Results 31 to 40 of about 176 (168)
Advanced Science, EarlyView.STransformer is a unified deep learning framework designed to seamlessly accommodate a comprehensive landscape of spatial data. By simultaneously capturing short‐range cellular interactions and tissue‐wide semantic patterns, it extracts robust representations to accurately dissect complex tissue heterogeneity.
Xingyi Li +9 more
wiley +1 more source
CauFinder: Steering Cell‐State and Phenotype Transitions by Causal Disentanglement Learning
Advanced Science, EarlyView.CauFinder combines causal disentanglement modeling and network control to prioritize causal drivers of cell‐state transitions from observational transcriptomic data. The framework separates transition‐relevant signals from spurious associations, nominates intervention targets across biological and disease contexts, and identifies DAAM1 as an actionable
Chengming Zhang +11 more
wiley +1 more source
Advanced Science, EarlyView.Both SVF and CD31+ SVF improve spontaneous osteoarthritis, but CD31+ enrichment refines the therapeutic profile rather than broadly enhancing all effects. More distinct benefits are observed in extracellular matrix remodeling, osteochondral integrity, and subchondral/trabecular bone preservation, supporting CD31+‐enriched SVF as a biologically enhanced
Sijia Zhou +16 more
wiley +1 more source
Ovarian Cancer Diagnosis and Chemoresistance Prediction Model Based on cfRNA Molecular Signature
Advanced Science, EarlyView.A deep learning model analyzes cfRNA profiles extracted from the blood of OVCA patients. This innovative approach distinguishes OVCA from healthy controls with high accuracy. Crucially, it reliably predicts patient response to chemotherapy (sensitive versus resistant subgroups).
Qinhao Guo +14 more
wiley +1 more source
Machine‐Learning Framework for Designing Stable Interfaces in All‐Solid‐State Lithium‐Ion Batteries
Advanced Science, EarlyView.A data‐driven strategy is developed to discover coating materials for all‐solid‐state lithium batteries. Using calculations of interfacial reactivity, unsupervised pattern recognition, and machine‐learning prediction, the study identifies low‐reactivity compositional patterns and screens new lithium‐based oxide and polyanion candidates, extending ...
Sehyeok Park +4 more
wiley +1 more source
Advanced Science, EarlyView.Large‐scale UK Biobank analyses identify clinical and proteomic signatures for early prediction of valvular heart disease and its subtypes. Proteins add predictive value for VHD, AVS, and MVR, with outcome‐specific compact panels showing translational potential. Multi‐layer evidence highlights matrix remodeling, protease regulation, immune inflammation,
Zhihao Jiang +10 more
wiley +1 more source
A Generative Neuro‐Symbolic AI for Protein Sequence Design
Advanced Science, EarlyView.We introduce EffieDes, a neuro‐symbolic framework coupling deep learning‐based fitness landscape parameterization with exact automated reasoning. Unlike greedy sampling, EffieDes identifies sequences that globally optimize fitness while satisfying intricate design constraints.
Marianne Defresne +12 more
wiley +1 more source
StackingNet: Collective Inference Across Independent AI Foundation Models
Advanced Science, EarlyView.ABSTRACT Artificial intelligence (AI) built on large foundation models has transformed language understanding, computer vision, and reasoning, yet these systems remain isolated and cannot readily share their capabilities. Coordinating the complementary strengths of independently developed, black‐box foundation models is essential for trustworthy ...
Siyang Li +4 more
wiley +1 more source
Automation and Active Learning for the Multi‐Objective Optimization of Antibody Formulations
Advanced Science, EarlyView.Successful antibody formulation necessitates balancing factors such as thermal stability, colloidal stability, and viscosity across a vast excipient design space. This work integrates robotic liquid handling, high‐throughput biophysical characterization, and multi‐objective Bayesian optimization in an iterative closed‐loop Design‐Build‐Test‐Learn cycle.
D. Christopher Radford +3 more
wiley +1 more source
Advanced Science, EarlyView.DDSurfer reconstructs cortical surfaces directly from diffusion MRI without requiring T1‐weighted scans. By fusing complementary microstructural features and learning diffeomorphic deformations, it efficiently generates accurate white matter and pial surfaces, improving geometric fidelity and morphometric reliability across datasets for robust surface ...
Chengjin Li +10 more
wiley +1 more source