Combining Molecular Dynamics and Machine Learning to Predict Self-Solvation Free Energies and Limiting Activity Coefficients
Julia Gebhardt, Matthias Kiesel, Sereina Riniker, Niels Hansen
Abstract
Computational prediction of limiting activity coefficients is of great relevance for process design. For highly nonideal mixtures including molecules with directed interactions, methods that maintain the molecular character of the solvent are most promising. Computational expense and force-field deficiencies are the main limiting factors that prevent the use of high-throughput molecular dynamics (MD) simulations in a predictive setup. The combination of MD simulations and machine learning used in this work accounts for both issues. Comparison to published data including free-energy simulations, COSMO-RS and UNIFAC models, reveals competitive prediction accuracy.
Topics & Concepts
SolvationLimitingMolecular dynamicsForce field (fiction)Computer scienceUNIFACWork (physics)Relevance (law)Field (mathematics)Machine learningStatistical physicsArtificial intelligenceChemistryComputational chemistryMoleculeThermodynamicsActivity coefficientPhysicsMathematicsPhysical chemistryEngineeringMechanical engineeringAqueous solutionLawOrganic chemistryPolitical sciencePure mathematicsComputational Drug Discovery MethodsMachine Learning in Materials SciencePhase Equilibria and Thermodynamics