3DReact: Geometric deep learning for chemical reactions
arXiv:2312.08307 · doi:10.1021/acs.jcim.4c00104
Abstract
Geometric deep learning models, which incorporate the relevant molecular symmetries within the neural network architecture, have considerably improved the accuracy and data efficiency of predictions of molecular properties. Building on this success, we introduce 3DReact, a geometric deep learning model to predict reaction properties from three-dimensional structures of reactants and products. We demonstrate that the invariant version of the model is sufficient for existing reaction datasets. We illustrate its competitive performance on the prediction of activation barriers on the GDB7-22-TS, Cyclo-23-TS and Proparg-21-TS datasets in different atom-mapping regimes. We show that, compared to existing models for reaction property prediction, 3DReact offers a flexible framework that exploits atom-mapping information, if available, as well as geometries of reactants and products (in an invariant or equivariant fashion). Accordingly, it performs systematically well across different datasets, atom-mapping regimes, as well as both interpolation and extrapolation tasks.
46 pages + SI (13 pages)
References in corpus (34)
- On representing chemical environments
- Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
- E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
- Machine Learning of Accurate Energy-Conserving Molecular Force Fields
- PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
- Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction
- Less is more: sampling chemical space with active learning
- By-passing the Kohn-Sham equations with machine learning
- Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
- Machine learning prediction errors better than DFT accuracy
- Machine Learning of Molecular Electronic Properties in Chemical Compound Space
- Physics-inspired structural representations for molecules and materials
- SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
- FCHL revisited: faster and more accurate quantum machine learning
- Alchemical and structural distribution based representation for improved QML
- Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
- A Transferable Machine-Learning Model of the Electron Density
- OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
- Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
- Incorporating long-range physics in atomic-scale machine learning
- Accurate molecular polarizabilities with coupled-cluster theory and machine learning
- Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
- Transferable atomic multipole machine learning models for small organic molecules
- Quantum chemistry-augmented neural networks for reactivity prediction: Performance, generalizability and interpretability
- Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties
- Towards the design of chemical reactions: Machine learning barriers of competing mechanisms in reactant space
- Recursive evaluation and iterative contraction of -body equivariant features
- Predicting tensorial molecular properties with equivariant machine-learning models
- Deep Reinforcement Learning of Transition States
- An equivariant graph neural network for the elasticity tensors of all seven crystal systems
- Multilayer atomic cluster expansion for semi-local interactions
- An orbital-based representation for accurate Quantum Machine Learning
- SPAM: the Spectrum of Approximated Hamiltonian Matrices representations
- SPAM(a,b): encoding the density information from guess Hamiltonian in quantum machine learning representations