AptaDB: a comprehensive database integrating aptamer-target interactions.

Aptamers have emerged as research hotspots of the next generation due to excellent performance benefits and application potentials in pharmacology, medicine, and analytical chemistry. Despite the numerous aptamer investigations, the lack of comprehensive data integration has hindered the development of computational methods for aptamers and the reuse of aptamers. A public access database named AptaDB, derived from experimentally validated data manually collected from the literature, was hence developed, integrating comprehensive aptamer-related data, which include six key components: (i) experimentally validated aptamer-target interaction information, (ii) aptamer property information, (iii) structure information of aptamer, (iv) target information, (v) experimental activity information, and (vi) algorithmically calculated similar aptamers. AptaDB currently contains 1350 experimentally validated aptamer-target interactions, 1230 binding affinity constants, 1293 aptamer sequences, and more. Compared to other aptamer databases, it contains twice the number of entries found in available databases. The collection and integration of the above information categories is unique among available aptamer databases and provides a user-friendly interface. AptaDB will also be continuously updated as aptamer research evolves. We expect that AptaDB will become a powerful source for aptamer rational design and a valuable tool for aptamer screening in the future. For access to AptaDB, please visit http://lmmd.ecust.edu.cn/aptadb/.

admetSAR3.0: a comprehensive platform for exploration, prediction and optimization of chemical ADMET properties.

Absorption, distribution, metabolism, excretion and toxicity (ADMET) properties play a crucial role in drug discovery and chemical safety assessment. Built on the achievements of admetSAR and its successor, admetSAR2.0, this paper introduced the new version of the series, admetSAR3.0, as a comprehensive platform for chemical ADMET assessment, including search, prediction and optimization modules. In the search module, admetSAR3.0 hosted over 370 000 high-quality experimental ADMET data for 104 652 unique compounds, and supplemented chemical structure similarity search function to facilitate read-across. In the prediction module, we introduced comprehensive ADMET endpoints and two new sections for environmental and cosmetic risk assessments, empowering admetSAR3.0 to provide prediction for 119 endpoints, more than double numbers compared to the previous version. Furthermore, the advanced multi-task graph neural network framework offered robust and reliable support for ADMET prediction. In particular, a module named ADMETopt was added to automatically optimize the ADMET properties of query molecules through transformation rules or scaffold hopping. Finally, admetSAR3.0 provides user-friendly interfaces for multiple types of input data, such as SMILES string, chemical structure and batch molecule file, and supports various output types, including digital, chart displays and file downloads. In summary, admetSAR3.0 is anticipated to be a valuable and powerful tool in drug discovery and chemical safety assessment at http://lmmd.ecust.edu.cn/admetsar3/.

Accurate virus identification with interpretable Raman signatures by machine learning.

Rapid identification of newly emerging or circulating viruses is an important first step toward managing the public health response to potential outbreaks. A portable virus capture device, coupled with label-free Raman spectroscopy, holds the promise of fast detection by rapidly obtaining the Raman signature of a virus followed by a machine learning (ML) approach applied to recognize the virus based on its Raman spectrum, which is used as a fingerprint. We present such an ML approach for analyzing Raman spectra of human and avian viruses. A convolutional neural network (CNN) classifier specifically designed for spectral data achieves very high accuracy for a variety of virus type or subtype identification tasks. In particular, it achieves 99% accuracy for classifying influenza virus type A versus type B, 96% accuracy for classifying four subtypes of influenza A, 95% accuracy for differentiating enveloped and nonenveloped viruses, and 99% accuracy for differentiating avian coronavirus (infectious bronchitis virus [IBV]) from other avian viruses. Furthermore, interpretation of neural net responses in the trained CNN model using a full-gradient algorithm highlights Raman spectral ranges that are most important to virus identification. By correlating ML-selected salient Raman ranges with the signature ranges of known biomolecules and chemical functional groups­for example, amide, amino acid, and carboxylic acid­we verify that our ML model effectively recognizes the Raman signatures of proteins, lipids, and other vital functional groups present in different viruses and uses a weighted combination of these signatures to identify viruses.

ADENet: a novel network-based inference method for prediction of drug adverse events.

Identification of adverse drug events (ADEs) is crucial to reduce human health risks and improve drug safety assessment. With an increasing number of biological and medical data, computational methods such as network-based methods were proposed for ADE prediction with high efficiency and low cost. However, previous network-based methods rely on the topological information of known drug-ADE networks, and hence cannot make predictions for novel compounds without any known ADE. In this study, we introduced chemical substructures to bridge the gap between the drug-ADE network and novel compounds, and developed a novel network-based method named ADENet, which can predict potential ADEs for not only drugs within the drug-ADE network, but also novel compounds outside the network. To show the performance of ADENet, we collected drug-ADE associations from a comprehensive database named MetaADEDB and constructed a series of network-based prediction models. These models obtained high area under the receiver operating characteristic curve values ranging from 0.871 to 0.947 in 10-fold cross-validation. The best model further showed high performance in external validation, which outperformed a previous network-based and a recent deep learning-based method. Using several approved drugs as case studies, we found that 32-54% of the predicted ADEs can be validated by the literature, indicating the practical value of ADENet. Moreover, ADENet is freely available at our web server named NetInfer (http://lmmd.ecust.edu.cn/netinfer). In summary, our method would provide a promising tool for ADE prediction and drug safety assessment in drug discovery and development.

In Silico Prediction of Chemical Acute Dermal Toxicity Using Explainable Machine Learning Methods.

The research on acute dermal toxicity has consistently been a crucial component in assessing the potential risks of human exposure to active ingredients in pesticides and related plant protection products. However, it is difficult to directly identify the acute dermal toxicity of potential compounds through animal experiments alone. In our study, we separately integrated 1735 experimental data based on rabbits and 1679 experimental data based on rats to construct acute dermal toxicity prediction models using machine learning and deep learning algorithms. The best models for the two animal species achieved AUC values of 78.0 and 82.0%, respectively, on 10-fold cross-validation. Additionally, we employed SARpy to extract structural alerts, and in conjunction with Shapley additive explanation and attentive FP heatmap, we identified important features and structural fragments associated with acute dermal toxicity. This approach offers valuable insights for the detection of positive compounds. Moreover, a standalone software tool was developed to make acute dermal toxicity prediction easier. In summary, our research would provide an effective tool for acute dermal toxicity evaluation of pesticides, cosmetics, and drug safety assessment.

A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks.

The powerful combination of large-scale drug-related interaction networks and deep learning provides new opportunities for accelerating the process of drug discovery. However, chemical structures that play an important role in drug properties and high-order relations that involve a greater number of nodes are not tackled in current biomedical networks. In this study, we present a general hypergraph learning framework, which introduces Drug-Substructures relationship into Molecular interaction Networks to construct the micro-to-macro drug centric heterogeneous network (DSMN), and develop a multi-branches HyperGraph learning model, called HGDrug, for Drug multi-task predictions. HGDrug achieves highly accurate and robust predictions on 4 benchmark tasks (drug-drug, drug-target, drug-disease, and drug-side-effect interactions), outperforming 8 state-of-the-art task specific models and 6 general-purpose conventional models. Experiments analysis verifies the effectiveness and rationality of the HGDrug model architecture as well as the multi-branches setup, and demonstrates that HGDrug is able to capture the relations between drugs associated with the same functional groups. In addition, our proposed drug-substructure interaction networks can help improve the performance of existing network models for drug-related prediction tasks.

Network-Based Methods and Their Applications in Drug Discovery.

Drug discovery is time-consuming, expensive, and predominantly follows the "one drug → one target → one disease" paradigm. With the rapid development of systems biology and network pharmacology, a novel drug discovery paradigm, "multidrug → multitarget → multidisease", has emerged. This new holistic paradigm of drug discovery aligns well with the essence of networks, leading to the emergence of network-based methods in the field of drug discovery. In this Perspective, we initially introduce the concept and data sources of networks and highlight classical methodologies employed in network-based methods. Subsequently, we focus on the practical applications of network-based methods across various areas of drug discovery, such as target prediction, virtual screening, prediction of drug therapeutic effects or adverse drug events, and elucidation of molecular mechanisms. In addition, we provide representative web servers for researchers to use network-based methods in specific applications. Finally, we discuss several challenges of network-based methods and the directions for future development. In a word, network-based methods could serve as powerful tools to accelerate drug discovery.

NADPHnet: a novel strategy to predict compounds for regulation of NADPH metabolism via network-based methods.

Identification of compounds to modulate NADPH metabolism is crucial for understanding complex diseases and developing effective therapies. However, the complex nature of NADPH metabolism poses challenges in achieving this goal. In this study, we proposed a novel strategy named NADPHnet to predict key proteins and drug-target interactions related to NADPH metabolism via network-based methods. Different from traditional approaches only focusing on one single protein, NADPHnet could screen compounds to modulate NADPH metabolism from a comprehensive view. Specifically, NADPHnet identified key proteins involved in regulation of NADPH metabolism using network-based methods, and characterized the impact of natural products on NADPH metabolism using a combined score, NADPH-Score. NADPHnet demonstrated a broader applicability domain and improved accuracy in the external validation set. This approach was further employed along with molecular docking to identify 27 compounds from a natural product library, 6 of which exhibited concentration-dependent changes of cellular NADPH level within 100 µM, with Oxyberberine showing promising effects even at 10 µM. Mechanistic and pathological analyses of Oxyberberine suggest potential novel mechanisms to affect diabetes and cancer. Overall, NADPHnet offers a promising method for prediction of NADPH metabolism modulation and advances drug discovery for complex diseases.

Observation of Room-Temperature Exciton-Polariton Emission from Wide-Ranging 2D Semiconductors Coupled with a Broadband Mie Resonator.

Two-dimensional exciton-polaritons in monolayer transition metal dichalcogenides (TMDs) exhibit practical advantages in valley coherence, optical nonlinearities, and even bosonic condensation owing to their light-emission capability. To achieve robust exciton-polariton emission, strong photon-exciton couplings are required at the TMD monolayer, which is challenging due to its atomic thickness. High-quality (Q) factor optical cavities with narrowband resonances are an effective approach but typically limited to a specific excitonic state of a certain TMD material. Herein, we achieve on-demand exciton-polariton emission from a wide range of TMDs at room temperature by hybridizing excitons with broadband Mie resonances spanning the whole visible spectrum. By confining broadband light at the TMD monolayer, our one type of Mie resonator on different TMDs enables enhanced light-matter interactions with multiple excitonic states simultaneously. We demonstrate multi-Rabi splittings and robust polaritonic photoluminescence in monolayer WSe2, WS2, and MoS2. The hybrid system also shows the potential to approach the ultrastrong coupling regime.

Charge Transfer Modulation in Vanadium-Doped WS2 /Bi2 O2 Se Heterostructures.

The field of photovoltaics is revolutionized in recent years by the development of two-dimensional (2D) type-II heterostructures. These heterostructures are made up of two different materials with different electronic properties, which allows for the capture of a broader spectrum of solar energy than traditional photovoltaic devices. In this study, the potential of vanadium (V)-doped WS2 is investigated, hereafter labeled V-WS2 , in combination with air-stable Bi2 O2 Se for use in high-performance photovoltaic devices. Various techniques are used to confirm the charge transfer of these heterostructures, including photoluminescence (PL) and Raman spectroscopy, along with Kelvin probe force microscopy (KPFM). The results show that the PL is quenched by 40%, 95%, and 97% for WS2 /Bi2 O2 Se, 0.4 at.% V-WS2 /Bi2 O2 Se, and 2 at.% V-WS2 /Bi2 O2 Se, respectively, indicating a superior charge transfer in V-WS2 /Bi2 O2 Se compared to pristine WS2 /Bi2 O2 Se. The exciton binding energies for WS2 /Bi2 O2 Se, 0.4 at.% V-WS2 /Bi2 O2 Se and 2 at.% V-WS2 /Bi2 O2 Se heterostructures are estimated to be ≈130, 100, and 80 meV, respectively, which is much lower than that for monolayer WS2 . These findings confirm that by incorporating V-doped WS2 , charge transfer in WS2 /Bi2 O2 Se heterostructures can be tuned, providing a novel light-harvesting technique for the development of the next generation of photovoltaic devices based on V-doped transition metal dichalcogenides (TMDCs)/Bi2 O2 Se.

Spatial Control of Substitutional Dopants in Hexagonal Monolayer WS2 : The Effect of Edge Termination.

The ability to control the density and spatial distribution of substitutional dopants in semiconductors is crucial for achieving desired physicochemical properties. Substitutional doping with adjustable doping levels has been previously demonstrated in 2D transition metal dichalcogenides (TMDs); however, the spatial control of dopant distribution remains an open field. In this work, edge termination is demonstrated as an important characteristic of 2D TMD monocrystals that affects the distribution of substitutional dopants. Particularly, in chemical vapor deposition (CVD)-grown monolayer WS2 , it is found that a higher density of transition metal dopants is always incorporated in sulfur-terminated domains when compared to tungsten-terminated domains. Two representative examples demonstrate this spatial distribution control, including hexagonal iron- and vanadium-doped WS2 monolayers. Density functional theory (DFT) calculations are further performed, indicating that the edge-dependent dopant distribution is due to a strong binding of tungsten atoms at tungsten-zigzag edges, resulting in the formation of open sites at sulfur-zigzag edges that enable preferential dopant incorporation. Based on these results, it is envisioned that edge termination in crystalline TMD monolayers can be utilized as a novel and effective knob for engineering the spatial distribution of substitutional dopants, leading to in-plane hetero-/multi-junctions that display fascinating electronic, optoelectronic, and magnetic properties.

Investigation of Anti-Alzheimer's Mechanisms of Sarsasapogenin Derivatives by Network-Based Combining Structure-Based Methods.

Alzheimer's disease (AD), a neurodegenerative disease with no cure, affects millions of people worldwide and has become one of the biggest healthcare challenges. Some investigated compounds play anti-AD roles at the cellular or the animal level, but their molecular mechanisms remain unclear. In this study, we designed a strategy combining network-based and structure-based methods together to identify targets for anti-AD sarsasapogenin derivatives (AAs). First, we collected drug-target interactions (DTIs) data from public databases, constructed a global DTI network, and generated drug-substructure associations. After network construction, network-based models were built for DTI prediction. The best bSDTNBI-FCFP_4 model was further used to predict DTIs for AAs. Second, a structure-based molecular docking method was employed for rescreening the prediction results to obtain more credible target proteins. Finally, in vitro experiments were conducted for validation of the predicted targets, and Nrf2 showed significant evidence as the target of anti-AD compound AA13. Moreover, we analyzed the potential mechanisms of AA13 for the treatment of AD. Generally, our combined strategy could be applied to other novel drugs or compounds and become a useful tool in identification of new targets and elucidation of disease mechanisms. Our model was deployed on our NetInfer web server (http://lmmd.ecust.edu.cn/netinfer/).

EDC-Predictor: A Novel Strategy for Prediction of Endocrine-Disrupting Chemicals by Integrating Pharmacological and Toxicological Profiles.

Identification of endocrine-disrupting chemicals (EDCs) is crucial in the reduction of human health risks. However, it is hard to do so because of the complex mechanisms of the EDCs. In this study, we propose a novel strategy named EDC-Predictor to integrate pharmacological and toxicological profiles for the prediction of EDCs. Different from conventional methods that only focus on a few nuclear receptors (NRs), EDC-Predictor considers more targets. It uses computational target profiles from network-based and machine learning-based methods to characterize compounds, including both EDCs and non-EDCs. The best model constructed by these target profiles outperformed those models by molecular fingerprints. In a case study to predict NR-related EDCs, EDC-Predictor showed a wider applicability domain and higher accuracy than four previous tools. Another case study further demonstrated that EDC-Predictor could predict EDCs targeting other proteins rather than NRs. Finally, a free web server was developed to make EDC prediction easier (http://lmmd.ecust.edu.cn/edcpred/). In summary, EDC-Predictor would be a powerful tool in EDC prediction and drug safety assessment.

MetaADEDB 2.0: a comprehensive database on adverse drug events.

SUMMARY: MetaADEDB is an online database we developed to integrate comprehensive information on adverse drug events (ADEs). The first version of MetaADEDB was released in 2013 and has been widely used by researchers. However, it has not been updated for more than seven years. Here, we reported its second version by collecting more and newer data from the U.S. FDA Adverse Event Reporting System (FAERS) and Canada Vigilance Adverse Reaction Online Database, in addition to the original three sources. The new version consists of 744 709 drug-ADE associations between 8498 drugs and 13 193 ADEs, which has an over 40% increase in drug-ADE associations compared to the previous version. Meanwhile, we developed a new and user-friendly web interface for data search and analysis. We hope that MetaADEDB 2.0 could provide a useful tool for drug safety assessment and related studies in drug discovery and development. AVAILABILITY AND IMPLEMENTATION: The database is freely available at: http://lmmd.ecust.edu.cn/metaadedb/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

NetInfer: A Web Server for Prediction of Targets and Therapeutic and Adverse Effects via Network-Based Inference Methods.

In this study, we developed a web server named NetInfer for prediction of targets and therapeutic and adverse effects via network-based inference methods. Compared with our previously developed standalone version of NetInfer, this web server provides a user-friendly interface. With the web server, users can easily predict potential target proteins, microRNAs, Anatomical Therapeutic Chemical (ATC) classification codes, or adverse drug events for small molecules of their interests in a few steps. Most of the prediction models were constructed on the basis of our previous studies, where those models have been evaluated systematically and demonstrated high performance. The high-quality models can generate accurate predictions. As a case study, we predicted ATC codes and target proteins for several drugs. The predicted therapeutic effects of these drugs on cardiovascular diseases and their potential molecular mechanisms were validated by the literature. This successful case study demonstrated that our web server would be a powerful tool in drug repositioning and systems pharmacology. The web server of NetInfer is freely available at http://lmmd.ecust.edu.cn/netinfer/.

The Role of Reactive Oxygen Species in Alzheimer's Disease: From Mechanism to Biomaterials Therapy.

Alzheimer's disease (AD) is a chronic, insidious, and progressive neurodegenerative disease that remains a clinical challenge for society. The fully approved drug lecanemab exhibits the prospect of therapy against the pathological processes, while debatable adverse events conflict with the drug concentration required for the anticipated therapeutic effects. Reactive oxygen species (ROS) are involved in the pathological progression of AD, as has been demonstrated in much research regarding oxidative stress (OS). The contradiction between anticipated dosage and adverse event may be resolved through targeted transport by biomaterials and get therapeutic effects through pathological progression via regulation of ROS. Besides, biomaterials fix delivery issues by promoting the penetration of drugs across the blood-brain barrier (BBB), protecting the drug from peripheral degradation, and elevating bioavailability. The goal is to comprehensively understand the mechanisms of ROS in the progression of AD disease and the potential of ROS-related biomaterials in the treatment of AD. This review focuses on OS and its connection with AD and novel biomaterials in recent years against AD via OS to inspire novel biomaterial development. Revisiting these biomaterials and mechanisms associated with OS in AD via thorough investigations presents a considerable potential and bright future for improving effective interventions for AD.

mtADENet: A novel interpretable method integrating multiple types of network-based inference approaches for prediction of adverse drug events.

Identification of adverse drug events (ADEs) is crucial to reduce human health risks and accelerate drug safety assessment. ADEs are mainly caused by unintended interactions with primary or additional targets (off-targets). In this study, we proposed a novel interpretable method named mtADENet, which integrates multiple types of network-based inference approaches for ADE prediction. Different from phenotype-based methods, mtADENet introduced computational target profiles predicted by network-based methods to bridge the gap between chemical structures and ADEs, and hence can not only predict ADEs for drugs and novel compounds within or outside the drug-ADE association network, but also provide insights for the elucidation of molecular mechanisms of the ADEs caused by drugs. We constructed a series of network-based prediction models for 23 ADE categories. These models achieved high AUC values ranging from 0.865 to 0.942 in 10-fold cross validation. The best model further showed high performance on four external validation sets, which outperformed two previous network-based methods. To show the practical value of mtADENet, we performed case studies on developmental neurotoxicity and cardio-oncology, and over 50 % of predicted ADEs and targets for drugs and novel compounds were validated by literature. Moreover, mtADENet is freely available at our web server named NetInfer (http://lmmd.ecust.edu.cn/netinfer/). In summary, mtADENet would be a powerful tool for ADE prediction and drug safety assessment in drug discovery and development.

Reversing the Natural Drug Resistance of Gram-Negative Bacteria to Fusidic Acid via Forming Drug-Phospholipid Complex.

Drug resistance substantially compromises antibiotic therapy and poses a serious threat to public health. Fusidic acid (FA) is commonly used to treat staphylococcal infections, such as pneumonia, osteomyelitis and skin infections. However, Gram-negative bacteria have natural resistance to FA, which is almost restrained in cell membranes due to the strong interactions between FA and phospholipids. Herein, we aim to utilize the strong FA-phospholipid interaction to pre-form a complex of FA with the exogenous phospholipid. The FA, in the form of an FA-phospholipid complex (FA-PC), no longer interacts with the endogenous membrane phospholipids and thus can be delivered into bacteria cells successfully. We found that the water solubility of FA (5 µg/mL) was improved to 133 µg/mL by forming the FA-PC (molar ratio 1:1). Furthermore, upon incubation for 6 h, the FA-PC (20 µg/mL) caused a 99.9% viability loss of E. coli and 99.1% loss of P. aeruginosa, while free FA did not work. The morphology of the elongated bacteria cells after treatment with the FA-PC was demonstrated by SEM. The successful intracellular delivery was shown by confocal laser scanning microscopy in the form of coumarin 6-PC (C6-PC), where C6 served as a fluorescent probe. Interestingly, the antibacterial effect of the FA-PC was significantly compromised by adding extra phospholipid in the medium, indicating that there may be a phospholipid-based transmembrane transport mechanism underlying the intracellular delivery of the FA-PC. This is the first report regarding FA-PC formation and its successful reversing of Gram-negative bacteria resistance to FA, and it provides a platform to reverse transmembrane delivery-related drug resistance. The ready availability of phospholipid and the simple preparation allow it to have great potential for clinical use.

Drug-free and multifunctional sodium bicarbonate/hyaluronic acid hybrid dressing for synergistic healing of infected wounds.

Skin wounds are susceptible to microbial infections which commonly lead to the delayed wound healing. Rapid clearance of pathogens from the wound is of great significance and importance for efficient healing of the infected wounds. Herein, we report a multifunctional hybrid dressing, which simply combines sodium bicarbonate (NaHCO3) and hyaluronic acid (HA) for the synergistic wound healing. Addition of NaHCO3 allows the hybrid dressing to have the great antibacterial and antioxidant activity, while maintaining the intrinsic skin repair function of HA. As a result, NaHCO3/HA hybrid dressing showed the great antibacterial activity against both Gram-positive (S. aureus) and Gram-negative (E. coli) pathogens, the ability to improve the fibroblasts proliferation and migration, the cell-protection capacity under H2O2-induced oxidative stress, and most importantly, the great healing efficacy for the mice wound infected by S. aureus. We further found that the epidermal regeneration, the collagen deposition and the angiogenesis were enhanced by NaHCO3/HA hybrid dressing. All these effects were NaHCO3 concentration-dependent. Since the NaHCO3/HA hybrid dressing is drug-free, easily fabricated, biocompatible, and efficient for wound healing, it may have great potentials for clinical management of infected wounds.

MedChatZH: A tuning LLM for traditional Chinese medicine consultations.

Generative Large Language Models (LLMs) have achieved significant success in various natural language processing tasks, including Question-Answering (QA) and dialogue systems. However, most models are trained on English data and lack strong generalization in providing answers in Chinese. This limitation is especially evident in specialized domains like traditional Chinese medical QA, where performance suffers due to the absence of fine-tuning and high-quality datasets. To address this, we introduce MedChatZH, a dialogue model optimized for Chinese medical QA based on transformer decoder with LLaMA architecture. Continued pre-training on a curated corpus of Chinese medical books is followed by fine-tuning with a carefully selected medical instruction dataset, resulting in MedChatZH outperforming several Chinese dialogue baselines on a real-world medical dialogue dataset. Our model, code, and dataset are publicly available on GitHub (https://github.com/tyang816/MedChatZH) to encourage further research in traditional Chinese medicine and LLMs.