Physics-Constrained Predictive Molecular Latent Space Discovery with Graph Scattering Variational Autoencoder

Abstract

Recent advances in artificial intelligence have propelled the development of innovative computational materials modeling and design techniques. Generative deep learning models have been used for molecular representation, discovery, and design. In this work, we assess the predictive capabilities of a molecular generative model developed based on variational inference and graph theory in the small data regime. Physical constraints that encourage energetically stable molecules are proposed. The encoding network is based on the scattering transform with adaptive spectral filters to allow for better generalization of the model. The decoding network is a one-shot graph generative model that conditions atom types on molecular topology. A Bayesian formalism is considered to capture uncertainties in the predictive estimates of molecular properties. The model's performance is evaluated by generating molecules with desired target properties.

References in corpus (22)

• Semi-Supervised Classification with Graph Convolutional Networks
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• NICE: Non-linear Independent Components Estimation
• Variational Graph Auto-Encoders
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Deep learning for molecular design - a review of the state of the art
• Understanding Deep Convolutional Networks
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• MolGAN: An implicit generative model for small molecular graphs
• Learning Deep Generative Models of Graphs
• 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
• Grammar Variational Autoencoder
• Covariant Compositional Networks For Learning Graphs
• Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
• N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials
• A Two-Step Graph Convolutional Decoder for Molecule Generation
• Predictive Collective Variable Discovery with Deep Bayesian Models
• Stability of Graph Scattering Transforms
• Learning to SMILE(S)