A5054999570- Neural dynamics and brain function
- Genetics, Aging, and Longevity in Model Organisms
- Photoreceptor and optogenetics research
- Advanced Memory and Neural Computing
- Infrastructure Maintenance and Monitoring
- Advanced Neural Network Applications
- Advanced biosensing and bioanalysis techniques
- RNA Interference and Gene Delivery
- Image Processing Techniques and Applications
- Asphalt Pavement Performance Evaluation
- Industrial Technology and Control Systems
- Circadian rhythm and melatonin
- Muscle activation and electromyography studies
- Simulation and Modeling Applications
- Gene expression and cancer classification
- Advanced Algorithms and Applications
- Advanced Measurement and Detection Methods
- Domain Adaptation and Few-Shot Learning
- Single-cell and spatial transcriptomics
- Remote-Sensing Image Classification
- Prosthetics and Rehabilitation Robotics
- Stroke Rehabilitation and Recovery
- Optimal Power Flow Distribution
- RNA and protein synthesis mechanisms
- Adversarial Robustness in Machine Learning
University of Shanghai for Science and Technology
2022-2025
National University of Defense Technology
2013-2024
Shanghai Jiao Tong University
2014-2024
Tianjin Medical University
2024
Hunan University
2011-2024
Huaihua University
2024
Ministry of Education of the People's Republic of China
2017-2024
Anhui University
2023-2024
Beijing Institute of Technology
2024
Tongji University
2022-2024
Lysine lactylation (Kla) links metabolism and gene regulation plays a key role in multiple biological processes. However, the regulatory mechanism functional consequence of Kla remain to be explored. Here, we report that HBO1 functions as lysine lactyltransferase regulate transcription. We show catalyzes addition vitro intracellularly, E508 is site for activity HBO1. Quantitative proteomic analysis further reveals 95 endogenous sites targeted by HBO1, with majority located on histones. Using...
The coronavirus disease 2019 (COVID-19), as a severe respiratory disease, affects many parts of the body, and approximately 20-85% patients exhibit functional impairment senses smell taste, some whom even experience permanent loss these senses. These symptoms are not life-threatening but severely affect patients' quality life increase risk depression anxiety. pathological mechanisms have been fully identified. In current study, we aimed to identify important biomarkers at expression level...
This article presents a graph convolutional network model (GCNM) for gait phase classification to control lower limb exoskeleton. The GCNM can recognize four leg phases between the foot and ground, including heel strike, flat, off, swing. proposed solve problem from non-Euclidean domain based on mechanism exoskeletons. Real-time performance of data acquisition system was then verified quantifies time delay with an optoelectronic system, VICON BONITA 10. Comparison works some existing...
Recently, many deep learning methods have achieved great results in the field of automated pavement distress detection, but most them ignore other types distresses beyond cracks. This paper proposes an efficient framework for asphalt segmentation called network (PDSNet). PDSNet can effectively segment multiple distresses, including crack, pothole, raveling, patch, and sealed crack. It consists two parallel feature extraction branches. One is P branch to extract prior global information. The...
Small-molecule fluorescent probes have emerged as potential tools for cancer cell imaging-based diagnostic and therapeutic applications, but their limited selectivity poor imaging contrast hinder broad applications. To address these problems, we present the design construction of a novel near-infrared (NIR) biotin-conjugated viscosity-activatable probe, named QL-VB, selective recognition cells. The designed probe exhibited NIR emission at 680 nm, with substantial Stokes shift 100 nm...
Human–robot interaction (HRI) is a key technology in the field of humanoid robotics, and motion imitation one most direct ways to achieve efficient HRI. However, due significant differences structure, range motion, joint torques between human body robots, remains challenging task. Traditional retargeting algorithms, while effective mapping typically either ensure similarity arm configuration (joint space-based) or focus solely on tracking end-effector position (Cartesian space-based). This...
The existence of redundant video frames results in a substantial waste computational resources during video-understanding tasks. Frame sampling is crucial technique improving resource utilization. However, existing strategies typically adopt fixed-frame selection, which lacks flexibility handling different action categories. In this paper, inspired by the neural mechanism human visual pathway, we propose an effective and interpretable frame-sampling method called Entropy-Guided Motion...
Antibody-mediated immune responses play a crucial role in the defense of human body. The evolution bioengineering has led progress antibody-derived drugs, showing promising efficacy cancer and autoimmune disease therapy. A critical step this development process is obtaining affinity between antibodies their binding antigens.In study, we introduce novel sequence-based antigen-antibody prediction method, named DG-Affinity. DG-Affinity uses deep neural networks to efficiently accurately predict...
Recently, character model based on integrated convolutional neural network (CNN) and deep bidirectional long short-term memory (DBLSTM) has achieved excellent performance for offline handwriting recognition (HWR). To deploy CNN-DBLSTM in products, it is necessary to reduce the footprint runtime latency as much possible. In this paper, we study two methods compress CNN part: (1) Use Tucker decomposition decompose pre-trained weights with low-rank approximation, followed by fine-tuning; (2)...
Utilizing LIBS and four machine learning methods in conjunction with a voting classifier, accurate classification results could be achieved. This approach effectively improves balances the accuracy rates for each origin.
Glioblastoma (GBM) is the most common and lethal primary brain tumor characterized by extensive vascularization. Anti-angiogenic therapy for this cancer offers possibility of universal efficacy. However, preclinical clinical studies suggest that anti-VEGF drugs, such as Bevacizumab, actively promote invasion, which ultimately leads to a therapy-resistant recurrent phenotype GBMs. Whether Bevacizumab can improve survival over chemotherapy alone remains debated. Herein, we emphasize importance...
Lipid nanoparticles (LNPs) are nanocarriers composed of four lipid components and can be used for gene therapy, protein replacement as well vaccine development. However, LNPs also face several challenges, such toxicity, immune activation, low delivery efficiency. To overcome these artificial intelligence (AI) to optimize the design formulation LNPs, predict their properties performance. Moreover, antibody targeted conjugation enhance specificity selectivity by attaching an that recognizes a...
As a sophisticated computing unit, the pyramidal neuron requires sufficient metabolic energy to fuel its powerful computational capabilities. However, majority of previous works focus on nonlinear integration and consumption in individual neurons but seldom effects synaptic transmission dendritic integration. Here, we developed biologically plausible models simulate neurons, exploring relations between energy. We find that not only drives vesicle cycle, also participates regulation this...
It is important to improve the forecasting performance of rainfall-runoff models due high complexity basin response and frequent data limitations. Recently, many studies have been carried out based on deep learning achieved significant improvements. However, their intrinsic characteristics remain unclear not explored. In this paper, we pioneered exploitation short lag-times in modeling measured its influence model performance. The proposed model, long short-term memory with attentive...
In its long service life, bridge structure will inevitably deteriorate due to coupling effects; thus, maintenance has become a research hotspot. The existing algorithms are mostly based on linear programming and dynamic programming, which have low efficiency high economic cost cannot meet the actual needs of maintenance. this paper, multi-agent reinforcement learning framework was proposed predict deterioration process reasonably achieve optimal policy. Using regression-based optimization...