Results 211 to 220 of about 3,745,728 (280)

TENTACLES: a consensus machine learning tool for robust biomarker discovery in heterogeneous data. [PDF]

BioData Min
Montesi G, Mouta GDS, Novedrati M, Cunha AF, Fuschi A, Lucchesi S, Sonnati C, Ciabattini A, Santoro F, Medaglini D, Nakaya HI.   +10 more
europepmc   +1 more source

Targeting the NR1D1–IGF2BP2–V‐ATPase Axis With Hybrid Nanovesicles Restores Macrophage Rhythms to Reverse Sepsis‐Induced Immunosuppression

Advanced Science, EarlyView.
Sepsis disrupts immune‐cell rhythms and weakens bacterial clearance. Biomimetic nanovesicles combining erythrocyte and inflammation‐activated macrophage membranes deliver siNR1D1 to dysfunctional macrophages, restoring the NR1D1–IGF2BP2–V‐ATPase pathway, circadian regulation, phagolysosomal acidification, and antimicrobial defense.
Lang Chen, Wenyi Lin, Lang Jiang, Xuehui Gao, Chenyan Yu, Jili Han, Zhenping Liu, Xuefeng Li, Mei He, Chang Li, Qilan Li, Chaoying Song, Jiqian Xu, You Shang   +13 more
wiley   +1 more source

Machine Learning-Integrated Metabolomics for Precision Pharmacotherapy: Advances, Challenges, and Clinical Translation. [PDF]

Metabolites
Li P, Mao J, Hu X, Hu Y, Zhang X, Zheng Q, Hou X, Liu Y, Huang M.   +8 more
europepmc   +1 more source

SerpinA3 is an Endogenous TGF‐β Receptor Antagonist that Attenuates Cardiac Fibroblast Activation and Fibrotic Remodeling

Advanced Science, EarlyView.
SerpinA3 acts as an endogenous TGF‐β receptor antagonist that binds to the extracellular domain of TGFR‐1, thereby preventing TGFR‐1–TGFR‐2 complex formation. This receptor‐level blockade suppresses TGF‐β/Smad2/3 signaling, attenuates cardiac fibroblast activation, and extracellular matrix deposition, and ultimately alleviates pressure overload–induced
Hui Wang, Jieyu Cui, Chunlu Huang, Wanyi Guo, Tong Liu, Yi Zhu, Shuai Shao, Kangyin Chen, Jinlong He, Qiankun Bao   +9 more
wiley   +1 more source

Unsupervised Anomaly Detection Framework for Multimodal Data in Industrial Control Systems. [PDF]

Sensors (Basel)
Kim Y, An G, Kim K, Ha J.
europepmc   +1 more source

Deep‐Learning‐Based Denoising for Improved Phase Precision in Electron Holography of Electromagnetic Fields in Nanoscale Materials

Advanced Science, EarlyView.
Low‐dose electron holography is limited by shot noise, which buries weak phase signals. HoloDenoiser, a physics‐informed network that works simultaneously in the spatial and frequency domains, locates and protects the holographic sideband while suppressing noise in the hologram.
Ye Luo, Luyang Wang, Zhiling Yu, Xiaowen Chen, Xiaoyu Wang, Ya‐Hui Jia, Thibaud Denneulin, Yu Han, Rafal E. Dunin‐Borkowski, Fengshan Zheng, Qi Liu   +10 more
wiley   +1 more source

A curriculum-guided unified framework for robust unsupervised domain adaptation on multi-cohort Parkinson's disease diagnosis. [PDF]

Quant Imaging Med Surg
Shen Y, Hai J, Qiao K, Chen J, Li Y, Yan B.   +5 more
europepmc   +1 more source

Matrix Stiffness Orchestrates Mesenchymal Stem Cell Lineage Commitment Toward Osteogenesis and Adipogenesis Through the PIEZO1/SP1/STC2 Axis

Advanced Science, EarlyView.
Matrix stiffness directs mesenchymal stem cell lineage commitment through PIEZO1‐dependent activation of the SP1/STC2 pathway. Stiff matrices favor osteogenesis and suppress adipogenesis, whereas the loss of PIEZO1 function impairs early bone formation. STC2 retains lineage‐regulatory activity even when PIEZO1 is inactive.
Shuo Zhang, Siteng Li, Wenzhong Chen, Qingcheng Song, Haiyue Zhao, Peng Wang, Yiran Zhang, Wenquan Liang, Shaowei Zheng, Juan Wang, Wei Chen, Yanbin Zhu, Yingze Zhang   +12 more
wiley   +1 more source

Limits and benefits of unsupervised transfer learning for Raman spectroscopy-based bioprocess monitoring. [PDF]

Bioprocess Biosyst Eng
Hüpfl B, Umprecht A, Kozma B, Ettinger P, Spadiut O.   +4 more
europepmc   +1 more source

MethyAnno: An Interpretable Automated Annotation Method Leveraging Multi‐Scale Information and Metric Learning Framework for scDNAm Data

Advanced Science, EarlyView.
MethyAnno enables robust and interpretable annotation of single‐cell DNA methylation data by integrating multi‐scale epigenetic information, bidirectional cross‐attention, and prototype‐based metric learning. The framework resolves rare and novel cell types across datasets while revealing cell‐type‐specific epigenetic signatures associated with disease
Yuhang Jia, Siyu Li, Songming Tang, Keju Gu, Shengquan Chen   +4 more
wiley   +1 more source