A5091294648- Computational Drug Discovery Methods
- Medical Imaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Biomedical Text Mining and Ontologies
- Higher Education and Teaching Methods
- Traditional Chinese Medicine Studies
- Machine Learning in Materials Science
- Human Pose and Action Recognition
- vaccines and immunoinformatics approaches
- Housing Market and Economics
- Cardiac Imaging and Diagnostics
- Protein Structure and Dynamics
- Advanced Text Analysis Techniques
- Bioinformatics and Genomic Networks
- Power Systems and Technologies
- Financial Risk and Volatility Modeling
- Educational Technology and Pedagogy
- Environmental and Agricultural Sciences
- CRISPR and Genetic Engineering
- Insurance and Financial Risk Management
- Innovative Educational Techniques
- Hand Gesture Recognition Systems
- Advanced Measurement and Detection Methods
- Power Systems and Renewable Energy
- Cell Image Analysis Techniques
Zhejiang University
2020-2025
Tongji University
2024-2025
Fudan University
1994-2025
Nankai University
2011-2024
Zhejiang Lab
2020-2024
State Key Laboratory of Industrial Control Technology
2024
Wenzhou University
2024
Wenzhou University of Technology
2024
Shanghai Institute of Optics and Fine Mechanics
2010-2024
China Southern Power Grid (China)
2024
Prediction of drug-target interactions (DTI) plays a vital role in drug development various areas, such as virtual screening, repurposing and identification potential side effects. Despite extensive efforts have been invested perfecting DTI prediction, existing methods still suffer from the high sparsity datasets cold start problem. Here, we develop KGE_NFM, unified framework for prediction by combining knowledge graph (KG) recommendation system. This firstly learns low-dimensional...
Abstract Monoclonal antibodies represent important weapons in our arsenal to against the COVID-19 pandemic. However, this potential is severely limited by time-consuming process of developing effective and relative high cost manufacturing. Herein, we present a rapid cost-effective lipid nanoparticle (LNP) encapsulated-mRNA platform for vivo delivery SARS-CoV-2 neutralization antibodies. Two mRNAs encoding light heavy chains potent neutralizing antibody HB27, which currently being evaluated...
Artificial intelligence (AI)-aided drug design has demonstrated unprecedented effects on modern discovery, but there is still an urgent need for user-friendly interfaces that bridge the gap between these sophisticated tools and scientists, particularly those who are less computer savvy. Herein, we present DrugFlow, AI-driven one-stop platform offers a clean, convenient, cloud-based interface to streamline early discovery workflows. By seamlessly integrating range of innovative AI algorithms,...
Abstract Hyperspectral imaging technology is playing an increasingly important role in the fields of food analysis, medicine and biotechnology. To improve speed operation increase light throughput a compact equipment structure, Fourier transform hyperspectral system based on single-pixel technique proposed this study. Compared with current spectrometry approaches, has wider spectral range (400–1100 nm), better resolution (1 nm) requires fewer measurement data (a sample rate 6.25%). The...
Deep learning (DL)-driven efficient synthesis planning may profoundly transform the paradigm for designing novel pharmaceuticals and materials. However, progress of many DL-assisted (DASP) algorithms has suffered from lack reliable automated pathway evaluation tools. As a critical metric evaluating chemical reactions, accurate prediction reaction yields helps improve practicality DASP in real-world scenarios. Currently, accurately predicting interesting reactions still faces numerous...
Analyzing drug-related interactions in the field of biomedicine has been a critical aspect drug discovery and development. While various artificial intelligence (AI)-based tools have proposed to analyze biomedical associations (DBAs), their feature encoding did not adequately account for crucial functions semantic concepts, thereby still hindering progress. Since advent ChatGPT by OpenAI 2022, large language models (LLMs) demonstrated rapid growth significant success across applications....
Abstract Integrating single‐cell datasets from multiple studies provides a cost‐effective way to build comprehensive cell atlases, granting deeper insights into cellular characteristics across diverse biological systems. However, current data integration methods struggle with interference in partially overlapping and varying annotation granularities. Here, multiselective adversarial network is introduced for the first time present UniMap, which functions as “discerner” identify exclude...
Discovering therapeutic molecules requires the integration of both phenotype-based drug discovery (PDD) and target-based (TDD). However, this remains challenging due to inherent heterogeneity, noise, bias present in biomedical data. In study, Knowledge-Guided Drug Relational Predictor (KGDRP), a graph representation learning approach is developed that effectively integrates multimodal data, including network data containing biological system information, gene expression sequence incorporates...
Selective drug delivery to podocytes remains a challenge. Aptamers, nucleic acids that bind specific cells, offer potential solution, though podocyte-targeting aptamers have not yet been developed. Podocytes stimulated with adriamycin, puromycin aminonucleoside, and high glucose are used screen an single-stranded DNA (ssDNA) library (10¹⁵ sequences). High-throughput sequencing identifies nucleotide sequences, the aptamer's affinity, stability, cytotoxicity, uptake, biodistribution...
Tuberculosis (TB) is an infectious disease caused by Mycobacterium tuberculosis (Mtb) and it has been one of the top 10 causes death globally. Drug-resistant (XDR-TB), extensively resistant to commonly used first-line drugs, emerged as a major challenge TB treatment. Hence, quite necessary discover novel drug candidates for In this study, based on different types molecular representations, four machine learning (ML) algorithms, including support vector machine, random forest (RF), extreme...
Abstract Target identification for bioactive molecules augments modern drug discovery efforts in a range of applications, from the elaboration mode‐of‐action drugs to repurposing even knowledge side‐effects and further optimization. However, traditional labor‐intensive time‐consuming experiment methods obstructed development. Driven by massive bioactivity data deposited chemogenomic databases, computational alternatives have been proposed widely developed expedite validation process. By...
Abstract Machine learning-based scoring functions (MLSFs) have shown potential for improving virtual screening capabilities over classical (SFs). Due to the high computational cost in process of feature generation, numbers descriptors used MLSFs and characterization protein–ligand interactions are always limited, which may affect overall accuracy efficiency. Here, we propose a new SF called TB-IECS (theory-based interaction energy component score), combines terms from Smina NNScore version...
Target detection is significant in many fields, including oceanic security, marine ecology, etc. In this paper, phase sensitive optical time domain reflectometry (Φ-OTDR) introduced for the non-cooperative ship detection, with large-scale diversity technology and suspended sensitized cable. outfield experiments, ship’s voiceprint information obtained high fidelity, power spectrum analyzed, over-top achieved. Moreover, an array orientation method based on adaptive difference correction (APDC)...
Cardiac MRI performed while the patient is breathing typically achieved using non-real-time techniques such as ECG triggering with respiratory gating; however, modern dynamic imaging are beginning to enable this type of in real-time. One these based on forming a Partially Separable Function (PSF) model data, but fitting process known be sensitive even when truncated SVD regularization used. As result, physiologically meaningless artifacts can appear images total number measurements limited....
Acquisition of spacers confers the CRISPR-Cas system with memory to defend against invading mobile genetic elements. We previously reported that CRISPR-associated factor Csa3a triggers CRISPR adaptation in Sulfolobus islandicus. However, a feedback regulation remains unclear. Here we show another factor, Csa3b, binds cyclic oligoadenylate (cOA) analog (5'-CAAAA-3') and mutation at its CARF domain, which reduces binding affinity. Csa3b also promoter cas genes, cOA enhances their probably by...
A spectral single-pixel imaging system facilitates effective image compression, but the region is limited by its single detector. This paper presents a hyperspectral camera that allows extended-field coverage to be collected one Compressive data of large field view achieved our highly sensitive detection camera, which can extended near-infrared or infrared monitoring. We acquire datacube 256×256 spatial pixels and 3 nm resolution at sampling rate 25%. Finally, we apply monitoring fruit...
Abstract The study aims to alleviate the pressure of operation and maintenance primary secondary power equipment improve work efficiency personnel. It explores early elimination safety hazards in hopes ensure safe grid. This article designs a remote master station architecture for equipment, through specialized communication protocols file transmission methods. summarizes data station. is then analyzed processed. personnel with are promptly notified. Further, distinguishes whether faulty...
Abstract The optimization of therapeutic antibodies through traditional techniques, such as candidate screening via hybridoma or phage display, is resource-intensive and time-consuming. In recent years, computational artificial intelligence-based methods have been actively developed to accelerate improve the development antibodies. this study, we an end-to-end sequence-based deep learning model, termed AttABseq, for predictions antigen–antibody binding affinity changes connected with...
Emerging studies underscore the promising capabilities of large language model-based chatbots in conducting fundamental bioinformatics data analyses. The recent feature accepting image-inputs by ChatGPT motivated us to explore its efficacy deciphering illustrations. Our evaluation with examples cancer research, including sequencing analysis, multimodal network-based drug repositioning, and tumor clonal evolution, revealed that can proficiently explain different plot types apply biological...
<abstract> <p>In traditional Chinese medicine (TCM), artificial intelligence (AI)-assisted syndrome differentiation and disease diagnoses primarily confront the challenges of accurate symptom identification classification. This study introduces a multi-label entity extraction model grounded in TCM ontology, specifically designed to address limitations existing recognition models characterized by limited label spaces an insufficient integration domain knowledge. synergizes...