Machine learning based energy-free structure predictions of molecules (closed and open-shell), transition states, and solids

Abstract

The computational prediction of atomistic structure is a long-standing problem in physics, chemistry, materials, and biology. Within conventional force-field or {\em ab initio} calculations, structure is determined through energy minimization, which is either approximate or computationally demanding. Alas, the accuracy-cost trade-off prohibits the generation of synthetic big data records with meaningful energy based conformational search and structure relaxation output. Exploiting implicit correlations among relaxed structures, our kernel ridge regression model, dubbed Graph-To-Structure (G2S), generalizes across chemical compound space, enabling direct predictions of relaxed structures for out-of-sample compounds, and effectively bypassing the energy optimization task. After training on constitutional and compositional isomers (no conformers) G2S infers atomic coordinates relying solely on stoichiometry and bond-network information as input (Our numerical evidence includes closed and open shell molecules, transition states, and solids). For all data considered, G2S learning curves reach mean absolute interatomic distance prediction errors of less than 0.2 Å for less than eight thousand training structures -- on par or better than popular empirical methods. Applicability test of G2S include meaningful structures of molecules for which standard methods require manual intervention, improved initial guesses for subsequent conventional {\em ab initio} based relaxation, and input for structural based representations commonly used in quantum machine learning models, (bridging the gap between graph and structure based models).

References in corpus (9)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• FCHL revisited: faster and more accurate quantum machine learning
• Alchemical and structural distribution based representation for improved QML
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Molecular geometry prediction using a deep generative graph neural network
• Rapid and accurate molecular deprotonation energies from quantum alchemy
• Wasserstein metric for improved QML with adjacency matrix representations

Cited by in corpus (17)

• SELFIES and the future of molecular string representations
• Inverse design of 3d molecular structures with conditional generative neural networks
• Towards the design of chemical reactions: Machine learning barriers of competing mechanisms in reactant space
• Quantum chemical roots of machine-learning molecular similarity descriptors
• Ab initio machine learning of phase space averages
• Alchemical geometry relaxation
• Improved decision making with similarity based machine learning: Applications in chemistry
• Differentiable Physics: A Position Piece
• Discovery of structure-property relations for molecules via hypothesis-driven active learning over the chemical space
• Molecular relaxation by reverse diffusion with time step prediction
• Evolutionary Monte Carlo of QM properties in chemical space: Electrolyte design
• Molecular Hessian matrices from a machine learning random forest regression algorithm
• Molecular distance matrix prediction based on graph convolutional networks
• Predicting quantum evolutions of excitation energy transfer in a light-harvesting complex using multi-optimized recurrent neural networks
• Multi-timescale time encoding for CNN prediction of Fenna-Matthews-Olson energy-transfer dynamics
• Simulation of Open Quantum Dynamics with Bootstrap-Based Long Short-Term Memory Recurrent Neural Network
• Neural Network Driven, Interactive Design for Nonlinear Optical Molecules Based on Group Contribution Method