- Computational Drug Discovery Methods
- Synthesis and biological activity
- Cancer therapeutics and mechanisms
- Advanced DC-DC Converters
- Protein Structure and Dynamics
- Power Quality and Harmonics
- Chemical Synthesis and Analysis
- Machine Learning in Materials Science
- Protein Degradation and Inhibitors
- EEG and Brain-Computer Interfaces
- Microgrid Control and Optimization
- Multilevel Inverters and Converters
- Melanoma and MAPK Pathways
- Neural dynamics and brain function
- Microtubule and mitosis dynamics
- Complex Network Analysis Techniques
- Functional Brain Connectivity Studies
- Microbial Natural Products and Biosynthesis
- Bioinformatics and Genomic Networks
- Receptor Mechanisms and Signaling
- Angiogenesis and VEGF in Cancer
- Advanced Neural Network Applications
- Cancer Mechanisms and Therapy
- Enzyme function and inhibition
- Photovoltaic System Optimization Techniques
China Pharmaceutical University
2016-2025
General Administration of Quality Supervision, Inspection and Quarantine
2024-2025
China Power Engineering Consulting Group (China)
2019-2024
Nanjing University of Aeronautics and Astronautics
2006-2024
Shanghai Jiao Tong University
2015-2023
Ningbo University
2023
Institute of Navigation
2022
Guangdong University of Foreign Studies
2020-2021
Liaoning University
2018
State Key Laboratory of Natural Medicine
2017
Model-based analysis tools, built on assumptions and simplifications, are difficult to handle smart grids with data characterized by volume, velocity, variety, veracity (i.e., 4Vs data). This paper, using random matrix theory (RMT), motivates data-driven tools perceive the complex in high-dimension; meanwhile, an architecture detailed procedures is proposed. In algorithm perspective, performs a high-dimensional compares findings RMT predictions conduct anomaly detections. Mean spectral...
Ab initio calculations have been performed on a series of complexes formed between halogen-containing molecules and ammonia to gain deeper insight into the nature halogen bonding. It appears that dihalogen form strongest halogen-bonded with ammonia, followed by HOX; charge-transfer-type contribution has demonstrated dominate bonding in these complexes. For involving carbon-bound molecules, our clearly indicate electrostatic interactions are mainly responsible for their binding energies....
Human pharmacokinetics is of great significance in the selection drug candidates, and silico estimation pharmacokinetic parameters early stage development has become trend research owing to its time- cost-saving advantages. Herein, quantitative structure-property relationship studies were carried out predict four human including volume distribution at steady state (VDss), clearance (CL), terminal half-life (t1/2), fraction unbound plasma (fu), using a data set consisting 1352 drugs. A series...
Abstract Numerous studies on short‐term load forecasting (STLF) have used feature extraction methods to increase the model's accuracy by incorporating multidimensional features containing time, weather and distance information. However, less attention has been paid input data size output dimensions in STLF. To address these two issues, an STLF model is proposed based using only data. First, data's long‐term behavior (trend seasonality) extracted through long memory network (LSTM), followed...
This paper proposes a new deep learning framework for the location of broken insulators (in particular self-blast glass insulator) in aerial images. We address problem low signal-noise-ratio (SNR) setting. deal with two modules: 1) object detection based on Faster R-CNN, and 2) classification pixels U-net. For first time, our combines above modules. combination is motivated as follows: R-CNN used to improve SNR, while U-net pixels. A diverse image set measured by power grid China tested...
NIK plays a crucial role in the noncanonical NF-κB signaling pathway associated with diverse inflammatory and autoimmune diseases. Our study presents compound 54, novel inhibitor, designed through structure-based scaffold-hopping approach from previously identified B022. Compound 54 demonstrates remarkable selectivity potency against both vitro vivo, effectively suppressing pro-inflammatory cytokines nitric oxide production. In mouse models, protected LPS-induced systemic sepsis, reducing...
In recent years, various virtual screening (VS) tools have been developed, and many successful campaigns showcased. However, whether by conventional molecular docking or pharmacophore screening, the selection of hits is based on ranking compounds scoring functions fit values, which remains bottleneck VS due to insufficient accuracy. As limitations individual methods persist, a comprehensive comparison integration different may provide insights into selecting suitable for VS. Here, we...
Kinase inhibitors are widely used in antitumor research, but there still many problems such as drug resistance and off-target toxicity. A more suitable solution is to design a multitarget inhibitor with certain selectivity. Herein, computational experimental studies were applied the discovery of dual against FGFR4 EGFR. quantitative structure–property relationship (QSPR) study was carried out predict EGFR activity data set consisting 843 5088 compounds, respectively. Four different machine...
Recently, there has been a growing interest in monitoring brain activity for individual recognition system. So far these works are mainly focussing on single channel data or fragment collected by some advanced modalities. In this study we propose new schemes based spatio-temporal resting state Electroencephalography (EEG) data. Besides, instead of using features derived from artificially-designed procedures, modified deep learning architectures which aim to automatically extract an...
Abstract Human ether‐a‐go‐go‐related gene (hERG) K+ channel blockage may cause severe cardiac side‐effects and has become a serious issue in safety evaluation of drug candidates. Therefore, improving the ability to avoid undesirable hERG activity early stage discovery is significant importance. The purpose this study was build predictive models by deep neural networks. For each combination sampling methods descriptors, networks with different architectures were implemented classification...
Abstract Data mining methods based on machine learning play an increasingly important role in drug design and discovery. In the current work, eight including decision trees, k‐Nearest neighbor, support vector machines, random forests, extremely randomized AdaBoost, gradient boosting XGBoost were evaluated comprehensively through a case study of ACC inhibitor data sets. Internal external sets employed for cross‐validation methods. Results showed that trees model performed best was adopted as...
Covalent drugs have attracted increasing attention in recent years due to good inhibitory activity and selectivity. Targeting noncatalytic cysteines with irreversible inhibitors is a powerful approach for enhancing pharmacological potency selectivity because can form covalent bonds through their nucleophilic thiol groups. However, most human kinases multiple within the active site; accurately predict which cysteine likely of great importance but remains challenge when designing inhibitors....
Abstract Background : Effective molecular feature representation is crucial for drug property prediction. Recent years have seen increased attention on graph neural networks (GNNs) that are pre‐trained using self‐supervised learning techniques, aiming to overcome the scarcity of labeled data in Traditional GNNs prediction typically perform a single masking operation nodes and edges input graph, only local information insufficient thorough training. Method Hence, we propose model based...
Abstract The emergence of autoimmune diseases represents a pressing concern, with NF‐κB assuming pivotal role as mediator immune regulation. It exerts substantial regulatory influence over both innate and adaptive immunity. NIK, an upstream protein NF‐κB2, triggers aberrant activation the non‐canonical signaling pathway upon overexpression, thereby influencing onset advancement various diseases. Consequently, exploring small molecule inhibitors aimed at NIK presents significant promise. This...
Destructive testing is a common method for obtaining tensile strength properties of welds. However, it inconvenient to characterize the overall weld, and cannot be applied in-service structures. Non-destructive evaluation (NDT&E) methods have potential ability overcoming these limitations. In this paper, an ultrasonic-based non-destructive evaluating weld was proposed. Multiple sets fully automatic welded X80 steel pipes were prepared. Acoustic signals from total 240 measurement points...
Enzyme inhibitors from natural products are becoming an attractive target for drug discovery and development; however, separating enzyme natural-product extracts is highly complex. In this study, we developed a strategy based on tyrosinase-site blocking ultrafiltration integrated with HPLC-QTOF-MS/MS optimized molecular docking to screen tyrosinase Puerariae lobatae Radix extract. Under parameters, previously used kojic acid, known inhibitor, block the active site in order eliminate...
A series of N-phenyl-7H-pyrrolo[2,3-d]pyrimidin-4-amine derivatives with NF-κB inducing kinase (NIK) inhibitory activity were obtained through structure-based drug design and synthetic chemistry. Among them, 4-(3-((7H-pyrrolo[2,3-d]pyrimidin-4-yl)amino)-4-morpholinophenyl)-2-(thiazol-2-yl)but-3-yn-2-ol (12f) was identified as a highly potent NIK inhibitor, along satisfactory selectivity. The pharmacokinetics 12f its ability to inhibit interleukin 6 secretion in BEAS-2B cells better than...
Rheumatoid arthritis (RA) is a chronic autoimmune disease, which compared to "immortal cancer" in industry. Currently, SYK, BTK, and JAK are the three major targets of protein tyrosine kinase for this disease. According existing research, marketed research drugs RA mostly based on single target, limits their efficacy. Therefore, designing multitarget or dual-target inhibitors provide new insights treatment regarding specific association between from two signal transduction pathways. In...