A5100765642- Computational Drug Discovery Methods
- Protein Structure and Dynamics
- Machine Learning in Materials Science
- Bioinformatics and Genomic Networks
- Functional Brain Connectivity Studies
- Rough Sets and Fuzzy Logic
- Chemical Synthesis and Analysis
- Distributed and Parallel Computing Systems
- T-cell and B-cell Immunology
- Microbial Fuel Cells and Bioremediation
- Image Processing Techniques and Applications
- Mobile Ad Hoc Networks
- Advanced Computational Techniques and Applications
- Advanced Image Processing Techniques
- Underwater Vehicles and Communication Systems
- Underwater Acoustics Research
- Cryptography and Data Security
- Cancer Immunotherapy and Biomarkers
- X-ray Diffraction in Crystallography
- Internet Traffic Analysis and Secure E-voting
- Neural dynamics and brain function
- Privacy-Preserving Technologies in Data
- Bluetooth and Wireless Communication Technologies
- Immune Cell Function and Interaction
- Image and Signal Denoising Methods
Northwestern Polytechnical University
2024-2025
Shanghai Institute of Materia Medica
2022-2024
University of Chinese Academy of Sciences
2009-2024
Chinese Academy of Sciences
2021-2024
Zhejiang University
2024
CAS Key Laboratory of Urban Pollutant Conversion
2021
Institute of Urban Environment
2021
Nanjing Audit University
2011
University of Ottawa
2003
In this paper we describe several new clustering algorithms for nodes in a mobile ad hoc network. We propose to combine two known approaches into single algorithm which considers connectivity as primary criterion and lower ID secondary selecting cluster heads. The goal is minimize the number of clusters, results dominating sets smaller sizes (this important applications broadcasting Bluetooth formation). also modifying structure presence topological changes. Next, generalize definition so...
Blood-brain barrier is a pivotal factor to be considered in the process of central nervous system (CNS) drug development, and it great significance rapidly explore blood-brain permeability (BBBp) compounds silico early discovery process. Here, we focus on whether how uncertainty estimation methods improve BBBp models. We briefly surveyed current state prediction deep learning models, curated an independent dataset determine reliability state-of-the-art algorithms. The results exhibit that,...
Abstract Structure-based lead optimization is an open challenge in drug discovery, which still largely driven by hypotheses and depends on the experience of medicinal chemists. Here we propose a pairwise binding comparison network (PBCNet) based physics-informed graph attention mechanism, specifically tailored for ranking relative affinity among congeneric ligands. Benchmarking two held-out sets (provided Schrödinger Merck) containing over 460 ligands 16 targets, PBCNet demonstrated...
ABSTRACT Super‐resolution can significantly enhance image visibility and restore features without requiring scanning devices to be updated. It is notably useful for magnetic resonance imaging (MRI), which suffers from low‐resolution issue. In practice, MR images possess more intricate texture details than natural images, leading the issue that existing super‐resolution algorithms struggle reach acceptable performance, particularly brain images. To this end, we propose a non‐local residual...
For resolving the problem that existing protocol of secure two-party vector dot product computation has low efficiency and may disclose privacy data, a method which is effective to find frequent item sets on vertically distributed data put forward. The uses semi-honest third party participate in calculation, converted parties calculate. results show compared original Vector algorithm, can obviously improve algorithm accuracy at precondition assured all parties.
Structure-based lead optimization is an open challenge in drug discovery, which still largely driven by hypotheses and depends on the experience of medicinal chemists. We here propose a pairwise binding comparison network (PBCNet) based physics-informed graph attention mechanism, specifically tailored for ranking relative affinity among congeneric ligands. Benchmarking two held-out sets (provided Schrödinger, Inc. Merck KGaA) containing over 460 ligands 16 targets, PBCNet demonstrated...
ABSTRACT Developing robust methods for evaluating protein-ligand interactions has been a long-standing problem. Here, we propose novel approach called EquiScore, which utilizes an equivariant heterogeneous graph neural network to integrate physical prior knowledge and characterize in geometric space. To improve generalization performance, constructed dataset PDBscreen designed multiple data augmentation strategies suitable training scoring methods. We also analyzed potential risks of leakage...
The latest advancements in nuclear medicine indicate that radioactive isotopes and associated metal chelators play crucial roles the diagnosis treatment of diseases. development mainly relies on traditional trial-and-error methods, lacking rational guidance design. In this study, we propose structure-aware transformer (SAT) combined with molecular fingerprint (SATCMF), a novel graph network framework incorporates prior chemical knowledge to construct coordination edges learns interactions...
Studying influential nodes (I-nodes) in brain networks is of great significance the field imaging. Most existing studies consider connectivity hubs as I-nodes. However, this approach relies heavily on prior knowledge from graph theory, which may overlook intrinsic characteristics network, especially when its architecture not fully understood. In contrast, self-supervised deep learning can learn meaningful representations directly data. This enables exploration I-nodes for networks, also...