Prediction Of Drug-drug Interactions Research Articles

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.

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.

Integrated Knowledge Graph and Drug Molecular Graph Fusion via Adversarial Networks for Drug-Drug Interaction Prediction.

The Co-administration of multiple drugs can enhance the efficacy of disease treatment by reducing drug resistance and side effects. However, it also raises the risk of adverse drug interactions, presenting a challenging problem in healthcare. Various approaches have been developed to predict drug-drug interactions (DDIs) by leveraging both knowledge graphs and drug attribute information. While these methods have shown promise, they often fail to effectively capture correlations between biomedical information in the knowledge graph and drug properties. This work introduces a novel end-to-end DDI predictor framework based on generative adversarial networks. This framework utilizes a message-passing neural network to capture molecular structure information while employing the knowledge-aware graph attention network to capture the representation of drugs in the knowledge graph through considering the importance of different multihop neighbor nodes and relationships. The dual generative adversarial networks employ two generators and two discriminators in knowledge graph embedding and molecular topology embedding for adversarial training to capture the interrelations and complementary knowledge between molecular structure information and semantic information from the knowledge graph. comprehensive experiments have demonstrated that the proposed method outperforms state-of-the-art algorithms in binary classification, with improvements of 1.0% in accuracy, 0.45% in area under the receiver operating characteristic curve (AUC), 0.24% in area under the precision-recall curve (AUPR), and 0.98% in F1 score. Furthermore, for multiclass classification tasks, improvements were observed across various evaluation metrics, including 0.9% in accuracy, 0.25% in macro precision, 0.2% in macro recall, and 0.28% in macro F1. Additionally, ablation studies were conducted to showcase the effectiveness and robustness of our method in DDI prediction tasks.

Heterotropic Allosteric Modulation of CYP3A4 In Vitro by Progesterone: Evidence for Improvement in Prediction of Time Dependent Inhibition for Macrolides.

Predictions of drug-drug interactions resulting from time-dependent inhibition (TDI) of CYP3A4 have consistently overestimated or mis-predicted (i.e. false positives) the interaction that is observed in vivo. Recent findings demonstrated that the presence of the allosteric modulator progesterone (PGS) in the in vitro assay could alter the in vitro kinetics of CYP3A4 TDI with inhibitors that interact with the heme moiety, such as metabolic-intermediate complex (MIC) forming inhibitors. The impact of the presence of 100 µM PGS on the TDI of molecules in the class of macrolides typically associated with MIC formation was investigated. Presence of PGS resulted in varied responses across the inhibitors tested. The TDI signal was eliminated for five inhibitors, and unaltered in the case of one, fidaxomicin. The remaining molecules erythromycin, clarithromycin, and troleandomycin, were observed to have a decrease in both potency and maximum inactivation rate ranging from 1.7-fold to 6.7-fold. These changes in TDI kinetics led to a >90% decrease in inactivation efficiency. In order to determine in vitro conditions that could reproduce in vivo inhibition, varied concentrations of PGS were incubated with clarithromycin and erythromycin. Resulting in vitro TDI kinetics were incorporated into dynamic physiologically-based pharmacokinetic (PBPK) models to predict clinically observed interactions. The results suggested that a concentration of ~45 µM PGS would result in TDI kinetic values that could reproduce in vivo observations and could potentially improve predictions for CYP3A4 TDI. Significance Statement The impact of the allosteric heterotropic modulator progesterone on the CYP3A4 time-dependent inhibition kinetics was quantified for a set of metabolic-intermediate complex forming mechanism-based inhibitors. We identify the in vitro conditions that optimally predict time-dependent inhibition for in vivo drug-drug interactions through dynamic physiologically-based pharmacokinetic modeling. The optimized assay conditions improve in vitro to in vivo translation and prediction of time-dependent inhibition.

Modulation of Multispecific Transporters by Uncaria tomentosa Extract and Its Major Phytoconstituents.

Background/Objectives: One of the major risks associated with the concomitant use of herbal products and therapeutic drugs is herb-drug interactions (HDIs). The most common mechanism leading to HDIs is the inhibition and/or induction of transport proteins and drug-metabolizing enzymes by herbal ingredients, causing changes in the pharmacokinetic disposition of the victim drug. The present study aimed to determine the potential interactions of Uncaria tomentosa (UT) (cat's claw), a popular herb due to its supposed health benefits. Methods: The effect of UT extract and its major oxindole alkaloids was investigated on multispecific solute carrier (SLC) and ATP-binding cassette (ABC) drug transporters, using SLC transporter-overexpressing cell lines and vesicles prepared from ABC transporter-overexpressing cells. Results: UT extract significantly inhibited all ABC transporters and the majority of the SLC transporters tested. Of the investigated oxindole alkaloids, isopteropodine significantly inhibited OATP, OCT1 and OCT2, OAT3, ENT4, MDR1, and BCRP transporters. OCTs, OCTN1-, ENT1-, and MDR1-mediated substrate accumulation was below 50% in the presence of mitraphylline. Conclusions: Based on the calculated intestinal concentration of UT extract, interactions with intestinal transporters, especially OATP2B1, ENTs, MRP1, MRP2, MDR1, and BCRP could be relevant in vivo. Our data can help to predict the clinical consequences of UT co-administration with drugs, such as increased toxicity or altered efficacy. In conclusion, the use of these in vitro models is applicable for the analysis of transporter-mediated HDIs similar to drug-drug interaction (DDI) prediction.

PTB-DDI: An Accurate and Simple Framework for Drug-Drug Interaction Prediction Based on Pre-Trained Tokenizer and BiLSTM Model.

The simultaneous use of two or more drugs in clinical treatment may raise the risk of a drug-drug interaction (DDI). DDI prediction is very important to avoid adverse drug events in combination therapy. Recently, deep learning methods have been applied successfully to DDI prediction and improved prediction performance. However, there are still some problems with the present models, such as low accuracy due to information loss during molecular representation or incomplete drug feature mining during the training process. Aiming at these problems, this study proposes an accurate and simple framework named PTB-DDI for drug-drug interaction prediction. The PTB-DDI framework consists of four key modules: (1) ChemBerta tokenizer for molecular representation, (2) Bidirectional Long Short-Term Memory (BiLSTM) to capture the bidirectional context-aware features of drugs, (3) Multilayer Perceptron (MLP) for mining the nonlinear relationship of drug features, and (4) interaction predictor to perform an affine transformation and final prediction. In addition, we investigate the effect of dual-mode on parameter-sharing and parameter-independent within the PTB-DDI framework. Furthermore, we conducted comprehensive experiments on the two real-world datasets (i.e., BIOSNAP and DrugBank) to evaluate PTB-DDI framework performance. The results show that our proposed framework has significant improvements over the baselines based on both datasets. Based on the BIOSNAP dataset, the AUC-ROC, PR-AUC, and F1 scores are 0.997, 0.995, and 0.984, respectively. These metrics are 0.896, 0.873, and 0.826 based on the DrugBank dataset. Then, we conduct the case studies on the three newly approved drugs by the Food and Drug Administration (FDA) in 2024 using the PTB-DDI framework in dual modes. The obtained results indicate that our proposed framework has advantages for predicting drug-drug interactions and that the dual modes of the framework complement each other. Furthermore, a free website is developed to enhance accessibility and user experience.

Learning personalized drug features and differentiated drug-pair interaction information for drug–drug interaction prediction

Multi-drug combination therapies are increasingly used for complex diseases but carry risks of harmful drug interactions. Effective drug–drug interaction prediction (DDIP) is essential for assessing risks among numerous drug pairs. Most DDIP methods involve two main steps: drug representation and drug pair interaction extraction, respectively challenged by the loss of personalized drug information and the need for differentiated interaction data, and are rarely studied. Specifically, personalized drug information refers to the distinct features of each drug. These properties can be easily confused by neighboring information during graph propagation. This issue is especially prominent in drug interaction graphs with long-tail distributions, which poses challenges for personalized drug information learning. Furthermore, it is crucial to learn interactions with differentiation in order to identify diverse drug relationships. Some methods simply concatenate drug features, often ignoring the differences of different drug relationships, while other methods based on substructures rely on professional pharmacological knowledge and are computationally complex. To address these issues, we propose a novel method, learning personalized Drug Features and differentiated Drug-Pair interaction information for drug–drug interaction prediction (DFPDDI). This approach employs a contrastive learning network with edge-aware augmentations and mutual information estimators to capture personalized drug features across various graph distributions. Furthermore, it applies a mutual information constraint to drug-pair representations, enhancing the accuracy of interaction predictions by better distinguishing between different types of drug relationships. The results evaluated on three public datasets demonstrate competitive performance compared to baselines. It also shows potential for accurate predictions, particularly in imbalanced-distribution graphs.

Building Confidence in Physiologically Based Pharmacokinetic Modeling of CYP3A Induction Mediated by Rifampin: An Industry Perspective.

Physiologically-based pharmacokinetic (PBPK) modeling offers a viable approach to predict induction drug-drug interactions (DDIs) with the potential to streamline or reduce clinical trial burden if predictions can be made with sufficient confidence. In the current work, the ability to predict the effect of rifampin, a well-characterized strong CYP3A4 inducer, on 20 CYP3A probes with publicly available PBPK models (often developed using a workflow with optimization following a strong inhibitor DDI study to gain confidence in fraction metabolized by CYP3A4, fm,CYP3A4, and fraction available after intestinal metabolism, Fg), was assessed. Substrates with a range of fm,CYP3A4 (0.086-1.0), Fg (0.11-1.0) and hepatic availability (0.09-0.96) were included. Predictions were most often accurate for compounds that are not P-gp substrates or that are P-gp substrates but that have high permeability. Case studies for three challenging DDI predictions (i.e., for eliglustat, tofacitinib, and ribociclib) are presented. Along with parameter sensitivity analysis to understand key parameters impacting DDI simulations, alternative model structures should be considered, for example, a mechanistic absorption model instead of a first-order absorption model might be more appropriate for a P-gp substrate with low permeability. Any mechanisms pertinent to the CYP3A substrate that rifampin might impact (e.g., induction of other enzymes or P-gp) should be considered for inclusion in the model. PBPK modeling was shown to be an effective tool to predict induction DDIs with rifampin for CYP3A substrates with limited mechanistic complications, increasing confidence in the rifampin model. While this analysis focused on rifampin, the learnings may apply to other inducers.

Early Prediction and Impact Assessment of CYP3A4-Related Drug-Drug Interactions for Small-Molecule Anticancer Drugs Using Human-CYP3A4-Transgenic Mouse Models.

Early detection of drug-drug interactions (DDIs) can facilitate timely drug development decisions, prevent unnecessary restrictions on patient enrollment, resulting in clinical study populations that are not representative of the indicated study population, and allow for appropriate dose adjustments to ensure safety in clinical trials. All of these factors contribute to a streamlined drug approval process and enhanced patient safety. Here we describe a new approach for early prediction of the magnitude of change in exposure for cytochrome P450 (P450) CYP3A4-related DDIs of small-molecule anticancer drugs based on the model-based extrapolation of human-CYP3A4-transgenic mice pharmacokinetics to humans. Victim drugs brigatinib and lorlatinib were evaluated with the new approach in combination with the perpetrator drugs itraconazole and rifampicin. Predictions of the magnitude of change in exposure deviated at most 0.99- to 1.31-fold from clinical trial results for inhibition with itraconazole, whereas exposure predictions for the induction with rifampicin were less accurate, with deviations of 0.22- to 0.48-fold. Results for the early prediction of DDIs and their clinical impact appear promising for CYP3A4 inhibition, but validation with more victim and perpetrator drugs is essential to evaluate the performance of the new method. SIGNIFICANCE STATEMENT: The described method offers an alternative for the early detection and assessment of potential clinical impact of CYP3A4-related drug-drug interactions. The model was able to adequately describe the inhibition of CYP3A4 metabolism and the subsequent magnitude of change in exposure. However, it was unable to accurately predict the magnitude of change in exposure of victim drugs in combination with an inducer.

DrugDAGT: a dual-attention graph transformer with contrastive learning improves drug-drug interaction prediction

BackgroundDrug-drug interactions (DDIs) can result in unexpected pharmacological outcomes, including adverse drug events, which are crucial for drug discovery. Graph neural networks have substantially advanced our ability to model molecular representations; however, the precise identification of key local structures and the capture of long-distance structural correlations for better DDI prediction and interpretation remain significant challenges.ResultsHere, we present DrugDAGT, a dual-attention graph transformer framework with contrastive learning for predicting multiple DDI types. The dual-attention graph transformer incorporates attention mechanisms at both the bond and atomic levels, thereby enabling the integration of short and long-range dependencies within drug molecules to pinpoint key local structures essential for DDI discovery. Moreover, DrugDAGT further implements graph contrastive learning to maximize the similarity of representations across different views for better discrimination of molecular structures. Experiments in both warm-start and cold-start scenarios demonstrate that DrugDAGT outperforms state-of-the-art baseline models, achieving superior overall performance. Furthermore, visualization of the learned representations of drug pairs and the attention map provides interpretable insights instead of black-box results.ConclusionsDrugDAGT provides an effective tool for accurately predicting multiple DDI types by identifying key local chemical structures, offering valuable insights for prescribing medications, and guiding drug development. All data and code of our DrugDAGT can be found at https://github.com/codejiajia/DrugDAGT.

StructNet-DDI: Molecular Structure Characterization-Based ResNet for Prediction of Drug-Drug Interactions.

This study introduces a deep learning framework based on SMILES representations of chemical structures to predict drug-drug interactions (DDIs). The model extracts Morgan fingerprints and key molecular descriptors, transforming them into raw graphical features for input into a modified ResNet18 architecture. The deep residual network, enhanced with regularization techniques, efficiently addresses training issues such as gradient vanishing and exploding, resulting in superior predictive performance. Experimental results show that StructNet-DDI achieved an AUC of 99.7%, an accuracy of 94.4%, and an AUPR of 99.9%, demonstrating the model's effectiveness and reliability. These findings highlight that StructNet-DDI can effectively extract crucial features from molecular structures, offering a simple yet robust tool for DDI prediction.

Quantitative Prediction of Drug-Drug Interactions Caused by CYP3A Induction Using Endogenous Biomarker 4β-Hydroxycholesterol.

Evaluation of the CYP3A induction risk is important in early drug development stages. This study focused on 4β-hydroxycholesterol (4β-HC) as an endogenous biomarker of drug-drug interactions (DDIs) caused by CYP3A induction. We investigated a new approach using 4β-HC for quantitative prediction of DDIs caused by CYP3A induction based on the mechanistic static pharmacokinetic (MSPK) model. The induction ratio, i.e., the ratio of plasma 4β-HC or 4β-HC/cholesterol (4β-HC/C) with and without a coadministered CYP3A inducer, and the ratio of the area under the plasma concentration-time curve (AUCR), i.e., the ratio of the AUC of plasma CYP3A substrate drugs with and without a coadministered CYP3A inducer, were collected. The scaling factor (d) in the MSPK model was calculated from the induction ratio of 4β-HC or 4β-HC/C based on the systemic term in the MSPK model. The AUCR of 18 CYP3A substrates with and without coadministration of seven CYP3A inducers were then predicted by substituting the calculated d value into the MSPK model. This approach showed that approximately 84% of the predicted AUCR values were within a twofold range of the observed values, showing that this approach can be a good tool to quantitatively predict DDIs caused by CYP3A induction. SIGNIFICANCE STATEMENT: A concise approach to predict drug interactions with adequate accuracy is preferable in the early drug development stage. In this study, a new approach using 4β-hydroxycholesterol for quantitative prediction of drug-drug interactions caused by CYP3A induction was investigated. The predictability was verified using seven CYP3A inducers and 18 substrates.

A Molecular Fragment Representation Learning Framework for Drug-Drug Interaction Prediction.

The concurrent use of multiple drugs may result in drug-drug interactions, increasing the risk of adverse reactions. Hence, it is particularly crucial to propose computational methods for precisely identifying unknown drug-drug interactions, which is of great significance for drug development and health. However, most recent studies have limited the drug-drug interaction prediction task to identifying interactions between substructures, overlooking molecular hierarchical information. Moreover, the extracted substructures in these methods are always restricted to have the same number of atoms as contained in the molecular graph, which does not align with real-world facts. In this study, a molecular fragment representation learning framework for drug-drug interaction prediction is introduced. Initially, a fragment extraction module is designed to acquire a series of molecular fragments. Subsequently, to capture more comprehensive features, molecular hierarchical information is effectively integrated, enabling drug-drug interaction prediction by identifying pairwise interactions between molecular fragments of each drug. Comprehensive evaluations demonstrate that the proposed method achieved state-of-the-art performance in both DrugBank and Twosides datasets, particularly achieving an improved accuracy of over 20% for unseen drugs in both two datasets. Furthermore, case studies and visual analysis confirm that the proposed method can accurately identify crucial substructures influencing the interactions, which are basically consistent with functional group structures in reality. In conclusion, this method not only enhances the performance of drug-drug interaction prediction but also offers high interpretability. Source code is freely available at https://github.com/kennysyp/MFR-DDI .

IMPACT OF REAL-LIFE ENVIRONMENTAL EXPOSURES ON REPRODUCTION: A contemporary review of machine learning to predict adverse pregnancy outcomes from pharmaceuticals, including DDIs.

Clinical drug trials often do not include pregnant people due to health risks; therefore, many medications have an unknown effect on the developing fetus. Machine learning QSAR models have been used successfully to predict the fetal risk of pharmaceutical use during pregnancy. Those undergoing pregnancy are often excluded from clinical drug trials due to the risk that participation would pose to their health and the health of the developing fetus. However, they often require pharmaceuticals to manage health conditions that, if left untreated, could harm themselves or the fetus. This can mean that such individuals take one or more pharmaceuticals during pregnancy, many of which have unknown reproductive effects. Machine learning models have been used to successfully predict a number of reproductive toxicological outcomes for pharmaceuticals, including transplacental transfer, US Food and Drug Administration safety rating, and drug interactions. Models use quantitative chemical and structural features of active compounds as inputs to make predictions concerning the outcome of interest using computational algorithms. Models are validated and evaluated rigorously with metrics such as accuracy, area under the receiver operator curve, sensitivity, and precision. Results from these models can be a potential source of valuable information for pregnant people and their medical providers when making decisions regarding therapeutic drug use. This review summarizes current machine learning applications to make predictions about the risk and toxicity of medication use during pregnancy. Our review of the recent literature revealed that machine learning quantitative structure-activity relationship models can be used successfully to predict the transplacental transfer and the US Food and Drug Administration pregnancy safety category of pharmaceuticals; such models have also been employed to predict drug interactions, though not specifically during pregnancy. This latter topic is a potential area for future research. In this review, no single algorithm or descriptor-calculation software emerged as the most widely used, and their performances depend on a variety of factors, including the outcome of interest and combination of such algorithms and software.

A Novel Deep Learning Model for Drug-drug Interactions.

Drug-drug interactions (DDIs) can lead to adverse events and compromised treatment efficacy that emphasize the need for accurate prediction and understanding of these interactions. In this paper, we propose a novel approach for DDI prediction using two separate message-passing neural network (MPNN) models, each focused on one drug in a pair. By capturing the unique characteristics of each drug and their interactions, the proposed method aims to improve the accuracy of DDI prediction. The outputs of the individual MPNN models combine to integrate the information from both drugs and their molecular features. Evaluating the proposed method on a comprehensive dataset, we demonstrate its superior performance with an accuracy of 0.90, an area under the curve (AUC) of 0.99, and an F1-score of 0.80. These results highlight the effectiveness of the proposed approach in accurately identifying potential drugdrug interactions. The use of two separate MPNN models offers a flexible framework for capturing drug characteristics and interactions, contributing to our understanding of DDIs. The findings of this study have significant implications for patient safety and personalized medicine, with the potential to optimize treatment outcomes by preventing adverse events. Further research and validation on larger datasets and real-world scenarios are necessary to explore the generalizability and practicality of this approach.

Prediction of Pharmacokinetic Drug-Drug Interactions Involving Anlotinib as a Victim by Using Physiologically Based Pharmacokinetic Modeling.

Anlotinib was approved as a third line therapy for advanced non-small cell lung cancer in China. However, the impact of concurrent administration of various clinical drugs on the drug-drug interaction (DDI) potential of anlotinib remains undetermined. As such, this study aims to evaluate the DDI of anlotinib as a victim by establishing a physiologically based pharmacokinetic (PBPK) model. The PBPK model of anlotinib as a victim drug was constructed and validated in the Simcyp® incorporating parameters derived from in vitro studies, pre-clinical investigations, and clinical research encompassing patients with cancer. Subsequently, plasma exposure of anlotinib in cancer patients was predicted for single- and multi-dose co-administration with typical perpetrators mentioned in Food and Drug Administration (FDA) industrial guidance. Based on predictions, the CYP3A potent inhibitor ketoconazole demonstrated the most significant DDI with anlotinib, regardless of whether anlotinib is administered as a single dose or multiple doses. Ketoconazole increased the area under the concentration-time curve (AUC) and maximum concentration (Cmax) of single-dose anlotinib to 1.41-fold and 1.08-fold, respectively. In contrast, rifampicin, a potent inducer of CYP3A enzymes, exhibited a relatively higher level of DDI, with AUCR and CmaxR values of 0.44 and 0.79, respectively. Based on the PBPK modeling, there is a low risk of DDI between anlotinib and potent CYP3A/1A2 inhibitors, but caution and enhanced monitoring for adverse reactions are advised. To mitigate the risk of anti-tumor treatment failure, it is recommended to avoid concurrent use of strong CYP3A inducers. In conclusion, our study enhances understanding of anlotinib's interaction with medications, aiding scientists, prescribers, and drug labels in gauging the expected impact of CYP3A/1A2 modulators on anlotinib's pharmacokinetics.