Results 121 to 130 of about 1,129,461 (196)

CoSP: Reconfigurable Metamaterial Inverse Design via Contrastive Pretrained Large Language Model

Advanced Science, EarlyView.
In this work, CoSP (contrastive multi‐state pretrain), an intelligent inverse design method for reconfigurable metamaterials based on a contrastive pretrained large language model, is proposed. Numerical experiments demonstrate that CoSP can design reconfigurable metamaterial structures for multi‐state, multi‐band optical responses, showing great ...
Shujie Yang, Yuqi Zhang, Xuzhe Zhao, Yansong Tang, Kaichen Dong   +4 more
wiley   +1 more source

SemanticST: A Scalable Multi‐Contextual Graph Learning Framework for Uncovering Spatial Niches and Robust Multi‐Sample Integration in Spatial Transcriptomics

Advanced Science, EarlyView.
Technical limitations often let dominant signals overshadow rare cell types and fine‐grained heterogeneity in spatial transcriptomics. SemanticST, a graph neural network using multi‐semantic graph fusion and a novel min‐cut loss, recovers these subtle patterns.
Roxana Zahedi, Ahmadreza Argha, Nona Farbehi, Ivan Bakhshayeshi, Thantrira Porntaveetus, Youqiong Ye, Nigel H. Lovell, Hamid Alinejad‐Rokny   +7 more
wiley   +1 more source

Learning Work Function via Implicit Reasoning on Electrostatic Potential Landscapes

Advanced Science, EarlyView.
StructPot‐CLR establishes a cross‐modal contrastive learning framework that aligns the crystal structures of 2D materials with plane‐averaged electrostatic potential landscapes for physically informed work‐function prediction. The model achieves an MAE of 0.265 eV and an R2 of 0.902 on the held‐out test set while accurately preserving key morphological
Haoyu Wan, Yue Wu, Tianhao Su, Deng Pan
wiley   +1 more source

A Site‐Aware Representation Learning Framework For Unified Molecular Interaction Modeling and Generative Design

Advanced Science, EarlyView.
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, Qianqian Zhang, Chenhao Wang, Zhiheng Yi, Alex Jinpeng Wang, Jing Tang, Min Li   +6 more
wiley   +1 more source

Artificial Intelligence‐Empowered Single‐Cell Phenotyping for Rapid, Automated Pathogen Diagnostics

Advanced Science, EarlyView.
This work presents an integrated diagnostic platform that combines microfluidic single‐cell bacterial detection with artificial intelligence‐driven analysis for rapid antimicrobial susceptibility testing. Single‐cell phenotyping enables assessment of antibiotic response in only a few cell replication cycles, while AI analysis supports precise bacterial
Sabita Khadka, Bushra Raahat, Spyros Tragoudas, Hui Li   +3 more
wiley   +1 more source

Spatiotemporal Multi‐Omic Mapping Reveals Liver‐Muscle Metabolic Crosstalk in Cancer Cachexia

Advanced Science, EarlyView.
The interactive CCAtlas platform delineates cross‐species, spatiotemporal, and sex‐specific molecular dynamics and metabolic rewiring across organs during cancer cachexia. Hepatic Gamt downregulation curtails hepatic creatine synthesis to trigger systemic creatine insufficiency and consequent skeletal muscle atrophy in LLC tumour‐bearing mice ...
Zihan Tian, Qianyu Wang, Wenyan Gao, Xianfeng Li, Jiawen Fan, Xiaoliang Wu, Siqi Liu, Xiangdong Ming, Danna Yeerken, Mutian Shen, Qingjie Min, Qimin Zhan, Yan Wang   +12 more
wiley   +1 more source

Towards a Compositional Framework for Describing Human Phenotypes

Advanced Science, EarlyView.
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, Yunchao Ling, Xinyue Hu, Wei Chen, Rong Zhou, Xinhao Zhuang, Yanfeng Jiang, Jialu Zhao, Xingdong Chen, Jingchun Luo, Li Jin, Guoqing Zhang   +11 more
wiley   +1 more source

MAPA: A Semantic Network Framework for Functional Module Discovery and Interpretation in Multi‐Omics Data

Advanced Science, EarlyView.
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, Feifan Zhang, Yijiang Liu, Chao Jiang, Peng Gao, Nguan Soon Tan, Sai Zhang, Yuchen Shen, Qianyi Zhou, Xin Zhou, Xiao Wang, Fangqing Zhao, Chuchu Wang, Xiaotao Shen   +13 more
wiley   +1 more source

Predicting Enzyme Turnover Numbers and Enabling Rational Enzyme Evolution

Advanced Science, EarlyView.
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, Xiangyang Ma, Jiyan Li, Mengxiang Wang, Fuping Lu, Yihan Liu, Lin Wang   +6 more
wiley   +1 more source

Disentangling Heterogeneous Molecular Networks for Multi‐Omics‐Driven Cancer Driver Discovery

Advanced Science, EarlyView.
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, Ji Li, Mu Su, Peishen Yu, Te Ma, Ruiyang Zhai, Chenye Zhang, Mengyan Zhang, Yan Zhang   +8 more
wiley   +1 more source