Machine Learning of Free Energies in Chemical Compound Space Using Ensemble Representations: Reaching Experimental Uncertainty for Solvation

Abstract

Free energies govern the behavior of soft and liquid matter, and improving their predictions could have a large impact on the development of drugs, electrolytes or homogeneous catalysts. Unfortunately, it is challenging to devise an accurate description of effects governing solvation such as hydrogen-bonding, van der Waals interactions, or conformational sampling. We present a Free energy Machine Learning (FML) model applicable throughout chemical compound space and based on a representation that employs Boltzmann averages to account for an approximated sampling of configurational space. Using the FreeSolv database, FML's out-of-sample prediction errors of experimental hydration free energies decay systematically with training set size, and experimental uncertainty (0.6 kcal/mol) is reached after training on 490 molecules (80\% of FreeSolv). Corresponding FML model errors are also on par with state-of-the art physics based approaches. To generate the input representation for a new query compound, FML requires approximate and short molecular dynamics runs. We showcase its usefulness through analysis of FML solvation free energies for 116k organic molecules (all force-field compatible molecules in QM9 database) identifying the most and least solvated systems, and rediscovering quasi-linear structure property relationships in terms of simple descriptors such as hydrogen-bond donors, number of NH or OH groups, number of oxygen atoms in hydrocarbons, and number of heavy atoms. FML's accuracy is maximal when the temperature used for the molecular dynamics simulation to generate averaged input representation samples in training is the same as for the query compounds. The sampling time for the representation converges rapidly with respect to the prediction error.

References in corpus (17)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Machine learning prediction errors better than DFT accuracy
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Machine learning for electronically excited states of molecules
• Ab initio thermodynamics of liquid and solid water
• FCHL revisited: faster and more accurate quantum machine learning
• Alchemical and structural distribution based representation for improved QML
• Transfer learning for solvation free energies: from quantum chemistry to experiments
• Evidence for supercritical behavior of high-pressure liquid hydrogen
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Hydration free energies from kernel-based machine learning: Compound-database bias
• Controlled exploration of chemical space by machine learning of coarse-grained representations
• Resolution limit of data-driven coarse-grained models spanning chemical space
• Large yet bounded: Spin gap ranges in carbenes
• Molecular machine learning with conformer ensembles

Cited by in corpus (14)

• Physics-inspired structural representations for molecules and materials
• Towards the design of chemical reactions: Machine learning barriers of competing mechanisms in reactant space
• Solvation Free Energies in Subsystem Density Functional Theory
• Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations
• Ab initio machine learning of phase space averages
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Alchemical geometry relaxation
• Improved decision making with similarity based machine learning: Applications in chemistry
• Condensed-phase molecular representation to link structure and thermodynamics in molecular dynamics
• Solvation Free Energies from Neural Thermodynamic Integration
• Molecular Hessian matrices from a machine learning random forest regression algorithm
• Extending the definition of atomic basis sets to atoms with fractional nuclear charge
• Machine-Learned Potentials for Solvation Modeling
• Efficient interpolation of molecular properties across chemical compound space with low-dimensional descriptors