Hydration free energies from kernel-based machine learning: Compound-database bias

Abstract

We consider the prediction of a basic thermodynamic property---hydration free energies---across a large subset of the chemical space of small organic molecules. Our in silico study is based on computer simulations at the atomistic level with implicit solvent. We report on a kernel-based machine learning approach that is inspired by recent work in learning electronic properties, but differs in key aspects: The representation is averaged over several conformers to account for the statistical ensemble. We also include an atomic-decomposition ansatz, which we show offers significant added transferability compared to molecular learning. Finally, we explore the existence of severe biases from databases of experimental compounds. By performing a combination of dimensionality reduction and cross-learning models, we show that the rate of learning depends significantly on the breadth and variety of the training dataset. Our study highlights the dangers of fitting machine-learning models to databases of narrow chemical range.

10 pages, 7 figures

References in corpus (14)

• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• A Transferable Machine-Learning Model of the Electron Density
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• Transferable atomic multipole machine learning models for small organic molecules
• Controlled exploration of chemical space by machine learning of coarse-grained representations
• The fundamentals of quantum machine learning

Cited by in corpus (7)

• Machine Learning of Free Energies in Chemical Compound Space Using Ensemble Representations: Reaching Experimental Uncertainty for Solvation
• Random projections and Kernelised Leave One Cluster Out Cross-Validation: Universal baselines and evaluation tools for supervised machine learning for materials properties
• Compact atomic descriptors enable accurate predictions via linear models
• Graphical Gaussian Process Regression Model for Aqueous Solvation Free Energy Prediction of Organic Molecules in Redox Flow Battery
• Condensed-phase molecular representation to link structure and thermodynamics in molecular dynamics
• Solvation Free Energies from Neural Thermodynamic Integration
• MLSolv-A: A Novel Machine Learning-Based Prediction of Solvation Free Energies from Pairwise Atomistic Interactions