Transferring Knowledge from MM to QM for a Graph Neural Network Based Implicit QM Solvent

The conformational ensemble of a molecule is strongly influenced by the surrounding environment. Correctly modeling the effect of any given environment is, hence, of pivotal importance in computational studies. Machine learning (ML) has been shown to be able to model these interactions probabilistically, with successful applications demonstrated for classical molecular dynamics. While first instances of ML implicit solvents for quantum-mechanical (QM) calculations exist, the high computational cost of QM reference calculations hinders the development of a generally applicable ML implicit solvent model for QM calculations. Here, we present a novel way of developing such a general machine-learned QM implicit solvent model, which relies neither on QM reference calculations for training nor experimental data, by transferring knowledge obtained from classical interactions to QM. This strategy makes the obtained graph neural network (GNN) based implicit solvent model (termed QM-GNNIS) independent of the chosen functional and basis set. The performance of QM-GNNIS is validated on NMR and IR experiments, demonstrating that the approach can reproduce experimentally observed trends unattainable by state-of-the-art implicit-solvent models.