Results 131 to 140 of about 214,409 (272)

Long‐Tea‐CLIP: An Expert‐Level Multimodal AI Framework for Fine‐Grained Green Tea Grading Across Five Sensory Dimensions

Advanced Science, EarlyView.
Long‐Tea‐CLIP (Contrastive Language‐Image Pre‐training) presents a multimodal AI framework that integrates visual, metabolomic, and sensory knowledge to grade green tea across appearance, soup color, aroma, taste, and infused leaf. By combining expert‐guided modeling with CLIP‐supervised learning, the system delivers fine‐grained quality evaluation and
Yanqun Xu, Zhengfang Xue, Qing Luo, Xu Liu, Yongquan Xu, Huang Jing, Xingcai Zhang, Xinyuan Zhang, Zhonghua Liu, Zisheng Luo   +9 more
wiley   +1 more source

Genetic Diagnosis and Discovery Enabled by Large Language Models

Advanced Science, EarlyView.
We demonstrate that large language models (LLMs) can facilitate genetic diagnosis and discovery. LLMs were used to solve four types of genetic problems of sequentially increased complexity. An LLM‐based pipeline could analyze genetic variants in the genomic sequences of human hearing loss or rare genetic disease patients and assist in identifying ...
Tao Tu, Khaled Saab, Weida Liu, Zhouqing Fang, Zhuanfen Cheng, Svetolik Spasic, Maja Djurisic, Hiroaki Mohri, Wenlong Ren, Anil Palepu, Juraj Gottweis, Alan Karthikesalingam, Kavita Kulkarni, Annalisa Pawlosky, Devon Bonner, Elijah Kravets, Shruti Marwaha, Hector R. Mendez, Matthew T. Wheeler, Jonathan A. Bernstein, Undiagnosed Diseases Network, Cheng‐Yu Tsai, Chen‐Chi Wu, Konstantina M. Stankovic, Vivek Natarajan, Gary Peltz   +25 more
wiley   +1 more source

Encoding Cumulation to Learn Perturbative Nonlinear Oscillatory Dynamics

Advanced Science, EarlyView.
Weak nonlinearities critically shape the long term behavior of oscillatory systems but are difficult to identify from data. A data‐driven framework is introduced to infer governing equations of weakly nonlinear oscillators from sparse and noisy observations.
Teng Ma, Ting‐Ting Gao, Wei Cui, Attilio Frangi, Gang Yan, Lin Zhao   +5 more
wiley   +1 more source

Neural Fields for Highly Accelerated 2D Cine Phase Contrast MRI

Advanced Science, EarlyView.
ABSTRACT 2D cine phase contrast (CPC) MRI provides quantitative information on blood velocity and flow within the human vasculature. However, data acquisition is time‐consuming, motivating the reconstruction of the velocity field from undersampled measurements to reduce scan times. In this work, neural fields are proposed as a continuous spatiotemporal
Pablo Arratia, Martin J. Graves, Mary McLean, Carolin Pirkl, Carola‐Bibiane Schönlieb, Timo Schirmer, Florian Wiesinger, Matthias J. Ehrhardt   +7 more
wiley   +1 more source

ZBTB21 Is a Dual Suppressor of Pyroptosis and MHC‐I Antigen Presentation That Promotes Tumor Immune Evasion

Advanced Science, EarlyView.
ZBTB21 is a transcription factor that epigenetically suppresses pyroptosis and MHC‐I antigen presentation, enabling tumor immune evasion. Genetic ablation of ZBTB21 activates pyroptotic cell death and enhances antigen presentation, recruiting CD8+ T cells to overcome immune checkpoint blockade resistance.
Lei Zhao, Linlin Sheng, Jianhao Qiu, Junjie Ma, Kai Jin, Binggong Zhao, Tianrun Miao, Jing Chen, Yehong Li, Zhan Zhang, Dongfeng Sun, Yongmeng Li, Hui Tian   +12 more
wiley   +1 more source

Multimodal Cross‐Attentive Graph‐Based Framework for Predicting In Vivo Endocrine Disruptors

Advanced Science, EarlyView.
A multimodal cross‐attentive graph neural network integrates molecular graphs with androgen and estrogen adverse outcome pathway (AOP)–anchored in vitro assay signals to predict in vivo endocrine disruption. By fusing information on Tier‐1 AOP logits with chemical structures, the framework achieves high accuracy and provides assay‐traceable ...
Eder Soares de Almeida Santos, Gustavo Felizardo Santos Sandes, Artur Christian Garcia da Silva, Holli‐Joi Martin, Eugene N. Muratov, Rodolpho de Campos Braga, Bruno Junior Neves   +6 more
wiley   +1 more source

Learnable Diffusion Framework for Mouse V1 Neural Decoding

Advanced Science, EarlyView.
We introduce Sensorium‐Viz, a diffusion‐based framework for reconstructing high‐fidelity visual stimuli from mouse primary visual cortex activity. By integrating a novel spatial embedding module with a Diffusion Transformer (DiT) and a synthetic‐response augmentation strategy, our model outperforms state‐of‐the‐art fMRI‐based baselines, enabling robust
Kaiwen Deng, Peter S. Schwendeman, Yuanfang Guan   +2 more
wiley   +1 more source

Genetic Control of Tissue Remodeling by a Non‐Coding SNP in ITGA8 Explains Carotenoid‐Based Color Polymorphism in Marine Mollusks

Advanced Science, EarlyView.
In this study, the orange‐muscle giant abalone (Haliotis gigantea) is used as a model to identify a non‐coding SNP that disrupts the interaction between ITGA8 pre‐mRNA and the splicing factor ILF2, leading to altered ITGA8 splicing. These splicing changes promote carotenoid accumulation in abalone muscle through the regulation of tissue remodeling ...
Xiaohui Wei, Wenzhu Peng, Zekun Huang, Bingye Yang, Yiyu Wu, Minzhen Han, Yi Wang, Bingling Peng, Guosheng Hu, Jiawei Hong, Guijia Liu, Linwei Nie, Yang Gan, Miaoqin Huang, Xuan Luo, Weiwei You, Wen Liu, Caihuan Ke   +17 more
wiley   +1 more source

A Guide for Spatial Omics Technologies: Innovation, Evaluation, and Application

Advanced Science, EarlyView.
This review presents a strategy‐centric framework for spatial omics technologies, organizing methods by how spatial information is experimentally encoded. It compares key performance trade‐offs across sequencing‐ and imaging‐based approaches, examines computational and practical limitations, and highlights biomedical applications. The analysis provides
Xiaofeng Wu, Weize Xu, Da Lin, Leqiang Sun, Jinxia Dai, Gang Cao   +5 more
wiley   +1 more source

Machine Learning‐Guided Engineering of Protein Phase Separation Properties in Immune Regulation

Advanced Science, EarlyView.
PScalpel, a machine learning model integrating protein structure extraction, graph contrastive learning, and a genetic algorithm, guides the engineering of protein phase separation ability. It adopts transfer learning methods to provide predictive recommendations for protein phase separation ability changes through single amino acid mutations in a ...
Chenqiu Zhang, Jia Wang, Zhe Wang, Liyan Zhu, Sihui Cai, Luzhi Zhan, Haorui Liang, Yaoxing Wu, Jianqiang Li, Jun Cui   +9 more
wiley   +1 more source