A5009087852- Microbial Metabolic Engineering and Bioproduction
- Image Retrieval and Classification Techniques
- Face recognition and analysis
- Handwritten Text Recognition Techniques
- RNA and protein synthesis mechanisms
- Thermography and Photoacoustic Techniques
- Video Surveillance and Tracking Methods
- SARS-CoV-2 and COVID-19 Research
- Image Processing and 3D Reconstruction
- Protein Structure and Dynamics
- Gene Regulatory Network Analysis
- Domain Adaptation and Few-Shot Learning
- Virology and Viral Diseases
- Gas Sensing Nanomaterials and Sensors
- vaccines and immunoinformatics approaches
- Remote Sensing and LiDAR Applications
- Computational Drug Discovery Methods
- Automated Road and Building Extraction
- Enzyme Catalysis and Immobilization
- Generative Adversarial Networks and Image Synthesis
- Welding Techniques and Residual Stresses
- Monoclonal and Polyclonal Antibodies Research
- Bacteriophages and microbial interactions
Peng Cheng Laboratory
2025
Peking University
2024
Tianjin University
2024
Shanghai Jiao Tong University
2005-2023
This paper presents a method to extract buildings in monocular urban aerial images without prior knowledge of illumination. With building concept model interpret at different levels and scales, extraction is carried out two stages: sunshine parts self‐shadow extraction. Based on region‐oriented radiometric features, are first simplified segmented into three parts: high objects, shadow regions ground. To verify initial segmentations, estimating the direction cast was proposed by context...
Face identity editing (FIE) shows great value in AI content creation. Low-resolution FIE approaches have achieved tremendous progress, but high-quality struggles. Two major challenges hinder higher-resolution and higher-performance development of FIE: lack high-resolution dataset unacceptable complexity forbidding for mobile platforms. To address both issues, we establish a novel large-scale, tailored FIE. Based on our SimSwap (Chen et al. 2020), propose an upgraded version named SimSwap++...
Abstract With the application of personalized and precision medicine, more precise efficient antibody drug development technology is urgently needed. Identification antibody-antigen interactions crucial to engineering. The time-consuming expensive nature wet-lab experiments calls for computational methods. Taking into account non-overlapping advantage current structure-dependent sequence-only methods, we propose an interpretable interaction prediction method, S3AI. introduction structural...
Abstract Protein stability offers valuable insights into protein folding and functionality, making it an integral component of evolutionary fitness. Previous computational methods possess both strengths weaknesses, leading to practical inter-pretational limitations. Here, we propose interpretable change prediction method, S3C, anchor fitness for with virtual chemical environment recovery. S3C first gets rid the shackles high-resolution structure data restores local environments mutations at...
<title>Abstract</title> Understanding and modeling enzyme-substrate interactions is crucial for designing enzymes with tailored functions, thereby advancing the field of enzyme engineering. The diversity downstream tasks related to catalysis calls a computational architecture that actively perceives interaction patterns make unified predictions multiple objectives. Here, we introduce MESI, progressive conditional deep learning framework multi-purpose prediction. By decomposing into two-stage...