Combining Molecular Dynamics and Machine Learning to Predict Self-Solvation Free Energies and Limiting Activity Coefficients

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 highthroughput 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.

Mechanistic Understanding from Molecular Dynamics in Pharmaceutical Research 2: Lipid Membrane in Drug Design

“…If one is also only interested in the difference of the binding affinities of two different molecules and the absolute Finally, it bears mentioning that, as in other fields of computational science, an emergent trend is the incorporation of the toolkit of novel computational tools widely known as Machine Learning (ML) into hybrid MD algorithms; for a recent review (2020) of achievements in the hybridization of MD with ML, see Noé et al [117]. Recently, a hybrid FEP + ML algorithm was found to provide a more accurate result, given the same expenditure of computational resources, than the use of FEP alone, for the prediction of hydration free energies [118]; a hybrid MD + ML algorithm was used to predict self-solvation free energies and limiting activity coefficients [119].…”

Optimizing peptide inhibitors of SARS-Cov-2 nsp10/nsp16 methyltransferase predicted through molecular simulation and machine learning

“…Sinha and Wang created a feature set including RMSD (Root-mean-square-deviation), RMSF (Root-mean-square-fluctuations), Rg (Radius of gyration), SASA (Solvent accessible surface area), NH bond (hydrogen bond) and Covariance analysis calculated from molecular dynamics simulations for machine learning prediction on whether unclassified variants of the BRCA 1 gene were cancerous or non-cancerous [ 29 ]. Gebhard and co-workers predicted solvation energies using machine learning applied to a feature set consisting of intermolecular and intramolecular energies, Lenard-Jones potentials, SASA and Rg [ 30 ]. In another study, Kumar and Purohit showed that the RMSD, RMSF, radius of gyration, docking energy, total energy, and protein-solvent interactions were altered in the mutant predicted to be cancer causing [ 31 ].…”

Progress towards machine learning reaction rate constants

“…On the other hand, several researchers have successfully used ML to predict solvation free energies [97][98][99][100] and/or activity coefficients. 101 Recently, Vermeire et al 102 used transfer learning to predict solvation free energies with two datasets. One dataset was generated from existing experimental data (CombiSolv-Exp) and the other by computing solvation energies (CombiSolv-QM) with DFT at the BP-TZVP level with COSMO-RS.…”