Evaluating the Utilities of Foundation Models in Single‐Cell Data Analysis
This study delivers the first systematic, task‐level evaluation of single‐cell foundation models across eight core analytical tasks. By benchmarking 10 leading models with the scEval framework, it reveals where foundation models truly add value, where task‐specific methods still dominate, and provides concrete, reproducible guidelines to steer the next
Tianyu Liu +4 more
wiley +1 more source
A Miniature Inductive Encoder for Linear Displacement Measurement. [PDF]
Xiong W +6 more
europepmc +1 more source
Paving the Way to Elucidate Hg's Role in Tumorigenesis
Tumorigenesis can result from diverse environmental carcinogens. Among them, mercury—a lifelong bioaccumulative Group 2B carcinogen—has tumorigenic potential that remains poorly understood due to confounding co‐exposures and limited organ‐specific data.
Shouying Li +10 more
wiley +1 more source
Harmonic distortion reduction and dynamic stability in PMSG-CHBI wind energy systems via a dual optimization-prediction approach. [PDF]
Varghese LJ +3 more
europepmc +1 more source
Climate change reshapes the spatial alignment between crop production and environmental resources. Using multi‐source data and a crop model, integrated climatic, water, and soil endowments for maize and wheat are quantified and compared with harvest distributions.
Zheng'e Su +13 more
wiley +1 more source
An electric spring with an extended range of operation and current filtering capability for SEIG-based isolated system. [PDF]
Pati S, Nanda AB, Choudhury A, Sahu BK.
europepmc +1 more source
Causal Prediction of TP53 Variant Pathogenicity Using a Perturbation‐Informed Protein Language Model
A TP53‐specific predictor, CaVepP53, is developed by fine‐tuning ESMC on experimentally validated variants, quantifying pathogenicity via Euclidean distances. It outperforms general‐purpose models and extends to five cancer genes, enabling interpretable variant classification for precision medicine.
Huiying Chen +15 more
wiley +1 more source
Multiparametric robust sensing via readout of characteristic magnetization loops. [PDF]
Path MP, Vogel M, McCord J.
europepmc +1 more source
Geometry and connectivity are complementary structures, which have demonstrated their ability to represent the brain's functional activity. This study evaluates geometric and connectome eigenmodes as biologically informed constraints for EEG source localization.
Pok Him Siu +6 more
wiley +1 more source
A dual-mode dual-stator hybrid rotor synchronous and vernier machine for variable speed applications. [PDF]
Ali S, Ali Q, Munir HM, Zidan HA.
europepmc +1 more source

