Prediction Of Drug-drug Interactions Research Articles

A Multi-View Feature-Based Interpretable Deep Learning Framework for Drug-Drug Interaction Prediction.

Drug-drug interactions (DDIs) can result in deleterious consequences when patients take multiple medications simultaneously, emphasizing the critical need for accurate DDI prediction. Computational methods for DDI prediction have garnered recent attention. However, current approaches concentrate solely on single-view features, such as atomic-view or substructure-view features, limiting predictive capacity. The scarcity of research on interpretability studies based on multi-view features is crucial for tracing interactions. Addressing this gap, we present MI-DDI, a multi-view feature-based interpretable deep learning framework for DDI. To fully extract multi-view features, we employ a Message Passing Neural Network (MPNN) to learn atomic features from molecular graphs generated by RDkit, and transformer encoders are used to learn substructure-view embeddings from drug SMILES simultaneously. These atomic-view and substructure-view features are then amalgamated into a holistic drug embedding matrix. Subsequently, an intricately designed interaction module not only establishes a tractable path for understanding interactions but also directly informs the construction of weight matrices, enabling precise and interpretable interaction predictions. Validation on the BIOSNAP dataset and DrugBank dataset demonstrates MI-DDI's superiority. It surpasses the current benchmarks by a substantial average of 3% on BIOSNAP and 1% on DrugBank. Additional experiments underscore the significance of atomic-view information for DDI prediction and confirm that our interaction module indeed learns more effective information for DDI prediction. The source codes are available at https://github.com/ZihuiCheng/MI-DDI .

Adaptive Multi-Kernel Graph Neural Network for Drug-Drug Interaction Prediction.

Combination therapy, which synergistically enhances treatment efficacy and inhibits disease progression through the combined effects of multiple drugs, has emerged as a mainstream approach for treating complex diseases and alleviating symptoms. However, drug-drug interactions (DDIs) can sometimes lead to adverse reactions, potentially endangering lives. Therefore, developing efficient and accurate DDI prediction methods is crucial for elucidating drug mechanisms and preventing side effects. Current prediction methods often focus solely on the presence of interactions between drugs when constructing DDI graphs, neglecting the specific types of DDIs. This oversight can result in a decline in predictive performance. To address this issue, we propose an Adaptive Multi-Kernel Graph Neural Network (AMKGNN) for DDI prediction. AMKGNN differentiates DDIs into increase-type and decrease-type interactions, constructing separate increased DDI and decreased DDI graphs as convolutional kernels. AMKGNN employs a graph kernel learning mechanism that adaptively determines the optimal threshold between high-frequency and low-frequency signals in the network to capture node embeddings. Initially, AMKGNN learns drug embedding representations based on these two graph convolutional kernels and various drug features. These representations are then concatenated and input into a deep neural network to predict potential DDIs. The results show that our model achieved AUC and AUPR values above 90% across three sub-tasks on two datasets, significantly outperforming the other five comparison models. Furthermore, ablation experiments and case studies validate the superiority of AMKGNN.

Artificial Intelligence Revolution in Pharmaceutical Sciences: Advancements, Clinical Impacts, and Applications.

Artificial intelligence (AI) is a rapidly transforming drug discovery and development process, significantly impacting the pharmaceutical industry and enhancing human health. This review article examines the tremendous role of AI in analyzing complex biological data, optimizing research processes, and reducing costs of production. Implementation of AI in the pharmaceutical sector can store a vast dataset of manufacturing processes, identify potential disease targets, simulate physiological conditions, and predict drug interactions. The review article also discusses the AI concepts and their applications, particularly in developing solid dosage forms. Advanced algorithms optimize formulation processes, predict pharmacokinetics profiles, and assess drug toxicity profiles, facilitating a more efficient pathway from pilot study to market. Additionally, this review highlights the advancements in 3D printing technologies of dosage forms that have the ability to provide personalized treatment to different individuals. Furthermore, the article explores the opportunities and challenges of AI in healthcare, focusing on applications such as disease diagnosis, digital therapy, and epidemic forecasting. Prominent AI technologies like deep learning and neural networks are examined for their roles in predicting outbreaks of diseases like influenza and COVID-19. As the pharmaceutical landscape evolves, AI is poised to redefine traditional methods. This paves the way for more efficient healthcare solutions. By harnessing the interplay of technology and science, AI not only increases productivity; but it also promotes a new era of precision medicine tailored to the needs of each patient.

Drug-Drug interactions prediction calculations between cardiovascular drugs and antidepressants for discovering the potential co-medication risks.

Predicting Drug-Drug Interactions (DDIs) enables cost reduction and time savings in the drug discovery process, while effectively screening and optimizing drugs. The intensification of societal aging and the increase in life stress have led to a growing number of patients suffering from both heart disease and depression. These patients often need to use cardiovascular drugs and antidepressants for polypharmacy, but potential DDIs may compromise treatment effectiveness and patient safety. To predict interactions between drugs used to treat these two diseases, we propose a method named Multi-Drug Features Learning with Drug Relation Regularization (MDFLDRR). First, we map feature vectors representing drugs in different feature spaces to the same. Second, we propose drug relation regularization to determine drug pair relationships in the interaction space. Experimental results demonstrate that MDFLDRR can be effectively applied to two DDI prediction goals: predicting unobserved interactions among drugs within the drug network and predicting interactions between drugs inside and outside the network. Publicly available evidence confirms that MDFLDRR can accurately identify DDIs between cardiovascular drugs and antidepressants. Lastly, by utilizing drug structure calculations, we ascertained the severity of newly discovered DDIs to mine the potential co-medication risks and aid in the smart management of pharmaceuticals.

A Domain Adaptive Interpretable Substructure-Aware Graph Attention Network for Drug-Drug Interaction Prediction.

Accurate prediction of drug-drug interaction (DDI) is essential to improve clinical efficacy, avoid adverse effects of drug combination therapy, and enhance drug safety. Recently researchers have developed several computer-aided methods for DDI prediction. However, these methods lack the substructural features that are critical to drug interactions and are not effective in generalizing across domains and different distribution data. In this work, we present SAGAN, a domain adaptive interpretable substructure-aware graph attention network for DDI prediction. Based on attention mechanism and unsupervised clustering algorithm, we propose a new substructure segmentation method, which segments the drug molecule into multiple substructures, learns the mechanism of drug interaction from the perspective of interaction, and identifies important interaction regions between drugs. To enhance the generalization ability of the model, we improve and apply a conditional domain adversarial network to achieve cross-domain generalization by alternately optimizing the cross-entropy loss on the source domain and the adversarial loss of the domain discriminator. We evaluate and compare SAGAN with the state-of-the-art DDI prediction model on four real-world datasets for both in-domain and cross-domain scenarios, and show that SAGAN achieves the best overall performance. Moreover, the visualization results of the model show that SAGAN has achieved pharmacologically significant substructure extraction, which can help drug developers screen for some undiscovered local interaction sites, and provide important information for further drug structure optimization. The codes and datasets are available online at https://github.com/wyx2012/SAGAN .

A Multi-Source drug combination and Omnidirectional feature fusion approach for predicting Drug-Drug interaction events.

In the medical context where polypharmacy is increasingly common, accurately predicting drug-drug interactions (DDIs) is necessary for enhancing clinical medication safety and personalized treatment. Despite progress in identifying potential DDIs, a deep understanding of the underlying mechanisms of DDIs remains limited, constraining the rapid development and clinical application of new drugs. This study introduces a novel multimodal drug-drug interaction (MMDDI) model based on multi-source drug data and comprehensive feature fusion techniques, aiming to improve the accuracy and depth of DDI prediction. We utilized the real-world DrugBank dataset, which contains rich drug information. Our task was to predict multiple interaction events between drug pairs and analyze the underlying mechanisms of these interactions. The MMDDI model achieves precise predictions through four key stages: feature extraction, drug pairing strategy, fusion network, and multi-source feature integration. We employed advanced data fusion techniques and machine learning algorithms for multidimensional analysis of drug features and interaction events. The MMDDI model was comprehensively evaluated on three representative prediction tasks. Experimental results demonstrated that the MMDDI model outperforms existing technologies in terms of predictive accuracy, generalization ability, and interpretability. Specifically, the MMDDI model achieved an accuracy of 93% on the test set, and the area under the AUC-ROC curve reached 0.9505, showing excellent predictive performance. Furthermore, the model's interpretability analysis revealed the complex relationships between drug features and interaction mechanisms, providing new insights for clinical medication decisions. The MMDDI model not only improves the accuracy of DDI prediction but also provides significant scientific support for clinical medication safety and drug development by deeply analyzing the mechanisms of drug interactions. These findings have the potential to improve patient medication outcomes and contribute to the development of personalized medicine.

Development of a physiologically-based pharmacokinetic model for Ritonavir characterizing exposure and drug interaction potential at both acute and steady-state conditions.

Ritonavir (RTV) is a potent CYP3A inhibitor that is widely used as a pharmacokinetic (PK) enhancer to increase exposure to select protease inhibitors. However, as a strong and complex perpetrator of CYP3A interactions, RTV can also enhance the exposure of other co-administered CYP3A substrates, potentially causing toxicity. Therefore, the prediction of drug-drug interactions (DDIs) and estimation of dosing requirements for concomitantly administered drugs is imperative. In this study, we aimed to develop a physiologically-based PK (PBPK) model for RTV using the PK-sim® software platform. A total of 13 clinical PK studies of RTV covering a wide dose range (100 to 600 mg including both single and multiple dosing), and eight clinical DDI studies with RTV on CYP3A and P-gp substrates, including alprazolam, midazolam, rivaroxaban, clarithromycin, fluconazole, sildenafil, and digoxinwere used for the model development and evaluation. Chronopharmacokinetic differences (between morning vs. evening doses) and limitations in parameter estimation for biochemical processes of RTV from invitro studies were incorporated in the PBPK model. The final developed PBPK model predicted 100% of RTV AUClast and Cmax within a twofold dimension error. The geometric mean fold error (GMFE) from all PK datasets was 1.275 and 1.194, respectively. In addition, 97% of the DDI profiles were predicted with the DDI ratios within a twofold dimension error. The GMFE values from all DDI datasets were 1.297 and 1.212, respectively. Accordingly, this model could be applied to the prediction of DDI profiles of RTV and CYP3A substrates and used to estimate dosing requirements for concomitantly administered drugs.

Advanced classification of drug-drug interactions for assessing adverse effect risks of Fluvoxamine and Curcumin using deep learning in COVID-19

Accurate drug-drug interaction (DDI) prediction is essential to prevent adverse effects, especially with the increased use of multiple medications during the COVID-19 pandemic. Traditional machine learning methods often miss the complex relationships necessary for effective DDI prediction. This study introduces a deep learning-based classification framework to assess adverse effects from interactions between Fluvoxamine and Curcumin. Our model integrates a wide range of drug-related data (e.g., molecular structures, targets, side effects) and synthesizes them into high-level features through a specialized deep neural network (DNN). This approach significantly outperforms traditional classifiers in accuracy, precision, recall, and F1-score. Additionally, our framework enables real-time DDI monitoring, which is particularly valuable in COVID-19 patient care. The model’s success in accurately predicting adverse effects demonstrates the potential of deep learning to enhance drug safety and support personalized medicine, paving the way for safer, data-driven treatment strategies.

Prediction of Drug-Drug Interactions for Highly Plasma Protein Bound Compounds.

Accurate prediction of drug-drug interactions (DDI) from in vitro data is important, as it provides insights on clinical DDI risk and study design. Historically, the lower limit of plasma fraction unbound (fu,p) is set at 1% for DDI prediction of highly bound compounds by the regulatory agencies due to the uncertainty of the fu,p measurements. This leads to high false positive DDI predictions for highly bound compounds. The recently published ICH M12 DDI guideline allows the use of experimental fu,p for DDI prediction of highly bound compounds. To further build confidence in DDI prediction of highly bound compounds using experimental fu,p values, we evaluated a set of drugs with fu,p < 1% and clinical DDI > 20% using both basic and mechanistic static models. All the compounds evaluated were flagged for DDI risk with the mechanistic model using experimental fu,p values. There was no false negative DDI prediction. Similarly, using the basic model, the DDI risk of all the compounds was identified except for CYP2D6 inhibition of almorexant. The totality of the data demonstrates that the DDI potential of highly bound compounds can be predicted accurately when actual protein binding numbers are measured.

Static Versus Dynamic Model Predictions of Competitive Inhibitory Metabolic Drug-Drug Interactions via Cytochromes P450: One Step Forward and Two Steps Backwards.

Predicting metabolic drug-drug interactions (DDIs) via cytochrome P450 enzymes (CYP) is essential in drug development, but controversy has reemerged recently about whether in vitro-in vivo extrapolation (IVIVE) using static models can replace dynamic models for some regulatory filings and label recommendations. The aim of this study was to determine if static and dynamic models are equivalent for the quantitative prediction of metabolic DDIs arising from competitive CYP inhibition. Drug parameter spaces were varied to simulate 30,000 DDIs between hypothetical substrates and inhibitors of CYP3A4. Predicted area under the plasma concentration-time profile ratios for substrates (AUCr = AUC(presence of precipitant)/AUC(absence of precipitant)) were compared between dynamic simulations (Simcyp® V21) and corresponding static calculations, giving an inter-model discrepancy ratio (IMDR = AUCrdynamic/AUCrstatic). Dynamic simulations were conducted using a 'population' representative and a 'vulnerable patient' representative with maximal concentration (Cmax) or average steady-state concentration (Cavg,ss) as the inhibitor driver concentrations. IMDRs outside the interval 0.8-1.25 were defined as discrepancy between models. The highest rate of IMDR <0.8 and IMDR >1.25 discrepancies in the 'population' representative was 85.9% and 3.1%, respectively, when using Cavg,ss as the inhibitor driver concentration. Using the 'vulnerable patient' representative showed the highest rate of IMDR >1.25 discrepancies at 37.8%. Static models are not equivalent to dynamic models for predicting metabolic DDIs via competitive CYP inhibition across diverse drug parameter spaces, particularly for vulnerable patients. Caution is warranted in drug development if static IVIVE approaches are used alone to evaluate metabolic DDI risks.

Interpretable prediction of drug-drug interactions via text embedding in biomedical literature

Polypharmacy is a promising approach for treating diseases, especially those with complex symptoms. However, it can lead to unexpected drug-drug interactions (DDIs), potentially reducing efficacy and triggering adverse drug reactions (ADRs). Predicting the risk of DDIs is crucial for ensuring safe drug use, particularly by identifying the types of DDIs and the mechanisms involved. Therefore, this study used biomedical literature to proposed hierarchical attention-based deep learning models to predict DDIs and their types. The proposed model consists of two components: drug embedding and DDI prediction. The drug embedding module extracts representation vectors that effectively capture drug properties using sentence and sequence embedding methods. For sentence embedding, a pre-trained biomedical language model is used to map drug-related sentences into vector space. For sequence embedding, sentence embedding vectors are sequentially fed into bidirectional long short-term memory with a hierarchical attention network, enabling the analysis of sentences relevant to DDI prediction while accounting for the order of the sentences. Finally, DDI prediction is performed using a deep neural network based on the sequence embedding vectors of a drug pair. Our model achieved high performances in the accuracy (0.85–0.90), AUROC (0.98–0.99), and AUPR (0.63–0.95) performance across 164 DDI types. Additionally, the proposed model showed improvements in up to 11 % in AUROC, and 8 % in AUPR. Furthermore, model interprets predictions by leveraging attention mechanisms and drug similarity. The results indicated that the model considered various factors beyond similarity to predict DDIs. These findings may help prevent unforeseen medical accidents and reduce healthcare costs by predicting detailed drug interaction types.

Geometric molecular graph representation learning model for drug-drug interactions prediction.

Drug-drug interaction (DDI) can trigger many adverse effects in patients and has emerged as a threat to medicine and public health. Therefore, it is important to predict potential drug interactions since it can provide combination strategies of drugs for systematic and effective treatment. Existing deep learning-based methods often rely on DDI functional networks, or use them as an important part of the model information source. However, it is difficult to discover the interactions of a new drug. To address the above limitations, we propose a geometric molecular graph representation learning model (Mol-DDI) for DDI prediction based on the basic assumption that structure determines function. Mol-DDI only considers the covalent and non-covalent bond information of molecules, then it uses the pre-training idea of large-scale models to learn drug molecular representations and predict drug interactions during the fine-tuning process. Experimental results show that the Mol-DDI model outperforms others on the three datasets and performs better in predicting new drug interaction experiments.

RCAN-DDI: Relation-aware Cross Adversarial Network for Drug-Drug Interaction Prediction

RCAN-DDI: Relation-aware Cross Adversarial Network for Drug-Drug Interaction Prediction

Group graph: a molecular graph representation with enhanced performance, efficiency and interpretability

The exploration of chemical space holds promise for developing influential chemical entities. Molecular representations, which reflect features of molecular structure in silico, assist in navigating chemical space appropriately. Unlike atom-level molecular representations, such as SMILES and atom graph, which can sometimes lead to confusing interpretations about chemical substructures, substructure-level molecular representations encode important substructures into molecular features; they not only provide more information for predicting molecular properties and drug‒drug interactions but also help to interpret the correlations between molecular properties and substructures. However, it remains challenging to represent the entire molecular structure both intactly and simply with substructure-level molecular representations. In this study, we developed a novel substructure-level molecular representation and named it a group graph. The group graph offers three advantages: (a) the substructure of the group graph reflects the diversity and consistency of different molecular datasets; (b) the group graph retains molecular structural features with minimal information loss because the graph isomorphism network (GIN) of the group graph performs well in molecular properties and drug‒drug interactions prediction, showing higher accuracy and efficiency than the model of other molecular graphs, even without any pretraining; and (c) the molecular property may change when the substructure is substituted with another of differing importance in group graph, facilitating the detection of activity cliffs. In addition, we successfully predicted structural modifications to improve blood‒brain barrier permeability (BBBP) via the GIN of group graph. Therefore, the group graph takes advantages for simultaneously representing molecular local characteristics and global features.Scientific contribution The group graph, as a substructure-level molecular representation, has the ability to retain molecular structural features with minimal information loss. As a result, it shows superior performance in predicting molecular properties and drug‒drug interactions with enhanced efficiency and interpretability.

EDDINet: Enhancing drug–drug interaction prediction via information flow and consensus constrained multi-graph contrastive learning

Predicting drug–drug interactions (DDIs) is crucial for understanding and preventing adverse drug reactions (ADRs). However, most existing methods inadequately explore the interactive information between drugs in a self-supervised manner, limiting our comprehension of drug–drug associations. This paper introduces EDDINet: Enhancing Drug-Drug Interaction Prediction via Information Flow and Consensus-Constrained Multi-Graph Contrastive Learning for precise DDI prediction. We first present a cross-modal information-flow mechanism to integrate diverse drug features, enriching the structural insights conveyed by the drug feature vector. Next, we employ contrastive learning to filter various biological networks, enhancing the model’s robustness. Additionally, we propose a consensus regularization framework that collaboratively trains multi-view models, producing high-quality drug representations. To unify drug representations derived from different biological information, we utilize an attention mechanism for DDI prediction. Extensive experiments demonstrate that EDDINet surpasses state-of-the-art unsupervised models and outperforms some supervised baseline models in DDI prediction tasks. Our approach shows significant advantages and holds promising potential for advancing DDI research and improving drug safety assessments. Our codes are available at: https://github.com/95LY/EDDINet_code.

A Systematic Review on Drug-to-Drug Interaction Prediction and Cryptographic Mechanism for Secure Drug Discovery Using AI Techniques

Recently, poly-pharmacy persistence has greatly improved in treating multiple diseases effectively. However, determining potential drug–drug interaction (DDIs) during the drug design is critical for controlling the target clinical drug during secure testing. In the medical field, DDIs are significant for disease diagnosis and treatment, mainly aiding researchers in predicting the link between biomolecules for efficient drug discovery (DD). Artificial intelligence (AI) has recently witnessed researchers accurately predict DDIs at minimum time consumption. Although the AI models show accurate results by aiding physicians to determine poly-pharmacy, several unresolvable issues remain in promoting reliability due to high error, complexity and cost-effectiveness. This paper aims to provide a comprehensive review using AI techniques (machine learning (ML)–deep learning (DL) models) and security enhancement techniques to improve DDI prediction and DD, respectively. The recent state of DDI prediction and the security concerns are presented initially, along with a short discussion about the need for effective techniques. Then, the critical evaluation related to existing studies is analyzed and compared to current issues faced in those existing studies. Various pharmaceutical drugs and their pros are also surveyed in addition to the security analysis for the newly invented drugs. Several assessment measures for the surveyed techniques are also conquered and put forth the need for advancements in future techniques effectively. The performance variations produced by the existing studies are also surveyed, and their use in the medical industry is also provided in this review study. The review of this research encourages the researchers to analyze the various issues faced in the pharmaceutical industry so that a novel technique can be introduced in the upcoming studies.

High-Order Multimodal Interaction Network for Efficient Prediction of Drug-Drug Interaction

The pharmaceutical industry places a lot of focus on preventing drug-drug interactions (DDIs). Medication interaction detection has been the primary emphasis of machine learning-based DDI prediction methods. Since studies have shown that DDIs can cause different future occurrences, it is more beneficial to predict DDI connected events while examining the mechanism behind combination medicine consumption or adverse reactions. The areas of medication development and illness diagnostics are seeing increased usage of a developing approach that predicts DDIs-associated occurrences. We examine potential interactions between the two medications as well as the kinds of interactions that can occur in this research. Additionally, we provide a strategy that relies on learning and use High-Order Multimodal Interaction Network (HOMIN) to forecast DDIs by learning feature representations. The purpose of this work is to provide HOMIN-DDI, a new method for drug-drug interaction predictions that we have developed utilizing a HOMIN architecture. First, we develop feature vectors from medication categories, targets, paths, and digestive enzymes, and we use the Jaccard similarity to evaluate how similar drugs appear. After that, we build a new HOMIN using the feature representation to predict DDIs. The results of the experiments show that the drug categories feature type, when used to the HOMIN -DDI approach, is effective. Furthermore, compared to employing only one feature, combining numerous features yields more useful and informative results. Compared to other algorithms, HOMIN-DDI performs better when it comes to predicting DDIs.

Development and validation of a machine learning model for predicting drug-drug interactions with oral diabetes medications

Diabetes management is often complicated by comorbidities, requiring complex medication regimens that increase the risk of drug-drug interactions (DDIs), potentially compromising treatment outcomes or causing toxicity. Although machine learning (ML) models have made strides in DDI prediction, existing approaches lack specificity for oral diabetes medications and face challenges in interpretability. To address these limitations, we propose a novel ML-based framework utilizing the Simplified Molecular Input Line Entry System (SMILES) to encode structural information of oral diabetes drugs. Using this representation, we developed an XGBoost model, selecting molecular features through LASSO. Our dataset, sourced from DrugBank, included 42 oral diabetes drugs and 1,884 interacting drugs, divided into training, validation, and testing sets. The model identified 606 optimal features, achieving an F1-score of 0.8182. SHAP analysis was employed for feature interpretation, enhancing model transparency and clinical relevance. By predicting adverse DDIs, our model offers a valuable tool for clinical decision-making, aiding safer prescription practices. The 606 critical features provide insights into atomic-level interactions, linking computational predictions with biological experiments. We present a classification model specifically designed for predicting DDIs associated with oral diabetes medications, with an openly accessible web application to support diabetes management in multi-drug regimens and comorbidity settings.

A knowledge graph-based method for drug-drug interaction prediction with contrastive learning.

Precisely predicting Drug-Drug Interactions (DDIs) carries the potential to elevate the quality and safety of drug therapies, protecting the well-being of patients, and providing essential guidance and decision support at every stage of the drug development process. In recent years, leveraging large-scale biomedical knowledge graphs has improved DDI prediction performance. However, the feature extraction procedures in these methods are still rough. More refined features may further improve the quality of predictions. To overcome these limitations, we develop a knowledge graph-based method for multi-typed DDI prediction with contrastive learning (KG-CLDDI). In KG-CLDDI, we combine drug knowledge aggregation features from the knowledge graph with drug topological aggregation features from the DDI graph. Additionally, we build a contrastive learning module that uses horizontal reversal and dropout operations to produce high-quality embeddings for drug-drug pairs. The comparison results indicate that KG-CLDDI is superior to state-of-the-art models in both the transductive and inductive settings. Notably, for the inductive setting, KG-CLDDI outperforms the previous best method by 17.49% and 24.97% in terms of AUC and AUPR, respectively. Furthermore, we conduct the ablation analysis and case study to show the effectiveness of KG-CLDDI. These findings illustrate the potential significance of KG-CLDDI in advancing DDI research and its clinical applications. The codes of KG-CLDDI are available at https://github.com/jianzhong123/KG-CLDDI.

KGRLFF: Detecting Drug-Drug Interactions Based on Knowledge Graph Representation Learning and Feature Fusion.

Accurate prediction of drug-drug interactions (DDIs) plays an important role in improving the efficiency of drug development and ensuring the safety of combination therapy. Most existing models rely on a single source of information to predict DDIs, and few models can perform tasks on biomedical knowledge graphs. This paper proposes a new hybrid method, namely Knowledge Graph Representation Learning and Feature Fusion (KGRLFF), to fully exploit the information from the biomedical knowledge graph and molecular structure of drugs to better predict DDIs. KGRLFF first uses a Bidirectional Random Walk sampling method based on the PageRank algorithm (BRWP) to obtain higher-order neighborhood information of drugs in the knowledge graph, including neighboring nodes, semantic relations, and higher-order information associated with triple facts. Then, an embedded representation learning model named Knowledge Graph-based Cyclic Recursive Aggregation (KGCRA) is used to learn the embedded representations of drugs by recursively propagating and aggregating messages with drugs as both the source and destination. In addition, the model learns the molecular structures of the drugs to obtain the structured features. Finally, a Feature Representation Fusion Strategy (FRFS) was developed to integrate embedded representations and structured feature representations. Experimental results showed that KGRLFF is feasible for predicting potential DDIs.