Results 161 to 170 of about 615,736 (341)

MGM as a Large‐Scale Pretrained Foundation Model for Microbiome Analyses in Diverse Contexts

open access: yesAdvanced Science, EarlyView.
We present the Microbial General Model (MGM), a transformer‐based foundation model pretrained on over 260,000 microbiome samples. MGM learns contextualized microbial representations via self‐supervised language modeling, enabling robust transfer learning, cross‐regional generalization, keystone taxa discovery, and prompt‐guided generation of realistic,
Haohong Zhang   +5 more
wiley   +1 more source

Learned Conformational Space and Pharmacophore Into Molecular Foundational Model

open access: yesAdvanced Science, EarlyView.
The Ouroboros model introduces two orthogonal modules within a unified framework that independently learn molecular representations and generate chemical structures. This design enables flexible optimization strategies for each module and faithful structure reconstruction without prompts or noise.
Lin Wang   +8 more
wiley   +1 more source

Initial Distance‐Dependent Mean Force Drives Synaptic Vesicle Motion Toward Fusion Sites in Stimulated Hippocampal Neurons

open access: yesAdvanced Science, EarlyView.
Synaptic vesicle (SV) motion and exocytosis dynamics in the presynaptic terminals of live neurons are intimately linked to synaptic transmission during neuronal activity. In this work, it is revealed that, during electrical stimulation, SVs located farther from their fusion sites exhibit greater straightness and experience larger mean forces directed ...
Gyunam Park   +7 more
wiley   +1 more source

Population‐Based Multi‐Omics and Cohort Study Identifying Predictive Biomarkers and Therapeutic Targets for Psoriatic Disease

open access: yesAdvanced Science, EarlyView.
Psoriatic disease (PsD) is a chronic skin disease, with challenges in early risk stratification and drug development. Through gene‐level causal inference framework and expression level validation, combined with longitudinal cohort study, CDSN and PRSS8 have been identified as candidate biomarkers and therapeutic targets for PsD.
Tianxing Wu   +13 more
wiley   +1 more source

HiST: Histological Images Reconstruct Tumor Spatial Transcriptomics via MultiScale Fusion Deep Learning

open access: yesAdvanced Science, EarlyView.
HiST, a multiscale deep learning framework, reconstructs spatially resolved gene expression profiles directly from histological images. It accurately identifies tumor regions, captures intratumoral heterogeneity, and predicts patient prognosis and immunotherapy response.
Wei Li   +8 more
wiley   +1 more source

Home - About - Disclaimer - Privacy