convolutional layers to create comprehensive drug embeddings. The embeddings from the two views are summed as the final representation for classification. Experiments on two real-world datasets demonstrate that MSDF achieves higher accuracy than state-of-the-art methods, as the dual-view, multi-scale approach better captures drug characteristics.

Critical role of growth medium for detecting drug interactions in Gram-negative bacteria that model in vivo responses.

Drug-resistant bacterial infections are a growing concern and have only continued to increase during the SARS-CoV-2 pandemic. Though not routinely used for Gram-negative bacteria, drug combinations are sometimes used for serious infections and may become more widely used as the prevalence of extremely drug-resistant organisms increases. To date, reliable methods are not available for identifying beneficial drug combinations for a particular infection. Our study shows variability across strains in how drug interactions are impacted by growth conditions. It also demonstrates that testing drug combinations in tissue-relevant growth conditions for some strains better models what happens during infection and may better inform combination therapy selection.

Physiologically Based Pharmacokinetic (PBPK) Modeling to Predict CYP3A-Mediated Drug Interaction between Saxagliptin and Nicardipine: Bridging Rat-to-Human Extrapolation.

The aim of this study was to predict the cytochrome P450 3A (CYP3A)-mediated drug-drug interactions (DDIs) between saxagliptin and nicardipine using a physiologically based pharmacokinetic (PBPK) model. Initially, in silico and in vitro parameters were gathered from experiments or the literature to construct PBPK models for each drug in rats. These models were integrated to predict the DDIs between saxagliptin, metabolized via CYP3A2, and nicardipine, exhibiting CYP3A inhibitory activity. The rat DDI PBPK model was completed by optimizing parameters using experimental rat plasma concentrations after co-administration of both drugs. Following co-administration in Sprague-Dawley rats, saxagliptin plasma concentration significantly increased, resulting in a 2.60-fold rise in AUC, accurately predicted by the rat PBPK model. Subsequently, the workflow of the rat PBPK model was applied to humans, creating a model capable of predicting DDIs between the two drugs in humans. Simulation from the human PBPK model indicated that nicardipine co-administration in humans resulted in a nearly unchanged AUC of saxagliptin, with an approximate 1.05-fold change, indicating no clinically significant changes and revealing a lack of direct translation of animal interaction results to humans. The animal-to-human PBPK model extrapolation used in this study could enhance the reliability of predicting drug interactions in clinical settings where DDI studies are challenging.

Deep learning for drug‐drug interaction prediction: A comprehensive review

AbstractThe prediction of drug‐drug interactions (DDIs) is a crucial task for drug safety research, and identifying potential DDIs helps us to explore the mechanism behind combinatorial therapy. Traditional wet chemical experiments for DDI are cumbersome and time‐consuming, and are too small in scale, limiting the efficiency of DDI predictions. Therefore, it is particularly crucial to develop improved computational methods for detecting drug interactions. With the development of deep learning, several computational models based on deep learning have been proposed for DDI prediction. In this review, we summarized the high‐quality DDI prediction methods based on deep learning in recent years, and divided them into four categories: neural network‐based methods, graph neural network‐based methods, knowledge graph‐based methods, and multimodal‐based methods. Furthermore, we discuss the challenges of existing methods and future potential perspectives. This review reveals that deep learning can significantly improve DDI prediction performance compared to traditional machine learning. Deep learning models can scale to large‐scale datasets and accept multiple data types as input, thus making DDI predictions more efficient and accurate.