Drug Molecular Structure Research Articles

Drug-induced torsadogenicity prediction model: An explainable machine learning-driven quantitative structure-toxicity relationship approach

Drug-induced Torsade de Pointes (TdP), a life-threatening polymorphic ventricular tachyarrhythmia, emerges due to the cardiotoxic effects of pharmaceuticals. The need for precise mechanisms and clinical biomarkers to detect this adverse effect presents substantial challenges in drug safety assessment. In this study, we propose that analyzing the physicochemical properties of pharmaceuticals can provide valuable insights into their potential for torsadogenic cardiotoxicity. Our research centers on estimating TdP risk based on the molecular structure of drugs. We introduce a novel quantitative structure-toxicity relationship (QSTR) prediction model that leverages an in silico approach developed by adopting the 4R rule in laboratory animals. This approach eliminates the need for animal testing, saves time, and reduces cost. Our algorithm has successfully predicted the torsadogenic risks of various pharmaceutical compounds. To develop this model, we employed Support Vector Machine (SVM) and ensemble techniques, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost). We enhanced the model's predictive accuracy through a rigorous two-step feature selection process. Furthermore, we utilized the SHapley Additive exPlanations (SHAP) technique to explain the prediction of torsadogenic risk, particularly within the RF model. This study represents a significant step towards creating a robust QSTR model, which can serve as an early screening tool for assessing the torsadogenic potential of pharmaceutical candidates or existing drugs. By incorporating molecular structure-based insights, we aim to enhance drug safety evaluation and minimize the risks of drug-induced TdP, ultimately benefiting both patients and the pharmaceutical industry.

A deep learning drug screening framework for integrating local-global characteristics: A novel attempt for limited data

At the beginning of the "Disease X" outbreak, drug discovery and development are often challenged by insufficient and unbalanced data. To address this problem and maximize the information value of limited data, we propose a drug screening model, LGCNN, based on convolutional neural network (CNN), which enables rapid drug screening by integrating features of drug molecular structures and drug-target interactions at both local and global (LG) levels. Experimental results show that LGCNN exhibits better performance compared to other state-of-the-art classification methods under limited data. In addition, LGCNN was applied to anti-SARS-CoV-2 drug screening to realize therapeutic drug mining against COVID-19. LGCNN transcends the limitations of traditional models for predicting interactions between single drug targets and shows new advantages in predicting multi-target drug-target interactions. Notably, the cross-coronavirus generalizability of the model is also implied by the analysis of targets, drugs, and mechanisms in the prediction results. In conclusion, LGCNN provides new ideas and methods for rapid drug screening in emergency situations where data are scarce.

Bond Incident Degree (BID) Indices of Line Graphs of some Chemical Structures in Drugs

A tremendous amount of drug experiments revealed that there exists a strong inherent relation between the molecular structures of drugs and their biomedical and pharmacology characteristics. Due to the effectiveness for pharmaceutical and medical scientists of their ability to grasp the biological and chemical characteristics of new drugs, analysis of the bond incident degree (BID) indices is significant of testing the chemical and pharmacological characteristics of drug molecular structures that can make up the defects of chemical and medicine experiments and can provide the theoretical basis for the manufacturing of drugs in pharmaceutical engineering. Such tricks are widely welcomed in developing areas where enough money is lacked to afford sufficient equipment, relevant chemical reagents, and human resources which are required to investigate the performance and the side effects of existing new drugs. This work is devoted to establishing a general expression for calculating the bond incident degree (BID) indices of the line graphs of various well-known chemical structures in drugs, based on the drug molecular structure analysis and edge dividing technique, which is quite common in drug molecular graphs.

Pharmaceutical Co-crystals: A Review on its Physico-chemical Properties and Role in the Management of Cancer

Academic and industry researchers are becoming more interested in pharmaceutical cocrystals as they emerge as a new class of solid pharmaceuticals with enhanced physico-chemical features. Pharmaceutical co-crystal formation is a simple method for significantly altering a therapeutic substance's solid-state characteristics namely its solubility and consequently bioavailability. A drug's physico-chemical properties can be adjusted by a cocrystal between an active pharmaceutical ingredient (API) and co-former without altering the drug's molecular structure. Numerous types of co-crystals, nano co-crystals and co-crystal-loaded nanocarriers have shown significant promise in the fight against cancer through enhanced pharmacokinetic capabilities, decreased toxicities and improved physico-chemical properties. In this review the physico-chemical properties of co-crystals along with its impact in management of cancer have been demonstrated. Keywords Co-Crystals, Physicochemical, Co-Former, Bioavailability, Nanocarriers

An effective framework for predicting drug–drug interactions based on molecular substructures and knowledge graph neural network

Drug–drug interactions (DDIs) play a central role in drug research, as the simultaneous administration of multiple drugs can have harmful or beneficial effects. Harmful interactions lead to adverse reactions, some of which can be life-threatening, while beneficial interactions can promote efficacy. Therefore, it is crucial for physicians, patients, and the research community to identify potential DDIs. Although many AI-based techniques have been proposed for predicting DDIs, most existing computational models primarily focus on integrating multiple data sources or combining popular embedding methods. Researchers often overlook the valuable information within the molecular structure of drugs or only consider the structural information of drugs, neglecting the relationship or topological information between drugs and other biological objects. In this study, we propose MSKG-DDI – a two-component framework that incorporates the Drug Chemical Structure Graph-based component and the Drug Knowledge Graph-based component to capture multimodal characteristics of drugs. Subsequently, a multimodal fusion neural layer is utilized to explore the complementarity between multimodal representations of drugs. Extensive experiments were conducted using two real-world datasets, and the results demonstrate that MSKG-DDI outperforms other state-of-the-art models in binary-class, multi-class, and multi-label prediction tasks under both transductive and inductive settings. Furthermore, the ablation analysis further confirms the practical usefulness of MSKG-DDI.

The phenomenon of phototoxicity and long-term risks of commonly prescribed and structurally diverse drugs

Photosensitivity to structurally diverse drugs is a common but under-reported adverse cutaneous reaction and can be classified as phototoxic or photoallergic. Phototoxic reactions occur when the skin is exposed to sunlight after administering topical or systemic medications that exhibit photosensitizing activity. These reactions depend on the dose of medication, degree of exposure to ultraviolet light, type of ultraviolet light, and sufficient skin distribution volume. Accurate prediction of the incidence and phototoxic response severity is challenging due to a paucity of literature, suggesting that phototoxicity may be more frequent than reported. This paper reports an extensive literature review on phototoxic drugs; the review employed pre-determined search criteria that included meta-analyses, systematic reviews, literature reviews, and case reports freely available in full text. Additional reports were identified from reference sections that contributed to the understanding of phototoxicity. The following drugs and/or drug classes are discussed: amiodarone, voriconazole, chlorpromazine, doxycycline, fluoroquinolones, hydrochlorothiazide, nonsteroidal anti-inflammatory drugs, and vemurafenib. In reviewing phototoxic skin reactions, this review highlights drug molecular structures, their reactive pathways, and, as there is a growing association between photosensitizing drugs and the increasing incidence of skin cancer, the consequential long-term implications of photocarcinogenesis.

Fusion-Based Deep Learning Architecture for Detecting Drug-Target Binding Affinity Using Target and Drug Sequence and Structure.

Accurately predicting drug-target binding affinity plays a vital role in accelerating drug discovery. Many computational approaches have been proposed due to costly and time-consuming of wet laboratory experiments. In the input representation, most methods only focus on the target sequence properties or target structure properties while ignore the overall contribution. Therefore, we develop a novel fusion protocol based on multiscale convolutional neural networks and graph neural networks, named CGraphDTA, to predict drug-target binding affinity using target sequence and structure. Unlike existing methods, CGraphDTA is the first model constructed with target sequence and structure as input. Concretely, the multiscale convolutional neural networks are utilized to extract target and drug presentation from sequence, graph neural networks are employed to extract graph presentation from target and drug molecular structure. We compare CGraphDTA with the state-of-the-art methods, the results show that our model outperforms the current methods on the test sets. Furthermore, we conduct ablation studies, biological interpretation examination and drug selectivity evaluation, all results suggest that CGraphDTA is a useful tool to predict drug-target binding affinity and accelerate drug discovery.

Simple elaboration of drug-SPION nanocapsules (hybridosomes®) by solvent shifting: Effect of the drug molecular structure and concentration

Drug nanocapsules coated with iron oxide nanoparticles (SPION) were elaborated by the simultaneous nanoprecipitation of the drug and the nanoparticles, through solvent shifting. We examined four drugs: sorafenib, sorafenib tosylate, α-tocopherol and paclitaxel, to cover the cases of molecular solids, ionic solids, and molecular liquids. We first investigated the formation of the drug core in the final mixture of solvents at different concentrations. A Surfactant-Free Micro-Emulsion domain (SFME, thermodynamically stable) was observed at low drug concentration and an Ouzo domain (metastable) at high drug concentration, except for the case of paclitaxel which crystallizes at high concentration without forming an Ouzo domain. When co-nanoprecipitated with the molecular drugs in the Ouzo domain (sorafenib or α-tocopherol), the SPION limited the coalescence of the drug particles to less than 100 nm, forming capsules with a drug encapsulation efficiency of ca 80 %. In contrast, larger capsules were formed from the SFME or when using the ionic form (sorafenib tosylate). Finally, the sorafenib-SPION capsules exhibit a similar chemotherapeutic effect as the free drug on the hepatocellular carcinoma in vitro.

Desirable molecule discovery via generative latent space exploration

Drug molecule design is a classic research topic. Drug experts traditionally design molecules relying on their experience. Manual drug design is time-consuming and may produce low-efficacy and off-target molecules. With the popularity of deep learning, drug experts are beginning to use generative models to design drug molecules. A well-trained generative model can learn the distribution of training samples and infinitely generate drug-like molecules similar to the training samples. The automatic process improves design efficiency. However, most existing methods focus on proposing and optimizing generative models. How to discover ideal molecules from massive candidates is still an unresolved challenge. We propose a visualization system to discover ideal drug molecules generated by generative models. In this paper, we investigated the requirements and issues of drug design experts when using generative models, i.e., generating molecular structures with specific constraints and finding other molecular structures similar to potential drug molecular structures. We formalized the first problem as an optimization problem and proposed using a genetic algorithm to solve it. For the second problem, we proposed using a neighborhood sampling algorithm based on the continuity of the latent space to find solutions. We integrated the proposed algorithms into a visualization tool, and a case study for discovering potential drug molecules to make KOR agonists and experiments demonstrated the utility of our approach.

Vertex-Based Resolvability Parameters for Identification of Certain Chemical Structures.

Chemical graph theory explores chemical phenomena and entities through the conceptual framework of graph theory. In chemical graph theory, molecular structures are represented by chemical graphs, where edges and vertices correspond to bonds and atoms, respectively. Chemical graphs serve as fundamental data types in cheminformatics for illustrating chemical structures. The computable properties of graphs form the basis for quantitative structure-property and structure-activity predictions, which are central to cheminformatics. These graphs capture the physical characteristics of molecules and can be further reduced to graph-theoretical indices or descriptors. One extensively studied distance-based graph descriptor is the resolving set Z, which enables the distinction of every pair of distinct vertices in a connected simple graph. Resolving sets were specifically employed in pharmaceutical research to find patterns shared by several different drugs. Since very early times, medicinal drugs have played a significant part in human civilization. In this article, we investigate minimum resolving sets for certain significant drug molecular structures, namely, suramin (S86) and acemannan (A116).

DMFDDI: deep multimodal fusion for drug-drug interaction prediction.

Drug combination therapy has gradually become a promising treatment strategy for complex or co-existing diseases. As drug-drug interactions (DDIs) may cause unexpected adverse drug reactions, DDI prediction is an important task in pharmacology and clinical applications. Recently, researchers have proposed several deep learning methods to predict DDIs. However, these methods mainly exploit the chemical or biological features of drugs, which is insufficient and limits the performances of DDI prediction. Here, we propose a new deep multimodal feature fusion framework for DDI prediction, DMFDDI, which fuses drug molecular graph, DDI network and the biochemical similarity features of drugs to predict DDIs. To fully extract drug molecular structure, we introduce an attention-gated graph neural network for capturing the global features of the molecular graph and the local features of each atom. A sparse graph convolution network is introduced to learn the topological structure information of the DDI network. In the multimodal feature fusion module, an attention mechanism is used to efficiently fuse different features. To validate the performance of DMFDDI, we compare it with 10 state-of-the-art methods. The comparison results demonstrate that DMFDDI achieves better performance in DDI prediction. Our method DMFDDI is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DHUDEBLab/DMFDDI.git.

XMR: an explainable multimodal neural network for drug response prediction.

Introduction: Existing large-scale preclinical cancer drug response databases provide us with a great opportunity to identify and predict potentially effective drugs to combat cancers. Deep learning models built on these databases have been developed and applied to tackle the cancer drug-response prediction task. Their prediction has been demonstrated to significantly outperform traditional machine learning methods. However, due to the "black box" characteristic, biologically faithful explanations are hardly derived from these deep learning models. Interpretable deep learning models that rely on visible neural networks (VNNs) have been proposed to provide biological justification for the predicted outcomes. However, their performance does not meet the expectation to be applied in clinical practice. Methods: In this paper, we develop an XMR model, an eXplainable Multimodal neural network for drug Response prediction. XMR is a new compact multimodal neural network consisting of two sub-networks: a visible neural network for learning genomic features and a graph neural network (GNN) for learning drugs' structural features. Both sub-networks are integrated into a multimodal fusion layer to model the drug response for the given gene mutations and the drug's molecular structures. Furthermore, a pruning approach is applied to provide better interpretations of the XMR model. We use five pathway hierarchies (cell cycle, DNA repair, diseases, signal transduction, and metabolism), which are obtained from the Reactome Pathway Database, as the architecture of VNN for our XMR model to predict drug responses of triple negative breast cancer. Results: We find that our model outperforms other state-of-the-art interpretable deep learning models in terms of predictive performance. In addition, our model can provide biological insights into explaining drug responses for triple-negative breast cancer. Discussion: Overall, combining both VNN and GNN in a multimodal fusion layer, XMR captures key genomic and molecular features and offers reasonable interpretability in biology, thereby better predicting drug responses in cancer patients. Our model would also benefit personalized cancer therapy in the future.

Review on anti-corrosion properties of expired antihypertensive drugs as benign corrosion inhibitors for metallic materials in various environments

Discovering new classes of organic corrosion inhibitors, such as expired drugs, can provide cheaper, low-toxic, and highly efficient alternatives to the toxic organic counterparts that serve as an efficient recycling or disposal strategy. Antihypertensive drugs constitute one of the cheapest classes of drugs, globally, and have been reported as highly effective corrosion inhibitors for a variety of metallic materials in various corrosion environments. The corrosion inhibition mechanism of these drugs, generally, involves the adsorption on the metallic surfaces and the formation of a protective organic film that retards the attack of substrates by corrosive entities in the media. The drug molecular structure usually contains π-bonds, phenyl rings, and polar functional groups (such as –NH2, –OH, –CN, and −Cl) which influence the electron density within the inhibitor framework and also facilitate adsorption of the drug on the metal surface. Generally, most antihypertensive drugs act as mixed-type inhibitors and usually obey Langmuir adsorption isotherm revealing physisorption adsorption mechanisms except telmisartan, losartan potassium, and atenolol when used in nitric acid. The reported inhibition efficiency of the drugs is generally above 90% with spironolactone having the highest efficiency of 98.1% at 30 °C.

Multi-view feature representation and fusion for drug-drug interactions prediction

BackgroundDrug-drug interactions (DDIs) prediction is vital for pharmacology and clinical application to avoid adverse drug reactions on patients. It is challenging because DDIs are related to multiple factors, such as genes, drug molecular structure, diseases, biological processes, side effects, etc. It is a crucial technology for Knowledge graph to present multi-relation among entities. Recently some existing graph-based computation models have been proposed for DDIs prediction and get good performance. However, there are still some challenges in the knowledge graph representation, which can extract rich latent features from drug knowledge graph (KG).ResultsIn this work, we propose a novel multi-view feature representation and fusion (MuFRF) architecture to realize DDIs prediction. It consists of two views of feature representation and a multi-level latent feature fusion. For the feature representation from the graph view and KG view, we use graph isomorphism network to map drug molecular structures and use RotatE to implement the vector representation on bio-medical knowledge graph, respectively. We design concatenate-level and scalar-level strategies in the multi-level latent feature fusion to capture latent features from drug molecular structure information and semantic features from bio-medical KG. And the multi-head attention mechanism achieves the optimization of features on binary and multi-class classification tasks. We evaluate our proposed method based on two open datasets in the experiments. Experiments indicate that MuFRF outperforms the classic and state-of-the-art models.ConclusionsOur proposed model can fully exploit and integrate the latent feature from the drug molecular structure graph (graph view) and rich bio-medical knowledge graph (KG view). We find that a multi-view feature representation and fusion model can accurately predict DDIs. It may contribute to providing with some guidance for research and validation for discovering novel DDIs.

Predicting Drug-Target Interactions Over Heterogeneous Information Network.

Identifying Drug-Target Interactions (DTIs) is a critical step in studying pathogenesis and drug development. Due to the fact that conventional experimental methods usually suffer from high costs and low efficiency, various computational methods have been proposed to detect potential DTIs by extracting features from the biological information of drugs and their target proteins. Though effective, most of them fall short of considering the topological structure of the DTI network, which provides a global view to discover novel DTIs. In this paper, a network-based computational method, namely LG-DTI, is proposed to accurately predict DTIs over a heterogeneous information network. For drugs and target proteins, LG-DTI first learns not only their local representations from drug molecular structures and protein sequences, but also their global representations by using a semi-supervised heterogeneous network embedding method. These two kinds of representations consist of the final representations of drugs and target proteins, which are then incorporated into a Random Forest classifier to complete the task of DTI prediction. The performance of LG-DTI has been evaluated on two independent datasets and also compared with several state-of-the-art methods. Experimental results show the superior performance of LG-DTI. Moreover, our case study indicates that LG-DTI can be a valuable tool for identifying novel DTIs.

On Degree Based Topological Properties of the Molecular Structure of Polycyclic Aromatic Hydrocarbons

There is a strong correlation between the properties of their molecular structure based on medical experiments. The molecular structure of drugs contains all of the information for investigating their chemical, physical and biological properties. These properties can be determined using a theoretical descriptor tool known as topological indices. In this paper, we compute some of the mean Sombor indices of polycyclic aromatic hydrocarbons that our results in this paper may be useful to better understand the many physical and chemical properties of polycyclic aromatic hydrocarbons.

Rh(III)‐Catalyzed N‐Arylation of Alkyl Dioxazolones with Arylboronic Acids for the Synthesis of N‐Aryl Amides

AbstractHerein, a method for N‐aryl amides preparation has been established through Rh(III)‐catalyzed C(sp2)−N cross‐coupling reactions of alkyl dioxazolones with arylboronic acids, heterocyclic boronic acid, and alkenyl boronic acid. This efficient and straightforward catalytic approach was featured with broad substrate scope (38 examples), good functional group compatibility, high yields (up to 99 %), and is suitable for late‐stage modification of drug molecular structures. The possible mechanism hypothesis was also accomplished.

RoFDT: Identification of Drug-Target Interactions from Protein Sequence and Drug Molecular Structure Using Rotation Forest.

As the basis for screening drug candidates, the identification of drug-target interactions (DTIs) plays a crucial role in the innovative drugs research. However, due to the inherent constraints of small-scale and time-consuming wet experiments, DTI recognition is usually difficult to carry out. In the present study, we developed a computational approach called RoFDT to predict DTIs by combining feature-weighted Rotation Forest (FwRF) with a protein sequence. In particular, we first encode protein sequences as numerical matrices by Position-Specific Score Matrix (PSSM), then extract their features utilize Pseudo Position-Specific Score Matrix (PsePSSM) and combine them with drug structure information-molecular fingerprints and finally feed them into the FwRF classifier and validate the performance of RoFDT on Enzyme, GPCR, Ion Channel and Nuclear Receptor datasets. In the above dataset, RoFDT achieved 91.68%, 84.72%, 88.11% and 78.33% accuracy, respectively. RoFDT shows excellent performance in comparison with support vector machine models and previous superior approaches. Furthermore, 7 of the top 10 DTIs with RoFDT estimate scores were proven by the relevant database. These results demonstrate that RoFDT can be employed to a powerful predictive approach for DTIs to provide theoretical support for innovative drug discovery.

Design of Experiment Approach to Modeling the Effects of Formulation and Drug Loading on the Structure and Properties of Therapeutic Nanogels.

The physical properties of nanoparticles may affect the uptake mechanism, biodistribution, stability, and other physicochemical properties of drug delivery systems. This study aimed to first develop a model exploring the factors controlling the nanogel physical properties using a single drug (propranolol), followed by an evaluation of whether these models can be applied more generally to a range of drugs. Size, polydispersity, ζ potential, and encapsulation efficiency were investigated using a design of experiment (DOE) approach to optimize formulations by systematically identifying the effects of, and interactions between, parameters associated with nanogel formulation and drug loading. Three formulation factors were selected, namely, chitosan concentration, the ratio between the chitosan and cross-linker—sodium triphosphate—and the ratio between the chitosan and drug. The results indicate that the DOE approach can be used not only to model but also to predict the size and polydispersity index (PDI). To explore the application of these prediction models with other drugs and to identify the relationship between the drug structure and nanogel properties, nanogels loaded with 12 structurally distinct drugs and 6 structurally similar drugs were fabricated at the optimal condition for propranolol in the model. The measured size, PDI, and ζ potential of the nanogels could not be modeled using distinct DOE parameters for dissimilar drugs, indicating that each drug requires a separate analysis. Nevertheless, for drugs with structural similarities, various linear and nonlinear trends were observed in the size, PDI, and ζ potential of nanogels against selected molecular descriptors, indicating that there are indeed relationships between the drug molecular structure and the performance outcomes, which may be modeled and predicted using the DOE approach. In conclusion, the study demonstrates that DOE models can be applied to model and predict the influence of formulation and drug loading on key performance parameters. While distinct models are required for structurally unrelated drugs, it was possible to establish correlations for the drug series investigated, which were based on polarity, hydrophobicity, and polarizability, thereby elucidating the importance of the interactions between the drug and the nanogels based on the nanogel properties and thus deepening the understanding of the drug-loading mechanisms in nanogels.

DeepMGT-DTI: Transformer network incorporating multilayer graph information for Drug–Target interaction prediction

Drug–target interaction (DTI) prediction reduces the cost and time of drug development, and plays a vital role in drug discovery. However, most of research does not fully explore the molecular structures of drug compounds in DTI prediction. To this end, we propose a deep learning model to capture the molecular structure information of drug compounds for DTI prediction. This model utilizes a transformer network incorporating multilayer graph information, which captures the features of a drug's molecular structure so that the interactions between atoms of drug compounds can be explored more deeply. At the same time, a convolutional neural network is employed to capture the local residue information in the target sequence, and effectively extract the feature information of the target. The experiments on the DrugBank dataset showed that the proposed model outperformed previous models based on the structure of target sequences. The results indicate that the improved transformer network fuses the feature information between layers in the graph convolutional neural network and extracts the interaction data for the molecular structure. The drug repositioning experiment on COVID-19 and Alzheimer's disease demonstrated the proposed model's ability to find therapeutic drugs in drug discovery. The code of our model is available at https://github.com/zhangpl109/DeepMGT-DTI.