CoeffNet : predicting activation barriers through a chemically-interpretable, equivariant and physically constrained graph neural network

2024/01/01 by Sudarshan Vijay, Maxwell C. Venetos, Evan Walter Clark Spotte‐Smith +3 · 1 voice
Computer Science · Energy · Materials Science · #CO2 Reduction Techniques and Catalysts #Computational Drug Discovery Methods #Machine Learning in Materials Science

paper · pdf · doi:10.1039/d3sc04411d

openalex publication_date 2024/01/01 · openalex created_date 2024/01/23 · openalex updated_date 2026/08/01

Abstract

CoeffNet uses coefficients of molecular orbitals of reactants and products to predict activation barriers.

Citations

• Density-functional thermochemistry. III. The role of exact exchange
• Ab Initio Calculation of Vibrational Absorption and Circular Dichroism Spectra Using Density Functional Force Fields
• e3nn: Euclidean Neural Networks

Discussions

• Congrats to Sudarshan Vijay and my other coauthors on a new Chemical Science (#ChemSci) article: "CoeffNet: predicting activation barriers through a chemically-interpretable, equivariant and physicall [bsky, 3 points, 1 comments]

Related

• MolNet: A Chemically Intuitive Graph Neural Network for Prediction of Molecular Properties
• Graph-based prediction of reaction barrier heights with on-the-fly prediction of transition states
• NeuralNEB -- Neural Networks can find Reaction Paths Fast
• Quantum Mechanics and Machine Learning Synergies: Graph Attention Neural Networks to Predict Chemical Reactivity
• Graph Neural Networks for the Prediction of Substrate-Specific Organic Reaction Conditions