Results 61 to 70 of about 244 (231)
MolDBG is a site‐aware, sequence‐only framework that unifies drug‐target affinity prediction, binding‐site identification, and affinity‐conditioned molecular generation for structured proteins. Guided by multi‐task binding‐site supervision, it aligns interaction‐critical residues before learning drug‐target representations and simultaneously infers ...
Gang Luo +6 more
wiley +1 more source
A novel targeted and pH‐responsive MRI contrast agent was integrated with a 3D nnU‐Net deep learning framework to enable accurate delineation of tumor boundary morphology in HER2‐positive breast cancer imaging. ABSTRACT Breast cancer continues to be a leading cause of cancer‐related mortality in women globally, where precise diagnosis and clear tumor ...
Jiaying Zheng +7 more
wiley +1 more source
Mechanically Reprogrammed Coaxial Fibers for Multiphysics Transduction and Human‐Machine Interfaces
A continuously wet‐spun coaxial fiber is developed to combine stretchable conductivity, resistive sensing, and self‐powered triboelectric sensing in a single architecture. A mechanically reprogrammed dual‐network sheath stabilizes large deformation and improves signal reliability. These fibers can be woven into textile interfaces for multichannel touch
Xinyi Cao +6 more
wiley +1 more source
Multi‐Modal Low‐Power Adaptive Braille Recognition System Based on Hf0.3Zr0.7O2 Memristor
A multimodal adaptive perception system based on HZO ferroelectric memristor realizes efficient Braille digit recognition via reservoir computing. It delivers high recognition accuracy with ultralow‑energy analog computation, offering a promising hardware solution for environment‑robust neuromorphic assistive devices for visually impaired users ...
Jikang Xu +9 more
wiley +1 more source
Towards a Compositional Framework for Describing Human Phenotypes
The Phenotype Assembly Method (PhenoAM) decomposes phenotype variables into measurable Features and typed Qualifiers, enabling standardized, machine‐readable Phenome Data Elements (PhenoDEs) that preserve measurement context. Applied in the International Human Phenome Project (IHPP), the framework yields 58 371 PhenoDEs and supports component‐level ...
Wanting Hu +11 more
wiley +1 more source
MAPA transforms complex multi‐omics data into biologically coherent functional modules by integrating pathway information with molecular interaction networks. Retrieval‐augmented large language models then generate structured, literature‐informed interpretations.
Yifei Ge +13 more
wiley +1 more source
Essentially Contested Concepts and Semantic Externalism [PDF]
Abstract In 1956, W.B. Gallie introduced his idea of essentially contested concepts. In my paper, I offer a novel interpretation of his theory and argue that his theory, thus interpreted, is correct. The key to my interpretation lies in a condition Gallie places on essentially contested concepts that other interpreters downplay or dismiss: that the ...
openaire +1 more source
DeepLNM: A Multimodal Model for Predicting Lymph Node Metastasis in Colorectal Cancer
Traditional diagnosis may miss positive LNM cases, and pathologists face a workload; therefore, we develop DeepLNM, a multimodal model that predicts lymph node metastasis in colorectal cancer from H&E WSIs, CT images, and text. DeepLNM is robust across internal, external, and prospective cohorts and, in a user study, improves diagnostic accuracy while ...
Zhengyu Zhang +24 more
wiley +1 more source
A Facial Foundation Model for Clinical Biomarker Prediction and Real‐World Mobile Deployment
MedicalFaceFound is a facial foundation model developed through three‐stage progressive pre‐training, adapting representations from general vision to facial structure and clinical phenotypes. Using a single facial image, it estimates 62 biomarkers across multiple physiological systems and supports downstream risk prediction for cardiovascular ...
Tingfeng Xu +15 more
wiley +1 more source
Disentangling Heterogeneous Molecular Networks for Multi‐Omics‐Driven Cancer Driver Discovery
DRIVE integrates PPI topology and pan‐cancer multi‐omics profiles through dual‐view graph disentanglement, contrastive representation learning, and joint optimization. Across six PPI networks, DRIVE outperforms ten baselines and remains robust to structural and annotation perturbations.
Xinjing Gong +8 more
wiley +1 more source

