Deep Learning– tag –
-
bioRxiv: ORIGAMI, an Orientation-Aware GNN, Developed for Assessing Multimeric Interfaces of Protein Complex Structures
bioRxiv Unknown Overview A study published on bioRxiv introduces "ORIGAMI," an orientation-aware graph neural network (GNN) for evaluating multimeric interfaces of protein complex structures. ORIGAMI innovatively utilizes both scalar and... -
arXiv: PolyGraphPy Unifies Atomistic Simulation and ML-Driven Polymer Design in a Python Framework
arXiv Unknown Overview A new paper on arXiv introduces "PolyGraphPy," a unified Python framework for atomistic simulation and machine learning (ML)-driven polymer design. This open-source framework seamlessly integrates atomistic simulat... -
IBS Develops Crossbreeding Neural Network Enabling AI to Discover Catalysts from Disparate Material Families
Lab Manager South Korea Overview Researchers at the Institute for Basic Science have developed the "Crossbreeding Neural Network (CBNN)" deep learning model to overcome limitations in traditional machine learning for materials. This mode... -
arXiv: BiMat-ML Advances Stacked 2D Material Property Prediction via Multimodal Learning and GNNs
arXiv Unknown Overview A new research paper on arXiv proposes "BiMat-ML," a multimodal learning approach for property prediction in stacked two-dimensional (2D) materials. This method utilizes graph neural networks (GNNs) to process mole... -
AI and Graph Neural Networks Drive a Materials Revolution: Gulf University on Property Prediction
Gulf University バーレーン Overview Gulf University research highlights AI's profound impact on materials science, particularly through Graph Neural Networks (GNNs). These models predict material properties directly from atomic structure... -
Top 7 AI Formulation Software Platforms Compared: Schrödinger, Citrine Informatics Accelerate R&D in Materials
ChemCopilot USA Overview ChemCopilot's 2026 'Top 7 AI Formulation Software' report highlights leading platforms like Schrödinger, Citrine Informatics, and Uncountable for accelerating R&D in the chemical and materials industries. The... -
Google DeepMind’s GNoME Predicts Over 2 Million New Crystal Structures, Revolutionizing Chemical Engineering with AI and Autonomous Labs
Medium USA Overview Google DeepMind's GNoME project, utilizing graph neural networks (GNNs), has predicted over 2 million new stable crystal structures, surpassing the total known material catalog accumulated over the past century. This ...
