This study introduces DualPG‐DTA, a framework integrating two pre‐trained models to generate molecular and protein representations. It constructs dual graphs processed by specialized neural networks with dynamic attention for feature fusion, achieving superior benchmark performance.
Yihao Chen +7 more
wiley +1 more source
Denoising self-supervised learning for disease-gene association prediction. [PDF]
Zhang Y, Xiang J, Li J.
europepmc +1 more source
MGM as a Large‐Scale Pretrained Foundation Model for Microbiome Analyses in Diverse Contexts
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
Lightweight self supervised learning framework for domain generalization in histopathology. [PDF]
Shafique A +6 more
europepmc +1 more source
A Lightweight Medical Image Classification Framework via Self-Supervised Contrastive Learning and Quantum-Enhanced Feature Modeling [PDF]
Jingsong Xia, Siqi Wang
openalex
Stroke‐induced lactate accumulation promotes p300‐mediated lactylation of methyl‐CpG binding protein 2 (MeCP2) at lysine 210, which reprograms microglial metabolism toward glycolysis and activates the hexokinase 2 (HK2)/mTOR axis. This cascade promotes proinflammatory responses and impairs neurofunctional outcomes.
Zengyu Zhang +12 more
wiley +1 more source
Self-supervised learning and transformer-based technologies in breast cancer imaging. [PDF]
Wang L.
europepmc +1 more source
Learned Conformational Space and Pharmacophore Into Molecular Foundational Model
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
A Practical Study of Data Requirements for Self-Supervised Learning in Medical Image Analysis. [PDF]
Hommyo M +4 more
europepmc +1 more source
Light Therapy Alleviates Addiction‐Related Symptoms and Reshapes Habenula and Midbrain Pathways
This study investigates light therapy for treating Internet Gaming Disorder (IGD). Functional MRI (fMRI) data reveal that light therapy enhances brain connectivity, particularly between the habenula and the medial orbitofrontal cortex (mOFC). These changes are associated with reduced withdrawal symptoms and addiction severity, highlighting the ...
Jinhui Li +10 more
wiley +1 more source

