Advanced Science, EarlyView.By overcoming the fixed‐path limitations of conventional machine learning, a heterogeneous graph neural network fundamentally reconstructs material data representation. Integrating variable processing sequences with intrinsic elemental features, this framework enables exploratory optimization across high‐dimensional spaces.
Jie Yin +12 more
wiley +1 more source
HarveST uses a heterogeneous graph learning framework to reveal spatial transcriptomics patterns. [PDF]
Commun BiolFeng J, Yu T, Zhang Y.
europepmc +1 more source
Efficient Screening of Organic Singlet Fission Molecules Using Graph Neural Networks
Advanced Science, EarlyView.A high‐throughput screening framework based on graph neural networks (GNNs) and multi‐level validation facilitates the identification of singlet fission (SF) candidates. By efficiently predicting excitation energies across 20 million molecules, and integrating TDDFT calculations, synthetic accessibility assessments, and GW+BSE calculations, this ...
Li Fu +5 more
wiley +1 more source
SIMBA-GNN: mechanistic graph learning for microbiome prediction. [PDF]
NPJ Syst Biol ApplAminian-Dehkordi J +3 more
europepmc +1 more source
Broadening Hard‐Magnet Discovery Beyond Symmetry Constraints via Unified Effective Anisotropy
Advanced Science, EarlyView.A unified effective‐anisotropy descriptor (Keff) extends hard‐magnet screening across all seven crystal systems, beyond the uniaxial restriction of conventional searches. Machine‐learning screening of 9320 known ferromagnets and diffusion‐model generation together yield 38 rare‐earth‐free or ‐lean candidates with DFT‐validated magnetic hardness (κ > 1),
Hojae Kim +5 more
wiley +1 more source
Physics-Informed Graph Learning for Spatially Contiguous and Capacity-Constrained Hospital Service Area Delineation. [PDF]
Comput Environ Urban SystLiu L, Wang F.
europepmc +1 more source
Early Retinal UCHL1 Dysregulation Coupled With Synaptic Loss Reflects Alzheimer's Disease Severity
Advanced Science, EarlyView.This study identifies synapse‐enriched deubiquitinase UCHL1 as an early Aβ‐responsive regulator of retinal synaptopathy in Alzheimer's disease. Retinal UCHL1 loss accompanies excitatory synapse degeneration, p75NTR activation, and neuroinflammation, and predicts Braak stage and cognitive decline. Aβ42 fibrils trigger synaptic and UCHL1 depletion before
Altan Rentsendorj +25 more
wiley +1 more source
PU-GRAIL: residue-level graph learning for identifying protective bacterial antigens under positive-unlabeled supervision. [PDF]
BioinformaticsJeon J, Jung S, Jung I, Kim K, Yeom J.
europepmc +1 more source
Automated Extraction of Multicomponent Alloy Data Using Large Language Models for Sustainable Design
Advanced Science, EarlyView.A large language model (LLM) based pipeline is developed to automatically extract a comprehensive and accurate multicomponent alloy database from literature corpus. The extracted dataset is integrated with sustainability indicators to identify potential alloys that outperform existing industrial benchmark materials in terms of both performance and ...
Aravindan Kamatchi Sundaram +4 more
wiley +1 more source
Discovering proteo-transcriptomic networks via biologically informed heterogeneous graph learning. [PDF]
Nucleic Acids ResDuan J +14 more
europepmc +1 more source