News

Single-atom catalysts change spin state when boosted by a magnetic field
The job of a catalyst is to ultimately speed up reactions, which could reduce an hour-long process into several minutes. It ...
Rethinking our relationship with CO₂—greenhouse gas could lead to development of sustainable fuels
The goal of carbon dioxide (CO2) hydrogenation is to turn pollution into fuel. This process transforms CO2, one of the main ...
EurekAlert!2y
GAME-Net: a graph neural network for fast evaluation of the adsorption energy in heterogeneous catalysis
The algorithm proposed by the researchers employs a simple graph representation where nodes ... the understanding and design of heterogeneous catalysts for the development of more sustainable ...
IEEE2y
HGBER: Heterogeneous Graph Neural Network With Bidirectional Encoding Representation
In this article, we propose a novel unsupervised framework termed Heterogeneous Graph neural network with bidirectional encoding representation (HGBER) to learn comprehensive node representations.
Frontiers3y
MDGNN: Microbial Drug Prediction Based on Heterogeneous Multi-Attention Graph Neural Network
With the development of graph neural networks, there are more and more graph representation algorithms with better performance, such as GCN, GAT, heterogeneous graph attention networks (HANs) (Wang et ...
C&EN3y
Atomic Structure-Free Representation of Active Motifs for Expedited Catalyst Discovery
To discover new catalysts using density functional theory (DFT ... fingerprint enumeration details, and graphical representation of difference between absolute and fractional coordinates (PDF) ...
Frontiers5y
Predicting Microbe-Disease Association by Learning Graph Representations and Rule-Based Inference on the Heterogeneous Network
In this paper, we propose a predictive model based on the known microbe-disease associations to discover potential microbe-disease associations through integrating Learning Graph Representations and a ...