Interpretable PROTAC Degradation Prediction With Structure‐Informed Deep Ternary Attention Framework
Advanced Science, EarlyView.PROTAC‐STAN, a structure‐informed deep learning framework is presented for interpretable PROTAC degradation prediction. By modeling molecular hierarchies and protein structures, and simulating ternary interactions via a novel attention network, PROTAC‐STAN achieves significant performance gains over baselines.
Zhenglu Chen +11 more
wiley +1 more source
Hyperbolic multi-channel hypergraph convolutional neural network based on multilayer hypergraph. [PDF]
Sci RepBai L, Hu F, Tang C, Mei Z, Liu C.
europepmc +1 more source
Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling
, 2015 Takayoshi Yamashita +4 more
openalex +2 more sources
STEMDiff: A Wavelet‐Enhanced Diffusion Model for Physics‐Informed STEM Image Generation
Advanced Science, EarlyView.STEMDiff, which is a conditional diffusion model that generates realistic STEM images from crystal structure‐derived binary labels, is proposed, overcoming high‐frequency bias via a Discrete Wavelet Transform‐based architecture. It produces experimentally indistinguishable images, enabling annotation‐free training of networks for precise atomic ...
Yihui Bao +4 more
wiley +1 more source
Detection of fasting blood sugar using a microwave sensor and convolutional neural network. [PDF]
Sci RepSattari MA, Hayati M.
europepmc +1 more source
Multiscale Cell–Cell Interactive Spatial Transcriptomics Analysis
Advanced Science, EarlyView.In this study, we present the MultiScale Cell‐Cell Interactive Spatial Transcriptomics Analysis method, which unites the strengths of spatially resolved deep learning techniques with a topological representation of multi‐scale cell‐cell similarity relations.
Sean Cottrell, Guo‐Wei Wei
wiley +1 more source
BlendNet: a blending-based convolutional neural network for effective deep learning of electrocardiogram signals. [PDF]
Front Artif IntellPremanand S, Narayanan S.
europepmc +1 more source
Learning to Answer Questions From Image Using Convolutional Neural Network
, 2015 Lin Ma, Zhengdong Lu, Hang Li
openalex +2 more sources
Advanced Science, EarlyView.A prior knowledge‐guided diffusion model augmented by physics‐constrained active learning is developed to design high‐asymmetry terahertz metamaterials. Trained on only a small set of classical structures, the model efficiently generates new high‐metrics designs.
Qiqi Dai +7 more
wiley +1 more source
A Large Kernel Convolutional Neural Network with a Noise Transfer Mechanism for Real-Time Semantic Segmentation. [PDF]
Sensors (Basel)Liu J, Du Y, Wang J, Tang X.
europepmc +1 more source