Litcius/Paper detail

A graph neural network-state predictive information bottleneck (GNN-SPIB) approach for learning molecular thermodynamics and kinetics

Ziyue Zou, Dedi Wang, Pratyush Tiwary

2024Digital Discovery14 citationsDOIOpen Access PDF

Abstract

We present a graph-based differentiable representation learning method from atomic coordinates for enhanced sampling methods to learn both thermodynamic and kinetic properties of a system.

Topics & Concepts

BottleneckArtificial neural networkInformation bottleneck methodArtificial intelligenceKineticsComputer scienceGraphMachine learningChemistryThermodynamicsStatistical physicsPhysicsTheoretical computer scienceCluster analysisQuantum mechanicsEmbedded systemMachine Learning in Materials ScienceComputational Drug Discovery MethodsProtein Structure and Dynamics
A graph neural network-state predictive information bottleneck (GNN-SPIB) approach for learning molecular thermodynamics and kinetics | Litcius