Results 131 to 140 of about 26,730,494 (257)
Predicting Enzyme Turnover Numbers and Enabling Rational Enzyme Evolution
MCKcat, a deep learning framework combining multi‐scale convolution and cross‐attention, accurately predicts enzyme turnover number (kcat) by fusing sequence and reaction representations. It couples with rational design in a two‐step strategy for Bacillus aryabhattai laccase engineering, achieving a 75% positive rate with synergistically enhanced ...
Fengya Ge +6 more
wiley +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
DUET‐seq is an open‐source droplet platform that jointly profiles chromatin accessibility and gene expression from the same nucleus. Dissolvable dual‐linker hydrogel beads and a one‐step intra‐droplet RT‐PCR co‐index both modalities in under 12 h at roughly $0.04 per cell.
Dong Cheng +16 more
wiley +1 more source
qcGEM: A Graph‐Based Molecular Representation With Quantum Chemistry Awareness
In this work, we introduce qcGEM, a quantum‐chemistry‐aware graph‐based embedding of molecules that incorporates physical priors into molecular representation learning. Through a specially designed model architecture to adequately process quantum chemistry information as well as three‐dimensional molecular geometry, qcGEM provides a compact, physics ...
Haoyu Wang +3 more
wiley +1 more source
Large language models serve as representation generators for gradient‐free scientific optimization. Two complementary approaches produce executable battery‐charging policies either directly or through LLM‐designed neural representations coupled to Bayesian optimization.
Ge Lei +3 more
wiley +1 more source
DAIMS is a multimodal model for treatment stratified risk and survival assessment in colorectal cancer. Training draws on pathology, genomics, and clinical reports, yet inference requires only whole slide images, and adaptation to new cohorts proceeds without target survival outcomes.
Chuangjie Cao +15 more
wiley +1 more source
An Expertise Transfer Framework For Autonomous Surgical Assistance
This study introduces an expertise transfer framework for procedure‐spanning autonomous surgical assistance. By emulating expert logic through hierarchical perception, attention modeling, and knowledge graph‐based decision‐making, the system provides near‐expert surgical view assistance.
Yuan Gao +12 more
wiley +1 more source

