Journal of Chemical Theory and Computation · 2025 · 11 citations · 54 references
Natural SciencesChemistryComputer ScienceComputational ChemistryMachine LearningQuantum ChemistryInteratomic PotentialsMolecular InteractionsMolecular ModelingMolecular Property PredictionMolecular SimulationNeural NetworksExplainable Artificial IntelligenceMachine-learned Interatomic PotentialsMany-body DynamicsMany-body EffectsQuantum Chemical ModelingQuantum Chemical Property PredictionQuantum Chemistry SimulationQuantum Molecular Dynamics
While machine learning (ML) models have been able to achieve unprecedented accuracies across various prediction tasks in quantum chemistry, it is now apparent that accuracy on a test set alone is not a guarantee for robust chemical modeling such as stable molecular dynamics (MD). To go beyond accuracy, we use explainable artificial intelligence (XAI) techniques to develop a general analysis framework for atomic interactions and apply it to the SchNet and PaiNN neural network models. We compare these interactions with a set of fundamental chemical principles to understand how well the models have learned the underlying physicochemical concepts from the data. We focus on the strength of the interactions for different atomic species, how predictions for intensive and extensive quantum molecular properties are made, and analyze the decay and many-body nature of the interactions with interatomic distance. Models that deviate too far from known physical principles produce unstable MD trajectories, even when they have very high energy and force prediction accuracy. We also suggest further improvements to the ML architectures to better account for the polynomial decay of atomic interactions.
54
The Amber biomolecular simulation programs
David A. Case, Thomas E. Cheatham, Tom Darden et al. · Journal of Computational Chemistry · 2005 · 9.6K citations · Full text