Unified protein-small molecule graph neural networks for binding site prediction. [PDF]
Wang J, Dokholyan NV.
europepmc +1 more source
Multiferroic order parameters – polarization, magnetization, and ferroelastic strain – are positioned as dynamic design variables for batteries. Their mechanistic roles, practical tuning through fabrication and external fields, and ferroic‐resolved characterization routes are unified into a closed‐loop framework, revealing how coupled ferroic responses
Jiaqi Su +13 more
wiley +1 more source
EpiMII: Structure-Aware Graph Neural Networks for MHC-II Epitope Generation. [PDF]
Yuan J +11 more
europepmc +1 more source
Physics‐Informed Neural Network‐Enabled Forward Prediction and Inverse Design of Ring Origami
This work presents a KRT‐PINN framework that integrates Kirchhoff rod theory with physics‐informed neural networks for the forward prediction and inverse design of ring origami consisting of closed‐loop rods. The framework predicts stable states of segmented rings with prescribed natural‐curvature profiles and determines the natural‐curvature profiles ...
Luyuan Ning +3 more
wiley +1 more source
Hierarchical semantic extraction and heterogeneous graph neural networks for event-driven time series forecasting. [PDF]
Cen C +7 more
europepmc +1 more source
Polarization Dynamics in Ferroelectrics: Insights Enabled by Machine Learning Molecular Dynamics
Machine learning molecular dynamics is presented as a route to capture polarization switching, domain wall kinetics, topological polar textures, and polar mechanical coupling beyond the limits of conventional atomistic methods. This Perspective surveys recent progress and identifies key methodological directions, including long‐range electrostatics ...
Dongyu Bai +3 more
wiley +1 more source
Spatiotemporal weather forecasting via multi-scale graph neural networks and latent diffusion models. [PDF]
Wu Z.
europepmc +1 more source
A Generative Neuro‐Symbolic AI for Protein Sequence Design
We introduce EffieDes, a neuro‐symbolic framework coupling deep learning‐based fitness landscape parameterization with exact automated reasoning. Unlike greedy sampling, EffieDes identifies sequences that globally optimize fitness while satisfying intricate design constraints.
Marianne Defresne +12 more
wiley +1 more source
LSTM-attention-guided graph neural networks for integrated genotype-Environment modeling in maize yield prediction. [PDF]
Morshedian A, Domaratzki M.
europepmc +1 more source

