Ab initio machine learning of phase space averages

Abstract

Equilibrium structures determine material properties and biochemical functions. We propose to machine learn phase-space averages, conventionally obtained by {\em ab initio} or force-field based molecular dynamics (MD) or Monte Carlo simulations. In analogy to \textit(ab initio} molecular dynamics (AIMD), our {\em ab initio} machine learning (AIML) model does not require bond topologies and therefore enables a general machine learning pathway to ensemble properties throughout chemical compound space. We demonstrate AIML for predicting Boltzmann averaged structures after training on hundreds of MD trajectories. AIML output is subsequently used to train machine learning models of free energies of solvation using experimental data, and reaching competitive prediction errors (MAE $\sim$ 0.8 kcal/mol) for out-of-sample molecules -- within milli-seconds. As such, AIML effectively bypasses the need for MD or MC-based phase space sampling, enabling exploration campaigns throughout CCS at a much accelerated pace. We contextualize our findings by comparison to state-of-the-art methods resulting in a Pareto plot for the free energy of solvation predictions in terms of accuracy and time.

References in corpus (10)

• On-the-fly machine learning force field generation: Application to melting points
• What ice can teach us about water interactions: a critical comparison of the performance of different water models
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Transfer learning for solvation free energies: from quantum chemistry to experiments
• Quantum-mechanical exploration of the phase diagram of water
• Machine Learning of Free Energies in Chemical Compound Space Using Ensemble Representations: Reaching Experimental Uncertainty for Solvation
• An assessment of the structural resolution of various fingerprints commonly used in machine learning
• Comment on "Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning"
• Thermally Averaged Magnetic Anisotropy Tensors via Machine Learning Based on Gaussian Moments
• Dictionary of 140k GDB and ZINC derived AMONs

Cited by in corpus (5)

• Developments and Further Applications of Ephemeral Data Derived Potentials
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Condensed-phase molecular representation to link structure and thermodynamics in molecular dynamics
• Evolutionary Monte Carlo of QM properties in chemical space: Electrolyte design
• Calculated state-of-the art results for solvation and ionization energies of thousands of organic molecules relevant to battery design